From 3af75db12e3d3537bc01c06bbdc876cb17e82b35 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 24 Aug 2017 09:22:57 +0900 Subject: [PATCH 0001/1507] iio: adc: ti-ads1015: fix comparator polarity setting The comparator polarity field in config register is not correctly initialized as per the interrupt trigger setting. Because the bitfield definision is wrong and bit shifting is missed. Fixes: d9f39babd8ba ("iio: adc: ti-ads1015: add threshold event support") Cc: Daniel Baluta Cc: Jonathan Cameron Signed-off-by: Akinobu Mita Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti-ads1015.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index d1210024f6bcc..e0dc204883357 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -52,7 +52,7 @@ #define ADS1015_CFG_COMP_QUE_MASK GENMASK(1, 0) #define ADS1015_CFG_COMP_LAT_MASK BIT(2) -#define ADS1015_CFG_COMP_POL_MASK BIT(2) +#define ADS1015_CFG_COMP_POL_MASK BIT(3) #define ADS1015_CFG_COMP_MODE_MASK BIT(4) #define ADS1015_CFG_DR_MASK GENMASK(7, 5) #define ADS1015_CFG_MOD_MASK BIT(8) @@ -1017,10 +1017,12 @@ static int ads1015_probe(struct i2c_client *client, switch (irq_trig) { case IRQF_TRIGGER_LOW: - cfg_comp |= ADS1015_CFG_COMP_POL_LOW; + cfg_comp |= ADS1015_CFG_COMP_POL_LOW << + ADS1015_CFG_COMP_POL_SHIFT; break; case IRQF_TRIGGER_HIGH: - cfg_comp |= ADS1015_CFG_COMP_POL_HIGH; + cfg_comp |= ADS1015_CFG_COMP_POL_HIGH << + ADS1015_CFG_COMP_POL_SHIFT; break; default: return -EINVAL; -- GitLab From c65e3d6ef4bfdc4c8460509f08507cf7dc026974 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 29 Aug 2017 13:45:11 +0200 Subject: [PATCH 0002/1507] iio: magnetometer: st_magn: fix drdy line configuration for LIS3MDL Data-ready line in LIS3MDL is routed to drdy pin and it is not possible to select a different INT pin. st_sensors_set_dataready_irq() assumes that if drdy int address is not exported in register map, irq trigger is not supported by the sensor and hw_irq_trigger is always false. Based on this configuration st_sensors_irq_thread does not consume generated interrupt causing an unhandled irq. Fix this taking into account status register address in st_sensors_set_dataready_irq() Fixes: 90efe0556292 (iio: st_sensors: harden interrupt handling) Signed-off-by: Lorenzo Bianconi Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/common/st_sensors/st_sensors_core.c | 11 ++++++++++- drivers/iio/magnetometer/st_magn_core.c | 4 ++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index d99bb1460fe24..02e833b14db08 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -463,8 +463,17 @@ int st_sensors_set_dataready_irq(struct iio_dev *indio_dev, bool enable) u8 drdy_mask; struct st_sensor_data *sdata = iio_priv(indio_dev); - if (!sdata->sensor_settings->drdy_irq.addr) + if (!sdata->sensor_settings->drdy_irq.addr) { + /* + * there are some devices (e.g. LIS3MDL) where drdy line is + * routed to a given pin and it is not possible to select a + * different one. Take into account irq status register + * to understand if irq trigger can be properly supported + */ + if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) + sdata->hw_irq_trigger = enable; return 0; + } /* Enable/Disable the interrupt generator 1. */ if (sdata->sensor_settings->drdy_irq.ig1.en_addr > 0) { diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 703e770086527..2e36d746f5bce 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -315,6 +315,10 @@ static const struct st_sensor_settings st_magn_sensors_settings[] = { }, }, }, + .drdy_irq = { + /* drdy line is routed drdy pin */ + .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, + }, .multi_read_bit = true, .bootime = 2, }, -- GitLab From 50662499f9112ecced68d064846a2f1fd9640b66 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:18 +0200 Subject: [PATCH 0003/1507] ARM64: dts: meson-gx: Use correct mmc clock source 0 Now that the clock source 0 is properly described in the CCF, use it instead of assuming the default value (xtal) Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 6 +++--- arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 52f1687e7a099..8f0c0cb021574 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -661,21 +661,21 @@ &saradc { &sd_emmc_a { clocks = <&clkc CLKID_SD_EMMC_A>, - <&xtal>, + <&clkc CLKID_SD_EMMC_A_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_b { clocks = <&clkc CLKID_SD_EMMC_B>, - <&xtal>, + <&clkc CLKID_SD_EMMC_B_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_c { clocks = <&clkc CLKID_SD_EMMC_C>, - <&xtal>, + <&clkc CLKID_SD_EMMC_C_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index d6876e64979e7..829d84db5fc57 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -603,21 +603,21 @@ &saradc { &sd_emmc_a { clocks = <&clkc CLKID_SD_EMMC_A>, - <&xtal>, + <&clkc CLKID_SD_EMMC_A_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_b { clocks = <&clkc CLKID_SD_EMMC_B>, - <&xtal>, + <&clkc CLKID_SD_EMMC_B_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; &sd_emmc_c { clocks = <&clkc CLKID_SD_EMMC_C>, - <&xtal>, + <&clkc CLKID_SD_EMMC_C_CLK0>, <&clkc CLKID_FCLK_DIV2>; clock-names = "core", "clkin0", "clkin1"; }; -- GitLab From 673ccaaccf32a044d961c3bac3dd63452bdfa86c Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:19 +0200 Subject: [PATCH 0004/1507] ARM64: dts: meson: remove cap-sd-highspeed from emmc nodes It does not make much sense to define cap-sd-highspeed in the emmc nodes Just remove it. Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi | 1 - arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi | 1 - arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi | 1 - arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi | 1 - arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts | 1 - arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts | 1 - 11 files changed, 11 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index c89010e564888..d4f9c5b550c73 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -215,7 +215,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 9697a7a794644..7dae6acd3c8c3 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -297,7 +297,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; max-frequency = <200000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 9c59c3c6d1b6a..a690956d6c75f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -274,7 +274,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index d147c853ab054..a12303becab4a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -274,7 +274,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; max-frequency = <200000000>; non-removable; disable-wp; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index 81ffc689a5bf4..d77e19591ee3f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -241,7 +241,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 346753fb63243..0262ef8d48e4b 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -201,7 +201,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index 2a5804ce7f4bd..f779a985f9232 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -144,7 +144,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <100000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 4c2ac7650fcd3..21274a6c1b9bc 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -231,7 +231,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index f3eea8e89d12b..8899121f79e14 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -137,7 +137,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index 9b10c5f4f8c03..ff8a9f7804855 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -196,7 +196,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 08f1dd69b6792..470f72bb863c5 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -220,7 +220,6 @@ &sd_emmc_c { pinctrl-names = "default"; bus-width = <8>; - cap-sd-highspeed; cap-mmc-highspeed; max-frequency = <200000000>; non-removable; -- GitLab From 67e7607fcdf1fad10e9f183424e709c59713e45d Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:20 +0200 Subject: [PATCH 0005/1507] ARM64: dts: meson: add mmc clk gate pins Add the pinctrl to switch mmc clk pins in gpio (pulled down) mode. This is necessary to be able to gate the clk outside of the SoC while keeping it running in the controller Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- .../boot/dts/amlogic/meson-gx-p23x-q20x.dtsi | 9 +++-- .../boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 9 +++-- .../dts/amlogic/meson-gxbb-nexbox-a95x.dts | 11 ++++--- .../boot/dts/amlogic/meson-gxbb-odroidc2.dts | 8 +++-- .../boot/dts/amlogic/meson-gxbb-p20x.dtsi | 9 +++-- .../boot/dts/amlogic/meson-gxbb-vega-s95.dtsi | 9 +++-- arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi | 33 +++++++++++++++++++ .../meson-gxl-s905x-hwacom-amazetv.dts | 6 ++-- .../amlogic/meson-gxl-s905x-libretech-cc.dts | 6 ++-- .../amlogic/meson-gxl-s905x-nexbox-a95x.dts | 9 +++-- .../dts/amlogic/meson-gxl-s905x-p212.dtsi | 9 +++-- arch/arm64/boot/dts/amlogic/meson-gxl.dtsi | 33 +++++++++++++++++++ .../boot/dts/amlogic/meson-gxm-nexbox-a1.dts | 6 ++-- 13 files changed, 126 insertions(+), 31 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index d4f9c5b550c73..4157987f4a3d2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -168,7 +168,8 @@ &pwm_ef { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -194,7 +195,8 @@ brcmf: wifi@1 { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -212,7 +214,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 7dae6acd3c8c3..60d5f2da69160 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -250,7 +250,8 @@ &saradc { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>, <&sdio_irq_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -276,7 +277,8 @@ brcmf: wifi@1 { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -294,7 +296,8 @@ &sd_emmc_b { &sd_emmc_c { status = "disabled"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; max-frequency = <200000000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index a690956d6c75f..38dfdde5c1473 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -51,7 +51,7 @@ / { compatible = "nexbox,a95x", "amlogic,meson-gxbb"; model = "NEXBOX A95X"; - + aliases { serial0 = &uart_AO; }; @@ -232,7 +232,8 @@ &pwm_ef { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -253,7 +254,8 @@ &sd_emmc_a { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -271,7 +273,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index a12303becab4a..1ffa1c238a725 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -50,7 +50,7 @@ / { compatible = "hardkernel,odroid-c2", "amlogic,meson-gxbb"; model = "Hardkernel ODROID-C2"; - + aliases { serial0 = &uart_AO; }; @@ -253,7 +253,8 @@ &scpi_clocks { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -271,7 +272,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; max-frequency = <200000000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index d77e19591ee3f..704b214e8894a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -194,7 +194,8 @@ &pwm_ef { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -220,7 +221,8 @@ brcmf: wifi@1 { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -238,7 +240,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 0262ef8d48e4b..f2bc6dea1fc62 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -155,7 +155,8 @@ &pwm_ef { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins &sdio_irq_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -181,7 +182,8 @@ brcmf: wifi@1 { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -198,7 +200,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 8f0c0cb021574..af834cdbba791 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -392,6 +392,17 @@ mux { }; }; + emmc_clk_gate_pins: emmc_clk_gate { + mux { + groups = "BOOT_8"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "BOOT_8"; + bias-pull-down; + }; + }; + nor_pins: nor { mux { groups = "nor_d", @@ -430,6 +441,17 @@ mux { }; }; + sdcard_clk_gate_pins: sdcard_clk_gate { + mux { + groups = "CARD_2"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "CARD_2"; + bias-pull-down; + }; + }; + sdio_pins: sdio { mux { groups = "sdio_d0", @@ -442,6 +464,17 @@ mux { }; }; + sdio_clk_gate_pins: sdio_clk_gate { + mux { + groups = "GPIOX_4"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "GPIOX_4"; + bias-pull-down; + }; + }; + sdio_irq_pins: sdio_irq { mux { groups = "sdio_irq"; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index f779a985f9232..977b4240f3c1b 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -123,7 +123,8 @@ &pwm_ef { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -141,7 +142,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index 69ca14ac10fa0..a014c052241ec 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -197,7 +197,8 @@ &pinctrl_periphs { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -215,7 +216,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 21274a6c1b9bc..1b8f32867aa10 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -189,7 +189,8 @@ &pwm_ef { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -210,7 +211,8 @@ &sd_emmc_a { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -228,7 +230,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index 8899121f79e14..129af9068814d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -95,7 +95,8 @@ &saradc { &sd_emmc_a { status = "okay"; pinctrl-0 = <&sdio_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdio_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; #address-cells = <1>; #size-cells = <0>; @@ -116,7 +117,8 @@ &sd_emmc_a { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -134,7 +136,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 829d84db5fc57..d8dd3298b15cf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -281,6 +281,17 @@ mux { }; }; + emmc_clk_gate_pins: emmc_clk_gate { + mux { + groups = "BOOT_8"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "BOOT_8"; + bias-pull-down; + }; + }; + nor_pins: nor { mux { groups = "nor_d", @@ -319,6 +330,17 @@ mux { }; }; + sdcard_clk_gate_pins: sdcard_clk_gate { + mux { + groups = "CARD_2"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "CARD_2"; + bias-pull-down; + }; + }; + sdio_pins: sdio { mux { groups = "sdio_d0", @@ -331,6 +353,17 @@ mux { }; }; + sdio_clk_gate_pins: sdio_clk_gate { + mux { + groups = "GPIOX_4"; + function = "gpio_periphs"; + }; + cfg-pull-down { + pins = "GPIOX_4"; + bias-pull-down; + }; + }; + sdio_irq_pins: sdio_irq { mux { groups = "sdio_irq"; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index ff8a9f7804855..22c697732f668 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -175,7 +175,8 @@ &ir { &sd_emmc_b { status = "okay"; pinctrl-0 = <&sdcard_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&sdcard_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <4>; cap-sd-highspeed; @@ -193,7 +194,8 @@ &sd_emmc_b { &sd_emmc_c { status = "okay"; pinctrl-0 = <&emmc_pins>; - pinctrl-names = "default"; + pinctrl-1 = <&emmc_clk_gate_pins>; + pinctrl-names = "default", "clk-gate"; bus-width = <8>; cap-mmc-highspeed; -- GitLab From 42776561a1def5d96699574efd7c9cbbd2e0fbc4 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:21 +0200 Subject: [PATCH 0006/1507] ARM64: dts: meson-gxbb: nanopi-k2: add card regulator settle times Changing the card voltage on the nanopi-k2 is not instantaneous, especially when switching from 3.3v to 1.8v. It take at least 3ms for the regulator to go from 3.3v to 1.8v. Add margin to that to make sure we don't upset the sdcard during the voltage switch Fixes: 9bc7ffb08daf ("arm64: dts: amlogic: Add NanoPi K2") Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 60d5f2da69160..acb6797756e58 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -107,6 +107,9 @@ vddio_tf: regulator-vddio-tf { states = <3300000 0>, <1800000 1>; + + regulator-settling-time-up-us = <100>; + regulator-settling-time-down-us = <5000>; }; wifi_32k: wifi-32k { -- GitLab From 8a5085c420d272af04552b2d2213471247fa86f2 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:22 +0200 Subject: [PATCH 0007/1507] ARM64: dts: meson-gxl: libretech-cc: add card regulator settle times Changing the card voltage on the cc is not instantaneous, especially when switching from 3.3v to 1.8v. It take at least 30ms for the regulator to go from 3.3v to 1.8v. Add margin to that to make sure we don't upset the sdcard during the voltage switch Fixes: 61ff2af9b278 ("ARM64: dts: fixup libretech cc definition") Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index a014c052241ec..7d252168c2fa2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -91,6 +91,9 @@ vcc_card: regulator-vcc-card { states = <3300000 0>, <1800000 1>; + + regulator-settling-time-up-us = <200>; + regulator-settling-time-down-us = <50000>; }; vddio_boot: regulator-vddio_boot { -- GitLab From 3cde63ebc85cea63806d86a690d04457c0347703 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:23 +0200 Subject: [PATCH 0008/1507] ARM64: dts: meson-gxl: libretech-cc: enable high speed modes Enable sdcard UHS modes up to SDR50. Unfortunately, it seems the PCB of the libretech-cc cannot handle SDR104 at 200Mhz reliably. Also enable eMMC DDR52 mode. Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index 7d252168c2fa2..64c54c92e214d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -205,6 +205,9 @@ &sd_emmc_b { bus-width = <4>; cap-sd-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; max-frequency = <100000000>; disable-wp; @@ -224,6 +227,7 @@ &sd_emmc_c { bus-width = <8>; cap-mmc-highspeed; + mmc-ddr-3_3v; max-frequency = <50000000>; non-removable; disable-wp; -- GitLab From 0f553358241a3346b7eef133d631e5bc2f067a15 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:24 +0200 Subject: [PATCH 0009/1507] ARM64: dts: meson-gxbb: p20x: enable sdcard UHS modes Enable sdcard UHS modes, up to SDR50, on p20x based boards. While the s905 supports SDR104 mode, it appears that the PCB of p20x based boards can't cope with a rate as high as 200Mhz. Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index 704b214e8894a..23c08c3afd0ab 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -226,6 +226,9 @@ &sd_emmc_b { bus-width = <4>; cap-sd-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; max-frequency = <100000000>; disable-wp; -- GitLab From c1429e20a5a9f578e0e3ddb551c8ea94e8d3ddb3 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:25 +0200 Subject: [PATCH 0010/1507] ARM64: dts: meson-gxbb: nanopi-k2: enable sdcard UHS modes Enable UHS modes, up to SDR50, on the nanopi-k2 SBC. Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index acb6797756e58..4c1320a93fef2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -285,6 +285,9 @@ &sd_emmc_b { bus-width = <4>; cap-sd-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; max-frequency = <100000000>; disable-wp; -- GitLab From 485a308f05d843034b6e82f688704c44888aecde Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Thu, 31 Aug 2017 15:52:26 +0200 Subject: [PATCH 0011/1507] ARM64: dts: meson-gxbb: nanopi-k2: enable sdr104 mode SDR104 seems to be OK on the nanopi-k2 SBC so enable it Signed-off-by: Jerome Brunet Signed-off-by: Kevin Hilman --- arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 4c1320a93fef2..4b17a76959b2f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -288,7 +288,8 @@ &sd_emmc_b { sd-uhs-sdr12; sd-uhs-sdr25; sd-uhs-sdr50; - max-frequency = <100000000>; + sd-uhs-sdr104; + max-frequency = <200000000>; disable-wp; cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; -- GitLab From ce06760ba46b66dae50f2519ae76bd15e89b5710 Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Thu, 31 Aug 2017 15:50:03 -0700 Subject: [PATCH 0012/1507] HID: wacom: bits shifted too much for 9th and 10th buttons Cintiq 12 has 10 expresskey buttons. The bit shift for the last two buttons were off by 5. Fixes: c7f0522 ("HID: wacom: Slim down wacom_intuos_pad processing") Signed-off-by: Ping Cheng Tested-by: Matthieu Robin Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index bb17d7bbefd3e..f8ddcaaa2ac69 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -567,8 +567,8 @@ static int wacom_intuos_pad(struct wacom_wac *wacom) keys = data[9] & 0x07; } } else { - buttons = ((data[6] & 0x10) << 10) | - ((data[5] & 0x10) << 9) | + buttons = ((data[6] & 0x10) << 5) | + ((data[5] & 0x10) << 4) | ((data[6] & 0x0F) << 4) | (data[5] & 0x0F); } -- GitLab From 74aebed6dc13425233f2224668353cff7a112776 Mon Sep 17 00:00:00 2001 From: Aaron Armstrong Skomra Date: Mon, 28 Aug 2017 14:15:39 -0700 Subject: [PATCH 0013/1507] HID: wacom: leds: Don't try to control the EKR's read-only LEDs Commit a50aac7193f1 introduces 'led.groups' and adds EKR support for these groups. However, unlike the other devices with LEDs, the EKR's LEDs are read-only and we shouldn't attempt to control them in wacom_led_control(). See bug: https://sourceforge.net/p/linuxwacom/bugs/342/ Fixes: a50aac7193f1 ("HID: wacom: leds: dynamically allocate LED groups") Cc: stable # 4.9 Signed-off-by: Aaron Armstrong Skomra Reviewed-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_sys.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index e82a696a1d07c..735bfbbcaa827 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -766,6 +766,9 @@ static int wacom_led_control(struct wacom *wacom) if (!wacom->led.groups) return -ENOTSUPP; + if (wacom->wacom_wac.features.type == REMOTE) + return -ENOTSUPP; + if (wacom->wacom_wac.pid) { /* wireless connected */ report_id = WAC_CMD_WL_LED_CONTROL; buf_size = 13; -- GitLab From a3ae552b5259e6ffd8d124a9fa9923283af2828a Mon Sep 17 00:00:00 2001 From: Nicholas Bishop Date: Mon, 4 Sep 2017 15:40:42 -0400 Subject: [PATCH 0014/1507] HID: add multi-input quirk for IDC6680 touchscreen The Ideacom 6680 touchscreen is found in the Dell Latitude 2100. It has two USB descriptors, the first of which has two input reports. The HID_QUIRK_MULTI_INPUT quirk is needed to keep the correct maximum value for ABS_X/ABS_Y (8191 instead of 65535). Signed-off-by: Nicholas Bishop Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/usbhid/hid-quirks.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b397a14ab9703..11798b10e5223 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -533,6 +533,7 @@ #define USB_VENDOR_ID_IDEACOM 0x1cb6 #define USB_DEVICE_ID_IDEACOM_IDC6650 0x6650 #define USB_DEVICE_ID_IDEACOM_IDC6651 0x6651 +#define USB_DEVICE_ID_IDEACOM_IDC6680 0x6680 #define USB_VENDOR_ID_ILITEK 0x222a #define USB_DEVICE_ID_ILITEK_MULTITOUCH 0x0001 diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index a83fa76655b94..f489a5cfcb48c 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -99,6 +99,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0A4A, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C007, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL }, { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS, HID_QUIRK_NOGET }, -- GitLab From e57f4e67a0c73ca1c3afb68928b917906bd82eaf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 22 Aug 2017 08:37:52 +0200 Subject: [PATCH 0015/1507] HID: multitouch: Fix system-control buttons not working Some laptops have system-control buttons (e.g. KEY_SLEEP) on the same interface as a hid-multitouch touch-pad. This commit fixes these buttons not working. Signed-off-by: Hans de Goede Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-multitouch.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 440b999304a55..5609725df7146 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -930,6 +930,7 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi, field->application != HID_DG_PEN && field->application != HID_DG_TOUCHPAD && field->application != HID_GD_KEYBOARD && + field->application != HID_GD_SYSTEM_CONTROL && field->application != HID_CP_CONSUMER_CONTROL && field->application != HID_GD_WIRELESS_RADIO_CTLS && !(field->application == HID_VD_ASUS_CUSTOM_MEDIA_KEYS && -- GitLab From b63c4c2718d641ba9bec888994f0cb0c23a1ef45 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Wed, 30 Aug 2017 15:13:25 -0700 Subject: [PATCH 0016/1507] HID: wacom: Properly report negative values from Intuos Pro 2 Bluetooth The wacom driver's IRQ handler for Bluetooth reports from the 2nd-gen Intuos Pro does not correctly process negative numbers. Values for tilt and rotation (which can go negative) are instead interpreted as unsigned and so jump to very large values when the data should be negative. This commit properly casts the data to ensure we report negative numbers when necessary. Fixes: 4922cd2 ("HID: wacom: Support 2nd-gen Intuos Pro's Bluetooth classic interface") Cc: stable@vger.kernel.org # v4.11 Signed-off-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index f8ddcaaa2ac69..1d9e32d2bc63e 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1229,9 +1229,9 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) if (range) { input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1])); input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3])); - input_report_abs(pen_input, ABS_TILT_X, frame[7]); - input_report_abs(pen_input, ABS_TILT_Y, frame[8]); - input_report_abs(pen_input, ABS_Z, get_unaligned_le16(&frame[9])); + input_report_abs(pen_input, ABS_TILT_X, (char)frame[7]); + input_report_abs(pen_input, ABS_TILT_Y, (char)frame[8]); + input_report_abs(pen_input, ABS_Z, (int16_t)get_unaligned_le16(&frame[9])); input_report_abs(pen_input, ABS_WHEEL, get_unaligned_le16(&frame[11])); } input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5])); -- GitLab From d252f4a10fb9c8f7187c6c936ff530039f8cb799 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Wed, 30 Aug 2017 15:13:26 -0700 Subject: [PATCH 0017/1507] HID: wacom: Correct coordinate system of touchring and pen twist The MobileStudio Pro, Cintiq Pro, and 2nd-gen Intuos Pro devices use a different coordinate system for their touchring and pen twist than prior devices. Prior devices had zero aligned to the tablet's left and would increase clockwise. Userspace expects data from the kernel to be in this old coordinate space, so adjustments are necessary. While the coordinate system for pen twist is formally defined by the HID standard, no such definition existed for the touchring at the time these tablets were introduced. Future tablets are expected to report touchring data using the same "zero-up clockwise-increasing" coordinate system defined for twist. Fixes: 50066a042d ("HID: wacom: generic: Add support for height, tilt, and twist usages") Fixes: 4922cd26f0 ("HID: wacom: Support 2nd-gen Intuos Pro's Bluetooth classic interface") Fixes: 60a2218698 ("HID: wacom: generic: add support for touchring") Cc: stable@vger.kernel.org # 4.10, 4.11 Signed-off-by: Jason Gerecke Reviewed-by: Ping Cheng Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 73 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 68 insertions(+), 5 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 1d9e32d2bc63e..78d0398904dc6 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1227,11 +1227,17 @@ static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom) continue; if (range) { + /* Fix rotation alignment: userspace expects zero at left */ + int16_t rotation = (int16_t)get_unaligned_le16(&frame[9]); + rotation += 1800/4; + if (rotation > 899) + rotation -= 1800; + input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1])); input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3])); input_report_abs(pen_input, ABS_TILT_X, (char)frame[7]); input_report_abs(pen_input, ABS_TILT_Y, (char)frame[8]); - input_report_abs(pen_input, ABS_Z, (int16_t)get_unaligned_le16(&frame[9])); + input_report_abs(pen_input, ABS_Z, rotation); input_report_abs(pen_input, ABS_WHEEL, get_unaligned_le16(&frame[11])); } input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5])); @@ -1319,12 +1325,19 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) unsigned char *data = wacom->data; int buttons = (data[282] << 1) | ((data[281] >> 6) & 0x01); - int ring = data[285]; - int prox = buttons | (ring & 0x80); + int ring = data[285] & 0x7F; + bool ringstatus = data[285] & 0x80; + bool prox = buttons || ringstatus; + + /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ + ring = 71 - ring; + ring += 3*72/16; + if (ring > 71) + ring -= 72; wacom_report_numbered_buttons(pad_input, 9, buttons); - input_report_abs(pad_input, ABS_WHEEL, (ring & 0x80) ? (ring & 0x7f) : 0); + input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); input_report_key(pad_input, wacom->tool[1], prox ? 1 : 0); input_report_abs(pad_input, ABS_MISC, prox ? PAD_DEVICE_ID : 0); @@ -1616,6 +1629,20 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len) return 0; } +static int wacom_offset_rotation(struct input_dev *input, struct hid_usage *usage, + int value, int num, int denom) +{ + struct input_absinfo *abs = &input->absinfo[usage->code]; + int range = (abs->maximum - abs->minimum + 1); + + value += num*range/denom; + if (value > abs->maximum) + value -= range; + else if (value < abs->minimum) + value += range; + return value; +} + int wacom_equivalent_usage(int usage) { if ((usage & HID_USAGE_PAGE) == WACOM_HID_UP_WACOMDIGITIZER) { @@ -1898,6 +1925,7 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field unsigned equivalent_usage = wacom_equivalent_usage(usage->hid); int i; bool is_touch_on = value; + bool do_report = false; /* * Avoid reporting this event and setting inrange_state if this usage @@ -1912,6 +1940,29 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field } switch (equivalent_usage) { + case WACOM_HID_WD_TOUCHRING: + /* + * Userspace expects touchrings to increase in value with + * clockwise gestures and have their zero point at the + * tablet's left. HID events "should" be clockwise- + * increasing and zero at top, though the MobileStudio + * Pro and 2nd-gen Intuos Pro don't do this... + */ + if (hdev->vendor == 0x56a && + (hdev->product == 0x34d || hdev->product == 0x34e || /* MobileStudio Pro */ + hdev->product == 0x357 || hdev->product == 0x358)) { /* Intuos Pro 2 */ + value = (field->logical_maximum - value); + + if (hdev->product == 0x357 || hdev->product == 0x358) + value = wacom_offset_rotation(input, usage, value, 3, 16); + else if (hdev->product == 0x34d || hdev->product == 0x34e) + value = wacom_offset_rotation(input, usage, value, 1, 2); + } + else { + value = wacom_offset_rotation(input, usage, value, 1, 4); + } + do_report = true; + break; case WACOM_HID_WD_TOUCHRINGSTATUS: if (!value) input_event(input, usage->type, usage->code, 0); @@ -1945,10 +1996,14 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field value, i); /* fall through*/ default: + do_report = true; + break; + } + + if (do_report) { input_event(input, usage->type, usage->code, value); if (value) wacom_wac->hid_data.pad_input_event_flag = true; - break; } } @@ -2089,6 +2144,14 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); wacom_wac->serial[0] |= (__u32)value; return; + case HID_DG_TWIST: + /* + * Userspace expects pen twist to have its zero point when + * the buttons/finger is on the tablet's left. HID values + * are zero when buttons are toward the top. + */ + value = wacom_offset_rotation(input, usage, value, 1, 4); + break; case WACOM_HID_WD_SENSE: wacom_wac->hid_data.sense_state = value; return; -- GitLab From 56d859e11aad4016e1cf864d65a0954d83120571 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 25 Aug 2017 18:06:04 -0400 Subject: [PATCH 0018/1507] HID: multitouch: support buttons and trackpoint on Lenovo X1 Tab Gen2 On the 2nd generation Lenovo Tablet only clickpad is working; the trackpoint and three mouse buttons do not work. hid_multitouch must export all inputs in order to get trackpoint and buttons to function. Signed-off-by: Pavel Tatashin Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-multitouch.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 11798b10e5223..a989191998587 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -661,6 +661,7 @@ #define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048 #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 +#define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_VENDOR_ID_LG 0x1fd2 #define USB_DEVICE_ID_LG_MULTITOUCH 0x0064 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 5609725df7146..9e8c4d2ba11d2 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1420,6 +1420,12 @@ static const struct hid_device_id mt_devices[] = { USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) }, + /* Lenovo X1 TAB Gen 2 */ + { .driver_data = MT_CLS_WIN_8_DUAL, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X1_TAB) }, + /* Anton devices */ { .driver_data = MT_CLS_EXPORT_ALL_INPUTS, MT_USB_DEVICE(USB_VENDOR_ID_ANTON, -- GitLab From fcaa4a07d2a4b541e91da7a55d8b3331f96d1865 Mon Sep 17 00:00:00 2001 From: Shrirang Bagul Date: Thu, 10 Aug 2017 17:54:01 +0800 Subject: [PATCH 0019/1507] HID: multitouch: Support ALPS PTP stick with pid 0x120A This patch adds ALPS PTP sticks with pid/device id 0x120A to the list of devices supported by hid-multitouch. Signed-off-by: Shrirang Bagul Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-multitouch.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index a989191998587..832897d4a849d 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -75,6 +75,7 @@ #define USB_VENDOR_ID_ALPS_JP 0x044E #define HID_DEVICE_ID_ALPS_U1_DUAL 0x120B +#define HID_DEVICE_ID_ALPS_U1_PTP_2 0x120A #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP 0x121F #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 9e8c4d2ba11d2..c78625dceced9 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1419,6 +1419,10 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) }, + { .driver_data = MT_CLS_WIN_8_DUAL, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_ALPS_JP, + HID_DEVICE_ID_ALPS_U1_PTP_2) }, /* Lenovo X1 TAB Gen 2 */ { .driver_data = MT_CLS_WIN_8_DUAL, -- GitLab From 23e4c67ae13da7549a54f4e8c0014f48b2ef5204 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Sep 2017 23:45:34 +0200 Subject: [PATCH 0020/1507] ata: avoid gcc-7 warning in ata_timing_quantize gcc-7 warns about the result of a constant multiplication used as a boolean: drivers/ata/libata-core.c: In function 'ata_timing_quantize': drivers/ata/libata-core.c:3164:30: warning: '*' in boolean context, suggest '&&' instead [-Wint-in-bool-context] This slightly rearranges the macro to simplify the code and avoid the warning at the same time. Signed-off-by: Arnd Bergmann Signed-off-by: Tejun Heo --- drivers/ata/libata-core.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 1945a8ea20998..ee4c1ec9dca0e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3234,19 +3234,19 @@ static const struct ata_timing ata_timing[] = { }; #define ENOUGH(v, unit) (((v)-1)/(unit)+1) -#define EZ(v, unit) ((v)?ENOUGH(v, unit):0) +#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0) static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT) { - q->setup = EZ(t->setup * 1000, T); - q->act8b = EZ(t->act8b * 1000, T); - q->rec8b = EZ(t->rec8b * 1000, T); - q->cyc8b = EZ(t->cyc8b * 1000, T); - q->active = EZ(t->active * 1000, T); - q->recover = EZ(t->recover * 1000, T); - q->dmack_hold = EZ(t->dmack_hold * 1000, T); - q->cycle = EZ(t->cycle * 1000, T); - q->udma = EZ(t->udma * 1000, UT); + q->setup = EZ(t->setup, T); + q->act8b = EZ(t->act8b, T); + q->rec8b = EZ(t->rec8b, T); + q->cyc8b = EZ(t->cyc8b, T); + q->active = EZ(t->active, T); + q->recover = EZ(t->recover, T); + q->dmack_hold = EZ(t->dmack_hold, T); + q->cycle = EZ(t->cycle, T); + q->udma = EZ(t->udma, UT); } void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b, -- GitLab From 59cd827f26019ac790b2f34cbad478037f51c570 Mon Sep 17 00:00:00 2001 From: Matt Chen Date: Mon, 28 Aug 2017 14:57:54 +0800 Subject: [PATCH 0021/1507] iwlwifi: mvm: fix wowlan resume failed to load INIT ucode If we set disconnect on wowlan and run suspend/resume, will run into: ...snipped iwlwifi 0000:01:00.0: Failed to load firmware chunk! iwlwifi 0000:01:00.0: Could not load the [0] uCode section iwlwifi 0000:01:00.0: Failed to start INIT ucode: -110 iwlwifi 0000:01:00.0: Failed to run INIT ucode: -110 iwlwifi 0000:01:00.0: Failed to start RT ucode: -110 It is because we still keep IWL_MVM_STATUS_IN_HW_RESTART in __iwl_mvm_resume. When mac80211 starts the device as __iwl_mvm_mac_start(), we will miss iwl_mvm_restart_cleanup(mvm). Signed-off-by: Matt Chen Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 5de19ea105757..b205a7bfb828d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2167,7 +2167,7 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test) * 1. We are not using a unified image * 2. We are using a unified image but had an error while exiting D3 */ - set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status); + set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status); set_bit(IWL_MVM_STATUS_D3_RECONFIG, &mvm->status); /* * When switching images we return 1, which causes mac80211 -- GitLab From 6110d9e5bdd15c4e60fb67f330fbf74681e7daf7 Mon Sep 17 00:00:00 2001 From: David Spinadel Date: Tue, 29 Aug 2017 13:56:02 +0300 Subject: [PATCH 0022/1507] iwlwifi: mvm: Flush non STA TX queues When starting wowlan mac80211 requests flush w/o vif and we ignore this request. As a result some packets stay stuck in the queue and it may end up with a queue hang. Allow the driver to flush queues even if station isn't specified. Signed-off-by: David Spinadel Signed-off-by: Luca Coelho --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 44 ++++++++++++++++++- 1 file changed, 43 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 15f2d826bb4b2..64b0be73ea725 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3975,6 +3975,43 @@ static int iwl_mvm_post_channel_switch(struct ieee80211_hw *hw, return ret; } +static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop) +{ + if (drop) { + if (iwl_mvm_has_new_tx_api(mvm)) + /* TODO new tx api */ + WARN_ONCE(1, + "Need to implement flush TX queue\n"); + else + iwl_mvm_flush_tx_path(mvm, + iwl_mvm_flushable_queues(mvm) & queues, + 0); + } else { + if (iwl_mvm_has_new_tx_api(mvm)) { + struct ieee80211_sta *sta; + int i; + + mutex_lock(&mvm->mutex); + + for (i = 0; i < ARRAY_SIZE(mvm->fw_id_to_mac_id); i++) { + sta = rcu_dereference_protected( + mvm->fw_id_to_mac_id[i], + lockdep_is_held(&mvm->mutex)); + if (IS_ERR_OR_NULL(sta)) + continue; + + iwl_mvm_wait_sta_queues_empty(mvm, + iwl_mvm_sta_from_mac80211(sta)); + } + + mutex_unlock(&mvm->mutex); + } else { + iwl_trans_wait_tx_queues_empty(mvm->trans, + queues); + } + } +} + static void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u32 queues, bool drop) { @@ -3985,7 +4022,12 @@ static void iwl_mvm_mac_flush(struct ieee80211_hw *hw, int i; u32 msk = 0; - if (!vif || vif->type != NL80211_IFTYPE_STATION) + if (!vif) { + iwl_mvm_flush_no_vif(mvm, queues, drop); + return; + } + + if (vif->type != NL80211_IFTYPE_STATION) return; /* Make sure we're done with the deferred traffic before flushing */ -- GitLab From 0fe8bed6e37c259b85d123ef9667f972305c9d6b Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Thu, 31 Aug 2017 16:27:06 +0300 Subject: [PATCH 0023/1507] iwlwifi: mvm: send all non-bufferable frames on the probe queue AP interfaces now send all non-bufferable frames using the broadcast station. Thus allow them to use the probe queue and don't warn about it. Fixes: eb045e6e0389 ("iwlwifi: mvm: Avoid deferring non bufferable frames") Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 172b5e63d3fbe..6f2e2af23219a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -564,8 +564,8 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_ADHOC: /* - * Handle legacy hostapd as well, where station will be added - * only just before sending the association response. + * Non-bufferable frames use the broadcast station, thus they + * use the probe queue. * Also take care of the case where we send a deauth to a * station that we don't have, or similarly an association * response (with non-success status) for a station we can't @@ -573,9 +573,9 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, * Also, disassociate frames might happen, particular with * reason 7 ("Class 3 frame received from nonassociated STA"). */ - if (ieee80211_is_probe_resp(fc) || ieee80211_is_auth(fc) || - ieee80211_is_deauth(fc) || ieee80211_is_assoc_resp(fc) || - ieee80211_is_disassoc(fc)) + if (ieee80211_is_mgmt(fc) && + (!ieee80211_is_bufferable_mmpdu(fc) || + ieee80211_is_deauth(fc) || ieee80211_is_disassoc(fc))) return mvm->probe_queue; if (info->hw_queue == info->control.vif->cab_queue) return mvmvif->cab_queue; -- GitLab From bd800e41a3de5c7e56b2fd27088bdaf5e228d227 Mon Sep 17 00:00:00 2001 From: Naftali Goldstein Date: Mon, 28 Aug 2017 11:51:05 +0300 Subject: [PATCH 0024/1507] iwlwifi: mvm: change state when queueing agg start work Add a new state to enum iwl_mvm_agg_state, which is used between queueing the work that starts tx aggregations and actually starting that work (changing to state IWL_AGG_STARTING). This solves a race where ieee80211_start_tx_ba_session is called a second time, before the work queued by the first run has a chance to change the agg_state. In this case the second call to ieee80211_start_tx_ba_session returns an error, and the fallback is to abort the ba session start. Fixes: 482e48440a0e ("iwlwifi: mvm: change open and close criteria of a BA session") Signed-off-by: Naftali Goldstein Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 3 ++- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 6 ++++-- drivers/net/wireless/intel/iwlwifi/mvm/sta.h | 2 ++ 3 files changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index ba7bd049d3d4e..0fe723ca844ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -661,7 +661,8 @@ static void rs_tl_turn_on_agg(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, (lq_sta->tx_agg_tid_en & BIT(tid)) && (tid_data->tx_count_last >= IWL_MVM_RS_AGG_START_THRESHOLD)) { IWL_DEBUG_RATE(mvm, "try to aggregate tid %d\n", tid); - rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta); + if (rs_tl_turn_on_agg_for_tid(mvm, lq_sta, tid, sta) == 0) + tid_data->state = IWL_AGG_QUEUED; } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 411a2055dc451..2dafe9bb4d8b9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2385,8 +2385,10 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT)) return -EINVAL; - if (mvmsta->tid_data[tid].state != IWL_AGG_OFF) { - IWL_ERR(mvm, "Start AGG when state is not IWL_AGG_OFF %d!\n", + if (mvmsta->tid_data[tid].state != IWL_AGG_QUEUED && + mvmsta->tid_data[tid].state != IWL_AGG_OFF) { + IWL_ERR(mvm, + "Start AGG when state is not IWL_AGG_QUEUED or IWL_AGG_OFF %d!\n", mvmsta->tid_data[tid].state); return -ENXIO; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index d138938065136..aedabe101cf0f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -281,6 +281,7 @@ struct iwl_mvm_vif; * These states relate to a specific RA / TID. * * @IWL_AGG_OFF: aggregation is not used + * @IWL_AGG_QUEUED: aggregation start work has been queued * @IWL_AGG_STARTING: aggregation are starting (between start and oper) * @IWL_AGG_ON: aggregation session is up * @IWL_EMPTYING_HW_QUEUE_ADDBA: establishing a BA session - waiting for the @@ -290,6 +291,7 @@ struct iwl_mvm_vif; */ enum iwl_mvm_agg_state { IWL_AGG_OFF = 0, + IWL_AGG_QUEUED, IWL_AGG_STARTING, IWL_AGG_ON, IWL_EMPTYING_HW_QUEUE_ADDBA, -- GitLab From 8458e48ac7ad86a5ab7f3d1a8cacd9205a9a97ce Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Sun, 3 Sep 2017 16:04:38 +0300 Subject: [PATCH 0025/1507] iwlwifi: mvm: wake the correct mac80211 queue iwl_mvm_start_mac_queues() takes a bitmap of the queues to wake. When deferred tx is purged, set the bit of the hw_queue so the correct queue will be waken up. Fixes: 7e39a00d5931 ("iwlwifi: mvm: start mac queues when deferred tx frames are purged") Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 64b0be73ea725..3a6ce4222ff54 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2563,7 +2563,7 @@ static void iwl_mvm_purge_deferred_tx_frames(struct iwl_mvm *mvm, * queues, so we should never get a second deferred * frame for the RA/TID. */ - iwl_mvm_start_mac_queues(mvm, info->hw_queue); + iwl_mvm_start_mac_queues(mvm, BIT(info->hw_queue)); ieee80211_free_txskb(mvm->hw, skb); } } -- GitLab From 97bce57bd7f96e1218751996f549a6e61f18cc8c Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Fri, 1 Sep 2017 17:59:15 +0300 Subject: [PATCH 0026/1507] iwlwifi: mvm: use IWL_HCMD_NOCOPY for MCAST_FILTER_CMD The MCAST_FILTER_CMD can get quite large when we have many mcast addresses to set (we support up to 255). So the command should be send as NOCOPY to prevent a warning caused by too-long commands: WARNING: CPU: 0 PID: 9700 at /root/iwlwifi/stack-dev/drivers/net/wireless/intel/iwlwifi/pcie/tx.c:1550 iwl_pcie_enqueue_hcmd+0x8c7/0xb40 [iwlwifi] Command MCAST_FILTER_CMD (0x1d0) is too large (328 bytes) This fixes: https://bugzilla.kernel.org/show_bug.cgi?id=196743 Cc: stable@vger.kernel.org Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 3a6ce4222ff54..635db63f972ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1546,6 +1546,11 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac, struct iwl_mvm_mc_iter_data *data = _data; struct iwl_mvm *mvm = data->mvm; struct iwl_mcast_filter_cmd *cmd = mvm->mcast_filter_cmd; + struct iwl_host_cmd hcmd = { + .id = MCAST_FILTER_CMD, + .flags = CMD_ASYNC, + .dataflags[0] = IWL_HCMD_DFL_NOCOPY, + }; int ret, len; /* if we don't have free ports, mcast frames will be dropped */ @@ -1560,7 +1565,10 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac, memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN); len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4); - ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd); + hcmd.len[0] = len; + hcmd.data[0] = cmd; + + ret = iwl_mvm_send_cmd(mvm, &hcmd); if (ret) IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret); } -- GitLab From 61e7d91bcf7725b9fcd9cbfc5fa0e0f84f19e6de Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Fri, 1 Sep 2017 18:57:35 +0300 Subject: [PATCH 0027/1507] iwlwifi: mvm: handle FIF_ALLMULTI when setting multicast addresses We were ignoring the FIF_ALLMULTI flag when setting the multicast addresses with MCAST_FILTER_CMD. Check if this flag is set and enable pass_all accordingly. We also need to set the count to 0 if pass_all is enable so we don't pass addresses to the firmware when not needed (as doing so causes an assert). This fixes https://bugzilla.kernel.org/show_bug.cgi?id=196741 Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 635db63f972ee..3bcaa82f59b2d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1643,6 +1643,12 @@ static void iwl_mvm_configure_filter(struct ieee80211_hw *hw, if (!cmd) goto out; + if (changed_flags & FIF_ALLMULTI) + cmd->pass_all = !!(*total_flags & FIF_ALLMULTI); + + if (cmd->pass_all) + cmd->count = 0; + iwl_mvm_recalc_multicast(mvm); out: mutex_unlock(&mvm->mutex); -- GitLab From 3f497de997c7ed34ad8a90b64f1ca53a41d428b4 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 2 Sep 2017 11:05:22 +0300 Subject: [PATCH 0028/1507] iwlwifi: mvm: initialize status in iwl_mvm_add_int_sta_common() We always need to initialize the status argument to the success case before calling iwl_mvm_send_cmd_status() or iwl_mvm_send_cmd_pdu_status() (which calls the former) otherwise we may get an uninitialized value back. In this case, we use ADD_STA_SUCCESS as success. Fixes: 732d06e9d9cf ("iwlwifi: mvm: add station before allocating a queue") Reported by: Dan Carpenter Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 2dafe9bb4d8b9..c4a343534c5ea 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -1285,7 +1285,7 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm, { struct iwl_mvm_add_sta_cmd cmd; int ret; - u32 status; + u32 status = ADD_STA_SUCCESS; lockdep_assert_held(&mvm->mutex); -- GitLab From d460f1fb83a44833a09c8eaa34b30ce553cab8c5 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Sat, 2 Sep 2017 11:25:40 +0300 Subject: [PATCH 0029/1507] iwlwifi: mvm: set status before calling iwl_mvm_send_cmd_status() We always must set the status to what we consider success before calling iwl_mvm_send_cmd_status() (also iwl_mvm_send_cmd_pdu_status() which calls it). Fix a few places where initialization is missing. Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/tt.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 50983615dce67..774122fed454f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -555,7 +555,7 @@ static int iwl_mvm_lmac_scan_abort(struct iwl_mvm *mvm) struct iwl_host_cmd cmd = { .id = SCAN_OFFLOAD_ABORT_CMD, }; - u32 status; + u32 status = CAN_ABORT_STATUS; ret = iwl_mvm_send_cmd_status(mvm, &cmd, &status); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c index 8876c2abc440e..4d907f60bce9f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c @@ -529,6 +529,7 @@ int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state) lockdep_assert_held(&mvm->mutex); + status = 0; ret = iwl_mvm_send_cmd_pdu_status(mvm, WIDE_ID(PHY_OPS_GROUP, CTDP_CONFIG_CMD), sizeof(cmd), &cmd, &status); -- GitLab From 5f90472c00ddf1e64c2865f71cced297bd5f80a2 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Mon, 4 Sep 2017 20:27:04 +0300 Subject: [PATCH 0030/1507] iwlwifi: mvm: fix reorder buffer for 9000 devices The condition to check if reorder buffer ran out of space is faulty, as it takes into account only the NSSN. In case the head SN was too far behind the reorder buffer should move forward, regardless of the NSSN status. This caused the driver to release packets out of order in some scenarios. Fixes: b915c10174fb ("iwlwifi: mvm: add reorder buffer per queue") Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 67ffd9774712b..77f77bc5d0834 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -672,11 +672,12 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * If there was a significant jump in the nssn - adjust. * If the SN is smaller than the NSSN it might need to first go into * the reorder buffer, in which case we just release up to it and the - * rest of the function will take of storing it and releasing up to the - * nssn + * rest of the function will take care of storing it and releasing up to + * the nssn */ if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size, - buffer->buf_size)) { + buffer->buf_size) || + !ieee80211_sn_less(sn, buffer->head_sn + buffer->buf_size)) { u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn; iwl_mvm_release_frames(mvm, sta, napi, buffer, min_sn); -- GitLab From cac72b990d34f4c70208998a86f910ba38253c94 Mon Sep 17 00:00:00 2001 From: Lyude Date: Sat, 22 Jul 2017 21:15:09 -0400 Subject: [PATCH 0031/1507] HID: rmi: Make sure the HID device is opened on resume So it looks like that suspend/resume has actually always been broken on hid-rmi. The fact it worked was a rather silly coincidence that was relying on the HID device to already be opened upon resume. This means that so long as anything was reading the /dev/input/eventX node for for an RMI device, it would suspend and resume correctly. As well, if nothing happened to be keeping the HID device away it would shut off, then the RMI driver would get confused on resume when it stopped responding and explode. So, call hid_hw_open() in rmi_post_resume() so we make sure that the device is alive before we try talking to it. This fixes RMI device suspend/resume over HID. Link: https://bugzilla.kernel.org/show_bug.cgi?id=196851 [jkosina@suse.cz: removed useless hunk that was zero-initializing 'ret'] Signed-off-by: Lyude Cc: Andrew Duggan Cc: stable@vger.kernel.org Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-rmi.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 5b40c26145993..ef241d66562e0 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -436,17 +436,24 @@ static int rmi_post_resume(struct hid_device *hdev) if (!(data->device_flags & RMI_DEVICE)) return 0; - ret = rmi_reset_attn_mode(hdev); + /* Make sure the HID device is ready to receive events */ + ret = hid_hw_open(hdev); if (ret) return ret; + ret = rmi_reset_attn_mode(hdev); + if (ret) + goto out; + ret = rmi_driver_resume(rmi_dev, false); if (ret) { hid_warn(hdev, "Failed to resume device: %d\n", ret); - return ret; + goto out; } - return 0; +out: + hid_hw_close(hdev); + return ret; } #endif /* CONFIG_PM */ -- GitLab From bfaa1ce809bbcd12b1399409ab1dbf0cdaba6e27 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 8 Sep 2017 15:13:33 +0100 Subject: [PATCH 0032/1507] drm/amdkfd: check for null dev to avoid a null pointer dereference The call to kfd_device_by_id can potentially return null, so check that dev is null and return with -EINVAL to avoid a null pointer dereference. Detected by CoverityScan CID#1454629 ("Dereference null return value") Fixes: 5d71dbc3a588 ("drm/amdkfd: Implement image tiling mode support v2") Signed-off-by: Colin Ian King Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e4a8c2e52cb2c..660b3fbade419 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -892,6 +892,8 @@ static int kfd_ioctl_get_tile_config(struct file *filep, int err = 0; dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; dev->kfd2kgd->get_tile_config(dev->kgd, &config); -- GitLab From c5d4d7d83165ae863954b113c7f403d8b58febed Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 4 Sep 2017 10:28:02 +0200 Subject: [PATCH 0033/1507] xfrm: Fix deletion of offloaded SAs on failure. When we off load a SA, it gets pushed to the NIC before we can add it. In case of a failure, we don't delete this SA from the NIC. Fix this by calling xfrm_dev_state_delete on failure. Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Reported-by: Shannon Nelson Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2bfbd9121e3b2..b997f1395357e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -657,6 +657,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) { x->km.state = XFRM_STATE_DEAD; + xfrm_dev_state_delete(x); __xfrm_state_put(x); goto out; } -- GitLab From 67a63387b1417b5954eedb15f638f1f0bee3da49 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 4 Sep 2017 10:59:55 +0200 Subject: [PATCH 0034/1507] xfrm: Fix negative device refcount on offload failure. Reset the offload device at the xfrm_state if the device was not able to offload the state. Otherwise we drop the device refcount twice. Fixes: d77e38e612a0 ("xfrm: Add an IPsec hardware offloading API") Reported-by: Shannon Nelson Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_device.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index acf00104ef312..30e5746085b8f 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -91,6 +91,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { + xso->dev = NULL; dev_put(dev); return 0; } -- GitLab From b0e07da3f5c8d069d186a7983ff64eaebf2ea230 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Mon, 11 Sep 2017 11:39:50 +0200 Subject: [PATCH 0035/1507] qxl: fix primary surface handling The atomic conversion of the qxl driver didn't got the primary surface handling completely right. It works in the common simple cases, but fails for example when changing the display resolution using xrandr or in multihead setups. The rules are simple: There is one primary surface. Before defining a new one you have to destroy the old one. This patch makes qxl_primary_atomic_update() destroy the primary surface before defining a new one. It fixes is_primary flag updates. It adds is_primary checks so we don't try to update the primary surface in case it already has the state we want it being in. Fixes: 3538e80a869b ("drm: qxl: Atomic phase 1: Implement mode_set_nofb") Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102338 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196777 Signed-off-by: Gerd Hoffmann Reviewed-by: Gabriel Krisman Bertazi Link: http://patchwork.freedesktop.org/patch/msgid/20170911093950.22401-1-kraxel@redhat.com --- drivers/gpu/drm/qxl/qxl_display.c | 34 +++++++++++++++++-------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 03fe182203ce9..7babdd8f20fd4 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -512,23 +512,25 @@ static void qxl_primary_atomic_update(struct drm_plane *plane, .y2 = qfb->base.height }; - if (!old_state->fb) { - qxl_io_log(qdev, - "create primary fb: %dx%d,%d,%d\n", - bo->surf.width, bo->surf.height, - bo->surf.stride, bo->surf.format); + if (old_state->fb) { + qfb_old = to_qxl_framebuffer(old_state->fb); + bo_old = gem_to_qxl_bo(qfb_old->obj); + } else { + bo_old = NULL; + } - qxl_io_create_primary(qdev, 0, bo); - bo->is_primary = true; + if (bo == bo_old) return; - } else { - qfb_old = to_qxl_framebuffer(old_state->fb); - bo_old = gem_to_qxl_bo(qfb_old->obj); + if (bo_old && bo_old->is_primary) { + qxl_io_destroy_primary(qdev); bo_old->is_primary = false; } - bo->is_primary = true; + if (!bo->is_primary) { + qxl_io_create_primary(qdev, 0, bo); + bo->is_primary = true; + } qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1); } @@ -537,13 +539,15 @@ static void qxl_primary_atomic_disable(struct drm_plane *plane, { struct qxl_device *qdev = plane->dev->dev_private; - if (old_state->fb) - { struct qxl_framebuffer *qfb = + if (old_state->fb) { + struct qxl_framebuffer *qfb = to_qxl_framebuffer(old_state->fb); struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj); - qxl_io_destroy_primary(qdev); - bo->is_primary = false; + if (bo->is_primary) { + qxl_io_destroy_primary(qdev); + bo->is_primary = false; + } } } -- GitLab From 23e9fcfef1f3d10675acce023592796851bcaf1a Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Tue, 12 Sep 2017 14:53:46 +0300 Subject: [PATCH 0036/1507] vti: fix NULL dereference in xfrm_input() Can be reproduced with LTP tests: # icmp-uni-vti.sh -p ah -a sha256 -m tunnel -S fffffffe -k 1 -s 10 IPv4: RIP: 0010:xfrm_input+0x7f9/0x870 ... Call Trace: vti_input+0xaa/0x110 [ip_vti] ? skb_free_head+0x21/0x40 vti_rcv+0x33/0x40 [ip_vti] xfrm4_ah_rcv+0x33/0x60 ip_local_deliver_finish+0x94/0x1e0 ip_local_deliver+0x6f/0xe0 ? ip_route_input_noref+0x28/0x50 ... # icmp-uni-vti.sh -6 -p ah -a sha256 -m tunnel -S fffffffe -k 1 -s 10 IPv6: RIP: 0010:xfrm_input+0x7f9/0x870 ... Call Trace: xfrm6_rcv_tnl+0x3c/0x40 vti6_rcv+0xd5/0xe0 [ip6_vti] xfrm6_ah_rcv+0x33/0x60 ip6_input_finish+0xee/0x460 ip6_input+0x3f/0xb0 ip6_rcv_finish+0x45/0xa0 ipv6_rcv+0x34b/0x540 xfrm_input() invokes xfrm_rcv_cb() -> vti_rcv_cb(), the last callback might call skb_scrub_packet(), which in turn can reset secpath. Fix it by adding a check that skb->sp is not NULL. Fixes: 7e9e9202bccc ("xfrm: Clear RX SKB secpath xfrm_offload") Signed-off-by: Alexey Kodanev Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2515cd2bc5db1..8ac9d32fb79d8 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -429,7 +429,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) nf_reset(skb); if (decaps) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return 0; @@ -440,7 +441,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async); if (xfrm_gro) { - skb->sp->olen = 0; + if (skb->sp) + skb->sp->olen = 0; skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return err; -- GitLab From 5a642e6bc49f59922e19ebd639e74f72753fc77b Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 8 Sep 2017 16:24:32 +0200 Subject: [PATCH 0037/1507] etnaviv: fix submit error path If the gpu submit fails, bail out to avoid accessing a potentially unititalized fence. CC: stable@vger.kernel.org #4.12+ Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 6463fc2c736fd..b95362186f9c8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -445,8 +445,10 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, cmdbuf->user_size = ALIGN(args->stream_size, 8); ret = etnaviv_gpu_submit(gpu, submit, cmdbuf); - if (ret == 0) - cmdbuf = NULL; + if (ret) + goto out; + + cmdbuf = NULL; if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) { /* -- GitLab From 518417525f3652c12fb5fad6da4ade66c0072fa3 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 11 Sep 2017 15:29:31 +0200 Subject: [PATCH 0038/1507] etnaviv: fix gem object list corruption All manipulations of the gem_object list need to be protected by the list mutex, as GEM objects can be created and freed in parallel. This fixes a kernel memory corruption. CC: stable@vger.kernel.org Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 9a3bea7383302..87b95eeedd9e8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -551,12 +551,15 @@ static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { void etnaviv_gem_free_object(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); + struct etnaviv_drm_private *priv = obj->dev->dev_private; struct etnaviv_vram_mapping *mapping, *tmp; /* object should not be active */ WARN_ON(is_active(etnaviv_obj)); + mutex_lock(&priv->gem_lock); list_del(&etnaviv_obj->gem_node); + mutex_unlock(&priv->gem_lock); list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list, obj_node) { -- GitLab From 8320caeeffdefec3b58b9d4a7ed8e1079492fe7b Mon Sep 17 00:00:00 2001 From: Adrian Salido Date: Fri, 8 Sep 2017 10:55:27 -0700 Subject: [PATCH 0039/1507] HID: i2c-hid: allocate hid buffers for real worst case The buffer allocation is not currently accounting for an extra byte for the report id. This can cause an out of bounds access in function i2c_hid_set_or_send_report() with reportID > 15. Cc: stable@vger.kernel.org Signed-off-by: Adrian Salido Reviewed-by: Benson Leung Signed-off-by: Guenter Roeck Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- drivers/hid/i2c-hid/i2c-hid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 77396145d2d09..9145c2129a967 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -543,7 +543,8 @@ static int i2c_hid_alloc_buffers(struct i2c_hid *ihid, size_t report_size) { /* the worst case is computed from the set_report command with a * reportID > 15 and the maximum report length */ - int args_len = sizeof(__u8) + /* optional ReportID byte */ + int args_len = sizeof(__u8) + /* ReportID */ + sizeof(__u8) + /* optional ReportID byte */ sizeof(__u16) + /* data register */ sizeof(__u16) + /* size of the report */ report_size; /* report */ -- GitLab From 993f0d93f8538c15bd5c12a1a9fd74c777efea1b Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Thu, 7 Sep 2017 17:44:12 -0700 Subject: [PATCH 0040/1507] HID: wacom: generic: Send MSC_SERIAL and ABS_MISC when leaving prox The latest generation of pro devices (MobileStudio Pro, 2nd-gen Intuos Pro, Cintiq Pro) send a serial number of '0' whenever the pen is too far away for reliable communication. Userspace defines that a serial number of '0' is invalid, so we need to be careful not to actually forward this value. Additionally, since EMR ISDv4 devices do not support serial numbers or tool IDs, we'd like to not send these events if they aren't necessary. The existing code achieves these goals by adding a check for a non-zero serial number within the wacom_wac_pen_report function. The MSC_SERIAL and ABS_MISC events are only sent if the serial number is non-zero. This code fails, however when the pen for a pro device leaves proximity. When the pen leaves prox and the tablet sends a serial of 0, wacom_wac_pen_event dutifully clears the serial number. When wacom_wac_pen_report is called, it does not send either the MSC_SERIAL of the exiting tool nor an ABS_MISC event. This patch prevents the wacom_wac_pen_event function from clearing an already-set serial number. This ensures that we have the serial number handy when exiting proximity, but requires us to manually clear it afterwards to ensure the driver does not send stale data (e.g. when switching between AES pens that report a serial nubmer of 0 for the first few fully in-proximity packets). Fixes: f85c9dc678 ("HID: wacom: generic: Support tool ID and additional tool types") Cc: stable # v4.10 Signed-off-by: Ping Cheng Signed-off-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 78d0398904dc6..e2ba36da6e209 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2141,8 +2141,10 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field wacom_wac->hid_data.tipswitch |= value; return; case HID_DG_TOOLSERIALNUMBER: - wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); - wacom_wac->serial[0] |= (__u32)value; + if (value) { + wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); + wacom_wac->serial[0] |= (__u32)value; + } return; case HID_DG_TWIST: /* @@ -2156,15 +2158,17 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field wacom_wac->hid_data.sense_state = value; return; case WACOM_HID_WD_SERIALHI: - wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); - wacom_wac->serial[0] |= ((__u64)value) << 32; - /* - * Non-USI EMR devices may contain additional tool type - * information here. See WACOM_HID_WD_TOOLTYPE case for - * more details. - */ - if (value >> 20 == 1) { - wacom_wac->id[0] |= value & 0xFFFFF; + if (value) { + wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF); + wacom_wac->serial[0] |= ((__u64)value) << 32; + /* + * Non-USI EMR devices may contain additional tool type + * information here. See WACOM_HID_WD_TOOLTYPE case for + * more details. + */ + if (value >> 20 == 1) { + wacom_wac->id[0] |= value & 0xFFFFF; + } } return; case WACOM_HID_WD_TOOLTYPE: @@ -2279,6 +2283,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev, if (!prox) { wacom_wac->tool[0] = 0; wacom_wac->id[0] = 0; + wacom_wac->serial[0] = 0; } } -- GitLab From 92380b572d95caf48f8424746aeee63c5a2b1922 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Thu, 7 Sep 2017 17:47:38 -0700 Subject: [PATCH 0041/1507] HID: wacom: generic: Clear ABS_MISC when tool leaves proximity The tool ID information sent in ABS_MISC is expected to be reset to 0 when a tool leaves proximity. Not doing this can cause problems if a tool is removed and then re-introduced. Kernel event filtering will prevent the (identical) ABS_MISC event from being sent when the tool re-enters proxmity. This can cause userspace to not properly set the tool ID. Fixes: f85c9dc678 ("HID: wacom: generic: Support tool ID and additional tool types") Cc: stable # v4.10 Signed-off-by: Ping Cheng Signed-off-by: Jason Gerecke Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index e2ba36da6e209..aa692e28b2cd6 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2272,7 +2272,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev, input_report_key(input, wacom_wac->tool[0], prox); if (wacom_wac->serial[0]) { input_event(input, EV_MSC, MSC_SERIAL, wacom_wac->serial[0]); - input_report_abs(input, ABS_MISC, id); + input_report_abs(input, ABS_MISC, prox ? id : 0); } wacom_wac->hid_data.tipswitch = false; -- GitLab From d0b6e0a8ef24b1b07078ababe5d91bcdf4f4264a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Sep 2017 21:36:55 +0200 Subject: [PATCH 0042/1507] watchdog/hardlockup: Provide interface to stop/restart perf events Provide an interface to stop and restart perf NMI watchdog events on all CPUs. This is only usable during init and especially for handling the perf HT bug on Intel machines. It's safe to use it this way as nothing can start/stop the NMI watchdog in parallel. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.167649596@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 4 ++++ kernel/watchdog_hld.c | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a36abe2da13e1..b24d4a58674aa 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -75,7 +75,11 @@ static inline void hardlockup_detector_disable(void) {} #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); +extern void hardlockup_detector_perf_stop(void); +extern void hardlockup_detector_perf_restart(void); #else +static inline void hardlockup_detector_perf_stop(void) { } +static inline void hardlockup_detector_perf_restart(void) { } #if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline void arch_touch_nmi_watchdog(void) {} #endif diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d5..c9586ebc2e985 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -261,3 +261,44 @@ void watchdog_nmi_disable(unsigned int cpu) firstcpu_err = 0; } } + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} + +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} -- GitLab From 2406e3b166eee42777a6b0b38f52f924454474d7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 12 Sep 2017 21:36:56 +0200 Subject: [PATCH 0043/1507] perf/x86/intel, watchdog/core: Sanitize PMU HT bug workaround The lockup_detector_suspend/resume() interface is broken in several ways especially as it results in recursive locking of the CPU hotplug lock. Use the new stop/restart interface in the perf NMI watchdog to temporarily disable and reenable the already active watchdog events. That's enough to handle it. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.247141871@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 829e89cfcee2d..9fb9a1f1e47bd 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void) return 0; } - if (lockup_detector_suspend() != 0) { - pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); - return 0; - } + cpus_read_lock(); + + hardlockup_detector_perf_stop(); x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); @@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void) x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - lockup_detector_resume(); - - cpus_read_lock(); + hardlockup_detector_perf_restart(); for_each_online_cpu(c) free_excl_cntrs(c); -- GitLab From 6554fd8cf06db86f861bb24d7487b2873ca444c4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:36:57 +0200 Subject: [PATCH 0044/1507] watchdog/core: Provide interface to stop from poweroff() PARISC has a a busy looping power off routine. If the watchdog is enabled the watchdog timer will still fire, but the thread is not running, which causes the softlockup watchdog to trigger. Provide a interface which allows to turn the watchdog off. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Helge Deller Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linux-parisc@vger.kernel.org Link: http://lkml.kernel.org/r/20170912194146.327343752@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 +++--- kernel/watchdog.c | 14 +++++++++++++- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index b24d4a58674aa..85bb268be39ce 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -12,10 +12,10 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); +void lockup_detector_soft_poweroff(void); #else -static inline void lockup_detector_init(void) -{ -} +static inline void lockup_detector_init(void) { } +static inline void lockup_detector_soft_poweroff(void) { } #endif #ifdef CONFIG_SOFTLOCKUP_DETECTOR diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b72..f23e373aa3bfc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -333,7 +333,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled || + atomic_read(&watchdog_park_in_progress) != 0) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -660,6 +661,17 @@ static void set_sample_period(void) } #endif /* SOFTLOCKUP */ +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. + */ +void lockup_detector_soft_poweroff(void) +{ + watchdog_enabled = 0; +} + /* * Suspend the hard and soft lockup detector by parking the watchdog threads. */ -- GitLab From 47bb4baf7df43ac8bbc51c24022466972ba29ef1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:36:58 +0200 Subject: [PATCH 0045/1507] parisc, watchdog/core: Use lockup_detector_stop() The broken lockup_detector_suspend/resume() interface is going away. Use the new lockup_detector_soft_poweroff() interface to stop the watchdog from the busy looping power off routine. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Helge Deller Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linux-parisc@vger.kernel.org Link: http://lkml.kernel.org/r/20170912194146.407385557@linutronix.de Signed-off-by: Ingo Molnar --- arch/parisc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index a45a67d526f8c..30f92391a93ef 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -146,7 +146,7 @@ void machine_power_off(void) /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); - lockup_detector_suspend(); + lockup_detector_soft_poweroff(); for (;;); } -- GitLab From 5490125d77a43016b26f629d4b485e2c62172551 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:36:59 +0200 Subject: [PATCH 0046/1507] watchdog/core: Remove broken suspend/resume interfaces This interface has several issues: - It's causing recursive locking of the hotplug lock. - It's complete overkill to teardown all threads and then recreate them The same can be achieved with the simple hardlockup_detector_perf_stop / restart() interfaces. The abuse from the busy looping poweroff() loop of PARISC has been solved as well. Remove the cruft. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.487537732@linutronix.de Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/watchdog.c | 3 -- include/linux/nmi.h | 12 ----- kernel/watchdog.c | 89 +--------------------------------- 3 files changed, 1 insertion(+), 103 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2f6eadd9408d9..5ded171f02d6b 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return 0; - if (watchdog_suspended) - return 0; - if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 85bb268be39ce..7eefe7abf44b0 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -164,7 +164,6 @@ extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; @@ -192,17 +191,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int lockup_detector_suspend(void); -extern void lockup_detector_resume(void); -#else -static inline int lockup_detector_suspend(void) -{ - return 0; -} - -static inline void lockup_detector_resume(void) -{ -} #endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f23e373aa3bfc..b2d46757917ec 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -97,19 +97,6 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); * unregistered/stopped, so it is an indicator whether the threads exist. */ static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; /* * These functions can be overridden if an architecture implements its @@ -136,7 +123,6 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * - watchdog_cpumask * - sysctl_hardlockup_all_cpu_backtrace * - hardlockup_panic - * - watchdog_suspended */ void __weak watchdog_nmi_reconfigure(void) { @@ -672,61 +658,6 @@ void lockup_detector_soft_poweroff(void) watchdog_enabled = 0; } -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. - */ -int lockup_detector_suspend(void) -{ - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; -} - -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. - */ -void lockup_detector_resume(void) -{ - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); -} - #ifdef CONFIG_SYSCTL /* @@ -775,12 +706,6 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - /* * If the parameter is being read return the state of the corresponding * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the @@ -872,12 +797,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - old = ACCESS_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -917,12 +836,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, get_online_cpus(); mutex_lock(&watchdog_proc_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) { /* Remove impossible cpus to keep sysctl output cleaner. */ @@ -941,7 +854,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, watchdog_nmi_reconfigure(); } -out: + mutex_unlock(&watchdog_proc_mutex); put_online_cpus(); return err; -- GitLab From b7a349819d4b9b5db64e523351e66a79a758eaa5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:00 +0200 Subject: [PATCH 0047/1507] watchdog/core: Rework CPU hotplug locking The watchdog proc interface causes extensive recursive locking of the CPU hotplug percpu rwsem, which is deadlock prone. Replace the get/put_online_cpus() pairs with cpu_hotplug_disable()/enable() calls for now. Later patches will remove that requirement completely. Reported-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.568079057@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index b2d46757917ec..cd79f644ea34f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -703,7 +703,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, int err, old, new; int *watchdog_param = (int *)table->data; - get_online_cpus(); + cpu_hotplug_disable(); mutex_lock(&watchdog_proc_mutex); /* @@ -752,7 +752,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, } out: mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + cpu_hotplug_enable(); return err; } @@ -794,7 +794,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, { int err, old, new; - get_online_cpus(); + cpu_hotplug_disable(); mutex_lock(&watchdog_proc_mutex); old = ACCESS_ONCE(watchdog_thresh); @@ -818,7 +818,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, } out: mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + cpu_hotplug_enable(); return err; } @@ -833,7 +833,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); + cpu_hotplug_disable(); mutex_lock(&watchdog_proc_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); @@ -856,7 +856,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, } mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + cpu_hotplug_enable(); return err; } -- GitLab From 946d197794b23202b8b46c43016747c72fe23393 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:01 +0200 Subject: [PATCH 0048/1507] watchdog/core: Rename watchdog_proc_mutex Following patches will use the mutex for other purposes as well. Rename it as it is not longer a proc specific thing. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.647714850@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index cd79f644ea34f..7c3a0a76b41ba 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,8 +29,7 @@ #include #include -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); +static DEFINE_MUTEX(watchdog_mutex); int __read_mostly nmi_watchdog_enabled; @@ -704,7 +703,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, int *watchdog_param = (int *)table->data; cpu_hotplug_disable(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); /* * If the parameter is being read return the state of the corresponding @@ -751,7 +750,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, err = proc_watchdog_update(); } out: - mutex_unlock(&watchdog_proc_mutex); + mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; } @@ -795,7 +794,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, int err, old, new; cpu_hotplug_disable(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); old = ACCESS_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); @@ -817,7 +816,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, set_sample_period(); } out: - mutex_unlock(&watchdog_proc_mutex); + mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; } @@ -834,7 +833,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, int err; cpu_hotplug_disable(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) { @@ -855,7 +854,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, watchdog_nmi_reconfigure(); } - mutex_unlock(&watchdog_proc_mutex); + mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; } -- GitLab From 7a3558200739e1378800a7a6d7f63c031115f7a4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:02 +0200 Subject: [PATCH 0049/1507] watchdog/core: Mark hardlockup_detector_disable() __init The function is only used by the KVM init code. Mark it __init to prevent creative abuse. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.727134632@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 7c3a0a76b41ba..1c185d9dd4680 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -55,7 +55,7 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; } -- GitLab From 20d853fd0703b1d73c35a22024c0d4fcbcc57c8c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:03 +0200 Subject: [PATCH 0050/1507] watchdog/hardlockup/perf: Remove broken self disable on failure The self disabling feature is broken vs. CPU hotplug locking: CPU 0 CPU 1 cpus_write_lock(); cpu_up(1) wait_for_completion() .... unpark_watchdog() ->unpark() perf_event_create() <- fails watchdog_enable &= ~NMI_WATCHDOG; .... cpus_write_unlock(); CPU 2 cpus_write_lock() cpu_down(2) wait_for_completion() wakeup(watchdog); watchdog() if (!(watchdog_enable & NMI_WATCHDOG)) watchdog_nmi_disable() perf_event_disable() .... cpus_read_lock(); stop_smpboot_threads() park_watchdog(); wait_for_completion(watchdog->parked); Result: End of hotplug and instantaneous full lockup of the machine. There is a similar problem with disabling the watchdog via the user space interface as the sysctl function fiddles with watchdog_enable directly. It's very debatable whether this is required at all. If the watchdog works nicely on N CPUs and it fails to enable on the N + 1 CPU either during hotplug or because the user space interface disabled it via sysctl cpumask and then some perf user grabbed the counter which is then unavailable for the watchdog when the sysctl cpumask gets changed back. There is no real justification for this. One of the reasons WHY this is done is the utter stupidity of the init code of the perf NMI watchdog. Instead of checking upfront at boot whether PERF is available and functional at all, it just does this check at run time over and over when user space fiddles with the sysctl. That's broken beyond repair along with the idiotic error code dependent warn level printks and the even more silly printk rate limiting. If the init code checks whether perf works at boot time, then this mess can be more or less avoided completely. Perf does not come magically into life at runtime. Brain usage while coding is overrated. Remove the cruft and add a temporary safe guard which gets removed later. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.806708429@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 15 --------------- kernel/watchdog_hld.c | 20 +++++++------------- 2 files changed, 7 insertions(+), 28 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 1c185d9dd4680..af000956286c1 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -485,21 +485,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index c9586ebc2e985..7b602714ea536 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -23,6 +23,7 @@ static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); static unsigned long hardlockup_allcpu_dumped; +static bool hardlockup_detector_disabled; void arch_touch_nmi_watchdog(void) { @@ -178,6 +179,10 @@ int watchdog_nmi_enable(unsigned int cpu) if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) goto out; + /* A failure disabled the hardlockup detector permanently */ + if (hardlockup_detector_disabled) + return -ENODEV; + /* is it already setup and enabled? */ if (event && event->state > PERF_EVENT_STATE_OFF) goto out; @@ -206,18 +211,6 @@ int watchdog_nmi_enable(unsigned int cpu) goto out_save; } - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - /* skip displaying the same error again */ if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) return PTR_ERR(event); @@ -232,7 +225,8 @@ int watchdog_nmi_enable(unsigned int cpu) pr_err("disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); - pr_info("Shutting down hard lockup detector on all cpus\n"); + pr_info("Disabling hard lockup detector permanently\n"); + hardlockup_detector_disabled = true; return PTR_ERR(event); -- GitLab From 941154bd6937a710ae9193a3c733c0029e5ae7b8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:04 +0200 Subject: [PATCH 0051/1507] watchdog/hardlockup/perf: Prevent CPU hotplug deadlock The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra Reported-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 ++++++ kernel/cpu.c | 6 ++++++ kernel/watchdog.c | 25 +++++++++++++++++++++++++ kernel/watchdog_hld.c | 34 ++++++++++++++++++++++++++++------ 4 files changed, 65 insertions(+), 6 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 7eefe7abf44b0..80354e6fa86d6 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -13,9 +13,11 @@ #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); +void lockup_detector_cleanup(void); #else static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } +static inline void lockup_detector_cleanup(void) { } #endif #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -77,9 +79,13 @@ static inline void hardlockup_detector_disable(void) {} extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); +extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_cleanup(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } +static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_cleanup(void) { } #if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline void arch_touch_nmi_watchdog(void) {} #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51f..a96b348591dfd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -734,6 +735,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index af000956286c1..dd1fd59683c52 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -109,8 +109,10 @@ int __weak watchdog_nmi_enable(unsigned int cpu) { return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } /* @@ -193,6 +195,8 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); #endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -631,6 +635,24 @@ static void set_sample_period(void) } #endif /* SOFTLOCKUP */ +static void __lockup_detector_cleanup(void) +{ + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); +} + +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. + */ +void lockup_detector_cleanup(void) +{ + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); +} + /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * @@ -665,6 +687,8 @@ static int proc_watchdog_update(void) watchdog_nmi_reconfigure(); + __lockup_detector_cleanup(); + return err; } @@ -837,6 +861,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, } watchdog_nmi_reconfigure(); + __lockup_detector_cleanup(); } mutex_unlock(&watchdog_mutex); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 7b602714ea536..94111ccb09b52 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,6 +21,8 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static DEFINE_PER_CPU(struct perf_event *, dead_event); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static bool hardlockup_detector_disabled; @@ -239,16 +241,18 @@ int watchdog_nmi_enable(unsigned int cpu) return 0; } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); - per_cpu(watchdog_ev, cpu) = NULL; - - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); + this_cpu_write(watchdog_ev, NULL); + this_cpu_write(dead_event, event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); /* watchdog_nmi_enable() expects this to be zero initially. */ if (atomic_dec_and_test(&watchdog_cpus)) @@ -256,6 +260,24 @@ void watchdog_nmi_disable(unsigned int cpu) } } +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(dead_event, cpu); + + per_cpu(dead_event, cpu) = NULL; + perf_event_release_kernel(event); + } + cpumask_clear(&dead_events_mask); +} + /** * hardlockup_detector_perf_stop - Globally stop watchdog events * -- GitLab From 01f0a02701cbcf32d22cfc9d1ab9a3f0ff2ba68c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:05 +0200 Subject: [PATCH 0052/1507] watchdog/core: Remove the park_in_progress obfuscation Commit: b94f51183b06 ("kernel/watchdog: prevent false hardlockup on overloaded system") tries to fix the following issue: proc_write() set_sample_period() <--- New sample period becoms visible <----- Broken starts proc_watchdog_update() watchdog_enable_all_cpus() watchdog_hrtimer_fn() update_watchdog_all_cpus() restart_timer(sample_period) watchdog_park_threads() thread->park() disable_nmi() <----- Broken ends The reason why this is broken is that the update of the watchdog threshold becomes immediately effective and visible for the hrtimer function which uses that value to rearm the timer. But the NMI/perf side still uses the old value up to the point where it is disabled. If the rate has been lowered then the NMI can run fast enough to 'detect' a hard lockup because the timer has not fired due to the longer period. The patch 'fixed' this by adding a variable: proc_write() set_sample_period() <----- Broken starts proc_watchdog_update() watchdog_enable_all_cpus() watchdog_hrtimer_fn() update_watchdog_all_cpus() restart_timer(sample_period) watchdog_park_threads() park_in_progress = 1 <----- Broken ends nmi_watchdog() if (park_in_progress) return; The only effect of this variable was to make the window where the breakage can hit small enough that it was not longer observable in testing. From a correctness point of view it is a pointless bandaid which merily papers over the root cause: the unsychronized update of the variable. Looking deeper into the related code pathes unearthed similar problems in the watchdog_start()/stop() functions. watchdog_start() perf_nmi_event_start() hrtimer_start() watchdog_stop() hrtimer_cancel() perf_nmi_event_stop() In both cases the call order is wrong because if the tasks gets preempted or the VM gets scheduled out long enough after the first call, then there is a chance that the next NMI will see a stale hrtimer interrupt count and trigger a false positive hard lockup splat. Get rid of park_in_progress so the code can be gradually deobfuscated and pruned from several layers of duct tape papering over the root cause, which has been either ignored or not understood at all. Once this is removed the underlying problem will be fixed by rewriting the proc interface to do a proper synchronized update. Address the start/stop() ordering problem as well by reverting the call order, so this part is at least correct now. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1709052038270.2393@nanos Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 1 - kernel/watchdog.c | 37 +++++++++++++++++-------------------- kernel/watchdog_hld.c | 7 ++----- 3 files changed, 19 insertions(+), 26 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 80354e6fa86d6..91a3a4a4c8ae3 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -27,7 +27,6 @@ extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; extern int soft_watchdog_enabled; -extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { diff --git a/kernel/watchdog.c b/kernel/watchdog.c index dd1fd59683c52..c290135fb415f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -136,8 +136,6 @@ void __weak watchdog_nmi_reconfigure(void) #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); - static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -322,8 +320,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (!watchdog_enabled || - atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -437,32 +434,37 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); + /* Initialize timestamp */ + __touch_watchdog(); /* Enable the perf event */ watchdog_nmi_enable(cpu); - /* done here because hrtimer_start can only pin to smp_processor_id() */ - hrtimer_start(hrtimer, ns_to_ktime(sample_period), - HRTIMER_MODE_REL_PINNED); - - /* initialize timestamp */ watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); - __touch_watchdog(); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -518,16 +520,11 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; - atomic_set(&watchdog_park_in_progress, 1); - for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } - - atomic_set(&watchdog_park_in_progress, 0); - return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 94111ccb09b52..0aa191ee3d517 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -106,15 +106,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; -- GitLab From 2b9d7f233b835663cbc7b6b3f88dd20f61118d1e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:06 +0200 Subject: [PATCH 0053/1507] watchdog/core: Clean up stub functions Having stub functions which take a full page is not helping the readablility of code. Condense them and move the doubled #ifdef variant into the SYSFS section. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.045545271@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 68 +++++++++++++++-------------------------------- 1 file changed, 22 insertions(+), 46 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index c290135fb415f..af37c040436c9 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -125,10 +125,7 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * - sysctl_hardlockup_all_cpu_backtrace * - hardlockup_panic */ -void __weak watchdog_nmi_reconfigure(void) -{ -} - +void __weak watchdog_nmi_reconfigure(void) { } #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -136,6 +133,11 @@ void __weak watchdog_nmi_reconfigure(void) #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +int __read_mostly soft_watchdog_enabled; + static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -149,13 +151,9 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); @@ -593,44 +591,13 @@ static void watchdog_disable_all_cpus(void) } } -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif - -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} - -static void watchdog_unpark_threads(void) -{ -} - -static int watchdog_enable_all_cpus(void) -{ - return 0; -} - -static void watchdog_disable_all_cpus(void) -{ -} - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return 0; -} -#endif - -static void set_sample_period(void) -{ -} -#endif /* SOFTLOCKUP */ +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static inline void set_sample_period(void) { } +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) { @@ -827,6 +794,15 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, return err; } +static int watchdog_update_cpus(void) +{ + if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) { + return smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_cpumask); + } + return 0; +} + /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the -- GitLab From 368a7e2ce8ff0ddcdcb37eadb76530b033f6eb2d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:07 +0200 Subject: [PATCH 0054/1507] watchdog/core: Clean up the #ifdef maze The #ifdef maze in this file is horrible, group stuff at least a bit so one can figure out what belongs to what. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.139629546@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index af37c040436c9..a9bdfde73e4b2 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -41,7 +41,6 @@ unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -74,19 +73,21 @@ static int __init hardlockup_panic_setup(char *str) } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif +# ifdef CONFIG_SMP +int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ int __read_mostly watchdog_user_enabled; int __read_mostly watchdog_thresh = 10; -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; -int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -173,22 +174,14 @@ static int __init nosoftlockup_setup(char *str) __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif static void __lockup_detector_cleanup(void); -- GitLab From 05ba3de74a3f499dcaa37b186220aaf174c95a4b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:08 +0200 Subject: [PATCH 0055/1507] watchdog/core: Split out cpumask write function Split the write part of the cpumask proc handler out into a separate helper to avoid deep indentation. This also reduces the patch complexity in the following cleanups. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.218075991@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 40 +++++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index a9bdfde73e4b2..cedf45ab4d81e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -792,10 +792,29 @@ static int watchdog_update_cpus(void) if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) { return smpboot_update_cpumask_percpu_thread(&watchdog_threads, &watchdog_cpumask); + __lockup_detector_cleanup(); } return 0; } +static void proc_watchdog_cpumask_update(void) +{ + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + + if (watchdog_running) { + /* + * Failure would be due to being unable to allocate a + * temporary cpumask, so we are likely not in a position to + * do much else to make things better. + */ + if (watchdog_update_cpus() != 0) + pr_err("cpumask update failed\n"); + } + + watchdog_nmi_reconfigure(); +} + /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the @@ -811,30 +830,13 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } - - watchdog_nmi_reconfigure(); - __lockup_detector_cleanup(); - } + if (!err && write) + proc_watchdog_cpumask_update(); mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) -- GitLab From 0d85923c7a81719567311ba0eae8ecb2efd4c8a0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:09 +0200 Subject: [PATCH 0056/1507] smpboot/threads, watchdog/core: Avoid runtime allocation smpboot_update_cpumask_threads_percpu() allocates a temporary cpumask at runtime. This is suboptimal because the call site needs more code size for proper error handling than a statically allocated temporary mask requires data size. Add static temporary cpumask. The function is globaly serialized, so no further protection required. Remove the half baken error handling in the watchdog code and get rid of the export as there are no in tree modular users of that function. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.297288838@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/smpboot.h | 4 ++-- kernel/smpboot.c | 22 +++++++--------------- kernel/watchdog.c | 21 +++++---------------- 3 files changed, 14 insertions(+), 33 deletions(-) diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 12910cf19869c..c149aa7bedf30 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) } void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread); -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *); +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *); #endif diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a9515..ed7507b69b480 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,31 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - get_online_cpus(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index cedf45ab4d81e..8935a3a4c2fb9 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -787,31 +787,20 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, return err; } -static int watchdog_update_cpus(void) +static void watchdog_update_cpus(void) { - if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) { - return smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_cpumask); + if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR) && watchdog_running) { + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_cpumask); __lockup_detector_cleanup(); } - return 0; } static void proc_watchdog_cpumask_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate a - * temporary cpumask, so we are likely not in a position to - * do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } - + watchdog_update_cpus(); watchdog_nmi_reconfigure(); } -- GitLab From 2eb2527f847d1bd8d8fb9db1e8139db5d6eddb36 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:10 +0200 Subject: [PATCH 0057/1507] watchdog/core: Create new thread handling infrastructure The lockup detector reconfiguration tears down all watchdog threads when the watchdog is disabled and sets them up again when its enabled. That's a pointless exercise. The watchdog threads are not consuming an insane amount of resources, so it's enough to set them up at init time and keep them in parked position when the watchdog is disabled and unpark them when it is reenabled. The smpboot thread infrastructure takes care of keeping the force parked threads in place even across cpu hotplug. Another horrible mechanism are the open coded park/unpark loops which are used for reconfiguration of the watchdog. The smpboot infrastructure allows exactly the same via smpboot_update_cpumask_thread_percpu(), which is cpu hotplug safe. Using that instead of the open coded loops allows to get rid of the hotplug locking mess in the watchdog code. Implement a clean infrastructure which allows to replace the open coded nonsense. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.377182587@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 8935a3a4c2fb9..b35518375fb7a 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -139,6 +139,9 @@ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; int __read_mostly soft_watchdog_enabled; +struct cpumask watchdog_allowed_mask __read_mostly; +static bool softlockup_threads_initialized __read_mostly; + static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -584,12 +587,84 @@ static void watchdog_disable_all_cpus(void) } } +static void softlockup_update_smpboot_threads(void) +{ + lockdep_assert_held(&watchdog_mutex); + + if (!softlockup_threads_initialized) + return; + + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); + __lockup_detector_cleanup(); +} + +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) +{ + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); +} + +/* + * Park threads which are not longer enabled and unpark threads which have + * been newly enabled. + */ +static void softlockup_update_threads(void) +{ + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); +} + +static void softlockup_reconfigure_threads(bool enabled) +{ + softlockup_park_all_threads(); + set_sample_period(); + if (enabled) + softlockup_update_threads(); +} + +/* + * Create the watchdog thread infrastructure. + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void softlockup_init_threads(void) +{ + int ret; + + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; + + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } + + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); + mutex_unlock(&watchdog_mutex); +} + #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline int watchdog_park_threads(void) { return 0; } static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } static inline void set_sample_period(void) { } +static inline void softlockup_init_threads(void) { } +static inline void softlockup_update_threads(void) { } +static inline void softlockup_reconfigure_threads(bool enabled) { } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) -- GitLab From d57108d4f6791291e89d980e7f7a3566c32ab188 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:11 +0200 Subject: [PATCH 0058/1507] watchdog/core: Get rid of the thread teardown/setup dance The lockup detector reconfiguration tears down all watchdog threads when the watchdog is disabled and sets them up again when its enabled. That's a pointless exercise. The watchdog threads are not consuming an insane amount of resources, so it's enough to set them up at init time and keep them in parked position when the watchdog is disabled and unpark them when it is reenabled. The smpboot thread infrastructure takes care of keeping the force parked threads in place even across cpu hotplug. Aside of that the code implements the park/unpark facility of smp hotplug threads on its own, which is even more pointless. We have functionality in the smpboot thread code to do so. Use the new thread management functions and get rid of the unholy mess. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.470370113@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 190 +++++----------------------------------------- 1 file changed, 19 insertions(+), 171 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index b35518375fb7a..762d3ed82a087 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -91,13 +91,6 @@ int __read_mostly watchdog_thresh = 10; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; - /* * These functions can be overridden if an architecture implements its * own hardlockup detector. @@ -130,10 +123,6 @@ void __weak watchdog_nmi_reconfigure(void) { } #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; @@ -259,11 +248,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -303,9 +296,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -498,95 +488,6 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) -{ - int cpu, ret = 0; - - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - return ret; -} - -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) -{ - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); -} - -static int update_watchdog_all_cpus(void) -{ - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; -} - -static int watchdog_enable_all_cpus(void) -{ - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; -} - -static void watchdog_disable_all_cpus(void) -{ - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} - static void softlockup_update_smpboot_threads(void) { lockdep_assert_held(&watchdog_mutex); @@ -661,7 +562,6 @@ static inline int watchdog_park_threads(void) { return 0; } static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } -static inline void set_sample_period(void) { } static inline void softlockup_init_threads(void) { } static inline void softlockup_update_threads(void) { } static inline void softlockup_reconfigure_threads(bool enabled) { } @@ -701,28 +601,10 @@ void lockup_detector_soft_poweroff(void) /* * Update the run state of the lockup detectors. */ -static int proc_watchdog_update(void) +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - + softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); watchdog_nmi_reconfigure(); - - __lockup_detector_cleanup(); - - return err; - } /* @@ -778,17 +660,8 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, new = old & ~which; } while (cmpxchg(&watchdog_enabled, old, new) != old); - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (old != new) + proc_watchdog_update(); } out: mutex_unlock(&watchdog_mutex); @@ -832,50 +705,28 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; + int err, old; cpu_hotplug_disable(); mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; - - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; } -static void watchdog_update_cpus(void) -{ - if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR) && watchdog_running) { - smpboot_update_cpumask_percpu_thread(&watchdog_threads, - &watchdog_cpumask); - __lockup_detector_cleanup(); - } -} - static void proc_watchdog_cpumask_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - watchdog_update_cpus(); + + softlockup_update_threads(); watchdog_nmi_reconfigure(); } @@ -905,8 +756,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -917,6 +766,5 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + softlockup_init_threads(); } -- GitLab From e8b62b2dd14f8f2427856ba24cb7db922bda9bfd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:12 +0200 Subject: [PATCH 0059/1507] watchdog/core: Further simplify sysctl handling Use a single function to update sysctl changes. This is not a high frequency user space interface and it's root only. Preparatory patch to cleanup the sysctl variable handling. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.549114957@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 762d3ed82a087..ca8747221e870 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -507,11 +507,8 @@ static void softlockup_park_all_threads(void) softlockup_update_smpboot_threads(); } -/* - * Park threads which are not longer enabled and unpark threads which have - * been newly enabled. - */ -static void softlockup_update_threads(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); softlockup_update_smpboot_threads(); @@ -522,7 +519,7 @@ static void softlockup_reconfigure_threads(bool enabled) softlockup_park_all_threads(); set_sample_period(); if (enabled) - softlockup_update_threads(); + softlockup_unpark_threads(); } /* @@ -563,7 +560,6 @@ static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } -static inline void softlockup_update_threads(void) { } static inline void softlockup_reconfigure_threads(bool enabled) { } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ @@ -598,11 +594,11 @@ void lockup_detector_soft_poweroff(void) #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ +/* Propagate any changes to the watchdog threads */ static void proc_watchdog_update(void) { + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); watchdog_nmi_reconfigure(); } @@ -721,15 +717,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, return err; } -static void proc_watchdog_cpumask_update(void) -{ - /* Remove impossible cpus to keep sysctl output clean. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - - softlockup_update_threads(); - watchdog_nmi_reconfigure(); -} - /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the @@ -746,7 +733,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) - proc_watchdog_cpumask_update(); + proc_watchdog_update(); mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); -- GitLab From 3b371b5936e7777c819619c00ca60f196a8e13fa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:13 +0200 Subject: [PATCH 0060/1507] watchdog/core: Clean up header mess Having the same #ifdef in various places does not make it more readable. Collect stuff into one place. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.627096864@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 60 +++++++++++++++++++-------------------------- 1 file changed, 25 insertions(+), 35 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 91a3a4a4c8ae3..cfebb3bc4eed2 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -14,11 +14,29 @@ void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); void lockup_detector_cleanup(void); +bool is_hardlockup(void); + +extern int watchdog_user_enabled; +extern int nmi_watchdog_enabled; +extern int soft_watchdog_enabled; +extern int watchdog_thresh; +extern unsigned long watchdog_enabled; + +extern struct cpumask watchdog_cpumask; +extern unsigned long *watchdog_cpumask_bits; +#ifdef CONFIG_SMP +extern int sysctl_softlockup_all_cpu_backtrace; +extern int sysctl_hardlockup_all_cpu_backtrace; #else +#define sysctl_softlockup_all_cpu_backtrace 0 +#define sysctl_hardlockup_all_cpu_backtrace 0 +#endif /* !CONFIG_SMP */ + +#else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } -#endif +#endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); @@ -26,28 +44,17 @@ extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; -extern int soft_watchdog_enabled; #else -static inline void touch_softlockup_watchdog_sched(void) -{ -} -static inline void touch_softlockup_watchdog(void) -{ -} -static inline void touch_softlockup_watchdog_sync(void) -{ -} -static inline void touch_all_softlockup_watchdogs(void) -{ -} +static inline void touch_softlockup_watchdog_sched(void) { } +static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) { } +static inline void touch_all_softlockup_watchdogs(void) { } #endif #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else -static inline void reset_hung_task_detector(void) -{ -} +static inline void reset_hung_task_detector(void) { } #endif /* @@ -92,7 +99,7 @@ static inline void arch_touch_nmi_watchdog(void) {} /** * touch_nmi_watchdog - restart NMI watchdog timeout. - * + * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. @@ -162,21 +169,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu) u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif -#ifdef CONFIG_LOCKUP_DETECTOR -extern int nmi_watchdog_enabled; -extern int watchdog_user_enabled; -extern int watchdog_thresh; -extern unsigned long watchdog_enabled; -extern struct cpumask watchdog_cpumask; -extern unsigned long *watchdog_cpumask_bits; -#ifdef CONFIG_SMP -extern int sysctl_softlockup_all_cpu_backtrace; -extern int sysctl_hardlockup_all_cpu_backtrace; -#else -#define sysctl_softlockup_all_cpu_backtrace 0 -#define sysctl_hardlockup_all_cpu_backtrace 0 -#endif - #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); @@ -184,7 +176,6 @@ void watchdog_update_hrtimer_threshold(u64 period); static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif -extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); @@ -196,7 +187,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int proc_watchdog_cpumask(struct ctl_table *, int, void __user *, size_t *, loff_t *); -#endif #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include -- GitLab From 51d4052b01ca555e0d1d5fe297b309beb6c64aa0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:14 +0200 Subject: [PATCH 0061/1507] watchdog/sysctl: Get rid of the #ifdeffery The sysctl of the nmi_watchdog file prevents writes by setting: min = max = 0 if none of the users is enabled. That involves ifdeffery and is competely non obvious. If none of the facilities is enabeld, then the file can simply be made read only. Move the ifdeffery into the header and use a constant for file permissions. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.706073616@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 ++++++ kernel/sysctl.c | 6 +----- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index cfebb3bc4eed2..5774b443dba16 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -81,6 +81,12 @@ extern unsigned int hardlockup_panic; static inline void hardlockup_detector_disable(void) {} #endif +#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) +# define NMI_WATCHDOG_SYSCTL_PERM 0644 +#else +# define NMI_WATCHDOG_SYSCTL_PERM 0444 +#endif + #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157f..539cb4e97bb8f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -891,14 +891,10 @@ static struct ctl_table kern_table[] = { .procname = "nmi_watchdog", .data = &nmi_watchdog_enabled, .maxlen = sizeof (int), - .mode = 0644, + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", -- GitLab From 7feeb9cd4f5b34476ffb9e6d58d58c5416375b19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:15 +0200 Subject: [PATCH 0062/1507] watchdog/sysctl: Clean up sysctl variable name space Reflect that these variables are user interface related and remove the whitespace damage in the sysctl table while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.783210221@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 16 ++++++++-------- kernel/sysctl.c | 16 ++++++++-------- kernel/watchdog.c | 41 ++++++++++++++++++++--------------------- 3 files changed, 36 insertions(+), 37 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 5774b443dba16..4a8d1037364ef 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -17,8 +17,8 @@ void lockup_detector_cleanup(void); bool is_hardlockup(void); extern int watchdog_user_enabled; -extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; @@ -62,12 +62,12 @@ static inline void reset_hung_task_detector(void) { } * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 539cb4e97bb8f..4c08ed4a379e3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -871,9 +871,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -889,8 +889,8 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, @@ -906,9 +906,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index ca8747221e870..baae9fc950312 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,8 +31,6 @@ static DEFINE_MUTEX(watchdog_mutex); -int __read_mostly nmi_watchdog_enabled; - #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED; @@ -40,6 +38,17 @@ unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif +int __read_mostly nmi_watchdog_user_enabled; +int __read_mostly soft_watchdog_user_enabled; +int __read_mostly watchdog_user_enabled; +int __read_mostly watchdog_thresh = 10; + +struct cpumask watchdog_allowed_mask __read_mostly; +static bool softlockup_threads_initialized __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -85,12 +94,6 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); # endif /* CONFIG_SMP */ #endif /* CONFIG_HARDLOCKUP_DETECTOR */ -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); - /* * These functions can be overridden if an architecture implements its * own hardlockup detector. @@ -113,7 +116,7 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * watchdog_nmi_reconfigure can be implemented to be notified after any * watchdog configuration change. The arch hardlockup watchdog should * respond to the following variables: - * - nmi_watchdog_enabled + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask * - sysctl_hardlockup_all_cpu_backtrace @@ -126,10 +129,6 @@ void __weak watchdog_nmi_reconfigure(void) { } /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -int __read_mostly soft_watchdog_enabled; - -struct cpumask watchdog_allowed_mask __read_mostly; -static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; @@ -606,14 +605,14 @@ static void proc_watchdog_update(void) /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) -- GitLab From 6592ad2fcc8f15b4f99b36c1db7d9f65510c203b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:16 +0200 Subject: [PATCH 0063/1507] watchdog/core, powerpc: Make watchdog_nmi_reconfigure() two stage Both the perf reconfiguration and the powerpc watchdog_nmi_reconfigure() need to be done in two steps. 1) Stop all NMIs 2) Read the new parameters and start NMIs Right now watchdog_nmi_reconfigure() is a combination of both. To allow a clean reconfiguration add a 'run' argument and split the functionality in powerpc. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20170912194147.862865570@linutronix.de Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/watchdog.c | 17 +++++++++-------- include/linux/nmi.h | 2 ++ kernel/watchdog.c | 31 ++++++++++++++++++++++--------- 3 files changed, 33 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 5ded171f02d6b..291af79a98263 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -355,17 +355,18 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(void) +void watchdog_nmi_reconfigure(bool run) { int cpu; - watchdog_calc_timeouts(); - - for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); - - for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); + if (!run) { + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + } else { + watchdog_calc_timeouts(); + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); + } } /* diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4a8d1037364ef..eee255bc0fd62 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -103,6 +103,8 @@ static inline void arch_touch_nmi_watchdog(void) {} #endif #endif +void watchdog_nmi_reconfigure(bool run); + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * diff --git a/kernel/watchdog.c b/kernel/watchdog.c index baae9fc950312..5693afd2b8eae 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -112,17 +112,25 @@ void __weak watchdog_nmi_disable(unsigned int cpu) hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: +/** + * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs + * @run: If false stop the watchdogs on all enabled CPUs + * If true start the watchdogs on all enabled CPUs + * + * The core call order is: + * watchdog_nmi_reconfigure(false); + * update_variables(); + * watchdog_nmi_reconfigure(true); + * + * The second call which starts the watchdogs again guarantees that the + * following variables are stable across the call. * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic + * + * After the call the variables can be changed again. */ -void __weak watchdog_nmi_reconfigure(void) { } +void __weak watchdog_nmi_reconfigure(bool run) { } #ifdef CONFIG_SOFTLOCKUP_DETECTOR @@ -515,10 +523,12 @@ static void softlockup_unpark_threads(void) static void softlockup_reconfigure_threads(bool enabled) { + watchdog_nmi_reconfigure(false); softlockup_park_all_threads(); set_sample_period(); if (enabled) softlockup_unpark_threads(); + watchdog_nmi_reconfigure(true); } /* @@ -559,7 +569,11 @@ static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } -static inline void softlockup_reconfigure_threads(bool enabled) { } +static void softlockup_reconfigure_threads(bool enabled) +{ + watchdog_nmi_reconfigure(false); + watchdog_nmi_reconfigure(true); +} #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) @@ -599,7 +613,6 @@ static void proc_watchdog_update(void) /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); - watchdog_nmi_reconfigure(); } /* -- GitLab From 091549858ed881e5f3054374af4f5b1cac681d50 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:17 +0200 Subject: [PATCH 0064/1507] watchdog/core: Get rid of the racy update loop Letting user space poke directly at variables which are used at run time is stupid and causes a lot of race conditions and other issues. Seperate the user variables and on change invoke the reconfiguration, which then stops the watchdogs, reevaluates the new user value and restarts the watchdogs with the new parameters. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.939985640@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 95 +++++++++++++++++++++++------------------------ 1 file changed, 47 insertions(+), 48 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5693afd2b8eae..84886319d7b09 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -32,15 +32,17 @@ static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif -int __read_mostly nmi_watchdog_user_enabled; -int __read_mostly soft_watchdog_user_enabled; -int __read_mostly watchdog_user_enabled; +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; struct cpumask watchdog_allowed_mask __read_mostly; @@ -65,7 +67,7 @@ unsigned int __read_mostly hardlockup_panic = */ void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -75,9 +77,9 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -132,6 +134,23 @@ void __weak watchdog_nmi_disable(unsigned int cpu) */ void __weak watchdog_nmi_reconfigure(bool run) { } +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) +{ + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; +} + #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* Global variables, exported for sysctl */ @@ -160,14 +179,14 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); @@ -521,12 +540,13 @@ static void softlockup_unpark_threads(void) softlockup_update_smpboot_threads(); } -static void softlockup_reconfigure_threads(bool enabled) +static void softlockup_reconfigure_threads(void) { watchdog_nmi_reconfigure(false); softlockup_park_all_threads(); set_sample_period(); - if (enabled) + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) softlockup_unpark_threads(); watchdog_nmi_reconfigure(true); } @@ -546,6 +566,8 @@ static __init void softlockup_init_threads(void) * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. */ + lockup_detector_update_enable(); + if (!IS_ENABLED(CONFIG_SYSCTL) && !(watchdog_enabled && watchdog_thresh)) return; @@ -559,7 +581,7 @@ static __init void softlockup_init_threads(void) mutex_lock(&watchdog_mutex); softlockup_threads_initialized = true; - softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); + softlockup_reconfigure_threads(); mutex_unlock(&watchdog_mutex); } @@ -569,9 +591,10 @@ static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } -static void softlockup_reconfigure_threads(bool enabled) +static void softlockup_reconfigure_threads(void) { watchdog_nmi_reconfigure(false); + lockup_detector_update_enable(); watchdog_nmi_reconfigure(true); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ @@ -612,7 +635,7 @@ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh); + softlockup_reconfigure_threads(); } /* @@ -630,48 +653,24 @@ static void proc_watchdog_update(void) static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; cpu_hotplug_disable(); mutex_lock(&watchdog_mutex); - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - if (old != new) + if (!err && old != READ_ONCE(*param)) proc_watchdog_update(); } -out: mutex_unlock(&watchdog_mutex); cpu_hotplug_enable(); return err; -- GitLab From 178b9f7a36d2c74a38274b66dd89f53611298a19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:18 +0200 Subject: [PATCH 0065/1507] watchdog/hardlockup/perf: Implement init time perf validation The watchdog tries to create perf events even after it figured out that perf is not functional or the requested event is not supported. That's braindead as this can be done once at init time and if not supported the NMI watchdog can be turned off unconditonally. Implement the perf hardlockup detector functionality for that. This creates a new event create function, which will replace the unholy mess of the existing one in later patches. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.019090547@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 8 ++++++-- kernel/watchdog_hld.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 2 deletions(-) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index eee255bc0fd62..72c62a809e92e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -93,14 +93,18 @@ extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); extern void hardlockup_detector_perf_cleanup(void); +extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } -#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +# if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} -#endif +# else +static inline int hardlockup_detector_perf_init(void) { return 0; } +# endif #endif void watchdog_nmi_reconfigure(bool run); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 0aa191ee3d517..f7e752e6e9b41 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -238,6 +238,27 @@ int watchdog_nmi_enable(unsigned int cpu) return 0; } +static int hardlockup_detector_event_create(void) +{ + unsigned int cpu = smp_processor_id(); + struct perf_event_attr *wd_attr; + struct perf_event *evt; + + wd_attr = &wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + + /* Try to register using hardware perf events */ + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} + /** * hardlockup_detector_perf_disable - Disable the local event */ @@ -315,3 +336,19 @@ void __init hardlockup_detector_perf_restart(void) perf_event_enable(event); } } + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); + + if (ret) { + pr_info("Perf NMI watchdog permanetely disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); + } + return ret; +} -- GitLab From a994a3147e4c0c9c50a46e6cace7586254975e20 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:19 +0200 Subject: [PATCH 0066/1507] watchdog/hardlockup/perf: Implement init time detection of perf Use the init time detection of the perf NMI watchdog to determine whether the perf NMI watchdog is functional. If not disable it permanentely. It won't come back magically at runtime. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.099799541@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 84886319d7b09..fd8a998eb1976 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -44,6 +44,7 @@ int __read_mostly watchdog_user_enabled = 1; int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; struct cpumask watchdog_allowed_mask __read_mostly; static bool softlockup_threads_initialized __read_mostly; @@ -114,6 +115,12 @@ void __weak watchdog_nmi_disable(unsigned int cpu) hardlockup_detector_perf_disable(); } +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + /** * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs * @run: If false stop the watchdogs on all enabled CPUs @@ -145,7 +152,7 @@ static void lockup_detector_update_enable(void) watchdog_enabled = 0; if (!watchdog_user_enabled) return; - if (nmi_watchdog_user_enabled) + if (nmi_watchdog_available && nmi_watchdog_user_enabled) watchdog_enabled |= NMI_WATCHDOG_ENABLED; if (soft_watchdog_user_enabled) watchdog_enabled |= SOFT_WATCHDOG_ENABLED; @@ -692,6 +699,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -764,5 +773,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; softlockup_init_threads(); } -- GitLab From 2a1b8ee4f5665b4291e43e4a25d964c3eb2f4c32 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:20 +0200 Subject: [PATCH 0067/1507] watchdog/hardlockup/perf: Implement CPU enable replacement watchdog_nmi_enable() is an unparseable mess, Provide a clean perf specific implementation, which will be used when the existing setup/teardown mess is replaced. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.180215498@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 2 ++ kernel/watchdog_hld.c | 11 +++++++++++ 2 files changed, 13 insertions(+) diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 72c62a809e92e..89ba8b23c6fe1 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -92,12 +92,14 @@ extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); +extern void hardlockup_detector_perf_enable(void); extern void hardlockup_detector_perf_cleanup(void); extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } +static inline void hardlockup_detector_perf_enable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } # if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index f7e752e6e9b41..99a3f22e48cc6 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -259,6 +259,17 @@ static int hardlockup_detector_event_create(void) return 0; } +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; + + perf_event_enable(this_cpu_read(watchdog_ev)); +} + /** * hardlockup_detector_perf_disable - Disable the local event */ -- GitLab From 146c9d0e9dfdb62ed6afd43cc263efafbbfd1dcf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:21 +0200 Subject: [PATCH 0068/1507] watchdog/hardlockup/perf: Use new perf CPU enable mechanism Get rid of the hodgepodge which tries to be smart about perf being unavailable and error printout rate limiting. That's all not required simply because this is never invoked when the perf NMI watchdog is not functional. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.259651788@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 4 +- kernel/watchdog_hld.c | 88 +++---------------------------------------- 2 files changed, 8 insertions(+), 84 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index fd8a998eb1976..5eb11960e4a26 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -107,6 +107,7 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } @@ -465,7 +466,8 @@ static void watchdog_enable(unsigned int cpu) /* Initialize timestamp */ __touch_watchdog(); /* Enable the perf event */ - watchdog_nmi_enable(cpu); + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 99a3f22e48cc6..509bb6b59c414 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -25,7 +25,7 @@ static DEFINE_PER_CPU(struct perf_event *, dead_event); static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; -static bool hardlockup_detector_disabled; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -160,84 +160,6 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) -{ - struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* A failure disabled the hardlockup detector permanently */ - if (hardlockup_detector_disabled) - return -ENODEV; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; - - wd_attr = &wd_hw_attr; - wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); - - /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); - - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); - - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Disabling hard lockup detector permanently\n"); - hardlockup_detector_disabled = true; - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; -} - static int hardlockup_detector_event_create(void) { unsigned int cpu = smp_processor_id(); @@ -267,6 +189,9 @@ void hardlockup_detector_perf_enable(void) if (hardlockup_detector_event_create()) return; + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); + perf_event_enable(this_cpu_read(watchdog_ev)); } @@ -282,10 +207,7 @@ void hardlockup_detector_perf_disable(void) this_cpu_write(watchdog_ev, NULL); this_cpu_write(dead_event, event); cpumask_set_cpu(smp_processor_id(), &dead_events_mask); - - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + watchdog_cpus--; } } -- GitLab From a33d44843d4574ec05bec39527d8a87b7af2072c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:22 +0200 Subject: [PATCH 0069/1507] watchdog/hardlockup/perf: Simplify deferred event destroy Now that all functionality is properly serialized against CPU hotplug, remove the extra per cpu storage which holds the disabled events for cleanup. The core makes sure that cleanup happens before new events are created. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.340708074@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog_hld.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 509bb6b59c414..b2931154b5f28 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,7 +21,6 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); -static DEFINE_PER_CPU(struct perf_event *, dead_event); static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; @@ -204,8 +203,6 @@ void hardlockup_detector_perf_disable(void) if (event) { perf_event_disable(event); - this_cpu_write(watchdog_ev, NULL); - this_cpu_write(dead_event, event); cpumask_set_cpu(smp_processor_id(), &dead_events_mask); watchdog_cpus--; } @@ -221,9 +218,9 @@ void hardlockup_detector_perf_cleanup(void) int cpu; for_each_cpu(cpu, &dead_events_mask) { - struct perf_event *event = per_cpu(dead_event, cpu); + struct perf_event *event = per_cpu(watchdog_ev, cpu); - per_cpu(dead_event, cpu) = NULL; + per_cpu(watchdog_ev, cpu) = NULL; perf_event_release_kernel(event); } cpumask_clear(&dead_events_mask); -- GitLab From ab5fe3ff38ff9653490910cc71dbbedc95a86e41 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:23 +0200 Subject: [PATCH 0070/1507] watchdog/hardlockup: Clean up hotplug locking mess All watchdog thread related functions are delegated to the smpboot thread infrastructure, which handles serialization against CPU hotplug correctly. The sysctl interface is completely decoupled from anything which requires CPU hotplug protection. No need to protect the sysctl writes against cpu hotplug anymore. Remove it and add the now required protection to the powerpc arch_nmi_watchdog implementation. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/20170912194148.418497420@linutronix.de Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/watchdog.c | 2 ++ kernel/watchdog.c | 6 ------ 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 291af79a98263..dfb0677644801 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -359,6 +359,7 @@ void watchdog_nmi_reconfigure(bool run) { int cpu; + cpus_read_lock(); if (!run) { for_each_cpu(cpu, &wd_cpus_enabled) stop_wd_on_cpu(cpu); @@ -367,6 +368,7 @@ void watchdog_nmi_reconfigure(bool run) for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) start_wd_on_cpu(cpu); } + cpus_read_unlock(); } /* diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5eb11960e4a26..f6ef163b72cdb 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -664,7 +664,6 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, { int err, old, *param = table->data; - cpu_hotplug_disable(); mutex_lock(&watchdog_mutex); if (!write) { @@ -681,7 +680,6 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, proc_watchdog_update(); } mutex_unlock(&watchdog_mutex); - cpu_hotplug_enable(); return err; } @@ -725,7 +723,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, { int err, old; - cpu_hotplug_disable(); mutex_lock(&watchdog_mutex); old = READ_ONCE(watchdog_thresh); @@ -735,7 +732,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, proc_watchdog_update(); mutex_unlock(&watchdog_mutex); - cpu_hotplug_enable(); return err; } @@ -750,7 +746,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - cpu_hotplug_disable(); mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); @@ -758,7 +753,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, proc_watchdog_update(); mutex_unlock(&watchdog_mutex); - cpu_hotplug_enable(); return err; } #endif /* CONFIG_SYSCTL */ -- GitLab From 4cf97582b46f123a4b7cd88d999f1806c2eb4093 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 11 Sep 2017 17:43:56 +0200 Subject: [PATCH 0071/1507] drm/amdgpu: revert tile table update for oland MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Several users have complained that the tile table update broke Oland support. Despite several attempts to fix it, the root cause is still unknown at this point and no solution is available. As it is not acceptable to leave a known regression breaking a major functionality in the kernel for several releases, let's just reverse this optimization for now. It can be implemented again later if and only if the breakage is understood and fixed. As there were no complaints for Hainan so far, only the Oland part of the offending commit is reverted. Optimization is preserved on Hainan, so this commit isn't an actual revert of the original. This fixes bug #194761: https://bugzilla.kernel.org/show_bug.cgi?id=194761 Reviewed-by: Marek Olšák Signed-off-by: Jean Delvare Fixes: f8d9422ef80c ("drm/amdgpu: update tile table for oland/hainan") Cc: Flora Cui Cc: Junwei Zhang Cc: Alex Deucher Cc: Marek Olšák Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 189 +++++++++++++++++++++++++- 1 file changed, 188 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index d228f5a990449..dbbe986f90f29 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -636,7 +636,194 @@ static void gfx_v6_0_tiling_mode_table_init(struct amdgpu_device *adev) NUM_BANKS(ADDR_SURF_2_BANK); for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); - } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) { + } else if (adev->asic_type == CHIP_OLAND) { + tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_LINEAR_ALIGNED) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_1D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P4_8x16) | + TILE_SPLIT(split_equal_to_row_size) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4); + tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) | + NUM_BANKS(ADDR_SURF_16_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2); + tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) | + ARRAY_MODE(ARRAY_2D_TILED_THIN1) | + PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) | + TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) | + NUM_BANKS(ADDR_SURF_8_BANK) | + BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) | + BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) | + MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1); + for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) + WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]); + } else if (adev->asic_type == CHIP_HAINAN) { tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) | ARRAY_MODE(ARRAY_2D_TILED_THIN1) | PIPE_CONFIG(ADDR_SURF_P2) | -- GitLab From 820608548737e315c6f93e3099b4e65bde062334 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 15 Sep 2017 11:55:27 -0400 Subject: [PATCH 0072/1507] drm/radeon: disable hard reset in hibernate for APUs Fixes a hibernation regression on APUs. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=191571 Fixes: 274ad65c9d02bdc (drm/radeon: hard reset r600 and newer GPU when hibernating.) Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 997131d58c7f6..ffc10cadcf34c 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1663,7 +1663,7 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, radeon_agp_suspend(rdev); pci_save_state(dev->pdev); - if (freeze && rdev->family >= CHIP_CEDAR) { + if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) { rdev->asic->asic_reset(rdev, true); pci_restore_state(dev->pdev); } else if (suspend) { -- GitLab From 6c92f7dbf25c36f35320e4ae0b508676410bac04 Mon Sep 17 00:00:00 2001 From: Dave Carroll Date: Fri, 15 Sep 2017 11:04:28 -0600 Subject: [PATCH 0073/1507] scsi: aacraid: Fix 2T+ drives on SmartIOC-2000 The logic for supporting large drives was previously tied to 4Kn support for SmartIOC-2000. As SmartIOC-2000 does not support volumes using 4Kn drives, use the intended option flag AAC_OPT_NEW_COMM_64 to determine support for volumes greater than 2T. Cc: Signed-off-by: Dave Carroll Reviewed-by: Christoph Hellwig Reviewed-by: Raghava Aditya Renukunta Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/aachba.c | 12 ++++++------ drivers/scsi/aacraid/aacraid.h | 5 +++++ 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a64285ab0728f..af3e4d3f9735f 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -699,13 +699,13 @@ static void _aac_probe_container1(void * context, struct fib * fibptr) int status; dresp = (struct aac_mount *) fib_data(fibptr); - if (!(fibptr->dev->supplement_adapter_info.supported_options2 & - AAC_OPTION_VARIABLE_BLOCK_SIZE)) + if (!aac_supports_2T(fibptr->dev)) { dresp->mnt[0].capacityhigh = 0; - if ((le32_to_cpu(dresp->status) != ST_OK) || - (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { - _aac_probe_container2(context, fibptr); - return; + if ((le32_to_cpu(dresp->status) == ST_OK) && + (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { + _aac_probe_container2(context, fibptr); + return; + } } scsicmd = (struct scsi_cmnd *) context; diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 92fabf2b0c24c..403a639574e5e 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2701,6 +2701,11 @@ static inline int aac_is_src(struct aac_dev *dev) return 0; } +static inline int aac_supports_2T(struct aac_dev *dev) +{ + return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64); +} + char * get_container_type(unsigned type); extern int numacb; extern char aac_driver_version[]; -- GitLab From 5c756065e47dc3e84b00577bd109f0a8e69903d7 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 6 Sep 2017 11:02:56 +0200 Subject: [PATCH 0074/1507] scsi: lpfc: Don't return internal MBXERR_ERROR code from probe function Internal error codes happen to be positive, thus the PCI driver core won't treat them as failure, but we do. This would cause a crash later on as lpfc_pci_remove_one() is called (e.g. as shutdown function). Fixes: 6d368e532168 ("[SCSI] lpfc 8.3.24: Add resource extent support") Signed-off-by: Stefano Brivio Reviewed-by: Johannes Thumshirn Acked-by: Dick Kennedy Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7e7ae786121b6..100bc4c8798d7 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6131,6 +6131,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) "Extents and RPI headers enabled.\n"); } mempool_free(mboxq, phba->mbox_mem_pool); + rc = -EIO; goto out_free_bsmbx; } -- GitLab From 4cb433e856bce5974ea035181cc8eb406496dccc Mon Sep 17 00:00:00 2001 From: Nikola Pajkovsky Date: Wed, 13 Sep 2017 10:46:17 +0200 Subject: [PATCH 0075/1507] scsi: aacraid: error: testing array offset 'bus' after use Fix possible indexing array of bound for &aac->hba_map[bus][cid], where bus and cid boundary check happens later. Fixes: 0d643ff3c353 ("scsi: aacraid: use aac_tmf_callback for reset fib") Signed-off-by: Nikola Pajkovsky Reviewed-by: Dave Carroll Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/linit.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 87cc4a93e637e..62beb25964669 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -906,12 +906,14 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", @@ -962,12 +964,14 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", -- GitLab From 6354a06cbaa8c49d8377a6cee3e7db399c23601c Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Wed, 13 Sep 2017 09:38:40 +0200 Subject: [PATCH 0076/1507] Revert "arm64: dts: rockchip: Add basic cpu frequencies for RK3368" This reverts commit 6f2dea1f5fdb73eb2e050d9ebe990121d557e519. Without accurate cpu regulators being set for boards this will wreak havoc when cpufreq-dt begins to set new frequencies without adjusting the core frequency. Additionally the rk3368 has an unsolved issue in that it has two separate cpu clusters with separate clock lines but only one cpu supply regulator for both clusters, which causes even more problems. While it seems that originally only one cluster was supposed to be active at a time (big or little), talking with real users of the hardware revealed that having all 8 cores accessible at 1.2GHz max is way more liked than having 4 cores at 1.5GHz max. Such an approach needs changes to cpufreq and/or opp though to control the two separate clock lines when setting both clusters to the same frequencies. In any case, having the OPPs in the dts at this point in time is undesireable, so remove them again for now. Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3368.dtsi | 72 +----------------------- 1 file changed, 2 insertions(+), 70 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index e0518b4bc6c2a..19fbaa5e7bdd5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -113,8 +113,7 @@ cpu_l0: cpu@0 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x0>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; + #cooling-cells = <2>; /* min followed by max */ }; @@ -123,8 +122,6 @@ cpu_l1: cpu@1 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x1>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_l2: cpu@2 { @@ -132,8 +129,6 @@ cpu_l2: cpu@2 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x2>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_l3: cpu@3 { @@ -141,8 +136,6 @@ cpu_l3: cpu@3 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x3>; enable-method = "psci"; - clocks = <&cru ARMCLKL>; - operating-points-v2 = <&cluster0_opp>; }; cpu_b0: cpu@100 { @@ -150,8 +143,7 @@ cpu_b0: cpu@100 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x100>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; + #cooling-cells = <2>; /* min followed by max */ }; @@ -160,8 +152,6 @@ cpu_b1: cpu@101 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x101>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; }; cpu_b2: cpu@102 { @@ -169,8 +159,6 @@ cpu_b2: cpu@102 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x102>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; }; cpu_b3: cpu@103 { @@ -178,62 +166,6 @@ cpu_b3: cpu@103 { compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x103>; enable-method = "psci"; - clocks = <&cru ARMCLKB>; - operating-points-v2 = <&cluster1_opp>; - }; - }; - - cluster0_opp: opp-table0 { - compatible = "operating-points-v2"; - opp-shared; - - opp00 { - opp-hz = /bits/ 64 <312000000>; - opp-microvolt = <950000>; - clock-latency-ns = <40000>; - }; - opp01 { - opp-hz = /bits/ 64 <408000000>; - opp-microvolt = <950000>; - }; - opp02 { - opp-hz = /bits/ 64 <600000000>; - opp-microvolt = <950000>; - }; - opp03 { - opp-hz = /bits/ 64 <816000000>; - opp-microvolt = <1025000>; - }; - opp04 { - opp-hz = /bits/ 64 <1008000000>; - opp-microvolt = <1125000>; - }; - }; - - cluster1_opp: opp-table1 { - compatible = "operating-points-v2"; - opp-shared; - - opp00 { - opp-hz = /bits/ 64 <312000000>; - opp-microvolt = <950000>; - clock-latency-ns = <40000>; - }; - opp01 { - opp-hz = /bits/ 64 <408000000>; - opp-microvolt = <950000>; - }; - opp02 { - opp-hz = /bits/ 64 <600000000>; - opp-microvolt = <950000>; - }; - opp03 { - opp-hz = /bits/ 64 <816000000>; - opp-microvolt = <975000>; - }; - opp04 { - opp-hz = /bits/ 64 <1008000000>; - opp-microvolt = <1050000>; }; }; -- GitLab From e8620acc90785ecbde041d241a13778044df9208 Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Fri, 1 Sep 2017 10:01:44 +0800 Subject: [PATCH 0077/1507] clk: rockchip: add pclk_pmu as critical clock on rk3128 pclk_pmu need always on, and no dts node to handle this clk, so make it as critical clock Signed-off-by: Elaine Zhang Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3128.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index 62d7854e4b873..f15c9b8749119 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -541,7 +541,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS), GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS), + GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS), GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS), /* PD_MMC */ @@ -577,6 +577,7 @@ static const char *const rk3128_critical_clocks[] __initconst = { "aclk_peri", "hclk_peri", "pclk_peri", + "pclk_pmu", }; static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np) -- GitLab From a4eb286565eb07ee5acfe6a1409f68ad9f663845 Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Fri, 1 Sep 2017 10:01:45 +0800 Subject: [PATCH 0078/1507] clk: rockchip: fix up rk3128 pvtm and mipi_24m gate regs error A copy-paste error made them use the wrong bits in the register. Signed-off-by: Elaine Zhang Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3128.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index f15c9b8749119..ce02d2cff608d 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -315,13 +315,13 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = { RK2928_CLKGATE_CON(10), 8, GFLAGS), GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 0, GFLAGS), GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 1, GFLAGS), GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(10), 2, GFLAGS), GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED, - RK2928_CLKGATE_CON(10), 8, GFLAGS), + RK2928_CLKGATE_CON(2), 15, GFLAGS), COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0, RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS, -- GitLab From 00e6751ffc9e6e0651e514961316fd15f0409683 Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Fri, 1 Sep 2017 10:01:46 +0800 Subject: [PATCH 0079/1507] clk: rockchip: add sclk_timer5 as critical clock on rk3128 sclk_timer5 is for arm arch counter, so need always on. but no dts node to handle this clk, so make it as critical clock Signed-off-by: Elaine Zhang Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3128.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c index ce02d2cff608d..5970a50671b9a 100644 --- a/drivers/clk/rockchip/clk-rk3128.c +++ b/drivers/clk/rockchip/clk-rk3128.c @@ -578,6 +578,7 @@ static const char *const rk3128_critical_clocks[] __initconst = { "hclk_peri", "pclk_peri", "pclk_pmu", + "sclk_timer5", }; static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np) -- GitLab From 47061a24e2ee5bd8a40d473d47a5bd823fa0081f Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 17 Sep 2017 09:03:48 -0700 Subject: [PATCH 0080/1507] x86/mm: Factor out CR3-building code Current, the code that assembles a value to load into CR3 is open-coded everywhere. Factor it out into helpers build_cr3() and build_cr3_noflush(). This makes one semantic change: __get_current_cr3_fast() was wrong on SME systems. No one noticed because the only caller is in the VMX code, and there are no CPUs with both SME and VMX. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tom Lendacky Link: http://lkml.kernel.org/r/ce350cf11e93e2842d14d0b95b0199c7d881f527.1505663533.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 15 +++++++++++---- arch/x86/mm/tlb.c | 11 +++++------ 2 files changed, 16 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 7ae318c340d9b..a999ba6b721f0 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -286,6 +286,15 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } +static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) +{ + return __sme_pa(mm->pgd) | asid; +} + +static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) +{ + return __sme_pa(mm->pgd) | asid | CR3_NOFLUSH; +} /* * This can be used from process context to figure out what the value of @@ -296,10 +305,8 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); - - if (static_cpu_has(X86_FEATURE_PCID)) - cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1ab3821f9e262..93fe97cce5819 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -126,8 +126,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != - (__sme_pa(real_prev->pgd) | prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -172,7 +171,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, */ this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | prev_asid); + write_cr3(build_cr3(next, prev_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } @@ -216,12 +215,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | new_asid); + write_cr3(build_cr3(next, new_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH); + write_cr3(build_cr3_noflush(next, new_asid)); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } @@ -265,7 +264,7 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(cr3 & ~CR3_PCID_MASK); + write_cr3(build_cr3(mm, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); -- GitLab From 52a2af400c1075219b3f0ce5c96fc961da44018a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 17 Sep 2017 09:03:49 -0700 Subject: [PATCH 0081/1507] x86/mm/64: Stop using CR3.PCID == 0 in ASID-aware code Putting the logical ASID into CR3's PCID bits directly means that we have two cases to consider separately: ASID == 0 and ASID != 0. This means that bugs that only hit in one of these cases trigger nondeterministically. There were some bugs like this in the past, and I think there's still one in current kernels. In particular, we have a number of ASID-unware code paths that save CR3, write some special value, and then restore CR3. This includes suspend/resume, hibernate, kexec, EFI, and maybe other things I've missed. This is currently dangerous: if ASID != 0, then this code sequence will leave garbage in the TLB tagged for ASID 0. We could potentially see corruption when switching back to ASID 0. In principle, an initialize_tlbstate_and_flush() call after these sequences would solve the problem, but EFI, at least, does not call this. (And it probably shouldn't -- initialize_tlbstate_and_flush() is rather expensive.) Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/cdc14bbe5d3c3ef2a562be09a6368ffe9bd947a6.1505663533.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/mmu_context.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index a999ba6b721f0..c120b5db178aa 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -286,14 +286,31 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } +/* + * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID + * bits. This serves two purposes. It prevents a nasty situation in + * which PCID-unaware code saves CR3, loads some other value (with PCID + * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if + * the saved ASID was nonzero. It also means that any bugs involving + * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger + * deterministically. + */ + static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) { - return __sme_pa(mm->pgd) | asid; + if (static_cpu_has(X86_FEATURE_PCID)) { + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1); + } else { + VM_WARN_ON_ONCE(asid != 0); + return __sme_pa(mm->pgd); + } } static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) { - return __sme_pa(mm->pgd) | asid | CR3_NOFLUSH; + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; } /* -- GitLab From b8b7abaed7a49b350f8ba659ddc264b04931d581 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 17 Sep 2017 09:03:50 -0700 Subject: [PATCH 0082/1507] x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier Otherwise we might have the PCID feature bit set during cpu_init(). This is just for robustness. I haven't seen any actual bugs here. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: cba4671af755 ("x86/mm: Disable PCID on 32-bit kernels") Link: http://lkml.kernel.org/r/b16dae9d6b0db5d9801ddbebbfd83384097c61f3.1505663533.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/bugs.c | 8 -------- arch/x86/kernel/cpu/common.c | 8 ++++++++ 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index db684880d74ae..0af86d9242da0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -21,14 +21,6 @@ void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 775f10100d7fe..c9176bae7fd8c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -904,6 +904,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) -- GitLab From 4ba55e65f471d011d3ba2ac2022180ea0877d68e Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sun, 17 Sep 2017 09:03:51 -0700 Subject: [PATCH 0083/1507] x86/mm/32: Load a sane CR3 before cpu_init() on secondary CPUs For unknown historical reasons (i.e. Borislav doesn't recall), 32-bit kernels invoke cpu_init() on secondary CPUs with initial_page_table loaded into CR3. Then they set current->active_mm to &init_mm and call enter_lazy_tlb() before fixing CR3. This means that the x86 TLB code gets invoked while CR3 is inconsistent, and, with the improved PCID sanity checks I added, we warn. Fix it by loading swapper_pg_dir (i.e. init_mm.pgd) earlier. Reported-by: Paul Menzel Reported-by: Pavel Machek Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 72c0098d92ce ("x86/mm: Reinitialize TLB state on hotplug and resume") Link: http://lkml.kernel.org/r/30cdfea504682ba3b9012e77717800a91c22097f.1505663533.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0854ff1692745..ad59edd84de70 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -232,12 +232,6 @@ static void notrace start_secondary(void *unused) */ if (boot_cpu_has(X86_FEATURE_PCID)) __write_cr4(__read_cr4() | X86_CR4_PCIDE); - cpu_init(); - x86_cpuinit.early_percpu_clock_init(); - preempt_disable(); - smp_callin(); - - enable_start_cpu0 = 0; #ifdef CONFIG_X86_32 /* switch away from the initial page table */ @@ -245,6 +239,13 @@ static void notrace start_secondary(void *unused) __flush_tlb_all(); #endif + cpu_init(); + x86_cpuinit.early_percpu_clock_init(); + preempt_disable(); + smp_callin(); + + enable_start_cpu0 = 0; + /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); /* -- GitLab From bf29ed1567b67854dc13504f685c45a2ea9b2081 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 7 Sep 2017 08:30:44 -0700 Subject: [PATCH 0084/1507] syscalls: Use CHECK_DATA_CORRUPTION for addr_limit_user_check Use CHECK_DATA_CORRUPTION instead of BUG_ON to provide more flexibility on address limit failures. By default, send a SIGKILL signal to kill the current process preventing exploitation of a bad address limit. Make the TIF_FSCHECK flag optional so ARM can use this function. Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Pratyush Anand Cc: Dave Martin Cc: Will Drewry Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Andy Lutomirski Cc: David Howells Cc: Dave Hansen Cc: Al Viro Cc: linux-api@vger.kernel.org Cc: Yonghong Song Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1504798247-48833-2-git-send-email-keescook@chromium.org --- include/linux/syscalls.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95606a2d556fd..a78186d826d79 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -221,21 +221,25 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifdef TIF_FSCHECK /* * Called before coming back to user-mode. Returning to user-mode with an * address limit different than USER_DS can allow to overwrite kernel memory. */ static inline void addr_limit_user_check(void) { - +#ifdef TIF_FSCHECK if (!test_thread_flag(TIF_FSCHECK)) return; +#endif - BUG_ON(!segment_eq(get_fs(), USER_DS)); + if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS), + "Invalid address limit on user-mode return")) + force_sig(SIGKILL, current); + +#ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); -} #endif +} asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); -- GitLab From 2404269bc4e77a67875c8db6667be34c9913c96e Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 7 Sep 2017 08:30:45 -0700 Subject: [PATCH 0085/1507] Revert "arm/syscalls: Check address limit on user-mode return" This reverts commit 73ac5d6a2b6ac3ae8d1e1818f3e9946f97489bc9. The work pending loop can call set_fs after addr_limit_user_check removed the _TIF_FSCHECK flag. This may happen at anytime based on how ARM handles alignment exceptions. It leads to an infinite loop condition. After discussion, it has been agreed that the generic approach is not tailored to the ARM architecture and any fix might not be complete. This patch will be replaced by an architecture specific implementation. The work flag approach will be kept for other architectures. Reported-by: Leonard Crestez Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Pratyush Anand Cc: Dave Martin Cc: Will Drewry Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Andy Lutomirski Cc: David Howells Cc: Dave Hansen Cc: Al Viro Cc: linux-api@vger.kernel.org Cc: Yonghong Song Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1504798247-48833-3-git-send-email-keescook@chromium.org --- arch/arm/include/asm/thread_info.h | 15 ++++++--------- arch/arm/include/asm/uaccess.h | 2 -- arch/arm/kernel/entry-common.S | 9 ++------- arch/arm/kernel/signal.c | 5 ----- 4 files changed, 8 insertions(+), 23 deletions(-) diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index 1d468b527b7b6..776757d1604ab 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -139,11 +139,10 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_NEED_RESCHED 1 /* rescheduling necessary */ #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_UPROBE 3 /* breakpointed or singlestepping */ -#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */ -#define TIF_SYSCALL_TRACE 5 /* syscall trace active */ -#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */ -#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */ -#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ +#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ +#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ +#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ #define TIF_NOHZ 12 /* in adaptive nohz mode */ #define TIF_USING_IWMMXT 17 @@ -154,7 +153,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_UPROBE (1 << TIF_UPROBE) -#define _TIF_FSCHECK (1 << TIF_FSCHECK) #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) @@ -168,9 +166,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, /* * Change these and you break ASM code in entry-common.S */ -#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_FSCHECK) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_UPROBE) #endif /* __KERNEL__ */ #endif /* __ASM_ARM_THREAD_INFO_H */ diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 87936dd5d1510..0bf2347495f13 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -70,8 +70,6 @@ static inline void set_fs(mm_segment_t fs) { current_thread_info()->addr_limit = fs; modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER); - /* On user-mode return, check fs is correct */ - set_thread_flag(TIF_FSCHECK); } #define segment_eq(a, b) ((a) == (b)) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index ca3614dc6938e..0b60adf4a5d9b 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -49,9 +49,7 @@ ret_fast_syscall: UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK - bne fast_work_pending - tst r1, #_TIF_WORK_MASK + tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK bne fast_work_pending /* perform architecture specific actions before user return */ @@ -77,15 +75,12 @@ ret_fast_syscall: str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 disable_irq_notrace @ disable interrupts ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing - tst r1, #_TIF_SYSCALL_WORK - bne fast_work_pending - tst r1, #_TIF_WORK_MASK + tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK beq no_work_pending UNWIND(.fnend ) ENDPROC(ret_fast_syscall) /* Slower path - fall through to work_pending */ -fast_work_pending: #endif tst r1, #_TIF_SYSCALL_WORK diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index e2de50bf87425..5814298ef0b70 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include @@ -614,10 +613,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) * Update the trace code with the current status. */ trace_hardirqs_off(); - - /* Check valid user FS if needed */ - addr_limit_user_check(); - do { if (likely(thread_flags & _TIF_NEED_RESCHED)) { schedule(); -- GitLab From e33f8d32677fa4f4f8996ef46748f86aac81ccff Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 7 Sep 2017 08:30:46 -0700 Subject: [PATCH 0086/1507] arm/syscalls: Optimize address limit check Disable the generic address limit check in favor of an architecture specific optimized implementation. The generic implementation using pending work flags did not work well with ARM and alignment faults. The address limit is checked on each syscall return path to user-mode path as well as the irq user-mode return function. If the address limit was changed, a function is called to report data corruption (stopping the kernel or process based on configuration). The address limit check has to be done before any pending work because they can reset the address limit and the process is killed using a SIGKILL signal. For example the lkdtm address limit check does not work because the signal to kill the process will reset the user-mode address limit. Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Tested-by: Kees Cook Tested-by: Leonard Crestez Reviewed-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Pratyush Anand Cc: Dave Martin Cc: Will Drewry Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Andy Lutomirski Cc: David Howells Cc: Dave Hansen Cc: Al Viro Cc: linux-api@vger.kernel.org Cc: Yonghong Song Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1504798247-48833-4-git-send-email-keescook@chromium.org --- arch/arm/kernel/entry-common.S | 11 +++++++++++ arch/arm/kernel/signal.c | 7 +++++++ 2 files changed, 18 insertions(+) diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 0b60adf4a5d9b..99c908226065c 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -12,6 +12,7 @@ #include #include #include +#include #ifdef CONFIG_AEABI #include #endif @@ -48,10 +49,14 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK bne fast_work_pending + /* perform architecture specific actions before user return */ arch_ret_to_user r1, lr @@ -74,6 +79,9 @@ ret_fast_syscall: UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 disable_irq_notrace @ disable interrupts + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK beq no_work_pending @@ -106,6 +114,9 @@ ENTRY(ret_to_user) ret_slow_syscall: disable_irq_notrace @ disable interrupts ENTRY(ret_to_user_from_irq) + ldr r2, [tsk, #TI_ADDR_LIMIT] + cmp r2, #TASK_SIZE + blne addr_limit_check_failed ldr r1, [tsk, #TI_FLAGS] tst r1, #_TIF_WORK_MASK bne slow_work_pending diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 5814298ef0b70..b67ae12503f30 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -673,3 +674,9 @@ struct page *get_signal_page(void) return page; } + +/* Defer to generic check */ +asmlinkage void addr_limit_check_failed(void) +{ + addr_limit_user_check(); +} -- GitLab From a2048e34d4655c06d31400646ae495bbfeb16b27 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 7 Sep 2017 08:30:47 -0700 Subject: [PATCH 0087/1507] arm64/syscalls: Move address limit check in loop A bug was reported on ARM where set_fs might be called after it was checked on the work pending function. ARM64 is not affected by this bug but has a similar construct. In order to avoid any similar problems in the future, the addr_limit_user_check function is moved at the beginning of the loop. Fixes: cf7de27ab351 ("arm64/syscalls: Check address limit on user-mode return") Reported-by: Leonard Crestez Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Pratyush Anand Cc: Dave Martin Cc: Will Drewry Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Andy Lutomirski Cc: David Howells Cc: Dave Hansen Cc: Al Viro Cc: linux-api@vger.kernel.org Cc: Yonghong Song Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1504798247-48833-5-git-send-email-keescook@chromium.org --- arch/arm64/kernel/signal.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index c45214f8fb549..0bdc96c61bc0f 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -751,10 +751,10 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, */ trace_hardirqs_off(); - /* Check valid user FS if needed */ - addr_limit_user_check(); - do { + /* Check valid user FS if needed */ + addr_limit_user_check(); + if (thread_flags & _TIF_NEED_RESCHED) { schedule(); } else { -- GitLab From 8fce3dc5c5d6f6301f67311fa79f333902b58cea Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 15 Sep 2017 21:42:59 +0200 Subject: [PATCH 0088/1507] clocksource/integrator: Fix section mismatch warning gcc-4.6 and older fail to inline integrator_clocksource_init, so they end up showing a harmless warning: WARNING: vmlinux.o(.text+0x4aa94c): Section mismatch in reference from the function integrator_clocksource_init() to the function .init.text:clocksource_mmio_init() The function integrator_clocksource_init() references the function __init clocksource_mmio_init(). This is often because integrator_clocksource_init lacks a __init annotation or the annotation of clocksource_mmio_init is wrong. Add the missing __init annotation that makes it build cleanly with all compilers. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Cc: Thierry Reding Cc: Linus Walleij Cc: Daniel Lezcano Link: http://lkml.kernel.org/r/20170915194310.1170514-1-arnd@arndb.de --- drivers/clocksource/timer-integrator-ap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c index 2ff64d9d4fb31..62d24690ba020 100644 --- a/drivers/clocksource/timer-integrator-ap.c +++ b/drivers/clocksource/timer-integrator-ap.c @@ -36,8 +36,8 @@ static u64 notrace integrator_read_sched_clock(void) return -readl(sched_clk_base + TIMER_VALUE); } -static int integrator_clocksource_init(unsigned long inrate, - void __iomem *base) +static int __init integrator_clocksource_init(unsigned long inrate, + void __iomem *base) { u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC; unsigned long rate = inrate; -- GitLab From 27563cd9f8f52f09523e061985917c38f302bd0c Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Thu, 14 Sep 2017 17:28:12 +0300 Subject: [PATCH 0089/1507] ARM: dts: at91: sama5d27_som1_ek: update pinmux/pinconf for LEDs and USB There are some changes from the prototype board concerning LEDs and USB pins: - USBB power enable and red LED pins are inverted. - The polarity of LEDs is inverted too. Signed-off-by: Ludovic Desroches Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/at91-sama5d27_som1_ek.dts | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts index 9c9088c99cc4c..f13ef4fbab601 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts @@ -67,7 +67,7 @@ usb0: gadget@00300000 { usb1: ohci@00400000 { num-ports = <3>; - atmel,vbus-gpio = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>; + atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb_default>; status = "okay"; @@ -330,7 +330,7 @@ pinctrl_key_gpio_default: key_gpio_default { }; pinctrl_led_gpio_default: led_gpio_default { - pinmux = , + pinmux = , , ; bias-pull-up; @@ -396,7 +396,7 @@ pinctrl_uart3_default: uart3_default { }; pinctrl_usb_default: usb_default { - pinmux = , + pinmux = , ; bias-disable; }; @@ -520,17 +520,17 @@ leds { red { label = "red"; - gpios = <&pioA PIN_PA27 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>; }; green { label = "green"; - gpios = <&pioA PIN_PB1 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PB1 GPIO_ACTIVE_HIGH>; }; blue { label = "blue"; - gpios = <&pioA PIN_PA31 GPIO_ACTIVE_LOW>; + gpios = <&pioA PIN_PA31 GPIO_ACTIVE_HIGH>; linux,default-trigger = "heartbeat"; }; }; -- GitLab From 5f506faa0de810f07af9345826fd588f61bb3b2f Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Thu, 14 Sep 2017 17:28:13 +0300 Subject: [PATCH 0090/1507] ARM: dts: at91: sama5d27_som1_ek: fix typos Fix typos that prevent proper using of uart2 and uart4 devices. Signed-off-by: Ludovic Desroches Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre --- arch/arm/boot/dts/at91-sama5d27_som1_ek.dts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts index f13ef4fbab601..be5cd913f2746 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts @@ -120,7 +120,7 @@ uart2: serial@f8024000 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mikrobus2_uart>; atmel,use-dma-rx; - atmel-use-dma-tx; + atmel,use-dma-tx; status = "okay"; }; @@ -178,7 +178,7 @@ uart3: serial@fc008000 { uart4: serial@fc00c000 { atmel,use-dma-rx; atmel,use-dma-tx; - pinctrl-name = "default"; + pinctrl-names = "default"; pinctrl-0 = <&pinctrl_mikrobus1_uart>; status = "okay"; }; -- GitLab From e025a3ac3460275bf86a4c5d02857eee14db4247 Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Thu, 14 Sep 2017 17:28:14 +0300 Subject: [PATCH 0091/1507] ARM: dts: at91: sama5d27_som1_ek: fix USB host vbus The USB host has 3 ports so we must specify the entries for each in the atmel,vbus-gpio property. The specified pin (PA27) is the vbus for USBB and not USBA. Signed-off-by: Nicolas Ferre [claudiu.beznea@microchip.com: change subject to match the desired prefix] Signed-off-by: Claudiu Beznea --- arch/arm/boot/dts/at91-sama5d27_som1_ek.dts | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts index be5cd913f2746..60cb084a8d927 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts @@ -67,7 +67,10 @@ usb0: gadget@00300000 { usb1: ohci@00400000 { num-ports = <3>; - atmel,vbus-gpio = <&pioA PIN_PA27 GPIO_ACTIVE_HIGH>; + atmel,vbus-gpio = <0 /* &pioA PIN_PD20 GPIO_ACTIVE_HIGH */ + &pioA PIN_PA27 GPIO_ACTIVE_HIGH + 0 + >; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb_default>; status = "okay"; -- GitLab From 093d79f62a89f47d9b5fd0746768146d9696535c Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 24 Aug 2017 13:44:54 +0200 Subject: [PATCH 0092/1507] ARM: at91: Replace uses of virt_to_phys with __pa_symbol The PM code wrongly uses virt_to_phys() instead of __pa_symbol() and was not updated by commit 64fc2a947a98 ("ARM: 8641/1: treewide: Replace uses of virt_to_phys with __pa_symbol") because it was not yet in tree. Signed-off-by: Alexandre Belloni Signed-off-by: Nicolas Ferre --- arch/arm/mach-at91/pm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 5036f996e694a..849014c01cf4d 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -533,8 +533,8 @@ static void __init at91_pm_backup_init(void) } pm_bu->suspended = 0; - pm_bu->canary = virt_to_phys(&canary); - pm_bu->resume = virt_to_phys(cpu_resume); + pm_bu->canary = __pa_symbol(&canary); + pm_bu->resume = __pa_symbol(cpu_resume); return; -- GitLab From 2d48a237c8b61b457d146310d7e1e61224d0ca56 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Sat, 9 Sep 2017 06:02:46 +0200 Subject: [PATCH 0093/1507] ARC: reset: Only build on archs that have IOMEM This avoids the error: drivers/reset/reset-hsdk-v1.o: In function `hsdkv1_reset_probe': /home/thomas/git/linux/drivers/reset/reset-hsdk-v1.c:101: undefined reference to `devm_ioremap_resource' collect2: error: ld returned 1 exit status Signed-off-by: Thomas Meyer Signed-off-by: Philipp Zabel --- drivers/reset/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index e0c393214264a..d063bd5373dd8 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -36,6 +36,7 @@ config RESET_BERLIN config RESET_HSDK_V1 bool "HSDK v1 Reset Driver" + depends on HAS_IOMEM default n help This enables the reset controller driver for HSDK v1. -- GitLab From fc9655e65160936e32adae0d0e8aae25eb12c4e0 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Thu, 14 Sep 2017 12:49:41 +0200 Subject: [PATCH 0094/1507] ARC: reset: add missing DT binding documentation for HSDKv1 reset driver When applying the original patch [1], the DT binding docs were lost. This patch adds them back. [1] https://patchwork.kernel.org/patch/9852997/ Fixes: e0be864f1424 ("ARC: reset: introduce HSDKv1 reset driver") Signed-off-by: Eugeniy Paltsev Signed-off-by: Philipp Zabel --- .../bindings/reset/snps,hsdk-v1-reset.txt | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt diff --git a/Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt b/Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt new file mode 100644 index 0000000000000..6a68146ee3537 --- /dev/null +++ b/Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt @@ -0,0 +1,28 @@ +Binding for the HSDK v1 reset controller + +This binding uses the common reset binding[1]. + +[1] Documentation/devicetree/bindings/reset/reset.txt + +Required properties: +- compatible: should be "snps,hsdk-v1.0-reset". +- reg: should always contain 2 pairs address - length: first for reset + configuration register and second for corresponding SW reset and status bits + register. +- #reset-cells: from common reset binding; Should always be set to 1. + +Example: + reset: reset@880 { + compatible = "snps,hsdk-v1.0-reset"; + #reset-cells = <1>; + reg = <0x8A0 0x4>, <0xFF0 0x4>; + }; + +Specifying reset lines connected to IP modules: + ethernet@.... { + .... + resets = <&reset HSDK_V1_ETH_RESET>; + .... + }; + +The index could be found in -- GitLab From 70e743e4cec3733dc13559f6184b35d358b9ef3f Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 14 Sep 2017 16:52:59 +0200 Subject: [PATCH 0095/1507] uwb: ensure that endpoint is interrupt hwarc_neep_init() assumes that endpoint 0 is interrupt, but there's no check for that, which results in a WARNING in USB core code, when a bad USB descriptor is provided from a device: usb 1-1: BOGUS urb xfer, pipe 1 != type 3 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 3 at drivers/usb/core/urb.c:449 usb_submit_urb+0xf8a/0x11d0 Modules linked in: CPU: 0 PID: 3 Comm: kworker/0:0 Not tainted 4.13.0+ #111 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Workqueue: usb_hub_wq hub_event task: ffff88006bdc1a00 task.stack: ffff88006bde8000 RIP: 0010:usb_submit_urb+0xf8a/0x11d0 drivers/usb/core/urb.c:448 RSP: 0018:ffff88006bdee3c0 EFLAGS: 00010282 RAX: 0000000000000029 RBX: ffff8800672a7200 RCX: 0000000000000000 RDX: 0000000000000029 RSI: ffff88006c815c78 RDI: ffffed000d7bdc6a RBP: ffff88006bdee4c0 R08: fffffbfff0fe00ff R09: fffffbfff0fe00ff R10: 0000000000000018 R11: fffffbfff0fe00fe R12: 1ffff1000d7bdc7f R13: 0000000000000003 R14: 0000000000000001 R15: ffff88006b02cc90 FS: 0000000000000000(0000) GS:ffff88006c800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe4daddf000 CR3: 000000006add6000 CR4: 00000000000006f0 Call Trace: hwarc_neep_init+0x4ce/0x9c0 drivers/uwb/hwa-rc.c:710 uwb_rc_add+0x2fb/0x730 drivers/uwb/lc-rc.c:361 hwarc_probe+0x34e/0x9b0 drivers/uwb/hwa-rc.c:858 usb_probe_interface+0x351/0x8d0 drivers/usb/core/driver.c:361 really_probe drivers/base/dd.c:385 driver_probe_device+0x610/0xa00 drivers/base/dd.c:529 __device_attach_driver+0x230/0x290 drivers/base/dd.c:625 bus_for_each_drv+0x15e/0x210 drivers/base/bus.c:463 __device_attach+0x269/0x3c0 drivers/base/dd.c:682 device_initial_probe+0x1f/0x30 drivers/base/dd.c:729 bus_probe_device+0x1da/0x280 drivers/base/bus.c:523 device_add+0xcf9/0x1640 drivers/base/core.c:1703 usb_set_configuration+0x1064/0x1890 drivers/usb/core/message.c:1932 generic_probe+0x73/0xe0 drivers/usb/core/generic.c:174 usb_probe_device+0xaf/0xe0 drivers/usb/core/driver.c:266 really_probe drivers/base/dd.c:385 driver_probe_device+0x610/0xa00 drivers/base/dd.c:529 __device_attach_driver+0x230/0x290 drivers/base/dd.c:625 bus_for_each_drv+0x15e/0x210 drivers/base/bus.c:463 __device_attach+0x269/0x3c0 drivers/base/dd.c:682 device_initial_probe+0x1f/0x30 drivers/base/dd.c:729 bus_probe_device+0x1da/0x280 drivers/base/bus.c:523 device_add+0xcf9/0x1640 drivers/base/core.c:1703 usb_new_device+0x7b8/0x1020 drivers/usb/core/hub.c:2457 hub_port_connect drivers/usb/core/hub.c:4890 hub_port_connect_change drivers/usb/core/hub.c:4996 port_event drivers/usb/core/hub.c:5102 hub_event+0x23c8/0x37c0 drivers/usb/core/hub.c:5182 process_one_work+0x9fb/0x1570 kernel/workqueue.c:2097 worker_thread+0x1e4/0x1350 kernel/workqueue.c:2231 kthread+0x324/0x3f0 kernel/kthread.c:231 ret_from_fork+0x25/0x30 arch/x86/entry/entry_64.S:425 Code: 48 8b 85 30 ff ff ff 48 8d b8 98 00 00 00 e8 8e 93 07 ff 45 89 e8 44 89 f1 4c 89 fa 48 89 c6 48 c7 c7 a0 e5 55 86 e8 20 08 8f fd <0f> ff e9 9b f7 ff ff e8 4a 04 d6 fd e9 80 f7 ff ff e8 60 11 a6 ---[ end trace 55d741234124cfc3 ]--- Check that endpoint is interrupt. Found by syzkaller. Signed-off-by: Andrey Konovalov Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/uwb/hwa-rc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/uwb/hwa-rc.c b/drivers/uwb/hwa-rc.c index 35a1e777b4497..9a53912bdfe9f 100644 --- a/drivers/uwb/hwa-rc.c +++ b/drivers/uwb/hwa-rc.c @@ -825,6 +825,8 @@ static int hwarc_probe(struct usb_interface *iface, if (iface->cur_altsetting->desc.bNumEndpoints < 1) return -ENODEV; + if (!usb_endpoint_xfer_int(&iface->cur_altsetting->endpoint[0].desc)) + return -ENODEV; result = -ENOMEM; uwb_rc = uwb_rc_alloc(); -- GitLab From bbf26183b7a6236ba602f4d6a2f7cade35bba043 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 14 Sep 2017 14:30:55 +0200 Subject: [PATCH 0096/1507] uwb: properly check kthread_run return value uwbd_start() calls kthread_run() and checks that the return value is not NULL. But the return value is not NULL in case kthread_run() fails, it takes the form of ERR_PTR(-EINTR). Use IS_ERR() instead. Also add a check to uwbd_stop(). Signed-off-by: Andrey Konovalov Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/uwb/uwbd.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/uwb/uwbd.c b/drivers/uwb/uwbd.c index 01c20a260a8b3..39dd4ef53c779 100644 --- a/drivers/uwb/uwbd.c +++ b/drivers/uwb/uwbd.c @@ -302,18 +302,22 @@ static int uwbd(void *param) /** Start the UWB daemon */ void uwbd_start(struct uwb_rc *rc) { - rc->uwbd.task = kthread_run(uwbd, rc, "uwbd"); - if (rc->uwbd.task == NULL) + struct task_struct *task = kthread_run(uwbd, rc, "uwbd"); + if (IS_ERR(task)) { + rc->uwbd.task = NULL; printk(KERN_ERR "UWB: Cannot start management daemon; " "UWB won't work\n"); - else + } else { + rc->uwbd.task = task; rc->uwbd.pid = rc->uwbd.task->pid; + } } /* Stop the UWB daemon and free any unprocessed events */ void uwbd_stop(struct uwb_rc *rc) { - kthread_stop(rc->uwbd.task); + if (rc->uwbd.task) + kthread_stop(rc->uwbd.task); uwbd_flush(rc); } -- GitLab From b2a542bbb3081dbd64acc8929c140d196664c406 Mon Sep 17 00:00:00 2001 From: Dmitry Fleytman Date: Tue, 5 Sep 2017 11:40:56 +0300 Subject: [PATCH 0097/1507] usb: Increase quirk delay for USB devices Commit e0429362ab15 ("usb: Add device quirk for Logitech HD Pro Webcams C920 and C930e") introduced quirk to workaround an issue with some Logitech webcams. The workaround is introducing delay for some USB operations. According to our testing, delay introduced by original commit is not long enough and in rare cases we still see issues described by the aforementioned commit. This patch increases delays introduced by original commit. Having this patch applied we do not see those problems anymore. Signed-off-by: Dmitry Fleytman Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/config.c | 2 +- drivers/usb/core/hub.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 4be52c602e9b7..854c8d66cfbef 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -852,7 +852,7 @@ int usb_get_configuration(struct usb_device *dev) } if (dev->quirks & USB_QUIRK_DELAY_INIT) - msleep(100); + msleep(200); result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 41eaf0b525180..b5c7336138232 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -4838,7 +4838,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, goto loop; if (udev->quirks & USB_QUIRK_DELAY_INIT) - msleep(1000); + msleep(2000); /* consecutive bus-powered hubs aren't reliable; they can * violate the voltage drop budget. if the new child has -- GitLab From 0a51fb7174f2b7866b4d7a4a5c23b685b674beb6 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sat, 9 Sep 2017 12:19:22 +0300 Subject: [PATCH 0098/1507] quota: add missing lock into __dquot_transfer() Lock dq_dqb_lock around dquot_decr_inodes() Signed-off-by: Konstantin Khlebnikov Fixes: 7b9ca4c61bc2 ("quota: Reduce contention on dq_data_lock") Signed-off-by: Jan Kara --- fs/quota/dquot.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8381db9db6d9b..50b0556a124f2 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1980,7 +1980,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, &warn_to[cnt]); if (ret) { + spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } -- GitLab From 0ab0b271bf75073cb254b5ea0593aceae5a42bd3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 16 Sep 2017 22:32:12 +0200 Subject: [PATCH 0099/1507] isofs: fix build regression The new isofs_show_options() function fails to build when CONFIG_NLS is disabled: fs/isofs/inode.c: In function 'isofs_show_options': fs/isofs/inode.c:518:44: error: 'CONFIG_NLS_DEFAULT' undeclared (first use in this function) fs/isofs/inode.c:518:44: note: each undeclared identifier is reported only once for each function it appears in This adds a check for CONFIG_JOLIET (which selects NLS), matching the other uses of the iocharset handling in this file. Fixes: 6fecb86a44f5 ("isofs: Implement show_options") Signed-off-by: Arnd Bergmann Signed-off-by: Jan Kara --- fs/isofs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index db692f5541588..447a24d77b894 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -514,9 +514,11 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root) if (sbi->s_fmode != ISOFS_INVALID_MODE) seq_printf(m, ",fmode=%o", sbi->s_fmode); +#ifdef CONFIG_JOLIET if (sbi->s_nls_iocharset && strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); +#endif return 0; } -- GitLab From 056e4fc2018364ba01a23a1ced0ccbbdfa4520b3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 15 Sep 2017 21:23:13 +0200 Subject: [PATCH 0100/1507] staging: unisys/visorbus: add __init/__exit annotations gcc-4.6 causes a harmless warning about the init function: WARNING: vmlinux.o(.text+0xed62c2): Section mismatch in reference from the function init_unisys() to the function .init.text:visorutil_spar_detect() The function init_unisys() references the function __init visorutil_spar_detect(). This is often because init_unisys lacks a __init annotation or the annotation of visorutil_spar_detect is wrong. It appears that newer versions inline visorutil_spar_detect(), end up with an empty __init section. This marks the module entry points as __init and __exit respectively, which avoids the warning and slightly reduces the runtime code size. Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- drivers/staging/unisys/visorbus/visorchipset.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c index 74cce4f1a7bd7..27ecf6fb49fd9 100644 --- a/drivers/staging/unisys/visorbus/visorchipset.c +++ b/drivers/staging/unisys/visorbus/visorchipset.c @@ -1826,7 +1826,7 @@ static __init int visorutil_spar_detect(void) return 0; } -static int init_unisys(void) +static int __init init_unisys(void) { int result; @@ -1841,7 +1841,7 @@ static int init_unisys(void) return 0; }; -static void exit_unisys(void) +static void __exit exit_unisys(void) { acpi_bus_unregister_driver(&unisys_acpi_driver); } -- GitLab From a3563b09f132661d447f69224ef65fdec02f5c61 Mon Sep 17 00:00:00 2001 From: Arun Nagendran Date: Fri, 15 Sep 2017 12:30:32 -0400 Subject: [PATCH 0101/1507] staging: mt29f_spinand: Enable the read ECC before program the page Current program_page function did following operation: 1. read page (with ECC OFF) 2. modify the page 3. write the page (with ECC ON) For some case(buggy flash Chip), while read the page without ECC ON, we may read the page with bit flip error and modify that bad page without knowing the bit flip error on that page. also we re-calculate the hash for bad page and write it. This could bring potential in-consistency problem with Flash data. Verify this logic with GIGA DEVICE Part(GD5F2GQ4RCFIG): we see this in-conststency problem wit Giga Device and fix on this patch resovle that issue. Signed-off-by: Arun Nagendran Signed-off-by: Greg Kroah-Hartman --- drivers/staging/mt29f_spinand/mt29f_spinand.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/staging/mt29f_spinand/mt29f_spinand.c b/drivers/staging/mt29f_spinand/mt29f_spinand.c index 13eaf16ecd16a..87595c594b120 100644 --- a/drivers/staging/mt29f_spinand/mt29f_spinand.c +++ b/drivers/staging/mt29f_spinand/mt29f_spinand.c @@ -496,8 +496,12 @@ static int spinand_program_page(struct spi_device *spi_nand, if (!wbuf) return -ENOMEM; - enable_read_hw_ecc = 0; - spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + enable_read_hw_ecc = 1; + retval = spinand_read_page(spi_nand, page_id, 0, CACHE_BUF, wbuf); + if (retval < 0) { + dev_err(&spi_nand->dev, "ecc error on read page!!!\n"); + return retval; + } for (i = offset, j = 0; i < len; i++, j++) wbuf[i] &= buf[j]; -- GitLab From e1bf28868ab0bfd1fc73dd8d5e642d88456c30e9 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 8 Sep 2017 14:55:06 +0100 Subject: [PATCH 0102/1507] staging: r8822be: fix null pointer dereferences with a null driver_adapter The call to _rtl_dbg_trace via macro HALMAC_RT_TRACE will trigger a null pointer deference on a null driver_adapter. Fix this by assigning driver_adapter earlier to halmac_adapter->driver_adapter before the tracing call so that a non-null driver_adapter is passed instead. I should have spotted these with an earlier patch I sent, but I overlooked these in the rather large CoverityScan logs. Detected by CoverityScan, CID#1454550, CID#1454554, CID#1454565, CID#1454591, CID#1454598 ("Explicit null dereferenced") Fixes: 938a0447f094 ("staging: r8822be: Add code for halmac sub-driver") Signed-off-by: Colin Ian King Signed-off-by: Greg Kroah-Hartman --- .../rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c | 4 ++-- .../rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c | 13 +++++++------ 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c index 5f84526cb5b5b..edbf6af1c8b70 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_api_88xx.c @@ -2901,11 +2901,11 @@ halmac_update_datapack_88xx(struct halmac_adapter *halmac_adapter, if (halmac_adapter->fw_version.h2c_version < 4) return HALMAC_RET_FW_NO_SUPPORT; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s ==========>\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "[TRACE]%s <==========\n", __func__); diff --git a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c index f33024e4d853d..544f638ed3efb 100644 --- a/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c +++ b/drivers/staging/rtlwifi/halmac/halmac_88xx/halmac_func_88xx.c @@ -1618,10 +1618,11 @@ halmac_send_h2c_set_pwr_mode_88xx(struct halmac_adapter *halmac_adapter, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = h2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -1713,10 +1714,11 @@ halmac_media_status_rpt_88xx(struct halmac_adapter *halmac_adapter, u8 op_mode, void *driver_adapter = NULL; enum halmac_ret_status status = HALMAC_RET_SUCCESS; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_send_h2c_set_pwr_mode_88xx!!\n"); - driver_adapter = halmac_adapter->driver_adapter; h2c_header = H2c_buff; h2c_cmd = h2c_header + HALMAC_H2C_CMD_HDR_SIZE_88XX; @@ -2143,10 +2145,11 @@ halmac_func_ctrl_ch_switch_88xx(struct halmac_adapter *halmac_adapter, enum halmac_cmd_process_status *process_status = &halmac_adapter->halmac_state.scan_state_set.process_status; + driver_adapter = halmac_adapter->driver_adapter; + HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "halmac_ctrl_ch_switch!!\n"); - driver_adapter = halmac_adapter->driver_adapter; halmac_api = (struct halmac_api *)halmac_adapter->halmac_api; if (halmac_transition_scan_state_88xx( @@ -2276,15 +2279,13 @@ enum halmac_ret_status halmac_send_h2c_update_bcn_parse_info_88xx( { u8 h2c_buff[HALMAC_H2C_CMD_SIZE_88XX] = {0}; u16 h2c_seq_mum = 0; - void *driver_adapter = NULL; + void *driver_adapter = halmac_adapter->driver_adapter; struct halmac_h2c_header_info h2c_header_info; enum halmac_ret_status status = HALMAC_RET_SUCCESS; HALMAC_RT_TRACE(driver_adapter, HALMAC_MSG_H2C, DBG_DMESG, "%s!!\n", __func__); - driver_adapter = halmac_adapter->driver_adapter; - UPDATE_BEACON_PARSING_INFO_SET_FUNC_EN(h2c_buff, bcn_ie_info->func_en); UPDATE_BEACON_PARSING_INFO_SET_SIZE_TH(h2c_buff, bcn_ie_info->size_th); UPDATE_BEACON_PARSING_INFO_SET_TIMEOUT(h2c_buff, bcn_ie_info->timeout); -- GitLab From b72703e26b9478da531144ce5c4552dd22f1103d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 6 Sep 2017 17:40:25 +0200 Subject: [PATCH 0103/1507] staging: pi433: Move limit check to switch default to kill warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With gcc-4.1.2: drivers/staging/pi433/rf69.c: In function ‘rf69_set_dio_mapping’: drivers/staging/pi433/rf69.c:566: warning: ‘regaddr’ may be used uninitialized in this function drivers/staging/pi433/rf69.c:565: warning: ‘shift’ may be used uninitialized in this function drivers/staging/pi433/rf69.c:564: warning: ‘mask’ may be used uninitialized in this function While this is a false positive, it can easily be fixed by moving the limit check into the "default" case of the switch statement. Signed-off-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- drivers/staging/pi433/rf69.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/staging/pi433/rf69.c b/drivers/staging/pi433/rf69.c index c4b1b218ea38f..290b419aa9dd7 100644 --- a/drivers/staging/pi433/rf69.c +++ b/drivers/staging/pi433/rf69.c @@ -570,12 +570,6 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) dev_dbg(&spi->dev, "set: DIO mapping"); #endif - // check DIO number - if (DIONumber > 5) { - dev_dbg(&spi->dev, "set: illegal input param"); - return -EINVAL; - } - switch (DIONumber) { case 0: mask=MASK_DIO0; shift=SHIFT_DIO0; regaddr=REG_DIOMAPPING1; break; case 1: mask=MASK_DIO1; shift=SHIFT_DIO1; regaddr=REG_DIOMAPPING1; break; @@ -583,6 +577,9 @@ int rf69_set_dio_mapping(struct spi_device *spi, u8 DIONumber, u8 value) case 3: mask=MASK_DIO3; shift=SHIFT_DIO3; regaddr=REG_DIOMAPPING1; break; case 4: mask=MASK_DIO4; shift=SHIFT_DIO4; regaddr=REG_DIOMAPPING2; break; case 5: mask=MASK_DIO5; shift=SHIFT_DIO5; regaddr=REG_DIOMAPPING2; break; + default: + dev_dbg(&spi->dev, "set: illegal input param"); + return -EINVAL; } // read reg -- GitLab From e5f5d0e20b6cecc0ebe6fc8e7df6f8823ad2d594 Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Tue, 5 Sep 2017 12:51:59 +0100 Subject: [PATCH 0104/1507] staging: speakup: fix speakup-r empty line lockup When cursor is at beginning of an empty or whitespace-only line and speakup-r typed, kernel locks up. This happens because deadlock of in input_event function over dev->event_lock, as demonstrated by lockdep logs. The reason for that is speakup simulates a down arrow - because cursor is at an empty line - while inside key press notifier handler which is ultimately triggered from input_event function. The simulated key press leads to input_event being called again, this time under its own context. So the spinlock is dev->event_lock is acquired while still being held. This patch ensures that key press is not simulated from inside key press notifier handler. Instead it delegates to cursor_timer. It starts the timer and passes RA_DOWN_ARROW as argument. When timer handler runs and sees RA_DOWN_ARROW, it will then call kbd_fakekey2(RA_DOWN_ARROW) which will correctly simulate the keypress inside timer context. When not inside key press notifier callback, the behaviour will remain the same as before this patch. Signed-off-by: Okash Khawaja Reviewed-by: Samuel Thibault Signed-off-by: Greg Kroah-Hartman --- drivers/staging/speakup/main.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 67956e24779ce..56f7be6af1f69 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -1376,6 +1376,8 @@ static void reset_highlight_buffers(struct vc_data *); static int read_all_key; +static int in_keyboard_notifier; + static void start_read_all_timer(struct vc_data *vc, int command); enum { @@ -1408,7 +1410,10 @@ static void read_all_doc(struct vc_data *vc) cursor_track = read_all_mode; spk_reset_index_count(0); if (get_sentence_buf(vc, 0) == -1) { - kbd_fakekey2(vc, RA_DOWN_ARROW); + del_timer(&cursor_timer); + if (!in_keyboard_notifier) + speakup_fake_down_arrow(); + start_read_all_timer(vc, RA_DOWN_ARROW); } else { say_sentence_num(0, 0); synth_insert_next_index(0); @@ -2212,8 +2217,10 @@ static int keyboard_notifier_call(struct notifier_block *nb, int ret = NOTIFY_OK; static int keycode; /* to hold the current keycode */ + in_keyboard_notifier = 1; + if (vc->vc_mode == KD_GRAPHICS) - return ret; + goto out; /* * First, determine whether we are handling a fake keypress on @@ -2225,7 +2232,7 @@ static int keyboard_notifier_call(struct notifier_block *nb, */ if (speakup_fake_key_pressed()) - return ret; + goto out; switch (code) { case KBD_KEYCODE: @@ -2266,6 +2273,8 @@ static int keyboard_notifier_call(struct notifier_block *nb, break; } } +out: + in_keyboard_notifier = 0; return ret; } -- GitLab From 974d4d03fc020af4fa4e9e72a86f0fefa37803c5 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sun, 3 Sep 2017 19:06:31 +0200 Subject: [PATCH 0105/1507] staging: vchiq_2835_arm: Fix NULL ptr dereference in free_pagelist This fixes a NULL pointer dereference on RPi 2 with multi_v7_defconfig. The function page_address() could return NULL with enabled CONFIG_HIGHMEM. So fix this by using kmap() instead. Signed-off-by: Stefan Wahren Fixes: 71bad7f08641 ("staging: add bcm2708 vchiq driver") Cc: stable Signed-off-by: Greg Kroah-Hartman --- .../vc04_services/interface/vchiq_arm/vchiq_2835_arm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c index 0159ca4407d8a..be08849175ea3 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_2835_arm.c @@ -612,18 +612,20 @@ free_pagelist(struct vchiq_pagelist_info *pagelistinfo, if (head_bytes > actual) head_bytes = actual; - memcpy((char *)page_address(pages[0]) + + memcpy((char *)kmap(pages[0]) + pagelist->offset, fragments, head_bytes); + kunmap(pages[0]); } if ((actual >= 0) && (head_bytes < actual) && (tail_bytes != 0)) { - memcpy((char *)page_address(pages[num_pages - 1]) + + memcpy((char *)kmap(pages[num_pages - 1]) + ((pagelist->offset + actual) & (PAGE_SIZE - 1) & ~(g_cache_line_size - 1)), fragments + g_cache_line_size, tail_bytes); + kunmap(pages[num_pages - 1]); } down(&g_free_fragments_mutex); -- GitLab From 55168470835688e5da5828cdcf1b1498d7baadb1 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Mon, 11 Sep 2017 10:45:12 +0300 Subject: [PATCH 0106/1507] usb: dwc3: ep0: fix DMA starvation by assigning req->trb on ep0 If we don't assign a TRB to ep0 requests, we won't be able to unmap the request later on resulting in starvation of DMA resources. Fixes: 4a71fcb8ac5f ("usb: dwc3: gadget: only unmap requests from DMA if mapped") Reported-by: Thinh Nguyen Tested-by: Thinh Nguyen Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/ep0.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 827e376bfa971..75e6cb044eb2b 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -990,6 +990,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, maxpacket - rem, @@ -1015,6 +1017,8 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, DWC3_TRBCTL_CONTROL_DATA, true); + req->trb = &dwc->ep0_trb[dep->trb_enqueue - 1]; + /* Now prepare one extra TRB to align transfer size */ dwc3_ep0_prepare_one_trb(dep, dwc->bounce_addr, 0, DWC3_TRBCTL_CONTROL_DATA, @@ -1029,6 +1033,9 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, DWC3_TRBCTL_CONTROL_DATA, false); + + req->trb = &dwc->ep0_trb[dep->trb_enqueue]; + ret = dwc3_ep0_start_trans(dep); } -- GitLab From 13541226dc056fa3f54417ce12f18ba711a1591c Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 31 Aug 2017 11:06:07 -0700 Subject: [PATCH 0107/1507] ARC: reset: remove the misleading v1 suffix all over There is no plan yet to do a v2 board. And even if we were to do it only some IPs would actually change, so it be best to add suffixes at that point, not now ! Signed-off-by: Vineet Gupta Signed-off-by: Philipp Zabel --- ...,hsdk-v1-reset.txt => snps,hsdk-reset.txt} | 8 ++-- MAINTAINERS | 6 +-- drivers/reset/Kconfig | 6 +-- drivers/reset/Makefile | 2 +- .../reset/{reset-hsdk-v1.c => reset-hsdk.c} | 44 +++++++++---------- include/dt-bindings/reset/snps,hsdk-reset.h | 17 +++++++ .../dt-bindings/reset/snps,hsdk-v1-reset.h | 17 ------- 7 files changed, 50 insertions(+), 50 deletions(-) rename Documentation/devicetree/bindings/reset/{snps,hsdk-v1-reset.txt => snps,hsdk-reset.txt} (74%) rename drivers/reset/{reset-hsdk-v1.c => reset-hsdk.c} (72%) create mode 100644 include/dt-bindings/reset/snps,hsdk-reset.h delete mode 100644 include/dt-bindings/reset/snps,hsdk-v1-reset.h diff --git a/Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt similarity index 74% rename from Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt rename to Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt index 6a68146ee3537..830069b1c37c4 100644 --- a/Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt +++ b/Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt @@ -1,11 +1,11 @@ -Binding for the HSDK v1 reset controller +Binding for the Synopsys HSDK reset controller This binding uses the common reset binding[1]. [1] Documentation/devicetree/bindings/reset/reset.txt Required properties: -- compatible: should be "snps,hsdk-v1.0-reset". +- compatible: should be "snps,hsdk-reset". - reg: should always contain 2 pairs address - length: first for reset configuration register and second for corresponding SW reset and status bits register. @@ -13,7 +13,7 @@ Required properties: Example: reset: reset@880 { - compatible = "snps,hsdk-v1.0-reset"; + compatible = "snps,hsdk-reset"; #reset-cells = <1>; reg = <0x8A0 0x4>, <0xFF0 0x4>; }; @@ -25,4 +25,4 @@ Specifying reset lines connected to IP modules: .... }; -The index could be found in +The index could be found in diff --git a/MAINTAINERS b/MAINTAINERS index 2281af4b41b6c..3b9887b3644ef 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12915,9 +12915,9 @@ F: drivers/mmc/host/dw_mmc* SYNOPSYS HSDK RESET CONTROLLER DRIVER M: Eugeniy Paltsev S: Supported -F: drivers/reset/reset-hsdk-v1.c -F: include/dt-bindings/reset/snps,hsdk-v1-reset.h -F: Documentation/devicetree/bindings/reset/snps,hsdk-v1-reset.txt +F: drivers/reset/reset-hsdk.c +F: include/dt-bindings/reset/snps,hsdk-reset.h +F: Documentation/devicetree/bindings/reset/snps,hsdk-reset.txt SYSTEM CONFIGURATION (SYSCON) M: Lee Jones diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index d063bd5373dd8..a7c7d5a8c089d 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -34,12 +34,12 @@ config RESET_BERLIN help This enables the reset controller driver for Marvell Berlin SoCs. -config RESET_HSDK_V1 - bool "HSDK v1 Reset Driver" +config RESET_HSDK + bool "Synopsys HSDK Reset Driver" depends on HAS_IOMEM default n help - This enables the reset controller driver for HSDK v1. + This enables the reset controller driver for HSDK board. config RESET_IMX7 bool "i.MX7 Reset Driver" if COMPILE_TEST diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile index d368367110e55..af1c15c330b30 100644 --- a/drivers/reset/Makefile +++ b/drivers/reset/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-$(CONFIG_RESET_A10SR) += reset-a10sr.o obj-$(CONFIG_RESET_ATH79) += reset-ath79.o obj-$(CONFIG_RESET_BERLIN) += reset-berlin.o -obj-$(CONFIG_RESET_HSDK_V1) += reset-hsdk-v1.o +obj-$(CONFIG_RESET_HSDK) += reset-hsdk.o obj-$(CONFIG_RESET_IMX7) += reset-imx7.o obj-$(CONFIG_RESET_LANTIQ) += reset-lantiq.o obj-$(CONFIG_RESET_LPC18XX) += reset-lpc18xx.o diff --git a/drivers/reset/reset-hsdk-v1.c b/drivers/reset/reset-hsdk.c similarity index 72% rename from drivers/reset/reset-hsdk-v1.c rename to drivers/reset/reset-hsdk.c index bca13e4bf6223..8bce391c6943b 100644 --- a/drivers/reset/reset-hsdk-v1.c +++ b/drivers/reset/reset-hsdk.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2017 Synopsys. * - * Synopsys HSDKv1 SDP reset driver. + * Synopsys HSDK Development platform reset driver. * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any @@ -18,9 +18,9 @@ #include #include -#define to_hsdkv1_rst(p) container_of((p), struct hsdkv1_rst, rcdev) +#define to_hsdk_rst(p) container_of((p), struct hsdk_rst, rcdev) -struct hsdkv1_rst { +struct hsdk_rst { void __iomem *regs_ctl; void __iomem *regs_rst; spinlock_t lock; @@ -49,12 +49,12 @@ static const u32 rst_map[] = { #define CGU_IP_SW_RESET_RESET BIT(0) #define SW_RESET_TIMEOUT 10000 -static void hsdkv1_reset_config(struct hsdkv1_rst *rst, unsigned long id) +static void hsdk_reset_config(struct hsdk_rst *rst, unsigned long id) { writel(rst_map[id], rst->regs_ctl + CGU_SYS_RST_CTRL); } -static int hsdkv1_reset_do(struct hsdkv1_rst *rst) +static int hsdk_reset_do(struct hsdk_rst *rst) { u32 reg; @@ -69,28 +69,28 @@ static int hsdkv1_reset_do(struct hsdkv1_rst *rst) !(reg & CGU_IP_SW_RESET_RESET), 5, SW_RESET_TIMEOUT); } -static int hsdkv1_reset_reset(struct reset_controller_dev *rcdev, +static int hsdk_reset_reset(struct reset_controller_dev *rcdev, unsigned long id) { - struct hsdkv1_rst *rst = to_hsdkv1_rst(rcdev); + struct hsdk_rst *rst = to_hsdk_rst(rcdev); unsigned long flags; int ret; spin_lock_irqsave(&rst->lock, flags); - hsdkv1_reset_config(rst, id); - ret = hsdkv1_reset_do(rst); + hsdk_reset_config(rst, id); + ret = hsdk_reset_do(rst); spin_unlock_irqrestore(&rst->lock, flags); return ret; } -static const struct reset_control_ops hsdkv1_reset_ops = { - .reset = hsdkv1_reset_reset, +static const struct reset_control_ops hsdk_reset_ops = { + .reset = hsdk_reset_reset, }; -static int hsdkv1_reset_probe(struct platform_device *pdev) +static int hsdk_reset_probe(struct platform_device *pdev) { - struct hsdkv1_rst *rst; + struct hsdk_rst *rst; struct resource *mem; rst = devm_kzalloc(&pdev->dev, sizeof(*rst), GFP_KERNEL); @@ -110,7 +110,7 @@ static int hsdkv1_reset_probe(struct platform_device *pdev) spin_lock_init(&rst->lock); rst->rcdev.owner = THIS_MODULE; - rst->rcdev.ops = &hsdkv1_reset_ops; + rst->rcdev.ops = &hsdk_reset_ops; rst->rcdev.of_node = pdev->dev.of_node; rst->rcdev.nr_resets = HSDK_MAX_RESETS; rst->rcdev.of_reset_n_cells = 1; @@ -118,20 +118,20 @@ static int hsdkv1_reset_probe(struct platform_device *pdev) return reset_controller_register(&rst->rcdev); } -static const struct of_device_id hsdkv1_reset_dt_match[] = { - { .compatible = "snps,hsdk-v1.0-reset" }, +static const struct of_device_id hsdk_reset_dt_match[] = { + { .compatible = "snps,hsdk-reset" }, { }, }; -static struct platform_driver hsdkv1_reset_driver = { - .probe = hsdkv1_reset_probe, +static struct platform_driver hsdk_reset_driver = { + .probe = hsdk_reset_probe, .driver = { - .name = "hsdk-v1.0-reset", - .of_match_table = hsdkv1_reset_dt_match, + .name = "hsdk-reset", + .of_match_table = hsdk_reset_dt_match, }, }; -builtin_platform_driver(hsdkv1_reset_driver); +builtin_platform_driver(hsdk_reset_driver); MODULE_AUTHOR("Eugeniy Paltsev "); -MODULE_DESCRIPTION("Synopsys HSDKv1 SDP reset driver"); +MODULE_DESCRIPTION("Synopsys HSDK SDP reset driver"); MODULE_LICENSE("GPL v2"); diff --git a/include/dt-bindings/reset/snps,hsdk-reset.h b/include/dt-bindings/reset/snps,hsdk-reset.h new file mode 100644 index 0000000000000..e1a643e4bc915 --- /dev/null +++ b/include/dt-bindings/reset/snps,hsdk-reset.h @@ -0,0 +1,17 @@ +/** + * This header provides index for the HSDK reset controller. + */ +#ifndef _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK +#define _DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK + +#define HSDK_APB_RESET 0 +#define HSDK_AXI_RESET 1 +#define HSDK_ETH_RESET 2 +#define HSDK_USB_RESET 3 +#define HSDK_SDIO_RESET 4 +#define HSDK_HDMI_RESET 5 +#define HSDK_GFX_RESET 6 +#define HSDK_DMAC_RESET 7 +#define HSDK_EBI_RESET 8 + +#endif /*_DT_BINDINGS_RESET_CONTROLLER_SNPS_HSDK*/ diff --git a/include/dt-bindings/reset/snps,hsdk-v1-reset.h b/include/dt-bindings/reset/snps,hsdk-v1-reset.h deleted file mode 100644 index d898c89b71232..0000000000000 --- a/include/dt-bindings/reset/snps,hsdk-v1-reset.h +++ /dev/null @@ -1,17 +0,0 @@ -/** - * This header provides index for the HSDK v1 reset controller. - */ -#ifndef _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1 -#define _DT_BINDINGS_RESET_CONTROLLER_HSDK_V1 - -#define HSDK_V1_APB_RESET 0 -#define HSDK_V1_AXI_RESET 1 -#define HSDK_V1_ETH_RESET 2 -#define HSDK_V1_USB_RESET 3 -#define HSDK_V1_SDIO_RESET 4 -#define HSDK_V1_HDMI_RESET 5 -#define HSDK_V1_GFX_RESET 6 -#define HSDK_V1_DMAC_RESET 7 -#define HSDK_V1_EBI_RESET 8 - -#endif /*_DT_BINDINGS_RESET_CONTROLLER_HSDK_V1*/ -- GitLab From a931b9ce93841a5b66b709ba5a244276e345e63b Mon Sep 17 00:00:00 2001 From: Guneshwor Singh Date: Thu, 14 Sep 2017 17:49:40 +0530 Subject: [PATCH 0108/1507] ALSA: compress: Remove unused variable Commit 04c5d5a430fc ("ALSA: compress: Embed struct device") removed the statement that used 'str' but didn't remove the variable itself. So remove it. [Adding stable to Cc since pr_debug() may refer to the uninitialized buffer -- tiwai] Fixes: 04c5d5a430fc ("ALSA: compress: Embed struct device") Signed-off-by: Guneshwor Singh Cc: Signed-off-by: Takashi Iwai --- sound/core/compress_offload.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index fec1dfdb14adf..4490a699030b1 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -948,14 +948,13 @@ static const struct file_operations snd_compr_file_ops = { static int snd_compress_dev_register(struct snd_device *device) { int ret = -EINVAL; - char str[16]; struct snd_compr *compr; if (snd_BUG_ON(!device || !device->device_data)) return -EBADFD; compr = device->device_data; - pr_debug("reg %s for device %s, direction %d\n", str, compr->name, + pr_debug("reg device %s, direction %d\n", compr->name, compr->direction); /* register compressed device */ ret = snd_register_device(SNDRV_DEVICE_TYPE_COMPRESS, -- GitLab From 1c363eaece2752c5f8b1b874cb4ae435de06aa66 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 5 Sep 2017 10:56:13 +0200 Subject: [PATCH 0109/1507] android: binder: fix type mismatch warning Allowing binder to expose the 64-bit API on 32-bit kernels caused a build warning: drivers/android/binder.c: In function 'binder_transaction_buffer_release': drivers/android/binder.c:2220:15: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] fd_array = (u32 *)(parent_buffer + fda->parent_offset); ^ drivers/android/binder.c: In function 'binder_translate_fd_array': drivers/android/binder.c:2445:13: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] fd_array = (u32 *)(parent_buffer + fda->parent_offset); ^ drivers/android/binder.c: In function 'binder_fixup_parent': drivers/android/binder.c:2511:18: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast] This adds extra type casts to avoid the warning. However, there is another problem with the Kconfig option: turning it on or off creates two incompatible ABI versions, a kernel that has this enabled cannot run user space that was built without it or vice versa. A better solution might be to leave the option hidden until the binder code is fixed to deal with both ABI versions. Fixes: e8d2ed7db7c3 ("Revert "staging: Fix build issues with new binder API"") Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d055b3f2a2078..72af95c9ea228 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2217,7 +2217,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, debug_id, (u64)fda->num_fds); continue; } - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); for (fd_index = 0; fd_index < fda->num_fds; fd_index++) task_close_fd(proc, fd_array[fd_index]); } break; @@ -2442,7 +2442,7 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, */ parent_buffer = parent->buffer - binder_alloc_get_user_buffer_offset(&target_proc->alloc); - fd_array = (u32 *)(parent_buffer + fda->parent_offset); + fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { binder_user_error("%d:%d parent offset not aligned correctly.\n", proc->pid, thread->pid); @@ -2508,7 +2508,7 @@ static int binder_fixup_parent(struct binder_transaction *t, proc->pid, thread->pid); return -EINVAL; } - parent_buffer = (u8 *)(parent->buffer - + parent_buffer = (u8 *)((uintptr_t)parent->buffer - binder_alloc_get_user_buffer_offset( &target_proc->alloc)); *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; -- GitLab From 52b81611f209da5f49019260522633e994e241b5 Mon Sep 17 00:00:00 2001 From: Xu YiPing Date: Tue, 5 Sep 2017 10:25:38 -0700 Subject: [PATCH 0110/1507] binder: fix an ret value override commit 372e3147df70 ("binder: guarantee txn complete / errors delivered in-order") incorrectly defined a local ret value. This ret value will be invalid when out of the if block Fixes: 372e3147df70 ("binder: refactor binder ref inc/dec for thread safety") Signed-off-by: Xu YiPing Signed-off-by: Todd Kjos Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 72af95c9ea228..b257bb0e2cfec 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2326,7 +2326,6 @@ static int binder_translate_handle(struct flat_binder_object *fp, (u64)node->ptr); binder_node_unlock(node); } else { - int ret; struct binder_ref_data dest_rdata; binder_node_unlock(node); -- GitLab From d53bebdf4d779497b29e1aad26e19cac1d446f42 Mon Sep 17 00:00:00 2001 From: Xu YiPing Date: Tue, 5 Sep 2017 10:21:52 -0700 Subject: [PATCH 0111/1507] binder: fix memory corruption in binder_transaction binder commit 7a4408c6bd3e ("binder: make sure accesses to proc/thread are safe") made a change to enqueue tcomplete to thread->todo before enqueuing the transaction. However, in err_dead_proc_or_thread case, the tcomplete is directly freed, without dequeued. It may cause the thread->todo list to be corrupted. So, dequeue it before freeing. Fixes: 7a4408c6bd3e ("binder: make sure accesses to proc/thread are safe") Signed-off-by: Xu YiPing Signed-off-by: Todd Kjos Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index b257bb0e2cfec..ab34239a76ee5 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3082,6 +3082,7 @@ static void binder_transaction(struct binder_proc *proc, err_dead_proc_or_thread: return_error = BR_DEAD_REPLY; return_error_line = __LINE__; + binder_dequeue_work(proc, tcomplete); err_translate_failed: err_bad_object_type: err_bad_offset: -- GitLab From 93dc1774d2a4c7a298d5cdf78cc8acdcb7b1428d Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Thu, 7 Sep 2017 15:37:30 +0200 Subject: [PATCH 0112/1507] auxdisplay: charlcd: properly restore atomic counter on error path Commit f4757af ("staging: panel: Fix single-open policy race condition") introduced in 3.19-rc1 attempted to fix a race condition on the open, but failed to properly do it and used to exit without restoring the semaphore. This results in -EBUSY being returned after the first open error until the module is reloaded or the system restarted (ie: consecutive to a dual open resulting in -EBUSY or to a permission error). [ Note for stable maintainers: the code moved from drivers/misc/panel.c to drivers/auxdisplay/{charlcd,panel}.c during 4.12. The patch easily applies there (modulo the renamed atomic counter) but I can provide a tested backport if desired. ] Fixes: f4757af85 # 3.19-rc1 Cc: stable@vger.kernel.org Cc: Mariusz Gorski Cc: Geert Uytterhoeven Cc: Miguel Ojeda Sandonis Signed-off-by: Willy Tarreau Signed-off-by: Greg Kroah-Hartman --- drivers/auxdisplay/charlcd.c | 11 +++++++++-- drivers/auxdisplay/panel.c | 11 +++++++++-- 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index cfeb049a01ef8..642afd88870ba 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -647,18 +647,25 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf, static int charlcd_open(struct inode *inode, struct file *file) { struct charlcd_priv *priv = to_priv(the_charlcd); + int ret; + ret = -EBUSY; if (!atomic_dec_and_test(&charlcd_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_READ) /* device is write-only */ - return -EPERM; + goto fail; if (priv->must_clear) { charlcd_clear_display(&priv->lcd); priv->must_clear = false; } return nonseekable_open(inode, file); + + fail: + atomic_inc(&charlcd_available); + return ret; } static int charlcd_release(struct inode *inode, struct file *file) diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index df126dcdaf18e..6911acd896d93 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1105,14 +1105,21 @@ static ssize_t keypad_read(struct file *file, static int keypad_open(struct inode *inode, struct file *file) { + int ret; + + ret = -EBUSY; if (!atomic_dec_and_test(&keypad_available)) - return -EBUSY; /* open only once at a time */ + goto fail; /* open only once at a time */ + ret = -EPERM; if (file->f_mode & FMODE_WRITE) /* device is read-only */ - return -EPERM; + goto fail; keypad_buflen = 0; /* flush the buffer on opening */ return 0; + fail: + atomic_inc(&keypad_available); + return ret; } static int keypad_release(struct inode *inode, struct file *file) -- GitLab From 38b0774c0598c7a54b8499d18c2b764c35dc94ab Mon Sep 17 00:00:00 2001 From: Guy Shapiro Date: Mon, 11 Sep 2017 11:00:11 +0200 Subject: [PATCH 0113/1507] nvmem: core: return EFBIG on out-of-range write When writing data that exceeds the nvmem size to a nvmem sysfs file using the sh redirection operator >, the shell hangs, trying to write the out-of-range bytes endlessly. Fix the problem by returning EFBIG described in man 2 write. Similar change was done for binary sysfs files on commit 0936896056365349afa867c16e9f9100a6707cbf Signed-off-by: Guy Shapiro Cc: linux-api@vger.kernel.org Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index de54c7f5048af..3866117bc285c 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -135,7 +135,7 @@ static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, /* Stop the user from writing */ if (pos >= nvmem->size) - return 0; + return -EFBIG; if (count < nvmem->word_size) return -EINVAL; -- GitLab From aad8d097c9224be264939fc6c02a5570ea094f60 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 11 Sep 2017 11:00:12 +0200 Subject: [PATCH 0114/1507] nvmem: add missing of_node_put() in of_nvmem_cell_get() of_get_next_parent() increments the refcount of the returned node. It should be put when done. Signed-off-by: Masahiro Yamada Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 3866117bc285c..d12e5de78e700 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -789,6 +789,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, return ERR_PTR(-EINVAL); nvmem = __nvmem_device_get(nvmem_np, NULL, NULL); + of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); -- GitLab From 6878e7de6af726de47f9f3bec649c3f49e786586 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 13 Sep 2017 16:29:48 -0700 Subject: [PATCH 0115/1507] driver core: suppress sending MODALIAS in UNBIND uevents The current udev rules cause modules to be loaded on all device events save for "remove". With the introduction of KOBJ_BIND/KOBJ_UNBIND this causes issues, as driver modules that have devices bound to their drivers get immediately reloaded, and it appears to the user that module unloading doe snot work. The standard udev matching rule is foillowing: ENV{MODALIAS}=="?*", RUN{builtin}+="kmod load $env{MODALIAS}" Given that MODALIAS data is not terribly useful for UNBIND event, let's zap it from the generated uevent environment until we get userspace updated with the correct udev rule that only loads modules on "add" event. Reported-by: Jakub Kicinski Tested-by: Jakub Kicinski Fixes: 1455cf8dbfd0 ("driver core: emit uevents when device is bound ...") Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 49 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 41 insertions(+), 8 deletions(-) diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index e590523ea4761..f237a09a58627 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -294,6 +294,26 @@ static void cleanup_uevent_env(struct subprocess_info *info) } #endif +static void zap_modalias_env(struct kobj_uevent_env *env) +{ + static const char modalias_prefix[] = "MODALIAS="; + int i; + + for (i = 0; i < env->envp_idx;) { + if (strncmp(env->envp[i], modalias_prefix, + sizeof(modalias_prefix) - 1)) { + i++; + continue; + } + + if (i != env->envp_idx - 1) + memmove(&env->envp[i], &env->envp[i + 1], + sizeof(env->envp[i]) * env->envp_idx - 1); + + env->envp_idx--; + } +} + /** * kobject_uevent_env - send an uevent with environmental data * @@ -409,16 +429,29 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, } } - /* - * Mark "add" and "remove" events in the object to ensure proper - * events to userspace during automatic cleanup. If the object did - * send an "add" event, "remove" will automatically generated by - * the core, if not already done by the caller. - */ - if (action == KOBJ_ADD) + switch (action) { + case KOBJ_ADD: + /* + * Mark "add" event so we can make sure we deliver "remove" + * event to userspace during automatic cleanup. If + * the object did send an "add" event, "remove" will + * automatically generated by the core, if not already done + * by the caller. + */ kobj->state_add_uevent_sent = 1; - else if (action == KOBJ_REMOVE) + break; + + case KOBJ_REMOVE: kobj->state_remove_uevent_sent = 1; + break; + + case KOBJ_UNBIND: + zap_modalias_env(env); + break; + + default: + break; + } mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ -- GitLab From 452562abb5b76c14449dead2a7113f641893e8bc Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 7 Sep 2017 15:16:05 +0100 Subject: [PATCH 0116/1507] base: arch_topology: fix section mismatch build warnings Commit 2ef7a2953c81 ("arm, arm64: factorize common cpu capacity default code") introduced init_cpu_capacity_callback and init_cpu_capacity_notifier which are referenced from initcall and are missing __init{,data} annotations resulting the below section mismatch build warnings. "WARNING: vmlinux.o(.text+0xbab790): Section mismatch in reference from the function init_cpu_capacity_callback() to the variable .init.text:$x The function init_cpu_capacity_callback() references the variable __init $x. This is often because init_cpu_capacity_callback lacks a __init annotation or the annotation of $x is wrong." This patch fixes the above build warnings by adding the required annotations. Fixes: 2ef7a2953c81 ("arm, arm64: factorize common cpu capacity default code") Cc: Juri Lelli Cc: stable Signed-off-by: Sudeep Holla Signed-off-by: Greg Kroah-Hartman --- drivers/base/arch_topology.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 41be9ff7d70a9..6df7d6676a481 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -166,11 +166,11 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) } #ifdef CONFIG_CPU_FREQ -static cpumask_var_t cpus_to_visit; -static void parsing_done_workfn(struct work_struct *work); -static DECLARE_WORK(parsing_done_work, parsing_done_workfn); +static cpumask_var_t cpus_to_visit __initdata; +static void __init parsing_done_workfn(struct work_struct *work); +static __initdata DECLARE_WORK(parsing_done_work, parsing_done_workfn); -static int +static int __init init_cpu_capacity_callback(struct notifier_block *nb, unsigned long val, void *data) @@ -206,7 +206,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, return 0; } -static struct notifier_block init_cpu_capacity_notifier = { +static struct notifier_block init_cpu_capacity_notifier __initdata = { .notifier_call = init_cpu_capacity_callback, }; @@ -232,7 +232,7 @@ static int __init register_cpufreq_notifier(void) } core_initcall(register_cpufreq_notifier); -static void parsing_done_workfn(struct work_struct *work) +static void __init parsing_done_workfn(struct work_struct *work) { cpufreq_unregister_notifier(&init_cpu_capacity_notifier, CPUFREQ_POLICY_NOTIFIER); -- GitLab From 9821786d7c90eee2f6852261893d9703801aae47 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Sep 2017 17:39:12 +0300 Subject: [PATCH 0117/1507] usb: xhci: Free the right ring in xhci_add_endpoint() In the xhci_add_endpoint(), a new ring was allocated and saved at xhci_virt_ep->new_ring. Hence, when error happens, we need to free the allocated ring before returning error. Current code frees xhci_virt_ep->ring instead of the new_ring. This patch fixes this. Cc: Signed-off-by: Lu Baolu Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index b2ff1ff1a02fa..ee198ea47f49e 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1703,7 +1703,8 @@ static int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, if (xhci->quirks & XHCI_MTK_HOST) { ret = xhci_mtk_add_ep_quirk(hcd, udev, ep); if (ret < 0) { - xhci_free_endpoint_ring(xhci, virt_dev, ep_index); + xhci_ring_free(xhci, virt_dev->eps[ep_index].new_ring); + virt_dev->eps[ep_index].new_ring = NULL; return ret; } } -- GitLab From 5a838a13c9b4e5dd188b7a6eaeb894e9358ead0c Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 18 Sep 2017 17:39:13 +0300 Subject: [PATCH 0118/1507] xhci: fix finding correct bus_state structure for USB 3.1 hosts xhci driver keeps a bus_state structure for each hcd (usb2 and usb3) The structure is picked based on hcd speed, but driver only compared for HCD_USB3 speed, returning the wrong bus_state for HCD_USB31 hosts. This caused null pointer dereference errors in bus_resume function. Cc: Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 2abaa4d6d39da..e96e90d0fe9ff 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1681,7 +1681,7 @@ struct xhci_bus_state { static inline unsigned int hcd_index(struct usb_hcd *hcd) { - if (hcd->speed == HCD_USB3) + if (hcd->speed >= HCD_USB3) return 0; else return 1; -- GitLab From 114ec3a6f9096d211a4aff4277793ba969a62c73 Mon Sep 17 00:00:00 2001 From: Jim Dickerson Date: Mon, 18 Sep 2017 17:39:14 +0300 Subject: [PATCH 0119/1507] usb: pci-quirks.c: Corrected timeout values used in handshake Servers were emitting failed handoff messages but were not waiting the full 1 second as designated in section 4.22.1 of the eXtensible Host Controller Interface specifications. The handshake was using wrong units so calls were made with milliseconds not microseconds. Comments referenced 5 seconds not 1 second as in specs. The wrong units were also corrected in a second handshake call. Cc: Signed-off-by: Jim Dickerson Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/pci-quirks.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 658d9d1f9ea37..e02dbb1e1cdde 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -1022,7 +1022,7 @@ EXPORT_SYMBOL_GPL(usb_disable_xhci_ports); * * Takes care of the handoff between the Pre-OS (i.e. BIOS) and the OS. * It signals to the BIOS that the OS wants control of the host controller, - * and then waits 5 seconds for the BIOS to hand over control. + * and then waits 1 second for the BIOS to hand over control. * If we timeout, assume the BIOS is broken and take control anyway. */ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) @@ -1069,9 +1069,9 @@ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) if (val & XHCI_HC_BIOS_OWNED) { writel(val | XHCI_HC_OS_OWNED, base + ext_cap_offset); - /* Wait for 5 seconds with 10 microsecond polling interval */ + /* Wait for 1 second with 10 microsecond polling interval */ timeout = handshake(base + ext_cap_offset, XHCI_HC_BIOS_OWNED, - 0, 5000, 10); + 0, 1000000, 10); /* Assume a buggy BIOS and take HC ownership anyway */ if (timeout) { @@ -1100,7 +1100,7 @@ static void quirk_usb_handoff_xhci(struct pci_dev *pdev) * operational or runtime registers. Wait 5 seconds and no more. */ timeout = handshake(op_reg_base + XHCI_STS_OFFSET, XHCI_STS_CNR, 0, - 5000, 10); + 5000000, 10); /* Assume a buggy HC and start HC initialization anyway */ if (timeout) { val = readl(op_reg_base + XHCI_STS_OFFSET); -- GitLab From 76a14d7bf92960aac2f5450bfd23783bfa618be9 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 18 Sep 2017 17:39:15 +0300 Subject: [PATCH 0120/1507] xhci: fix wrong endpoint ESIT value shown in tracing Read the endpiont ESIT from endpiont context using correct macro. Add a macro for reading the high bits of ESIT for Large ESIT Payload Capable hosts (LEC=1) Cc: # 4.12 Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index e96e90d0fe9ff..7c87189e8110d 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -735,6 +735,8 @@ struct xhci_ep_ctx { #define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) /* Endpoint is set up with a Linear Stream Array (vs. Secondary Stream Array) */ #define EP_HAS_LSA (1 << 15) +/* hosts with LEC=1 use bits 31:24 as ESIT high bits. */ +#define CTX_TO_MAX_ESIT_PAYLOAD_HI(p) (((p) >> 24) & 0xff) /* ep_info2 bitmasks */ /* @@ -2540,8 +2542,8 @@ static inline const char *xhci_decode_ep_context(u32 info, u32 info2, u64 deq, u8 lsa; u8 hid; - esit = EP_MAX_ESIT_PAYLOAD_HI(info) << 16 | - EP_MAX_ESIT_PAYLOAD_LO(tx_info); + esit = CTX_TO_MAX_ESIT_PAYLOAD_HI(info) << 16 | + CTX_TO_MAX_ESIT_PAYLOAD(tx_info); ep_state = info & EP_STATE_MASK; max_pstr = info & EP_MAXPSTREAMS_MASK; -- GitLab From c6b8e79306f515b5483eb11076e0fbfc140434a8 Mon Sep 17 00:00:00 2001 From: Adam Wallis Date: Mon, 18 Sep 2017 17:39:16 +0300 Subject: [PATCH 0121/1507] usb: host: xhci-plat: allow sysdev to inherit from ACPI Commit 4c39d4b949d3 ("usb: xhci: use bus->sysdev for DMA configuration") updated the method determining DMA for XHCI from sysdev. However, this patch broke the ability to enumerate the FWNODE from parent ACPI devices from the child plat XHCI device. Currently, xhci_plat is not set up properly when the parent device is an ACPI node. The conditions that xhci_plat_probe should satisfy are 1. xhci_plat comes from firmware 2. xhci_plat is child of a device from firmware (dwc3-plat) 3. xhci_plat is grandchild of a pci device (dwc3-pci) Case 2 is covered when the child is an OF node (by checking sysdev->parent->of_node), however, an ACPI parent will return NULL in the of_node check and will thus not result in sysdev being set to sysdev->parent [ 17.591549] xhci-hcd: probe of xhci-hcd.6.auto failed with error -5 This change adds a check for ACPI to completely allow for condition 2. This is done by first checking if the parent node is of type ACPI (e.g., dwc3-plat) and set sysdev to sysdev->parent if either of the two following conditions are met: 1: If fwnode is empty (in the case that platform_device_add_properties was not called on the allocated platform device) 2: fwnode exists but is not of type ACPI (this would happen if platform_device_add_properties was called on the allocated device. Instead of type FWNODE_ACPI, you would end up with FWNODE_PDATA) Cc: stable@vger.kernel.org #4.12.x Cc: stable@vger.kernel.org #4.13.x Fixes: 4c39d4b949d3 ("usb: xhci: use bus->sysdev for DMA configuration") Tested-by: Thang Q. Nguyen Signed-off-by: Adam Wallis Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-plat.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 163bafde709f7..1cb6eaef4ae14 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -178,14 +178,18 @@ static int xhci_plat_probe(struct platform_device *pdev) * 2. xhci_plat is child of a device from firmware (dwc3-plat) * 3. xhci_plat is grandchild of a pci device (dwc3-pci) */ - sysdev = &pdev->dev; - if (sysdev->parent && !sysdev->of_node && sysdev->parent->of_node) - sysdev = sysdev->parent; + for (sysdev = &pdev->dev; sysdev; sysdev = sysdev->parent) { + if (is_of_node(sysdev->fwnode) || + is_acpi_device_node(sysdev->fwnode)) + break; #ifdef CONFIG_PCI - else if (sysdev->parent && sysdev->parent->parent && - sysdev->parent->parent->bus == &pci_bus_type) - sysdev = sysdev->parent->parent; + else if (sysdev->bus == &pci_bus_type) + break; #endif + } + + if (!sysdev) + sysdev = &pdev->dev; /* Try to set 64-bit DMA first */ if (WARN_ON(!sysdev->dma_mask)) -- GitLab From 4ec1cd3eeeee7ccc35681270da028dbc29ca7bbd Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 18 Sep 2017 17:39:17 +0300 Subject: [PATCH 0122/1507] xhci: Fix sleeping with spin_lock_irq() held in ASmedia 1042A workaround The flow control workaround for ASM1042A xHC hosts sleeps between register polling. The workaround gets called in several places, among them with spin_lock_irq() held when xHC host is resumed or hoplug removed. This was noticed as kernel panics at resume on a Dell XPS15 9550 with TB16 thunderbolt dock. Avoid sleeping with spin_lock_irq() held, use udelay() instead The original workaround was added to 4.9 and 4.12 stable releases, this patch needs to be applied to those as well. Fixes: 9da5a1092b13 ("xhci: Bad Ethernet performance plugged in ASM1042A host") Cc: #4.9+ Reported-by: Jose Marino Tested-by: Jose Marino Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/pci-quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index e02dbb1e1cdde..6dda3623a276d 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -447,7 +447,7 @@ static int usb_asmedia_wait_write(struct pci_dev *pdev) if ((value & ASMT_CONTROL_WRITE_BIT) == 0) return 0; - usleep_range(40, 60); + udelay(50); } dev_warn(&pdev->dev, "%s: check_write_ready timeout", __func__); -- GitLab From 7bea22b124d77845c85a62eaa29a85ba6cc2f899 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 18 Sep 2017 17:39:18 +0300 Subject: [PATCH 0123/1507] xhci: set missing SuperSpeedPlus Link Protocol bit in roothub descriptor A SuperSpeedPlus roothub needs to have the Link Protocol (LP) bit set in the bmSublinkSpeedAttr[] entry of a SuperSpeedPlus descriptor. If the xhci controller has an optional Protocol Speed ID (PSI) table then that will be used as a base to create the roothub SuperSpeedPlus descriptor. The PSI table does not however necessary contain the LP bit so we need to set it manually. Check the psi speed and set LP bit if speed is 10Gbps or higher. We're not setting it for 5 to 10Gbps as USB 3.1 specification always mention SuperSpeedPlus for 10Gbps or higher, and some SSIC USB 3.0 speeds can be over 5Gbps, such as SSIC-G3B-L1 at 5830 Mbps Cc: # 4.6+ Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-hub.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index ad89a6d4111b4..4dba2cf73cbec 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -112,7 +112,7 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, /* If PSI table exists, add the custom speed attributes from it */ if (usb3_1 && xhci->usb3_rhub.psi_count) { - u32 ssp_cap_base, bm_attrib, psi; + u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp; int offset; ssp_cap_base = USB_DT_BOS_SIZE + USB_DT_USB_SS_CAP_SIZE; @@ -139,6 +139,15 @@ static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf, for (i = 0; i < xhci->usb3_rhub.psi_count; i++) { psi = xhci->usb3_rhub.psi[i]; psi &= ~USB_SSP_SUBLINK_SPEED_RSVD; + psi_exp = XHCI_EXT_PORT_PSIE(psi); + psi_mant = XHCI_EXT_PORT_PSIM(psi); + + /* Shift to Gbps and set SSP Link BIT(14) if 10Gpbs */ + for (; psi_exp < 3; psi_exp++) + psi_mant /= 1000; + if (psi_mant >= 10) + psi |= BIT(14); + if ((psi & PLT_MASK) == PLT_SYM) { /* Symmetric, create SSA RX and TX from one PSI entry */ put_unaligned_le32(psi, &buf[offset]); -- GitLab From bcd6a7aa13800afc1418e6b29d944d882214939a Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Mon, 18 Sep 2017 17:39:19 +0300 Subject: [PATCH 0124/1507] Revert "xhci: Limit USB2 port wake support for AMD Promontory hosts" This reverts commit dec08194ffeccfa1cf085906b53d301930eae18f. Commit dec08194ffec ("xhci: Limit USB2 port wake support for AMD Promontory hosts") makes all high speed USB ports on ASUS PRIME B350M-A cease to function after enabling runtime PM. All boards with this chipsets will be affected, so revert the commit. The original patch was added to stable 4.9, 4.11 and 4.12 and needs to reverted from there as well Cc: # 4.9+ Signed-off-by: Kai-Heng Feng Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-hub.c | 3 --- drivers/usb/host/xhci-pci.c | 12 ------------ drivers/usb/host/xhci.h | 2 +- 3 files changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 4dba2cf73cbec..da9158f171cbe 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1515,9 +1515,6 @@ int xhci_bus_suspend(struct usb_hcd *hcd) t2 |= PORT_WKOC_E | PORT_WKCONN_E; t2 &= ~PORT_WKDISC_E; } - if ((xhci->quirks & XHCI_U2_DISABLE_WAKE) && - (hcd->speed < HCD_USB3)) - t2 &= ~PORT_WAKE_BITS; } else t2 &= ~PORT_WAKE_BITS; diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 8071c8fdd15e7..76f3929547336 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -54,11 +54,6 @@ #define PCI_DEVICE_ID_INTEL_APL_XHCI 0x5aa8 #define PCI_DEVICE_ID_INTEL_DNV_XHCI 0x19d0 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 -#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba -#define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb -#define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc - #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142 static const char hcd_name[] = "xhci_hcd"; @@ -142,13 +137,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; - if ((pdev->vendor == PCI_VENDOR_ID_AMD) && - ((pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_3) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2) || - (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_1))) - xhci->quirks |= XHCI_U2_DISABLE_WAKE; - if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; xhci->quirks |= XHCI_INTEL_HOST; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 7c87189e8110d..2b48aa4f6b767 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1828,7 +1828,7 @@ struct xhci_hcd { /* For controller with a broken Port Disable implementation */ #define XHCI_BROKEN_PORT_PED (1 << 25) #define XHCI_LIMIT_ENDPOINT_INTERVAL_7 (1 << 26) -#define XHCI_U2_DISABLE_WAKE (1 << 27) +/* Reserved. It was XHCI_U2_DISABLE_WAKE */ #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) unsigned int num_active_eps; -- GitLab From bf563b01c2895a4bfd1a29cc5abc67fe706ecffd Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 11 Sep 2017 09:45:42 +0200 Subject: [PATCH 0125/1507] driver core: platform: Don't read past the end of "driver_override" buffer When printing the driver_override parameter when it is 4095 and 4094 bytes long, the printing code would access invalid memory because we need count+1 bytes for printing. Reject driver_override values of these lengths in driver_override_store(). This is in close analogy to commit 4efe874aace5 ("PCI: Don't read past the end of sysfs "driver_override" buffer") from Sasha Levin. Fixes: 3d713e0e382e ("driver core: platform: add device binding path 'driver_override'") Cc: stable@vger.kernel.org # v3.17+ Signed-off-by: Nicolai Stange Signed-off-by: Greg Kroah-Hartman --- drivers/base/platform.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index d1bd992710663..9045c5f3734e8 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -868,7 +868,8 @@ static ssize_t driver_override_store(struct device *dev, struct platform_device *pdev = to_platform_device(dev); char *driver_override, *old, *cp; - if (count > PATH_MAX) + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) return -EINVAL; driver_override = kstrndup(buf, count, GFP_KERNEL); -- GitLab From 432219fd002ada95d2f45dd3a25c3f7c73f27864 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 2 Sep 2017 01:15:13 +0300 Subject: [PATCH 0126/1507] serial: sh-sci: document R8A77970 bindings R-Car V3M (R8A77970) SoC also has the R-Car gen3 compatible SCIF and HSCIF ports, so document the SoC specific bindings. Signed-off-by: Sergei Shtylyov Acked-by: Rob Herring Acked-by: Geert Uytterhoeven Acked-by: Simon Horman Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/renesas,sci-serial.txt | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt index 4fc96946f81d6..cf504d0380aeb 100644 --- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt +++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt @@ -41,6 +41,8 @@ Required properties: - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART. - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART. - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART. + - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART. + - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART. - "renesas,scif-r8a77995" for R8A77995 (R-Car D3) SCIF compatible UART. - "renesas,hscif-r8a77995" for R8A77995 (R-Car D3) HSCIF compatible UART. - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART. -- GitLab From 104583b504da8a3ad86d033b497cb6e58941a9a1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 12 Sep 2017 12:39:54 +0200 Subject: [PATCH 0127/1507] mxser: fix timeout calculation for low rates Paul reported, that low rates like B300 make the driver to hang in mxser_wait_until_sent. His debugging tackled the issue down to the info->timeout computation in mxser_set_baud. Obviously, ints are used there and they easily overflow with these low rates: B300 makes info->timeout to be -373. So switch all these types to unsigned as it ought to be. And use the u64 domain to perform the computation as in the worst case, we need 35 bits to store the computed value (before division). And use do_div not to break 32 bit kernels. [v2] make it actually build Signed-off-by: Jiri Slaby Cc: Paul Tested-by: Signed-off-by: Greg Kroah-Hartman --- drivers/tty/mxser.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index 1c0c9553bc050..7dd38047ba235 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -246,11 +246,11 @@ struct mxser_port { unsigned char err_shadow; struct async_icount icount; /* kernel counters for 4 input interrupts */ - int timeout; + unsigned int timeout; int read_status_mask; int ignore_status_mask; - int xmit_fifo_size; + unsigned int xmit_fifo_size; int xmit_head; int xmit_tail; int xmit_cnt; @@ -572,8 +572,9 @@ static void mxser_dtr_rts(struct tty_port *port, int on) static int mxser_set_baud(struct tty_struct *tty, long newspd) { struct mxser_port *info = tty->driver_data; - int quot = 0, baud; + unsigned int quot = 0, baud; unsigned char cval; + u64 timeout; if (!info->ioaddr) return -1; @@ -594,8 +595,13 @@ static int mxser_set_baud(struct tty_struct *tty, long newspd) quot = 0; } - info->timeout = ((info->xmit_fifo_size * HZ * 10 * quot) / info->baud_base); - info->timeout += HZ / 50; /* Add .02 seconds of slop */ + /* + * worst case (128 * 1000 * 10 * 18432) needs 35 bits, so divide in the + * u64 domain + */ + timeout = (u64)info->xmit_fifo_size * HZ * 10 * quot; + do_div(timeout, info->baud_base); + info->timeout = timeout + HZ / 50; /* Add .02 seconds of slop */ if (quot) { info->MCR |= UART_MCR_DTR; -- GitLab From 0e5ec4140c4a8a38c4ff7293c018eb7da69a30db Mon Sep 17 00:00:00 2001 From: Russell Enderby Date: Tue, 5 Sep 2017 12:16:47 -0500 Subject: [PATCH 0128/1507] serial: bcm63xx: fix timing issue. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Issue where unprintable characters can occur or output is cut off over the serial uart / linux console depending on timing. Problem occurs when changing the serial baud rate when setting up the new console.The bcm63xx driver does a disable and flush of the uart tx fifo while there is data still in the tx fifo. If the tx fifo still has data it is trying to send out, we need to wait until it is empty before disabling and flushing the uart. When we now go to change the uart parameters including speed we check if there is data currently in the tx fifo.If there is was mdelay(10) and check again.If it tries 3 times and still has data in it we just continue and sacrifice the tx fifo buffer. A cleaner and more preferred approach would be to remove : - spin_lock_irqsave() - bcm_uart_disable() - bcm_uart_flush() However it is not clear if the author put those in to fix another underlying issue.As a result this solution is a safer approach. Output before the fix: [0.306000] 14e00520.serial: ttyS0 at MMIO 0x14e00520 (irq = 9, base_baud = 1687500) is a° 0.315000] console[ttyS0] enabled Output verified after the fix: [0.315000] 14e00520.serial: ttyS0 at MMIO 0x14e00520 (irq = 9, base_baud = 1687500) is a bcm63xx_uart [0.334000] console[ttyS0] enabled Signed-off-by: Russell Enderby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/bcm63xx_uart.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index 583c9a0c7eccd..8c48c3784831b 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -507,9 +507,14 @@ static void bcm_uart_set_termios(struct uart_port *port, { unsigned int ctl, baud, quot, ier; unsigned long flags; + int tries; spin_lock_irqsave(&port->lock, flags); + /* Drain the hot tub fully before we power it off for the winter. */ + for (tries = 3; !bcm_uart_tx_empty(port) && tries; tries--) + mdelay(10); + /* disable uart while changing speed */ bcm_uart_disable(port); bcm_uart_flush(port); -- GitLab From 9d7ee0e28da59b05647c3d2a7ad4076c16b1a6ef Mon Sep 17 00:00:00 2001 From: Fugang Duan Date: Mon, 4 Sep 2017 19:20:24 +0800 Subject: [PATCH 0129/1507] tty: serial: lpuart: avoid report NULL interrupt The current driver register irq in .startup() and free the irq in .shutdown(), then user will see the NULL interrupt output from 'cat /proc/interrupts' after the uart port test completed: ... 41: 515 0 0 0 GICv3 257 Level fsl-lpuart 42: 2 0 0 0 GICv3 258 Level ... It is better to register all the irqs during probe function via devm_request_irq() to avoid to call free_irq(). Signed-off-by: Fugang Duan Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 40 ++++++++++++++------------------- 1 file changed, 17 insertions(+), 23 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 849c1f9991cec..f0252184291ed 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1276,7 +1276,6 @@ static void rx_dma_timer_init(struct lpuart_port *sport) static int lpuart_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned char temp; @@ -1291,11 +1290,6 @@ static int lpuart_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTPFIFO_RXSIZE_OFF) & UARTPFIFO_FIFOSIZE_MASK) + 1); - ret = devm_request_irq(port->dev, port->irq, lpuart_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart_setup_watermark(sport); @@ -1333,7 +1327,6 @@ static int lpuart_startup(struct uart_port *port) static int lpuart32_startup(struct uart_port *port) { struct lpuart_port *sport = container_of(port, struct lpuart_port, port); - int ret; unsigned long flags; unsigned long temp; @@ -1346,11 +1339,6 @@ static int lpuart32_startup(struct uart_port *port) sport->rxfifo_size = 0x1 << (((temp >> UARTFIFO_RXSIZE_OFF) & UARTFIFO_FIFOSIZE_MASK) - 1); - ret = devm_request_irq(port->dev, port->irq, lpuart32_int, 0, - DRIVER_NAME, sport); - if (ret) - return ret; - spin_lock_irqsave(&sport->port.lock, flags); lpuart32_setup_watermark(sport); @@ -1380,8 +1368,6 @@ static void lpuart_shutdown(struct uart_port *port) spin_unlock_irqrestore(&port->lock, flags); - devm_free_irq(port->dev, port->irq, sport); - if (sport->lpuart_dma_rx_use) { del_timer_sync(&sport->lpuart_timer); lpuart_dma_rx_free(&sport->port); @@ -1400,7 +1386,6 @@ static void lpuart_shutdown(struct uart_port *port) static void lpuart32_shutdown(struct uart_port *port) { - struct lpuart_port *sport = container_of(port, struct lpuart_port, port); unsigned long temp; unsigned long flags; @@ -1413,8 +1398,6 @@ static void lpuart32_shutdown(struct uart_port *port) lpuart32_write(port, temp, UARTCTRL); spin_unlock_irqrestore(&port->lock, flags); - - devm_free_irq(port->dev, port->irq, sport); } static void @@ -2212,16 +2195,22 @@ static int lpuart_probe(struct platform_device *pdev) platform_set_drvdata(pdev, &sport->port); - if (lpuart_is_32(sport)) + if (lpuart_is_32(sport)) { lpuart_reg.cons = LPUART32_CONSOLE; - else + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart32_int, 0, + DRIVER_NAME, sport); + } else { lpuart_reg.cons = LPUART_CONSOLE; + ret = devm_request_irq(&pdev->dev, sport->port.irq, lpuart_int, 0, + DRIVER_NAME, sport); + } + + if (ret) + goto failed_irq_request; ret = uart_add_one_port(&lpuart_reg, &sport->port); - if (ret) { - clk_disable_unprepare(sport->clk); - return ret; - } + if (ret) + goto failed_attach_port; sport->dma_tx_chan = dma_request_slave_channel(sport->port.dev, "tx"); if (!sport->dma_tx_chan) @@ -2240,6 +2229,11 @@ static int lpuart_probe(struct platform_device *pdev) } return 0; + +failed_attach_port: +failed_irq_request: + clk_disable_unprepare(sport->clk); + return ret; } static int lpuart_remove(struct platform_device *pdev) -- GitLab From c91261437985d481c472639d4397931d77f5d4e9 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Sat, 2 Sep 2017 23:13:55 +0300 Subject: [PATCH 0130/1507] serial: sccnxp: Fix error handling in sccnxp_probe() sccnxp_probe() returns result of regulator_disable() that may lead to returning zero, while device is not properly initialized. Also the driver enables clocks, but it does not disable it. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sccnxp.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c index cdd2f942317c5..b9c7a904c1eaf 100644 --- a/drivers/tty/serial/sccnxp.c +++ b/drivers/tty/serial/sccnxp.c @@ -889,7 +889,16 @@ static int sccnxp_probe(struct platform_device *pdev) goto err_out; uartclk = 0; } else { - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); + if (ret) + goto err_out; + + ret = devm_add_action_or_reset(&pdev->dev, + (void(*)(void *))clk_disable_unprepare, + clk); + if (ret) + goto err_out; + uartclk = clk_get_rate(clk); } @@ -988,7 +997,7 @@ static int sccnxp_probe(struct platform_device *pdev) uart_unregister_driver(&s->uart); err_out: if (!IS_ERR(s->regulator)) - return regulator_disable(s->regulator); + regulator_disable(s->regulator); return ret; } -- GitLab From 64cfcaed7b25f69d8b7a091a23961f50c6788a66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Daniel=20D=C3=ADaz?= Date: Fri, 7 Jul 2017 10:27:06 -0500 Subject: [PATCH 0131/1507] selftests: net: More graceful finding of `ip'. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ip tool might be provided by another package (such as Busybox), not necessarily implementing the -Version switch. Trying an actual usage (`ip link show') might be a better test that would work with all implementations of `ip'. Signed-off-by: Daniel Díaz Signed-off-by: Shuah Khan --- tools/testing/selftests/net/netdevice.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index 4e00568d70c2c..90cb903c33815 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -178,7 +178,7 @@ if [ "$(id -u)" -ne 0 ];then exit 0 fi -ip -Version 2>/dev/null >/dev/null +ip link show 2>/dev/null >/dev/null if [ $? -ne 0 ];then echo "SKIP: Could not run test without the ip tool" exit 0 -- GitLab From 96e5335859e30fa2bb2da8befc86292c3c1a73dd Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 11 Sep 2017 12:49:01 +0200 Subject: [PATCH 0132/1507] tools: fix testing/selftests/sigaltstack for s390x MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On s390x the compilation of the file sas.c in directory tools/testing/selftests/sigaltstack fails with this error message: root@s35lp76 testing]# make selftests/sigaltstack/sas cc selftests/sigaltstack/sas.c -o selftests/sigaltstack/sas selftests/sigaltstack/sas.c: In function ‘my_usr1’: selftests/sigaltstack/sas.c:42:25: error: invalid register name for ‘sp’ register unsigned long sp asm("sp"); ^~ : recipe for target 'selftests/sigaltstack/sas' failed make: *** [selftests/sigaltstack/sas] Error 1 [root@s35lp76 testing]# On s390x the stack pointer is register r15, the register name "sp" is unknown. Make this line platform dependend and use register r15. With this patch the compilation and test succeeds: [root@s35lp76 testing]# ./selftests/sigaltstack/sas TAP version 13 ok 1 Initial sigaltstack state was SS_DISABLE # [RUN] signal USR1 ok 2 sigaltstack is disabled in sighandler # [RUN] switched to user ctx # [RUN] signal USR2 # [OK] Stack preserved ok 3 sigaltstack is still SS_AUTODISARM after signal Pass 3 Fail 0 Xfail 0 Xpass 0 Skip 0 Error 0 1..3 [root@s35lp76 testing]# Signed-off-by: Thomas Richter Signed-off-by: Shuah Khan --- tools/testing/selftests/sigaltstack/sas.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 7d406c3973ba4..97bb150837df0 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -39,7 +39,11 @@ void my_usr1(int sig, siginfo_t *si, void *u) stack_t stk; struct stk_data *p; +#if __s390x__ + register unsigned long sp asm("%15"); +#else register unsigned long sp asm("sp"); +#endif if (sp < (unsigned long)sstack || sp >= (unsigned long)sstack + SIGSTKSZ) { -- GitLab From 172a8ca880f1c8b01bc4d1e0239bcb293ef65e0b Mon Sep 17 00:00:00 2001 From: Fathi Boudra Date: Thu, 29 Jun 2017 12:39:53 +0300 Subject: [PATCH 0133/1507] selftests: breakpoints: re-order TEST_GEN_PROGS targets breakpoint_test can fail on arm64 with older/unpatched glibc: breakpoint_test_arm64.c: In function 'run_test': breakpoint_test_arm64.c:170:25: error: 'TRAP_HWBKPT' undeclared (first use in this function) due to glibc missing several of the TRAP_* constants in the userspace definitions. Specifically TRAP_BRANCH and TRAP_HWBKPT. See https://sourceware.org/bugzilla/show_bug.cgi?id=21286 It prevents to build step_after_suspend_test afterward, since make won't continue. We still want to be able to build and run the test, independently of breakpoint_test_arm64 build failure. Re-order TEST_GEN_PROGS to be able to build step_after_suspend_test first. Signed-off-by: Fathi Boudra Signed-off-by: Shuah Khan --- tools/testing/selftests/breakpoints/Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 6b214b7b10fb7..247b0a1899d70 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -2,14 +2,14 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +TEST_GEN_PROGS := step_after_suspend_test + ifeq ($(ARCH),x86) -TEST_GEN_PROGS := breakpoint_test +TEST_GEN_PROGS += breakpoint_test endif ifneq (,$(filter $(ARCH),aarch64 arm64)) -TEST_GEN_PROGS := breakpoint_test_arm64 +TEST_GEN_PROGS += breakpoint_test_arm64 endif -TEST_GEN_PROGS += step_after_suspend_test - include ../lib.mk -- GitLab From 67b2e30eb7b346db60afe91b0927738fb604d0a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Daniel=20D=C3=ADaz?= Date: Thu, 17 Aug 2017 10:55:30 -0500 Subject: [PATCH 0134/1507] selftests: intel_pstate: build only on x86 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These tests are only for x86, so don't try to build or run them on other architectures. Signed-off-by: Daniel Díaz Signed-off-by: Shuah Khan --- tools/testing/selftests/intel_pstate/Makefile | 2 ++ tools/testing/selftests/intel_pstate/run.sh | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index 849a90ffe8dd2..a97e24edde39e 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,7 +1,9 @@ CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDLIBS := $(LDLIBS) -lm +ifeq (,$(filter $(ARCH),x86)) TEST_GEN_FILES := msr aperf +endif TEST_PROGS := run.sh diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index 7868c106b8b1b..1b4b8302dfc20 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -29,6 +29,11 @@ EVALUATE_ONLY=0 +if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then + echo "$0 # Skipped: Test can only run on x86 architectures." + exit 0 +fi + max_cpus=$(($(nproc)-1)) # compile programs -- GitLab From 6f0003363a13be699ba945cfa4074193e04fbea5 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Fri, 8 Sep 2017 14:01:18 +0200 Subject: [PATCH 0135/1507] selftests/intel_pstate: No need to compile test progs in the run script Both test programs are being compiled by make, so no need to compile both programs in the runner script. This resolves an error when installing all selftests via make install and run them in a different environemnt. Running tests in intel_pstate ======================================== ./run.sh: line 35: gcc: command not found Problem compiling aperf.c. Signed-off-by: Thomas Meyer Signed-off-by: Shuah Khan --- tools/testing/selftests/intel_pstate/run.sh | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index 1b4b8302dfc20..d3ab48f91cd6a 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -36,12 +36,6 @@ fi max_cpus=$(($(nproc)-1)) -# compile programs -gcc aperf.c -Wall -D_GNU_SOURCE -o aperf -lm -[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1 -gcc -o msr msr.c -lm -[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1 - function run_test () { file_ext=$1 -- GitLab From 56a268cd4a410081d477913d51e044039d3a8834 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Fri, 8 Sep 2017 13:19:23 +0200 Subject: [PATCH 0136/1507] selftests/bpf: Make bpf_util work on uniprocessor systems The current implementation fails to work on uniprocessor systems. Fix the parser to also handle the uniprocessor case. Signed-off-by: Thomas Meyer Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Shuah Khan --- tools/testing/selftests/bpf/bpf_util.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 20ecbaa0d85d7..6c53a8906eff4 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -12,6 +12,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; + int n; fp = fopen(fcpu, "r"); if (!fp) { @@ -20,17 +21,17 @@ static inline unsigned int bpf_num_possible_cpus(void) } while (fgets(buff, sizeof(buff), fp)) { - if (sscanf(buff, "%u-%u", &start, &end) == 2) { - possible_cpus = start == 0 ? end + 1 : 0; - break; + n = sscanf(buff, "%u-%u", &start, &end); + if (n == 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; } + possible_cpus = start == 0 ? end + 1 : 0; + break; } - fclose(fp); - if (!possible_cpus) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } return possible_cpus; } -- GitLab From 84c06566cfb84e5f6aed9582d4570df8406700c9 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Fri, 8 Sep 2017 14:01:17 +0200 Subject: [PATCH 0137/1507] selftests/ftrace: multiple_kprobes: Also check for support The multiple_kprobes test case fails to check for KPROBE_EVENT support. Add the check to prevent a false test result. Signed-off-by: Thomas Meyer Acked-by: Masami Hiramatsu Acked-by: Steven Rostedt (VMware) Signed-off-by: Shuah Khan --- .../testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc index 2a1cb99087461..a4fd4c851a5b7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/multiple_kprobes.tc @@ -1,6 +1,8 @@ #!/bin/sh # description: Register/unregister many kprobe events +[ -f kprobe_events ] || exit_unsupported # this is configurable + # ftrace fentry skip size depends on the machine architecture. # Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le case `uname -m` in -- GitLab From 47684e111f52fface17820d3ef84cc845b26070e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 18 Sep 2017 13:10:15 -0700 Subject: [PATCH 0138/1507] Documentation: core-api: minor workqueue.rst cleanups Clean up workqueue.rst: - fix minor typos - put '@' after `` instead of preceding them (one place) - use "CPU" instead of "cpu" in text consistently - quote one function name Signed-off-by: Randy Dunlap Cc: Tejun Heo Cc: Florian Mickler Signed-off-by: Tejun Heo --- Documentation/core-api/workqueue.rst | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 3943b5bfa8cff..00a5ba51e63fb 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -39,8 +39,8 @@ up. Although MT wq wasted a lot of resource, the level of concurrency provided was unsatisfactory. The limitation was common to both ST and MT wq albeit less severe on MT. Each wq maintained its own separate -worker pool. A MT wq could provide only one execution context per CPU -while a ST wq one for the whole system. Work items had to compete for +worker pool. An MT wq could provide only one execution context per CPU +while an ST wq one for the whole system. Work items had to compete for those very limited execution contexts leading to various problems including proneness to deadlocks around the single execution context. @@ -151,7 +151,7 @@ Application Programming Interface (API) ``alloc_workqueue()`` allocates a wq. The original ``create_*workqueue()`` functions are deprecated and scheduled for -removal. ``alloc_workqueue()`` takes three arguments - @``name``, +removal. ``alloc_workqueue()`` takes three arguments - ``@name``, ``@flags`` and ``@max_active``. ``@name`` is the name of the wq and also used as the name of the rescuer thread if there is one. @@ -197,7 +197,7 @@ resources, scheduled and executed. served by worker threads with elevated nice level. Note that normal and highpri worker-pools don't interact with - each other. Each maintain its separate pool of workers and + each other. Each maintains its separate pool of workers and implements concurrency management among its workers. ``WQ_CPU_INTENSIVE`` @@ -249,8 +249,8 @@ unbound worker-pools and only one work item could be active at any given time thus achieving the same ordering property as ST wq. In the current implementation the above configuration only guarantees -ST behavior within a given NUMA node. Instead alloc_ordered_queue should -be used to achieve system wide ST behavior. +ST behavior within a given NUMA node. Instead ``alloc_ordered_queue()`` should +be used to achieve system-wide ST behavior. Example Execution Scenarios -- GitLab From 80a921e207cea3dd18038501187078669a218dab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 18 Sep 2017 23:00:08 +0300 Subject: [PATCH 0139/1507] ata_piix: Add Fujitsu-Siemens Lifebook S6120 to short cable IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fujitsu-Siemens Lifebook S6120 misdetects the cable type for some drives. The problematic one in this case is an mSATA SSD hooked up via a mSATA->PATA bridge. With regular hard disks the detection seems to work correctly. Strangely an older Lifebook model (S6020) detects the cable as 80c with the mSATA SSD, even if using the exact same flex cable. Cc: Tejun Heo Signed-off-by: Ville Syrjälä Signed-off-by: Tejun Heo --- drivers/ata/ata_piix.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 8401c3b5be921..b702c20fbc2bb 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -492,6 +492,7 @@ static const struct ich_laptop ich_laptop[] = { { 0x27DF, 0x152D, 0x0778 }, /* ICH7 on unknown Intel */ { 0x24CA, 0x1025, 0x0061 }, /* ICH4 on ACER Aspire 2023WLMi */ { 0x24CA, 0x1025, 0x003d }, /* ICH4 on ACER TM290 */ + { 0x24CA, 0x10CF, 0x11AB }, /* ICH4M on Fujitsu-Siemens Lifebook S6120 */ { 0x266F, 0x1025, 0x0066 }, /* ICH6 on ACER Aspire 1694WLMi */ { 0x2653, 0x1043, 0x82D8 }, /* ICH6M on Asus Eee 701 */ { 0x27df, 0x104d, 0x900e }, /* ICH7 on Sony TZ-90 */ -- GitLab From 55e001aabb826c96f09e0a440bdcbce620189dbc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 18 Sep 2017 12:17:36 +0200 Subject: [PATCH 0140/1507] fpga: altera-cvp: remove DRIVER_ATTR() usage It's better to be explicit and use the DRIVER_ATTR_RW() macro when defining a driver's sysfs file. This is part of a series to drop DRIVER_ATTR() from the tree entirely. Cc: linux-fpga@vger.kernel.org Reviewed-by: Moritz Fischer Acked-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/altera-cvp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 08629ee69d112..00e73d28077ce 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -361,12 +361,12 @@ static const struct fpga_manager_ops altera_cvp_ops = { .write_complete = altera_cvp_write_complete, }; -static ssize_t show_chkcfg(struct device_driver *dev, char *buf) +static ssize_t chkcfg_show(struct device_driver *dev, char *buf) { return snprintf(buf, 3, "%d\n", altera_cvp_chkcfg); } -static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, +static ssize_t chkcfg_store(struct device_driver *drv, const char *buf, size_t count) { int ret; @@ -378,7 +378,7 @@ static ssize_t store_chkcfg(struct device_driver *drv, const char *buf, return count; } -static DRIVER_ATTR(chkcfg, 0600, show_chkcfg, store_chkcfg); +static DRIVER_ATTR_RW(chkcfg); static int altera_cvp_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id); -- GitLab From 850fdec8d2fd1eebfa003fea39bec08cd69b6155 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 18 Sep 2017 12:17:57 +0200 Subject: [PATCH 0141/1507] driver core: remove DRIVER_ATTR DRIVER_ATTR is no longer in use, and driver authors should be using DRIVER_ATTR_RW() or DRIVER_ATTR_RO() or DRIVER_ATTR_WO() instead in order to always get the permissions correct. So remove it so that no one can use it anymore. Acked-by: Alan Tull Reviewed-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-model/driver.txt | 7 ++++--- Documentation/filesystems/sysfs.txt | 3 ++- include/linux/device.h | 2 -- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt index 4421135826a2e..d661e6f7e6a0c 100644 --- a/Documentation/driver-model/driver.txt +++ b/Documentation/driver-model/driver.txt @@ -196,12 +196,13 @@ struct driver_attribute { }; Device drivers can export attributes via their sysfs directories. -Drivers can declare attributes using a DRIVER_ATTR macro that works -identically to the DEVICE_ATTR macro. +Drivers can declare attributes using a DRIVER_ATTR_RW and DRIVER_ATTR_RO +macro that works identically to the DEVICE_ATTR_RW and DEVICE_ATTR_RO +macros. Example: -DRIVER_ATTR(debug,0644,show_debug,store_debug); +DRIVER_ATTR_RW(debug); This is equivalent to declaring: diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 24da7b32c489f..9a3658cc399ed 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -366,7 +366,8 @@ struct driver_attribute { Declaring: -DRIVER_ATTR(_name, _mode, _show, _store) +DRIVER_ATTR_RO(_name) +DRIVER_ATTR_RW(_name) Creation/Removal: diff --git a/include/linux/device.h b/include/linux/device.h index c6f27207dbe87..2bc70ddda09b3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -307,8 +307,6 @@ struct driver_attribute { size_t count); }; -#define DRIVER_ATTR(_name, _mode, _show, _store) \ - struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store) #define DRIVER_ATTR_RW(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_RW(_name) #define DRIVER_ATTR_RO(_name) \ -- GitLab From d03d5d530a46c9def981a2a4ec98f6ec2e9b7878 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 8 Jul 2017 20:16:29 +0100 Subject: [PATCH 0142/1507] MAINTAINERS: add Macchiatobin maintainers entry Add a maintainers entry for the Macchiatobin board. Signed-off-by: Russell King Signed-off-by: Gregory CLEMENT --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 2281af4b41b6c..531ba1acae3e9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8253,6 +8253,12 @@ L: libertas-dev@lists.infradead.org S: Orphan F: drivers/net/wireless/marvell/libertas/ +MARVELL MACCHIATOBIN SUPPORT +M: Russell King +L: linux-arm-kernel@lists.infradead.org +S: Maintained +F: arch/arm64/boot/dts/marvell/armada-8040-mcbin.dts + MARVELL MV643XX ETHERNET DRIVER M: Sebastian Hesselbarth L: netdev@vger.kernel.org -- GitLab From 9e7460fc325dad06d2066abdbc1f4dd49456f9a4 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Fri, 15 Sep 2017 10:50:07 +0300 Subject: [PATCH 0143/1507] arm64: dt marvell: Fix AP806 system controller size Extend the container size to 0x2000 to include the gpio controller at offset 0x1040. While at it, add start address notation to the gpio node name to match its 'offset' property. Fixes: 63dac0f4924b ("arm64: dts: marvell: add gpio support for Armada 7K/8K") Cc: Signed-off-by: Baruch Siach Signed-off-by: Gregory CLEMENT --- arch/arm64/boot/dts/marvell/armada-ap806.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index 4d360713ed124..30d48ecf46e08 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -254,7 +254,7 @@ ap_sdhci0: sdhci@6e0000 { ap_syscon: system-controller@6f4000 { compatible = "syscon", "simple-mfd"; - reg = <0x6f4000 0x1000>; + reg = <0x6f4000 0x2000>; ap_clk: clock { compatible = "marvell,ap806-clock"; @@ -265,7 +265,7 @@ ap_pinctrl: pinctrl { compatible = "marvell,ap806-pinctrl"; }; - ap_gpio: gpio { + ap_gpio: gpio@1040 { compatible = "marvell,armada-8k-gpio"; offset = <0x1040>; ngpios = <20>; -- GitLab From bd7a3fe770ebd8391d1c7d072ff88e9e76d063eb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 19 Sep 2017 15:07:17 +0200 Subject: [PATCH 0144/1507] USB: fix out-of-bounds in usb_set_configuration Andrey Konovalov reported a possible out-of-bounds problem for a USB interface association descriptor. He writes: It seems there's no proper size check of a USB_DT_INTERFACE_ASSOCIATION descriptor. It's only checked that the size is >= 2 in usb_parse_configuration(), so find_iad() might do out-of-bounds access to intf_assoc->bInterfaceCount. And he's right, we don't check for crazy descriptors of this type very well, so resolve this problem. Yet another issue found by syzkaller... Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/config.c | 14 +++++++++++--- include/uapi/linux/usb/ch9.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 854c8d66cfbef..68b54bd88d1eb 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -643,15 +643,23 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { + struct usb_interface_assoc_descriptor *d; + + d = (struct usb_interface_assoc_descriptor *)header; + if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { + dev_warn(ddev, + "config %d has an invalid interface association descriptor of length %d, skipping\n", + cfgno, d->bLength); + continue; + } + if (iad_num == USB_MAXIADS) { dev_warn(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { - config->intf_assoc[iad_num] = - (struct usb_interface_assoc_descriptor - *)header; + config->intf_assoc[iad_num] = d; iad_num++; } diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index ce1169af39d72..2a5d63040a0b0 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -780,6 +780,7 @@ struct usb_interface_assoc_descriptor { __u8 iFunction; } __attribute__ ((packed)); +#define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ -- GitLab From aa767cfb75341a6b93742f4d7d1589ac2532c29e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 11 Sep 2017 22:07:50 +0200 Subject: [PATCH 0145/1507] of: provide inline helper for of_find_device_by_node The ipmmu-vmsa driver fails in compile-testing on non-OF platforms: drivers/iommu/ipmmu-vmsa.o: In function `ipmmu_of_xlate': ipmmu-vmsa.c:(.text+0x740): undefined reference to `of_find_device_by_node' It would be reasonable to assume that this interface works but returns failure on non-OF builds, like it does on machines that have been booted in another way, so this adds another inline function helper. Fixes: 7b2d59611fef ("iommu/ipmmu-vmsa: Replace local utlb code with fwspec ids") Signed-off-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/linux/of_platform.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index e0d1946270f38..fb908e5983480 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -57,7 +57,14 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); +#ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); +#else +static inline struct platform_device *of_find_device_by_node(struct device_node *np) +{ + return NULL; +} +#endif /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, -- GitLab From a6899e900509bb2442239d6198dc8bc64f8437ec Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Thu, 14 Sep 2017 23:39:38 +0200 Subject: [PATCH 0146/1507] dt-bindings: fix vendor prefix for Abracon Commit 446810f2dd41 ("of: add vendor prefix for Abracon Corporation") claimed that "abcn" was used as the vendor prefix while in fact "abracon" was used in the subsequent commits. It is also the only prefix used in the tree. Signed-off-by: Alexandre Belloni [robh: fix alphabetical order] Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/vendor-prefixes.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 1ea1fd4232ab2..1afd298eddd73 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -3,8 +3,8 @@ Device tree binding vendor prefix registry. Keep list in alphabetical order. This isn't an exhaustive list, but you should add new prefixes to it before using them to avoid name-space collisions. -abcn Abracon Corporation abilis Abilis Systems +abracon Abracon Corporation actions Actions Semiconductor Co., Ltd. active-semi Active-Semi International Inc ad Avionic Design GmbH -- GitLab From bb4e6ff01ac356f82327d980e45fee8a65491328 Mon Sep 17 00:00:00 2001 From: Nickey Yang Date: Mon, 18 Sep 2017 17:05:37 +0800 Subject: [PATCH 0147/1507] arm64: dts: rockchip: Correct MIPI DPHY PLL clock on rk3399 There is a further gate in between the mipidphy reference clock and the actual ref-clock input to the dsi host, making the clock hirarchy look like clk_24m --> Gate11[14] --> clk_mipidphy_ref --> Gate21[0] --> clk_dphy_pll Fix the clock reference so that the whole clock subtree gets enabled when the dsi host needs it. Signed-off-by: Nickey Yang [amended commit message] Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index d79e9b3265b98..6aa43fd471480 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1629,7 +1629,7 @@ mipi_dsi: mipi@ff960000 { compatible = "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi"; reg = <0x0 0xff960000 0x0 0x8000>; interrupts = ; - clocks = <&cru SCLK_MIPIDPHY_REF>, <&cru PCLK_MIPI_DSI0>, + clocks = <&cru SCLK_DPHY_PLL>, <&cru PCLK_MIPI_DSI0>, <&cru SCLK_DPHY_TX0_CFG>; clock-names = "ref", "pclk", "phy_cfg"; power-domains = <&power RK3399_PD_VIO>; -- GitLab From 4ae7c364b9320063504db78834fabe59d16f85bf Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 28 Aug 2017 15:18:16 +0200 Subject: [PATCH 0148/1507] ARM: dts: nokia n900: drop unneeded/undocumented parts of the dts Sakari mentioned that some parts of the dts are not needed and do not have proper documentation, yet. As the camera works without them, remove them for now. Signed-off-by: Pavel Machek Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/omap3-n900.dts | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 26c20e1167b95..4acd32a1c4ef7 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -144,15 +144,6 @@ battery: n900-battery { io-channel-names = "temp", "bsi", "vbat"; }; - rear_camera: camera@0 { - compatible = "linux,camera"; - - module { - model = "TCM8341MD"; - sensor = <&cam1>; - }; - }; - pwm9: dmtimer-pwm { compatible = "ti,omap-dmtimer-pwm"; #pwm-cells = <3>; @@ -189,10 +180,8 @@ csi_isp: endpoint { clock-lanes = <1>; data-lanes = <0>; lane-polarity = <0 0>; - clock-inv = <0>; /* Select strobe = <1> for back camera, <0> for front camera */ strobe = <1>; - crc = <0>; }; }; }; -- GitLab From 06480f8cf559001c9eb49b4e9d822e13ad1cc5c4 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 6 Sep 2017 16:03:58 +0530 Subject: [PATCH 0149/1507] ARM: OMAP2+: dra7xx: Set OPT_CLKS_IN_RESET flag for gpio1 gpio1 soft reset fails in the kexec path as the optional clock is not enabled hence enable the HWMOD_CONTROL_OPT_CLKS_IN_RESET flag for gpio1 hwmod. Signed-off-by: Keerthy Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_hwmod_7xx_data.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c index f040244c57e73..2f4f7002f38d0 100644 --- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c @@ -839,6 +839,7 @@ static struct omap_hwmod dra7xx_gpio1_hwmod = { .name = "gpio1", .class = &dra7xx_gpio_hwmod_class, .clkdm_name = "wkupaon_clkdm", + .flags = HWMOD_CONTROL_OPT_CLKS_IN_RESET, .main_clk = "wkupaon_iclk_mux", .prcm = { .omap4 = { -- GitLab From 8aed1026ccfe9cf5772c62bde35bc101ead9308c Mon Sep 17 00:00:00 2001 From: Keerthy Date: Wed, 6 Sep 2017 19:09:32 +0530 Subject: [PATCH 0150/1507] ARM: dts: dra7: Set a default parent to mcasp3_ahclkx_mux Assign a default parent to mcasp3_ahclkx_mux clock using the assigned-clock-parents property. This is helpful in cases like kexec where in the clock parent can be something other than the value at reset. Suggested-by: Tero Kristo Signed-off-by: Keerthy Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dra7xx-clocks.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index cf229dfabf617..e62b62875cbad 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -1817,6 +1817,8 @@ mcasp3_ahclkx_mux: mcasp3_ahclkx_mux@1868 { clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>; ti,bit-shift = <24>; reg = <0x1868>; + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&abe_24m_fclk>; }; mcasp3_aux_gfclk_mux: mcasp3_aux_gfclk_mux@1868 { -- GitLab From 20547dfd85f5baaf27ca01b32570bd6bfd7b209c Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Fri, 8 Sep 2017 21:15:51 +0200 Subject: [PATCH 0151/1507] ARM: OMAP2+: hsmmc: fix logic to call either omap_hsmmc_init or omap_hsmmc_late_init but not both MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With 4.13 kernel I get this boot message: [    1.051727] ------------[ cut here ]------------ [    1.051818] WARNING: CPU: 0 PID: 1 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x54/0x74 [    1.051849] sysfs: cannot create duplicate filename '/devices/platform/omap_hsmmc.2' [    1.051879] Modules linked in: [    1.051971] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.13.0-letux+ #1360 [    1.052001] Hardware name: Generic OMAP3 (Flattened Device Tree) [    1.052062] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [    1.052124] [] (show_stack) from [] (dump_stack+0x98/0xd0) [    1.052185] [] (dump_stack) from [] (__warn+0xd0/0x100) [    1.052215] [] (__warn) from [] (warn_slowpath_fmt+0x34/0x44) [    1.052276] [] (warn_slowpath_fmt) from [] (sysfs_warn_dup+0x54/0x74) [    1.052337] [] (sysfs_warn_dup) from [] (sysfs_create_dir_ns+0x74/0x84) [    1.052398] [] (sysfs_create_dir_ns) from [] (kobject_add_internal+0xd0/0x294) [    1.052429] [] (kobject_add_internal) from [] (kobject_add+0x6c/0x8c) [    1.052490] [] (kobject_add) from [] (device_add+0xe4/0x510) [    1.052551] [] (device_add) from [] (platform_device_add+0x130/0x1c0) [    1.052612] [] (platform_device_add) from [] (omap_hsmmc_late_init+0x3c/0x60) [    1.052673] [] (omap_hsmmc_late_init) from [] (omap3_pandora_legacy_init+0x24/0xb4) [    1.052734] [] (omap3_pandora_legacy_init) from [] (pdata_quirks_check+0x30/0x3c) [    1.052795] [] (pdata_quirks_check) from [] (omap_generic_init+0xc/0x18) [    1.052856] [] (omap_generic_init) from [] (customize_machine+0x1c/0x28) [    1.052917] [] (customize_machine) from [] (do_one_initcall+0xa8/0x150) [    1.052947] [] (do_one_initcall) from [] (kernel_init_freeable+0x110/0x1d4) [    1.053009] [] (kernel_init_freeable) from [] (kernel_init+0x8/0x10c) [    1.053070] [] (kernel_init) from [] (ret_from_fork+0x14/0x24) [    1.055023] ---[ end trace 44e490b09ac4ab88 ]--- This can be traced down to the calls of omap_hsmmc_init(pandora_mmc3); omap_hsmmc_late_init(pandora_mmc3); in omap3_pandora_legacy_init(). It turns out that both funcions disagree how to decide if the other one was alredy called. Signed-off-by: H. Nikolaus Schaller Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/hsmmc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c index 5b614388d72f4..6d28aa20a7d32 100644 --- a/arch/arm/mach-omap2/hsmmc.c +++ b/arch/arm/mach-omap2/hsmmc.c @@ -58,10 +58,10 @@ void omap_hsmmc_late_init(struct omap2_hsmmc_info *c) struct platform_device *pdev; int res; - if (omap_hsmmc_done != 1) + if (omap_hsmmc_done) return; - omap_hsmmc_done++; + omap_hsmmc_done = 1; for (; c->mmc; c++) { pdev = c->pdev; -- GitLab From cddfae253c875076750a03bd05ba5b1569e6876e Mon Sep 17 00:00:00 2001 From: Suniel Mahesh Date: Mon, 11 Sep 2017 12:00:16 +0530 Subject: [PATCH 0152/1507] ARM: dts: am33xx: Add spi alias to match SOC schematics Linux bus numbers should match the numbers defined by the chip manufacturer. This patch add's spi aliases to achieve that bus naming convention. Signed-off-by: Suniel Mahesh Signed-off-by: Karthik Tummala Tested-by: Karthik Tummala Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am33xx.dtsi | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 7d7ca054c557b..e58fab8aec5df 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -36,6 +36,8 @@ aliases { phy1 = &usb1_phy; ethernet0 = &cpsw_emac0; ethernet1 = &cpsw_emac1; + spi0 = &spi0; + spi1 = &spi1; }; cpus { -- GitLab From 4afa616ce937f88d9a69a71b8c561551596a81e3 Mon Sep 17 00:00:00 2001 From: Yogesh Siraswar Date: Thu, 14 Sep 2017 14:30:07 -0500 Subject: [PATCH 0153/1507] ARM: dts: am43xx-epos-evm: Remove extra CPSW EMAC entry On am438x EPOS boards there is only one ethernet port, remove extra port definition. This boot log warnings during PHY detection. Signed-off-by: Yogesh Siraswar Signed-off-by: Andrew F. Davis Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am43x-epos-evm.dts | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 9d276af7c539f..081fa68b6f980 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -388,6 +388,7 @@ &mac { pinctrl-0 = <&cpsw_default>; pinctrl-1 = <&cpsw_sleep>; status = "okay"; + slaves = <1>; }; &davinci_mdio { @@ -402,11 +403,6 @@ &cpsw_emac0 { phy-mode = "rmii"; }; -&cpsw_emac1 { - phy_id = <&davinci_mdio>, <1>; - phy-mode = "rmii"; -}; - &phy_sel { rmii-clock-ext; }; -- GitLab From 3fad4cdac235c5b13227d0c09854c689ae62c70b Mon Sep 17 00:00:00 2001 From: zijun_hu Date: Sat, 16 Sep 2017 01:59:41 +0800 Subject: [PATCH 0154/1507] irqchip/gic-v3: Iterate over possible CPUs by for_each_possible_cpu() get_cpu_number() doesn't use existing helper to iterate over possible CPUs, It will cause an error in case of discontinuous @cpu_possible_mask such as 0b11110001, which can result from a core having failed to come up on a SMP machine. Fixed by using existing helper for_each_possible_cpu(). Signed-off-by: zijun_hu Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 519149ec90537..b5df99c6f680f 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1042,7 +1042,7 @@ static int get_cpu_number(struct device_node *dn) { const __be32 *cell; u64 hwid; - int i; + int cpu; cell = of_get_property(dn, "reg", NULL); if (!cell) @@ -1056,9 +1056,9 @@ static int get_cpu_number(struct device_node *dn) if (hwid & ~MPIDR_HWID_BITMASK) return -1; - for (i = 0; i < num_possible_cpus(); i++) - if (cpu_logical_map(i) == hwid) - return i; + for_each_possible_cpu(cpu) + if (cpu_logical_map(cpu) == hwid) + return cpu; return -1; } -- GitLab From 6c09ffd027255d97c536aa4ac51a90973adfedc6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 12 Sep 2017 22:08:23 +0200 Subject: [PATCH 0155/1507] irqchip/gic-v4: Fix building with ancient gcc gcc-4.5 and earlier don't like named initializers for anonymous union members: drivers/irqchip/irq-gic-v4.c: In function 'its_map_vlpi': drivers/irqchip/irq-gic-v4.c:176:3: error: unknown field 'map' specified in initializer drivers/irqchip/irq-gic-v4.c:176:3: error: missing braces around initializer drivers/irqchip/irq-gic-v4.c:176:3: error: (near initialization for 'info.') drivers/irqchip/irq-gic-v4.c: In function 'its_get_vlpi': drivers/irqchip/irq-gic-v4.c:192:3: error: unknown field 'map' specified in initializer drivers/irqchip/irq-gic-v4.c:192:3: error: missing braces around initializer drivers/irqchip/irq-gic-v4.c:192:3: error: (near initialization for 'info.') drivers/irqchip/irq-gic-v4.c: In function 'its_prop_update_vlpi': drivers/irqchip/irq-gic-v4.c:208:3: error: unknown field 'config' specified in initializer drivers/irqchip/irq-gic-v4.c:208:3: error: missing braces around initializer drivers/irqchip/irq-gic-v4.c:208:3: error: (near initialization for 'info.') drivers/irqchip/irq-gic-v4.c:208:3: error: initialization makes pointer from integer without a cast This is fairly easy to work around, by using extra curly braces. Signed-off-by: Arnd Bergmann Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v4.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 2370e6d9e603a..cd0bcc3b7e337 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -173,7 +173,9 @@ int its_map_vlpi(int irq, struct its_vlpi_map *map) { struct its_cmd_info info = { .cmd_type = MAP_VLPI, - .map = map, + { + .map = map, + }, }; /* @@ -189,7 +191,9 @@ int its_get_vlpi(int irq, struct its_vlpi_map *map) { struct its_cmd_info info = { .cmd_type = GET_VLPI, - .map = map, + { + .map = map, + }, }; return irq_set_vcpu_affinity(irq, &info); @@ -205,7 +209,9 @@ int its_prop_update_vlpi(int irq, u8 config, bool inv) { struct its_cmd_info info = { .cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI, - .config = config, + { + .config = config, + }, }; return irq_set_vcpu_affinity(irq, &info); -- GitLab From 90019f8fcd71bf71653690329e32f41489e96122 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 5 Sep 2017 11:28:46 -0700 Subject: [PATCH 0156/1507] irqchip.mips-gic: Fix shared interrupt mask writes The write_gic_smask() & write_gic_rmask() functions take a shared interrupt number as a parameter, but we're incorrectly providing them a bitmask with the shared interrupt's bit set. This effectively means that we mask or unmask the shared interrupt 1< Fixes: 68898c8765f4 ("irqchip: mips-gic: Drop gic_(re)set_mask() functions") Cc: Jason Cooper Cc: Marc Zyngier Cc: Ralf Baechle Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-mips-gic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 6e52a88bbd9e9..40159ac12ac8c 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -169,7 +169,7 @@ static void gic_mask_irq(struct irq_data *d) { unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); - write_gic_rmask(BIT(intr)); + write_gic_rmask(intr); gic_clear_pcpu_masks(intr); } @@ -179,7 +179,7 @@ static void gic_unmask_irq(struct irq_data *d) unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); unsigned int cpu; - write_gic_smask(BIT(intr)); + write_gic_smask(intr); gic_clear_pcpu_masks(intr); cpu = cpumask_first_and(affinity, cpu_online_mask); @@ -767,7 +767,7 @@ static int __init gic_of_init(struct device_node *node, for (i = 0; i < gic_shared_intrs; i++) { change_gic_pol(i, GIC_POL_ACTIVE_HIGH); change_gic_trig(i, GIC_TRIG_LEVEL); - write_gic_rmask(BIT(i)); + write_gic_rmask(i); } for (i = 0; i < gic_vpes; i++) { -- GitLab From e1af344df4e5c8fe90f4a63235a68d5405afc41b Mon Sep 17 00:00:00 2001 From: Meng Xu Date: Tue, 19 Sep 2017 01:21:56 -0400 Subject: [PATCH 0157/1507] ALSA: asihpi: fix a potential double-fetch bug when copying puhm The hm->h.size is intended to hold the actual size of the hm struct that is copied from userspace and should always be <= sizeof(*hm). However, after copy_from_user(hm, puhm, hm->h.size), since userspace process has full control over the memory region pointed by puhm, it is possible that the value of hm->h.size is different from what is fetched-in previously (get_user(hm->h.size, (u16 __user *)puhm)). In other words, hm->h.size is overriden and the relation between hm->h.size and the hm struct is broken. This patch proposes to use a seperate variable, msg_size, to hold the value of the first fetch and override hm->h.size to msg_size after the second fetch to maintain the relation. Signed-off-by: Meng Xu Signed-off-by: Takashi Iwai --- sound/pci/asihpi/hpioctl.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index 7e3aa50b21f9d..5badd08e1d69c 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -103,6 +103,7 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg) void __user *puhr; union hpi_message_buffer_v1 *hm; union hpi_response_buffer_v1 *hr; + u16 msg_size; u16 res_max_size; u32 uncopied_bytes; int err = 0; @@ -127,22 +128,25 @@ long asihpi_hpi_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } /* Now read the message size and data from user space. */ - if (get_user(hm->h.size, (u16 __user *)puhm)) { + if (get_user(msg_size, (u16 __user *)puhm)) { err = -EFAULT; goto out; } - if (hm->h.size > sizeof(*hm)) - hm->h.size = sizeof(*hm); + if (msg_size > sizeof(*hm)) + msg_size = sizeof(*hm); /* printk(KERN_INFO "message size %d\n", hm->h.wSize); */ - uncopied_bytes = copy_from_user(hm, puhm, hm->h.size); + uncopied_bytes = copy_from_user(hm, puhm, msg_size); if (uncopied_bytes) { HPI_DEBUG_LOG(ERROR, "uncopied bytes %d\n", uncopied_bytes); err = -EFAULT; goto out; } + /* Override h.size in case it is changed between two userspace fetches */ + hm->h.size = msg_size; + if (get_user(res_max_size, (u16 __user *)puhr)) { err = -EFAULT; goto out; -- GitLab From fbcab13d2e2511a858590846ac2e2d7cbd830591 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 19 Sep 2017 09:51:28 -0400 Subject: [PATCH 0158/1507] selftests: silence test output by default Some of the networking tests are very noisy and make it impossible to see if we actually passed the tests as they run. Default to suppressing the output from any tests run in order to make it easier to track what failed. Signed-off-by: Josef Bacik Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 693616651da5c..4665463779f5f 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -24,7 +24,7 @@ define RUN_TESTS echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ else \ - cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ + cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\ fi; \ done; endef @@ -55,7 +55,7 @@ endif define EMIT_TESTS @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ BASENAME_TEST=`basename $$TEST`; \ - echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ + echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; endef -- GitLab From 422d8dc6fd3afecd66bd6acfcd73a2d53e338ff3 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 19 Sep 2017 09:51:26 -0400 Subject: [PATCH 0159/1507] selftest: add a reuseaddr test This is to test for a regression introduced by b9470c27607b ("inet: kill smallest_size and smallest_port") which introduced a problem with reuseaddr and bind conflicts. Signed-off-by: Josef Bacik Signed-off-by: Shuah Khan --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 +- .../selftests/net/reuseaddr_conflict.c | 114 ++++++++++++++++++ 3 files changed, 116 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/net/reuseaddr_conflict.c diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 9801253e48021..c612d6e38c628 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -6,3 +6,4 @@ reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack +reuseaddr_conflict diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index de1f5772b878e..3df542c846108 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -7,7 +7,7 @@ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetl TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy +TEST_GEN_FILES += reuseport_dualstack msg_zerocopy reuseaddr_conflict include ../lib.mk diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c new file mode 100644 index 0000000000000..7c5b12664b03b --- /dev/null +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -0,0 +1,114 @@ +/* + * Test for the regression introduced by + * + * b9470c27607b ("inet: kill smallest_size and smallest_port") + * + * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb + * when we open the ipv6 conterpart, which is what was happening previously. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define PORT 9999 + +int open_port(int ipv6, int any) +{ + int fd = -1; + int reuseaddr = 1; + int v6only = 1; + int addrlen; + int ret = -1; + struct sockaddr *addr; + int family = ipv6 ? AF_INET6 : AF_INET; + + struct sockaddr_in6 addr6 = { + .sin6_family = AF_INET6, + .sin6_port = htons(PORT), + .sin6_addr = in6addr_any + }; + struct sockaddr_in addr4 = { + .sin_family = AF_INET, + .sin_port = htons(PORT), + .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"), + }; + + + if (ipv6) { + addr = (struct sockaddr*)&addr6; + addrlen = sizeof(addr6); + } else { + addr = (struct sockaddr*)&addr4; + addrlen = sizeof(addr4); + } + + if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) { + perror("socket"); + goto out; + } + + if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only, + sizeof(v6only)) < 0) { + perror("setsockopt IPV6_V6ONLY"); + goto out; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr, + sizeof(reuseaddr)) < 0) { + perror("setsockopt SO_REUSEADDR"); + goto out; + } + + if (bind(fd, addr, addrlen) < 0) { + perror("bind"); + goto out; + } + + if (any) + return fd; + + if (listen(fd, 1) < 0) { + perror("listen"); + goto out; + } + return fd; +out: + close(fd); + return ret; +} + +int main(void) +{ + int listenfd; + int fd1, fd2; + + fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT); + listenfd = open_port(0, 0); + if (listenfd < 0) + error(1, errno, "Couldn't open listen socket"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + fprintf(stderr, "Opening in6addr_any:%d\n", PORT); + fd1 = open_port(1, 1); + if (fd1 < 0) + error(1, errno, "Couldn't open ipv6 reuseport"); + fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT); + fd2 = open_port(0, 1); + if (fd2 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket"); + close(fd1); + fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT); + fd1 = open_port(0, 1); + if (fd1 >= 0) + error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); + fprintf(stderr, "Success"); + return 0; +} -- GitLab From e06d79fbc338935ef27befc84f8b8b2e5f878a10 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 19 Sep 2017 09:51:27 -0400 Subject: [PATCH 0160/1507] selftests: actually run the various net selftests These self tests are just self contained binaries, they are not run by any of the scripts in the directory. This means they need to be marked with TEST_GEN_PROGS to actually be run, not TEST_GEN_FILES. Signed-off-by: Josef Bacik Signed-off-by: Shuah Khan --- tools/testing/selftests/net/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3df542c846108..d86bca991f456 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,9 +5,9 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket -TEST_GEN_FILES += psock_fanout psock_tpacket -TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy reuseaddr_conflict +TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk -- GitLab From 06e8852ceecccdeff6841a6c5cd78a947a75d5bc Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Fri, 8 Sep 2017 14:01:19 +0200 Subject: [PATCH 0161/1507] selftests/net: msg_zerocopy enable build with older kernel headers Explicitly define SO_EE_ORIGIN_ZEROCOPY. This makes the test program build with older kernel headers, e.g. from Debian 9. Signed-off-by: Thomas Meyer Signed-off-by: Shuah Khan --- tools/testing/selftests/net/msg_zerocopy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 40232af5b023e..3ab6ec4039059 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -55,7 +55,7 @@ #include #ifndef SO_EE_ORIGIN_ZEROCOPY -#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#define SO_EE_ORIGIN_ZEROCOPY 5 #endif #ifndef SO_ZEROCOPY -- GitLab From 17df6453d4be17910456e99c5a85025aa1b7a246 Mon Sep 17 00:00:00 2001 From: Arend Van Spriel Date: Tue, 12 Sep 2017 10:47:53 +0200 Subject: [PATCH 0162/1507] brcmfmac: add length check in brcmf_cfg80211_escan_handler() Upon handling the firmware notification for scans the length was checked properly and may result in corrupting kernel heap memory due to buffer overruns. This fix addresses CVE-2017-0786. Cc: stable@vger.kernel.org # v4.0.x Cc: Kevin Cernekee Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index aaed4ab503ad1..26a0de371c266 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -3162,6 +3162,7 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, struct brcmf_cfg80211_info *cfg = ifp->drvr->config; s32 status; struct brcmf_escan_result_le *escan_result_le; + u32 escan_buflen; struct brcmf_bss_info_le *bss_info_le; struct brcmf_bss_info_le *bss = NULL; u32 bi_length; @@ -3181,11 +3182,23 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, if (status == BRCMF_E_STATUS_PARTIAL) { brcmf_dbg(SCAN, "ESCAN Partial result\n"); + if (e->datalen < sizeof(*escan_result_le)) { + brcmf_err("invalid event data length\n"); + goto exit; + } escan_result_le = (struct brcmf_escan_result_le *) data; if (!escan_result_le) { brcmf_err("Invalid escan result (NULL pointer)\n"); goto exit; } + escan_buflen = le32_to_cpu(escan_result_le->buflen); + if (escan_buflen > BRCMF_ESCAN_BUF_SIZE || + escan_buflen > e->datalen || + escan_buflen < sizeof(*escan_result_le)) { + brcmf_err("Invalid escan buffer length: %d\n", + escan_buflen); + goto exit; + } if (le16_to_cpu(escan_result_le->bss_count) != 1) { brcmf_err("Invalid bss_count %d: ignoring\n", escan_result_le->bss_count); @@ -3202,9 +3215,8 @@ brcmf_cfg80211_escan_handler(struct brcmf_if *ifp, } bi_length = le32_to_cpu(bss_info_le->length); - if (bi_length != (le32_to_cpu(escan_result_le->buflen) - - WL_ESCAN_RESULTS_FIXED_SIZE)) { - brcmf_err("Invalid bss_info length %d: ignoring\n", + if (bi_length != escan_buflen - WL_ESCAN_RESULTS_FIXED_SIZE) { + brcmf_err("Ignoring invalid bss_info length: %d\n", bi_length); goto exit; } -- GitLab From 35f62727df0ed8e5e4857e162d94fd46d861f1cf Mon Sep 17 00:00:00 2001 From: Arend Van Spriel Date: Tue, 12 Sep 2017 10:47:54 +0200 Subject: [PATCH 0163/1507] brcmfmac: setup passive scan if requested by user-space The driver was not properly configuring firmware with regard to the type of scan. It always performed an active scan even when user-space was requesting for passive scan, ie. the scan request was done without any SSIDs specified. Cc: stable@vger.kernel.org # v4.0.x Reported-by: Huang, Jiangyang Reviewed-by: Hante Meuleman Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- .../broadcom/brcm80211/brcmfmac/cfg80211.c | 19 ++++--------------- .../broadcom/brcm80211/brcmfmac/fwil_types.h | 5 +++++ 2 files changed, 9 insertions(+), 15 deletions(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 26a0de371c266..4157c90ad9736 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -980,7 +980,7 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, eth_broadcast_addr(params_le->bssid); params_le->bss_type = DOT11_BSSTYPE_ANY; - params_le->scan_type = 0; + params_le->scan_type = BRCMF_SCANTYPE_ACTIVE; params_le->channel_num = 0; params_le->nprobes = cpu_to_le32(-1); params_le->active_time = cpu_to_le32(-1); @@ -988,12 +988,9 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, params_le->home_time = cpu_to_le32(-1); memset(¶ms_le->ssid_le, 0, sizeof(params_le->ssid_le)); - /* if request is null exit so it will be all channel broadcast scan */ - if (!request) - return; - n_ssids = request->n_ssids; n_channels = request->n_channels; + /* Copy channel array if applicable */ brcmf_dbg(SCAN, "### List of channelspecs to scan ### %d\n", n_channels); @@ -1030,16 +1027,8 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg, ptr += sizeof(ssid_le); } } else { - brcmf_dbg(SCAN, "Broadcast scan %p\n", request->ssids); - if ((request->ssids) && request->ssids->ssid_len) { - brcmf_dbg(SCAN, "SSID %s len=%d\n", - params_le->ssid_le.SSID, - request->ssids->ssid_len); - params_le->ssid_le.SSID_len = - cpu_to_le32(request->ssids->ssid_len); - memcpy(¶ms_le->ssid_le.SSID, request->ssids->ssid, - request->ssids->ssid_len); - } + brcmf_dbg(SCAN, "Performing passive scan\n"); + params_le->scan_type = BRCMF_SCANTYPE_PASSIVE; } /* Adding mask to channel numbers */ params_le->channel_num = diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h index 8391989b18829..e0d22fedb2b45 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h @@ -45,6 +45,11 @@ #define BRCMF_SCAN_PARAMS_COUNT_MASK 0x0000ffff #define BRCMF_SCAN_PARAMS_NSSID_SHIFT 16 +/* scan type definitions */ +#define BRCMF_SCANTYPE_DEFAULT 0xFF +#define BRCMF_SCANTYPE_ACTIVE 0 +#define BRCMF_SCANTYPE_PASSIVE 1 + #define BRCMF_WSEC_MAX_PSK_LEN 32 #define BRCMF_WSEC_PASSPHRASE BIT(0) -- GitLab From ce21574ad1922b403198ee664c4dff276f514f1d Mon Sep 17 00:00:00 2001 From: Sekhar Nori Date: Tue, 29 Aug 2017 13:52:51 +0530 Subject: [PATCH 0164/1507] ARM: dts: da850-evm: add serial and ethernet aliases Add aliases for serial and ethernet nodes. Serial aliases help keep order of tty nodes fixed and ethernet alias is used by bootloader to setup mac address correctly. Reported-by: Adam Ford Acked-by: Tony Lindgren Fixes: dd7deaf218bf ("ARM: davinci: da850: add DT node for ethernet") Signed-off-by: Sekhar Nori --- arch/arm/boot/dts/da850-evm.dts | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 67e72bc72e805..c75507922f7d7 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -15,6 +15,13 @@ / { compatible = "ti,da850-evm", "ti,da850"; model = "DA850/AM1808/OMAP-L138 EVM"; + aliases { + serial0 = &serial0; + serial1 = &serial1; + serial2 = &serial2; + ethernet0 = ð0; + }; + soc@1c00000 { pmx_core: pinmux@14120 { status = "okay"; -- GitLab From 5a5d718f952b55e7fa96bfaf6f31f2c08babd77b Mon Sep 17 00:00:00 2001 From: Sriram Periyasamy Date: Tue, 19 Sep 2017 17:25:05 -0500 Subject: [PATCH 0165/1507] ALSA: hda - program ICT bits to support HBR audio On recent Intel platforms (Haswell, Broadwell, Skylake, ApolloLake, KabyLake, ...), the IEC Coding Type (ICT) bitfield in the Digital Converter Control #3 needs to be set explicitly for HDMI/DisplayPort High Bit Rate (HBR) audio playback to work. This was not required in earlier platforms when HBR was first introduced. The ICT bits are defined in Section 7.3.3.9 of the HDaudio 1.0a specification. Since the ICT bitfield was not specified for HDAudio 1.0 devices (before 2009), we only program it on machines more recent than Haswell. We tested that this fix is not needed on Baytrail-I (MinnowBoard Turbot) and believe by extension it also does not apply to Braswell. [ Moved AC_VERB_SET_DIGI_CONVERT_3 definition to the right place by tiwai ] Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98797 Signed-off-by: Sriram Periyasamy Signed-off-by: Pierre-Louis Bossart Signed-off-by: Subhransu S. Prusty Acked-by: Vinod Koul Signed-off-by: Takashi Iwai --- include/sound/hda_verbs.h | 1 + sound/pci/hda/patch_hdmi.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/include/sound/hda_verbs.h b/include/sound/hda_verbs.h index d0509db6d0ec5..f89cd5ee1c7aa 100644 --- a/include/sound/hda_verbs.h +++ b/include/sound/hda_verbs.h @@ -95,6 +95,7 @@ enum { #define AC_VERB_SET_EAPD_BTLENABLE 0x70c #define AC_VERB_SET_DIGI_CONVERT_1 0x70d #define AC_VERB_SET_DIGI_CONVERT_2 0x70e +#define AC_VERB_SET_DIGI_CONVERT_3 0x73e #define AC_VERB_SET_VOLUME_KNOB_CONTROL 0x70f #define AC_VERB_SET_GPIO_DATA 0x715 #define AC_VERB_SET_GPIO_MASK 0x716 diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 2b64fabd5faa5..c19c81d230bd7 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -906,6 +906,7 @@ static int hdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, hda_nid_t pin_nid, u32 stream_tag, int format) { struct hdmi_spec *spec = codec->spec; + unsigned int param; int err; err = spec->ops.pin_hbr_setup(codec, pin_nid, is_hbr_format(format)); @@ -915,6 +916,26 @@ static int hdmi_setup_stream(struct hda_codec *codec, hda_nid_t cvt_nid, return err; } + if (is_haswell_plus(codec)) { + + /* + * on recent platforms IEC Coding Type is required for HBR + * support, read current Digital Converter settings and set + * ICT bitfield if needed. + */ + param = snd_hda_codec_read(codec, cvt_nid, 0, + AC_VERB_GET_DIGI_CONVERT_1, 0); + + param = (param >> 16) & ~(AC_DIG3_ICT); + + /* on recent platforms ICT mode is required for HBR support */ + if (is_hbr_format(format)) + param |= 0x1; + + snd_hda_codec_write(codec, cvt_nid, 0, + AC_VERB_SET_DIGI_CONVERT_3, param); + } + snd_hda_codec_setup_stream(codec, cvt_nid, stream_tag, 0, format); return 0; } -- GitLab From 97e133d54c1ca8948b191e5721a145a76c4db33d Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Tue, 19 Sep 2017 11:46:16 +0300 Subject: [PATCH 0166/1507] usb: gadget: core: fix ->udc_set_speed() logic Consider the following case: udc controller supports SuperSpeed. If we first load a HighSpeed gadget followed by a SuperSpeed gadget, the SuperSpeed gadget will be limited to HighSpeed as UDC core driver doesn't call ->udc_set_speed() in the second case. Call ->udc_set_speed() unconditionally to fix this issue. This will also fix the case for dwc3 controller driver when SuperSpeed gadget is loaded first and works in HighSpeed only as udc_set_speed() was never being called. Fixes: 6099eca796ae ("usb: gadget: core: introduce ->udc_set_speed() method") Cc: [v4.13+] Signed-off-by: Roger Quadros Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 75c51ca4ee0f3..d41d07aae0cec 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1320,8 +1320,7 @@ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *dri udc->dev.driver = &driver->driver; udc->gadget->dev.driver = &driver->driver; - if (driver->max_speed < udc->gadget->max_speed) - usb_gadget_udc_set_speed(udc, driver->max_speed); + usb_gadget_udc_set_speed(udc, driver->max_speed); ret = driver->bind(udc->gadget, driver); if (ret) -- GitLab From 9ada8c582088d32bd5c071c17213bc6edf37443a Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 13 Sep 2017 15:31:33 +0900 Subject: [PATCH 0167/1507] usb: gadget: function: printer: avoid spinlock recursion If usb_gadget_giveback_request() is called in usb_ep_queue(), this printer_write() is possible to cause spinlock recursion. So, this patch adds spin_unlock() before calls usb_ep_queue() to avoid it. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_printer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 8df244fc9d80d..ea0da35a44e2e 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -555,6 +555,7 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) size_t size; /* Amount of data in a TX request. */ size_t bytes_copied = 0; struct usb_request *req; + int value; DBG(dev, "printer_write trying to send %d bytes\n", (int)len); @@ -634,7 +635,11 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) return -EAGAIN; } - if (usb_ep_queue(dev->in_ep, req, GFP_ATOMIC)) { + /* here, we unlock, and only unlock, to avoid deadlock. */ + spin_unlock(&dev->lock); + value = usb_ep_queue(dev->in_ep, req, GFP_ATOMIC); + spin_lock(&dev->lock); + if (value) { list_add(&req->list, &dev->tx_reqs); spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->lock_printer_io); -- GitLab From 641663a19f6002ecc5c5af517a5184d4164cc749 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 11 Sep 2017 09:24:15 -0700 Subject: [PATCH 0168/1507] usb: gadget: udc: fix snps_udc_plat.c build errors Fix build errors that happen when CONFIG_EXTCON=m and CONFIG_USB_SNP_UDC_PLAT=y by preventing that combination in Kconfig. CONFIG_EXTCON can still be disabled or enabled for this driver since has stubs for the disabled case, but if CONFIG_EXTCON=m, USB_SNP_UDC_PLAT is restricted to m or n (cannot be builtin). drivers/built-in.o: In function `udc_plat_remove': snps_udc_plat.c:(.text+0x2c4060): undefined reference to `extcon_unregister_notifier' drivers/built-in.o: In function `udc_plat_probe': snps_udc_plat.c:(.text+0x2c438c): undefined reference to `extcon_get_edev_by_phandle' snps_udc_plat.c:(.text+0x2c43f2): undefined reference to `extcon_register_notifier' snps_udc_plat.c:(.text+0x2c4416): undefined reference to `extcon_get_state' snps_udc_plat.c:(.text+0x2c44f7): undefined reference to `extcon_unregister_notifier' Reported-by: kbuild test robot Signed-off-by: Randy Dunlap Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig index 7cd5c969fcbe9..1e9567091d860 100644 --- a/drivers/usb/gadget/udc/Kconfig +++ b/drivers/usb/gadget/udc/Kconfig @@ -273,6 +273,7 @@ config USB_SNP_CORE config USB_SNP_UDC_PLAT tristate "Synopsys USB 2.0 Device controller" depends on USB_GADGET && OF && HAS_DMA + depends on EXTCON || EXTCON=n select USB_GADGET_DUALSPEED select USB_SNP_CORE default ARCH_BCM_IPROC -- GitLab From 7661ca09b2ff98f48693f431bb01fed62830e433 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 7 Sep 2017 16:14:31 +0200 Subject: [PATCH 0169/1507] usb: gadget: dummy: fix nonsensical comparisons gcc-8 points out two comparisons that are clearly bogus and almost certainly not what the author intended to write: drivers/usb/gadget/udc/dummy_hcd.c: In function 'set_link_state_by_speed': drivers/usb/gadget/udc/dummy_hcd.c:379:31: error: bitwise comparison always evaluates to false [-Werror=tautological-compare] USB_PORT_STAT_ENABLE) == 1 && ^~ drivers/usb/gadget/udc/dummy_hcd.c:381:25: error: bitwise comparison always evaluates to false [-Werror=tautological-compare] USB_SS_PORT_LS_U0) == 1 && ^~ I looked at the code for a bit and came up with a change that makes it look like what the author probably meant here. This makes it look reasonable to me and to gcc, shutting up the warning. It does of course change behavior as the two conditions are actually evaluated rather than being hardcoded to false, and I have made no attempt at verifying that the changed logic makes sense in the context of a USB HCD, so that part needs to be reviewed carefully. Fixes: 1cd8fd2887e1 ("usb: gadget: dummy_hcd: add SuperSpeed support") Cc: Tatyana Brokhman Cc: Felipe Balbi Acked-by: Alan Stern Signed-off-by: Arnd Bergmann Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/dummy_hcd.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index a030d7923d7db..b1e21b3be6e11 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -375,11 +375,10 @@ static void set_link_state_by_speed(struct dummy_hcd *dum_hcd) USB_PORT_STAT_CONNECTION) == 0) dum_hcd->port_status |= (USB_PORT_STAT_C_CONNECTION << 16); - if ((dum_hcd->port_status & - USB_PORT_STAT_ENABLE) == 1 && - (dum_hcd->port_status & - USB_SS_PORT_LS_U0) == 1 && - dum_hcd->rh_state != DUMMY_RH_SUSPENDED) + if ((dum_hcd->port_status & USB_PORT_STAT_ENABLE) && + (dum_hcd->port_status & + USB_PORT_STAT_LINK_STATE) == USB_SS_PORT_LS_U0 && + dum_hcd->rh_state != DUMMY_RH_SUSPENDED) dum_hcd->active = 1; } } else { -- GitLab From 20da2ec06bfad2d4dfd40d77d3831f5e56365d20 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Mon, 18 Sep 2017 15:29:49 +0300 Subject: [PATCH 0170/1507] qtnfmac: lock access to h/w in tx path Fix tx path regression. Lock should be held when queuing packets to h/w fifos in order to properly handle configurations with multiple enabled interfaces. Signed-off-by: Sergey Matyukevich Signed-off-by: Kalle Valo --- drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c | 9 ++++++++- .../net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c index 502e72b7cdcc1..69131965a298f 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie.c @@ -661,14 +661,18 @@ static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb) struct qtnf_pcie_bus_priv *priv = (void *)get_bus_priv(bus); dma_addr_t txbd_paddr, skb_paddr; struct qtnf_tx_bd *txbd; + unsigned long flags; int len, i; u32 info; int ret = 0; + spin_lock_irqsave(&priv->tx0_lock, flags); + if (!qtnf_tx_queue_ready(priv)) { if (skb->dev) netif_stop_queue(skb->dev); + spin_unlock_irqrestore(&priv->tx0_lock, flags); return NETDEV_TX_BUSY; } @@ -717,8 +721,10 @@ static int qtnf_pcie_data_tx(struct qtnf_bus *bus, struct sk_buff *skb) dev_kfree_skb_any(skb); } - qtnf_pcie_data_tx_reclaim(priv); priv->tx_done_count++; + spin_unlock_irqrestore(&priv->tx0_lock, flags); + + qtnf_pcie_data_tx_reclaim(priv); return NETDEV_TX_OK; } @@ -1247,6 +1253,7 @@ static int qtnf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) strcpy(bus->fwname, QTN_PCI_PEARL_FW_NAME); init_completion(&bus->request_firmware_complete); mutex_init(&bus->bus_lock); + spin_lock_init(&pcie_priv->tx0_lock); spin_lock_init(&pcie_priv->irq_lock); spin_lock_init(&pcie_priv->tx_reclaim_lock); diff --git a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h index e76a23716ee01..86ac1ccedb52f 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h +++ b/drivers/net/wireless/quantenna/qtnfmac/pearl/pcie_bus_priv.h @@ -34,6 +34,8 @@ struct qtnf_pcie_bus_priv { /* lock for tx reclaim operations */ spinlock_t tx_reclaim_lock; + /* lock for tx0 operations */ + spinlock_t tx0_lock; u8 msi_enabled; int mps; -- GitLab From a715b3a0efe76d36c3ef96a93894a13db9d3a72f Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Mon, 18 Sep 2017 15:29:50 +0300 Subject: [PATCH 0171/1507] qtnfmac: cancel scans on wireless interface changes Cancel active scans and deactivate firmware scan watchdog timer when wireless interface configuration is changed. The usecases include wireless interface mode change, interface down, AP stop, virtual interface removal. Signed-off-by: Sergey Matyukevich Signed-off-by: Kalle Valo --- drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 9 ++++++--- drivers/net/wireless/quantenna/qtnfmac/cfg80211.h | 3 +++ drivers/net/wireless/quantenna/qtnfmac/event.c | 2 -- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 856fa6e8327ed..a450bc6bc7745 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -115,6 +115,8 @@ int qtnf_del_virtual_intf(struct wiphy *wiphy, struct wireless_dev *wdev) vif = qtnf_netdev_get_priv(wdev->netdev); + qtnf_scan_done(vif->mac, true); + if (qtnf_cmd_send_del_intf(vif)) pr_err("VIF%u.%u: failed to delete VIF\n", vif->mac->macid, vif->vifid); @@ -335,6 +337,8 @@ static int qtnf_stop_ap(struct wiphy *wiphy, struct net_device *dev) struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); int ret; + qtnf_scan_done(vif->mac, true); + ret = qtnf_cmd_send_stop_ap(vif); if (ret) { pr_err("VIF%u.%u: failed to stop AP operation in FW\n", @@ -570,8 +574,6 @@ qtnf_del_station(struct wiphy *wiphy, struct net_device *dev, !qtnf_sta_list_lookup(&vif->sta_list, params->mac)) return 0; - qtnf_scan_done(vif->mac, true); - ret = qtnf_cmd_send_del_sta(vif, params); if (ret) pr_err("VIF%u.%u: failed to delete STA %pM\n", @@ -1134,8 +1136,9 @@ void qtnf_virtual_intf_cleanup(struct net_device *ndev) } vif->sta_state = QTNF_STA_DISCONNECTED; - qtnf_scan_done(mac, true); } + + qtnf_scan_done(mac, true); } void qtnf_cfg80211_vif_reset(struct qtnf_vif *vif) diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h index 6a4af52522b8d..66db26613b1fb 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h @@ -34,6 +34,9 @@ static inline void qtnf_scan_done(struct qtnf_wmac *mac, bool aborted) .aborted = aborted, }; + if (timer_pending(&mac->scan_timeout)) + del_timer_sync(&mac->scan_timeout); + mutex_lock(&mac->mac_lock); if (mac->scan_req) { diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index 0fc2814eafad2..43d2e7fd6e021 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -345,8 +345,6 @@ qtnf_event_handle_scan_complete(struct qtnf_wmac *mac, return -EINVAL; } - if (timer_pending(&mac->scan_timeout)) - del_timer_sync(&mac->scan_timeout); qtnf_scan_done(mac, le32_to_cpu(status->flags) & QLINK_SCAN_ABORTED); return 0; -- GitLab From 35f3c984548524be5eb4c3f5295cf58d909e8746 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Mon, 18 Sep 2017 17:18:44 -0700 Subject: [PATCH 0172/1507] scripts/dtc: dtx_diff - 2nd update of include dts paths to match build Update dtx_diff include paths in the same manner as: commit b12869a8d519 ("of: remove drivers/of/testcase-data from include search path for CPP"), commit 5ffa2aed389c ("of: remove arch/$(SRCARCH)/boot/dts from include search path for CPP"), and commit 50f9ddaf64e1 ("of: search scripts/dtc/include-prefixes path for both CPP and DTC"). Remove proposed include path kernel/dts/, which was never implemented for the dtb build. For the diff case, each source file is compiled separately. For each of those compiles, provide the location of the source file as an include path, not the location of both source files. Signed-off-by: Frank Rowand Signed-off-by: Rob Herring --- scripts/dtc/dtx_diff | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/scripts/dtc/dtx_diff b/scripts/dtc/dtx_diff index f9a3d8d23c644..8c4fbad2055e5 100755 --- a/scripts/dtc/dtx_diff +++ b/scripts/dtc/dtx_diff @@ -86,6 +86,7 @@ eod compile_to_dts() { dtx="$1" + dtc_include="$2" if [ -d "${dtx}" ] ; then @@ -113,7 +114,7 @@ compile_to_dts() { # ----- input is DTS (source) if ( cpp ${cpp_flags} -x assembler-with-cpp ${dtx} \ - | ${DTC} -I dts ) ; then + | ${DTC} ${dtc_include} -I dts ) ; then return fi @@ -320,18 +321,13 @@ fi cpp_flags="\ -nostdinc \ - -I${srctree}/arch/${ARCH}/boot/dts \ -I${srctree}/scripts/dtc/include-prefixes \ - -I${srctree}/drivers/of/testcase-data \ -undef -D__DTS__" -dtc_flags="\ - -i ${srctree}/arch/${ARCH}/boot/dts/ \ - -i ${srctree}/kernel/dts \ - ${dtx_path_1_dtc_include} \ - ${dtx_path_2_dtc_include}" - -DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -" +DTC="\ + ${DTC} \ + -i ${srctree}/scripts/dtc/include-prefixes \ + -O dts -qq -f ${dtc_sort} -o -" # ----- do the diff or decompile @@ -339,11 +335,11 @@ DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -" if (( ${cmd_diff} )) ; then diff ${diff_flags} --label "${dtx_file_1}" --label "${dtx_file_2}" \ - <(compile_to_dts "${dtx_file_1}") \ - <(compile_to_dts "${dtx_file_2}") + <(compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}") \ + <(compile_to_dts "${dtx_file_2}" "${dtx_path_2_dtc_include}") else - compile_to_dts "${dtx_file_1}" + compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}" fi -- GitLab From 0dcd020b7abbff238f188d4db8f02389dc849553 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 20 Sep 2017 09:21:40 +0800 Subject: [PATCH 0173/1507] ALSA: usb-audio: Add sample rate quirk for Plantronics C310/C520-M Like other Plantronics devices, C310 and C520-M do not support sample rate reading. Add them to the sample rate quirk accordingly. BugLink: https://bugs.launchpad.net/bugs/1708499 BugLink: https://bugs.launchpad.net/bugs/1709282 Signed-off-by: Kai-Heng Feng Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 9135520782854..b8cb57aeec77f 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1137,6 +1137,8 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0x02F7): /* Plantronics BT-600 */ case USB_ID(0x047F, 0x0415): /* Plantronics BT-300 */ case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ + case USB_ID(0x047F, 0xC022): /* Plantronics C310 */ + case USB_ID(0x047F, 0xC036): /* Plantronics C520-M */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ -- GitLab From b22666febf6fc67776d49782057fe4dd06f41552 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 20 Sep 2017 18:10:17 -0400 Subject: [PATCH 0174/1507] drm/amdkfd: Fix incorrect destroy_mqd parameter When uninitializing a kernel queue. Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 0649dd43e7806..a4ca1133482ce 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -184,7 +184,7 @@ static void uninitialize(struct kernel_queue *kq) if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ) kq->mqd->destroy_mqd(kq->mqd, kq->queue->mqd, - false, + KFD_PREEMPT_TYPE_WAVEFRONT_RESET, QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS, kq->queue->pipe, kq->queue->queue); -- GitLab From cb1d9967461cdf3b6aac6317c8d954a14f842571 Mon Sep 17 00:00:00 2001 From: Yong Zhao Date: Wed, 20 Sep 2017 18:10:21 -0400 Subject: [PATCH 0175/1507] drm/amdkfd: Fix kernel-queue wrapping bugs Avoid intermediate negative numbers when doing calculations with a mix of signed and unsigned variables where implicit conversions can lead to unexpected results. When kernel queue buffer wraps around to 0, we need to check that rptr won't be overwritten by the new packet. Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index a4ca1133482ce..ed71ad40e8f79 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -210,6 +210,11 @@ static int acquire_packet_buffer(struct kernel_queue *kq, uint32_t wptr, rptr; unsigned int *queue_address; + /* When rptr == wptr, the buffer is empty. + * When rptr == wptr + 1, the buffer is full. + * It is always rptr that advances to the position of wptr, rather than + * the opposite. So we can only use up to queue_size_dwords - 1 dwords. + */ rptr = *kq->rptr_kernel; wptr = *kq->wptr_kernel; queue_address = (unsigned int *)kq->pq_kernel_addr; @@ -219,11 +224,10 @@ static int acquire_packet_buffer(struct kernel_queue *kq, pr_debug("wptr: %d\n", wptr); pr_debug("queue_address 0x%p\n", queue_address); - available_size = (rptr - 1 - wptr + queue_size_dwords) % + available_size = (rptr + queue_size_dwords - 1 - wptr) % queue_size_dwords; - if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) { + if (packet_size_in_dwords > available_size) { /* * make sure calling functions know * acquire_packet_buffer() failed @@ -233,6 +237,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, } if (wptr + packet_size_in_dwords >= queue_size_dwords) { + /* make sure after rolling back to position 0, there is + * still enough space. + */ + if (packet_size_in_dwords >= rptr) { + *buffer_ptr = NULL; + return -ENOMEM; + } + /* fill nops, roll back and start at position 0 */ while (wptr > 0) { queue_address[wptr] = kq->nop_packet; wptr = (wptr + 1) % queue_size_dwords; -- GitLab From c986169fdec992c464c84d0a3abdbfc846ed3df9 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Wed, 20 Sep 2017 18:10:22 -0400 Subject: [PATCH 0176/1507] drm/amdkfd: Print event limit messages only once per process To avoid spamming the log. Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_events.c | 5 ++++- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 5979158c3f7b9..944abfad39c1f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -292,7 +292,10 @@ static int create_signal_event(struct file *devkfd, struct kfd_event *ev) { if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) { - pr_warn("Signal event wasn't created because limit was reached\n"); + if (!p->signal_event_limit_reached) { + pr_warn("Signal event wasn't created because limit was reached\n"); + p->signal_event_limit_reached = true; + } return -ENOMEM; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index b397ec726400c..b87e96cee5fac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -521,6 +521,7 @@ struct kfd_process { struct list_head signal_event_pages; u32 next_nonsignal_event_id; size_t signal_event_count; + bool signal_event_limit_reached; }; /** -- GitLab From 79af1f866193de29e65a4dba7d0dab14b0c0ff93 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 22 Jun 2017 12:20:29 +0200 Subject: [PATCH 0177/1507] mac80211: avoid allocating TXQs that won't be used For AP_VLAN and monitor interfaces we'll never use the TXQs we allocated, so avoid doing so. Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f75029abf7286..2619daa299613 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1772,7 +1772,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sizeof(void *)); int txq_size = 0; - if (local->ops->wake_tx_queue) + if (local->ops->wake_tx_queue && + type != NL80211_IFTYPE_AP_VLAN && + type != NL80211_IFTYPE_MONITOR) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; -- GitLab From 2512b1b18d0748d867bb22387db7c86b903291ad Mon Sep 17 00:00:00 2001 From: Liad Kaufman Date: Sat, 5 Aug 2017 11:44:31 +0300 Subject: [PATCH 0178/1507] mac80211: extend ieee80211_ie_split to support EXTENSION Current ieee80211_ie_split() implementation doesn't account for elements that are sub-elements of the EXTENSION IE. To extend support to these IEs as well, treat the WLAN_EID_EXTENSION ids in the %ids array as indicating that the next id in the array is a sub-element of the EXTENSION IE. Signed-off-by: Liad Kaufman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 6 +++-- net/wireless/util.c | 54 +++++++++++++++++++++++++++++++++++------- 2 files changed, 50 insertions(+), 10 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f12fa5245a453..aa9d993e519a6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5934,7 +5934,8 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before - * the split + * the split. A WLAN_EID_EXTENSION value means that the next + * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @after_ric: array IE types that come after the RIC element * @n_after_ric: size of the @after_ric array @@ -5965,7 +5966,8 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before - * the split + * the split. A WLAN_EID_EXTENSION value means that the next + * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @offset: offset where to start splitting in the buffer * diff --git a/net/wireless/util.c b/net/wireless/util.c index bcb1284c3415f..4aab793c2f006 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1367,13 +1367,29 @@ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, } EXPORT_SYMBOL(cfg80211_get_p2p_attr); -static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id) +static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; - for (i = 0; i < n_ids; i++) - if (ids[i] == id) + /* Make sure array values are legal */ + if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) + return false; + + i = 0; + while (i < n_ids) { + if (ids[i] == WLAN_EID_EXTENSION) { + if (id_ext && (ids[i + 1] == id)) + return true; + + i += 2; + continue; + } + + if (ids[i] == id && !id_ext) return true; + + i++; + } return false; } @@ -1403,14 +1419,36 @@ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, { size_t pos = offset; - while (pos < ielen && ieee80211_id_in_list(ids, n_ids, ies[pos])) { + while (pos < ielen) { + u8 ext = 0; + + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], + ies[pos] == WLAN_EID_EXTENSION)) + break; + if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); - while (pos < ielen && - !ieee80211_id_in_list(after_ric, n_after_ric, - ies[pos])) - pos = skip_ie(ies, ielen, pos); + while (pos < ielen) { + if (ies[pos] == WLAN_EID_EXTENSION) + ext = 2; + else + ext = 0; + + if ((pos + ext) >= ielen) + break; + + if (!ieee80211_id_in_list(after_ric, + n_after_ric, + ies[pos + ext], + ext == 2)) + pos = skip_ie(ies, ielen, pos); + } } else { pos = skip_ie(ies, ielen, pos); } -- GitLab From a7f26d8050c4f172d2dc523aabf45c5cbd9558ac Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 5 Aug 2017 11:44:32 +0300 Subject: [PATCH 0179/1507] mac80211: simplify and clarify IE splitting There's no need to split off IEs from the ones obtained from userspace, if they were already split off, so for example IEs that went before HT don't have to be listed again to go before VHT. Simplify the code here so it's clearer. While at it, also clarify the comments regarding the DMG (60 GHz) elements. Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 19 +++++++------------ net/mac80211/util.c | 21 +++++++++------------ 2 files changed, 16 insertions(+), 24 deletions(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3b8e2709d8dea..ee5ca1bc5a20f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -780,11 +780,12 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_HT_CAPABILITY, WLAN_EID_BSS_COEX_2040, + /* luckily this is almost always there */ WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, - /* 60GHz doesn't happen right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ WLAN_EID_VHT_CAPABILITY, WLAN_EID_OPMODE_NOTIF, }; @@ -811,22 +812,16 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* if present, add any custom IEs that go before VHT */ if (assoc_data->ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_PWR_CAPABILITY, - WLAN_EID_SUPPORTED_CHANNELS, - WLAN_EID_RSN, - WLAN_EID_QOS_CAPA, - WLAN_EID_RRM_ENABLED_CAPABILITIES, - WLAN_EID_MOBILITY_DOMAIN, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off before HT + * or generated here + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_QOS_TRAFFIC_CAPA, WLAN_EID_TIM_BCAST_REQ, WLAN_EID_INTERWORKING, + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; /* RIC already taken above, so no need to handle here anymore */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 6aef6793d0523..bfecc3e863189 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1392,10 +1392,10 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before HT */ if (ie && ie_len) { static const u8 before_ht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_DS_PARAMS, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, }; @@ -1424,20 +1424,17 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local, /* insert custom IEs that go before VHT */ if (ie && ie_len) { static const u8 before_vht[] = { - WLAN_EID_SSID, - WLAN_EID_SUPP_RATES, - WLAN_EID_REQUEST, - WLAN_EID_EXT_SUPP_RATES, - WLAN_EID_DS_PARAMS, - WLAN_EID_SUPPORTED_REGULATORY_CLASSES, - WLAN_EID_HT_CAPABILITY, + /* + * no need to list the ones split off already + * (or generated here) + */ WLAN_EID_BSS_COEX_2040, WLAN_EID_EXT_CAPABILITY, WLAN_EID_SSID_LIST, WLAN_EID_CHANNEL_USAGE, WLAN_EID_INTERWORKING, WLAN_EID_MESH_ID, - /* 60 GHz can't happen here right now */ + /* 60 GHz (Multi-band, DMG, MMS) can't happen */ }; noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), -- GitLab From ffa4629e0c2b8b015f5fa174149c6dd269b4142c Mon Sep 17 00:00:00 2001 From: Tova Mussai Date: Sat, 5 Aug 2017 11:44:38 +0300 Subject: [PATCH 0180/1507] nl80211: return error for invalid center_freq in 40 MHz When NL80211_ATTR_WIPHY_CHANNEL_TYPE is given, nl80211 would parse the channel definition the old way, discarding NL80211_ATTR_CENTER_FREQ1, NL80211_ATTR_CENTER_FREQ2 etc. However, it is possible that user space added both NL80211_ATTR_WIPHY_CHANNEL_TYPE and NL80211_ATTR_CENTER_FREQ1 or NL80211_ATTR_CENTER_FREQ2 assuming that all settings would be honored. In such a case, validate that NL80211_ATTR_CENTER_FREQ1 and NL80211_ATTR_CENTER_FREQ2 values match the channel configuration, as otherwise user space would assume that the desired configuration was applied. For example, when trying to start ap with NL80211_ATTR_WIPHY_CHANNEL_TYPE = NL80211_CHAN_HT40MINUS, NL80211_ATTR_WIPHY_FREQ = 5180 and NL80211_ATTR_CENTER_FREQ1 = 5250 without this fix, the ap will start on channel 36 (center_freq1 will be corrected to 5180). With this fix, we will throw an error instead. Signed-off-by: Tova Mussai Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0df8023f480bb..66e97136ab44f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2122,6 +2122,15 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, case NL80211_CHAN_HT40MINUS: cfg80211_chandef_create(chandef, chandef->chan, chantype); + /* user input for center_freq is incorrect */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ1] && + chandef->center_freq1 != nla_get_u32( + info->attrs[NL80211_ATTR_CENTER_FREQ1])) + return -EINVAL; + /* center_freq2 must be zero */ + if (info->attrs[NL80211_ATTR_CENTER_FREQ2] && + nla_get_u32(info->attrs[NL80211_ATTR_CENTER_FREQ2])) + return -EINVAL; break; default: return -EINVAL; -- GitLab From 2d23d0736e3a4a0fdb92b8e46ea476639f16aae8 Mon Sep 17 00:00:00 2001 From: Roee Zamir Date: Sun, 6 Aug 2017 11:38:22 +0300 Subject: [PATCH 0181/1507] nl80211: add OCE scan and capability flags Add Optimized Connectivity Experience (OCE) scan and capability flags. Some of them unique to OCE and some are stand alone. And add scan flags to enable/disable them. Signed-off-by: Roee Zamir Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 37 +++++++++- net/wireless/nl80211.c | 137 ++++++++++++++++++++--------------- 2 files changed, 111 insertions(+), 63 deletions(-) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 51626b4175c00..76404d8a8863d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4914,6 +4914,15 @@ enum nl80211_feature_flags { * handshake with 802.1X in station mode (will pass EAP frames to the host * and accept the set_pmk/del_pmk commands), doing it in the host might not * be supported. + * @NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME: Driver is capable of overriding + * the max channel attribute in the FILS request params IE with the + * actual dwell time. + * @NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP: Driver accepts broadcast probe + * response + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE: Driver supports sending + * the first probe request in each channel at rate of at least 5.5Mbps. + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports + * probe request tx deferral and suppression * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4936,6 +4945,10 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_FILS_SK_OFFLOAD, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5012,12 +5025,28 @@ enum nl80211_timeout_reason { * locally administered 1, multicast 0) is assumed. * This flag must not be requested when the feature isn't supported, check * the nl80211 feature flags for the device. + * @NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME: fill the dwell time in the FILS + * request parameters IE in the probe request + * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at + * rate of at least 5.5M. In case non OCE AP is dicovered in the channel, + * only the first probe req in the channel will be sent in high rate. + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request + * tx deferral (dot11FILSProbeDelay shall be set to 15ms) + * and suppression (if it has received a broadcast Probe Response frame, + * Beacon frame or FILS Discovery frame from an AP that the STA considers + * a suitable candidate for (re-)association - suitable in terms of + * SSID and/or RSSI */ enum nl80211_scan_flags { - NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, - NL80211_SCAN_FLAG_FLUSH = 1<<1, - NL80211_SCAN_FLAG_AP = 1<<2, - NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, + NL80211_SCAN_FLAG_FLUSH = 1<<1, + NL80211_SCAN_FLAG_AP = 1<<2, + NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME = 1<<4, + NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7, }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 66e97136ab44f..2e6f5f4065f98 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6619,6 +6619,77 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) return regulatory_pre_cac_allowed(wdev->wiphy); } +static int +nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, + void *request, struct nlattr **attrs, + bool is_sched_scan) +{ + u8 *mac_addr, *mac_addr_mask; + u32 *flags; + enum nl80211_feature_flags randomness_flag; + + if (!attrs[NL80211_ATTR_SCAN_FLAGS]) + return 0; + + if (is_sched_scan) { + struct cfg80211_sched_scan_request *req = request; + + randomness_flag = wdev ? + NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR : + NL80211_FEATURE_ND_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } else { + struct cfg80211_scan_request *req = request; + + randomness_flag = NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } + + *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); + + if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + return -EOPNOTSUPP; + + if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + int err; + + if (!(wiphy->features & randomness_flag) || + (wdev && wdev->current_bss)) + return -EOPNOTSUPP; + + err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask); + if (err) + return err; + } + + if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6824,34 +6895,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_get_flag(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY]); } - if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - if (!(wiphy->features & - NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(info->attrs, - request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, info->attrs, + false); + if (err) + goto out_free; request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); @@ -7299,37 +7346,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->ie_len); } - if (attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR; - - if (!wdev) /* must be net-detect */ - flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR; - - if (!(wiphy->features & flg)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev && wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(attrs, request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, attrs, true); + if (err) + goto out_free; if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY]) request->delay = -- GitLab From 40b0bd24973487272167a09db040a70c053bedbe Mon Sep 17 00:00:00 2001 From: Roee Zamir Date: Sun, 6 Aug 2017 11:38:23 +0300 Subject: [PATCH 0182/1507] mac80211: oce: enable receiving of bcast probe resp One of OCE's optimizations is acception of broadcast probe responses. Accept broadcast probe responses but don't set NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP. Because a device's firmware may filter out the broadcast probe resp - drivers should set this flag. Signed-off-by: Roee Zamir Signed-off-by: Luca Coelho [johannes: make accepting broadcast conditional on the nl80211 scan flag that was added for that specific purpose] Signed-off-by: Johannes Berg --- net/mac80211/scan.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 47d2ed5704700..ef2becaade506 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007, Michael Wu * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright 2016 Intel Deutschland GmbH + * Copyright 2016-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -183,6 +183,20 @@ ieee80211_bss_info_update(struct ieee80211_local *local, return bss; } +static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, + u32 scan_flags, const u8 *da) +{ + if (!sdata) + return false; + /* accept broadcast for OCE */ + if (scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP && + is_broadcast_ether_addr(da)) + return true; + if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) + return true; + return ether_addr_equal(da, sdata->vif.addr); +} + void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); @@ -208,19 +222,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; + u32 scan_req_flags = 0, sched_scan_req_flags = 0; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); - /* ignore ProbeResp to foreign address unless scanning - * with randomised address + if (scan_req) + scan_req_flags = scan_req->flags; + + if (sched_scan_req) + sched_scan_req_flags = sched_scan_req->flags; + + /* ignore ProbeResp to foreign address or non-bcast (OCE) + * unless scanning with randomised address */ - if (!(sdata1 && - (ether_addr_equal(mgmt->da, sdata1->vif.addr) || - scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) && - !(sdata2 && - (ether_addr_equal(mgmt->da, sdata2->vif.addr) || - sched_scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR))) + if (!ieee80211_scan_accept_presp(sdata1, scan_req_flags, + mgmt->da) && + !ieee80211_scan_accept_presp(sdata2, sched_scan_req_flags, + mgmt->da)) return; elements = mgmt->u.probe_resp.variable; -- GitLab From 1272c5d89b597995cb10db87dd4a1adc91d36006 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Fri, 18 Aug 2017 15:33:56 +0300 Subject: [PATCH 0183/1507] mac80211: add documentation to ieee80211_rx_ba_offl() Add documentation to ieee80211_rx_ba_offl() function and, while at it, rename the bit argument to tid, for consistency. Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/mac80211.h | 8 +++++++- net/mac80211/agg-rx.c | 4 ++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 885690fa39c8d..cc9073e45be90 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5441,8 +5441,14 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, */ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); +/** + * ieee80211_manage_rx_ba_offl - helper to queue an RX BA work + * @vif: &struct ieee80211_vif pointer from the add_interface callback + * @addr: station mac address + * @tid: the rx tid + */ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr, - unsigned int bit); + unsigned int tid); /** * ieee80211_start_rx_ba_session_offl - start a Rx BA session diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 2849a1fc41c5d..88cc1ae935ead 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -459,7 +459,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, } void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, - const u8 *addr, unsigned int bit) + const u8 *addr, unsigned int tid) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; @@ -470,7 +470,7 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, if (!sta) goto unlock; - set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl); + set_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl); ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); unlock: rcu_read_unlock(); -- GitLab From 1281103770e909e064edbb22a1115a0c14eca081 Mon Sep 17 00:00:00 2001 From: Ilan peer Date: Wed, 6 Sep 2017 17:18:33 +0300 Subject: [PATCH 0184/1507] mac80211: Simplify locking in ieee80211_sta_tear_down_BA_sessions() Simplify the locking in ieee80211_sta_tear_down_BA_sessions() and lock sta->ampdu_mlme.mtx over the entire function instead of locking/unlocking it for each TID etc. Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- net/mac80211/ht.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d6d0b4201e40b..41f5e48f80219 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -290,13 +290,15 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, { int i; + mutex_lock(&sta->ampdu_mlme.mtx); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - __ieee80211_stop_tx_ba_session(sta, i, reason); - __ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_LEAVE_QBSS, - reason != AGG_STOP_DESTROY_STA && - reason != AGG_STOP_PEER_REQUEST); + ___ieee80211_stop_tx_ba_session(sta, i, reason); + ___ieee80211_stop_rx_ba_session(sta, i, WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_LEAVE_QBSS, + reason != AGG_STOP_DESTROY_STA && + reason != AGG_STOP_PEER_REQUEST); } + mutex_unlock(&sta->ampdu_mlme.mtx); /* stopping might queue the work again - so cancel only afterwards */ cancel_work_sync(&sta->ampdu_mlme.work); -- GitLab From 4c121fd690d9c465e4cb09b7859adfdd6a0aee1d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 8 Sep 2017 11:54:46 +0200 Subject: [PATCH 0185/1507] mac80211: use offsetofend() This was created using the following spatch: @find@ type S; expression M, M2; position p; @@ offsetof(S, M) + sizeof(M2)@p @script:python@ m << find.M; m2 << find.M2; @@ if not m2.endswith('-> ' + m): cocci.include_match(False) @change@ type find.S; expression find.M, find.M2; position find.p; @@ -offsetof(S, M) + sizeof(M2)@p +offsetofend(S, M) Signed-off-by: Johannes Berg --- net/mac80211/mesh.c | 3 +-- net/mac80211/mesh_hwmp.c | 8 ++++---- net/mac80211/mesh_plink.c | 3 +-- net/mac80211/util.c | 4 ++-- 4 files changed, 8 insertions(+), 10 deletions(-) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index a550c707cd8a6..7a76c4a6df306 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -675,8 +675,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) enum nl80211_band band; u8 *pos; struct ieee80211_sub_if_data *sdata; - int hdr_len = offsetof(struct ieee80211_mgmt, u.beacon) + - sizeof(mgmt->u.beacon); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); rcu_read_lock(); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index d8bbd0d2225a1..146ec6c0f12f8 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -111,8 +111,8 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, struct sk_buff *skb; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); skb = dev_alloc_skb(local->tx_headroom + hdr_len + @@ -242,8 +242,8 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_mgmt *mgmt; u8 *pos, ie_len; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.mesh_action) + - sizeof(mgmt->u.action.u.mesh_action); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.mesh_action); if (time_before(jiffies, ifmsh->next_perr)) return -EAGAIN; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f69c6c38ca439..dc8e10f872070 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -220,8 +220,7 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, bool include_plid = false; u16 peering_proto = 0; u8 *pos, ie_len = 4; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.self_prot) + - sizeof(mgmt->u.action.u.self_prot); + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; skb = dev_alloc_skb(local->tx_headroom + diff --git a/net/mac80211/util.c b/net/mac80211/util.c index bfecc3e863189..d57e5f6bd8b61 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2977,8 +2977,8 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; struct ieee80211_local *local = sdata->local; int freq; - int hdr_len = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch) + - sizeof(mgmt->u.action.u.chan_switch); + int hdr_len = offsetofend(struct ieee80211_mgmt, + u.action.u.chan_switch); u8 *pos; if (sdata->vif.type != NL80211_IFTYPE_ADHOC && -- GitLab From 62b093b375e3c10ff39896f2a172146cf5df529f Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Mon, 18 Sep 2017 15:56:51 +0200 Subject: [PATCH 0186/1507] mac80211_hwsim: use dyndbg for debug messages The mac80211_hwsim doesn't offer a way to disable the debugging output. Unfortunately, it's pretty chatty, dumping a lot of stuff into the message buffer. This patch changes it to use dyndbg for controlling the debug output. It's disabled by default, but can be enabled by a module parameter (1), at runtime (2) or persisted in modprobe.conf (3). (1) modprobe mac80211_hwsim dyndbg=+p (2) echo "module mac80211_hwsim +p" >/sys/kernel/debug/dynamic_debug/control (3) echo "options mac80211_hwsim dyndbg=+p" >>/etc/modprobe.d/my.conf Signed-off-by: Lubomir Rintel Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 192 +++++++++++++------------- 1 file changed, 96 insertions(+), 96 deletions(-) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6467ffac9811e..ec2f4c31425a1 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -396,7 +396,7 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy, if (!tb[QCA_WLAN_VENDOR_ATTR_TEST]) return -EINVAL; val = nla_get_u32(tb[QCA_WLAN_VENDOR_ATTR_TEST]); - wiphy_debug(wiphy, "%s: test=%u\n", __func__, val); + wiphy_dbg(wiphy, "%s: test=%u\n", __func__, val); /* Send a vendor event as a test. Note that this would not normally be * done within a command handler, but rather, based on some other @@ -643,9 +643,9 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif) if (!vp->assoc) return; - wiphy_debug(data->hw->wiphy, - "%s: send PS-Poll to %pM for aid %d\n", - __func__, vp->bssid, vp->aid); + wiphy_dbg(data->hw->wiphy, + "%s: send PS-Poll to %pM for aid %d\n", + __func__, vp->bssid, vp->aid); skb = dev_alloc_skb(sizeof(*pspoll)); if (!skb) @@ -674,9 +674,9 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, if (!vp->assoc) return; - wiphy_debug(data->hw->wiphy, - "%s: send data::nullfunc to %pM ps=%d\n", - __func__, vp->bssid, ps); + wiphy_dbg(data->hw->wiphy, + "%s: send data::nullfunc to %pM ps=%d\n", + __func__, vp->bssid, ps); skb = dev_alloc_skb(sizeof(*hdr)); if (!skb) @@ -1034,7 +1034,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, msg_head = genlmsg_put(skb, 0, 0, &hwsim_genl_family, 0, HWSIM_CMD_FRAME); if (msg_head == NULL) { - printk(KERN_DEBUG "mac80211_hwsim: problem with msg_head\n"); + pr_debug("mac80211_hwsim: problem with msg_head\n"); goto nla_put_failure; } @@ -1093,7 +1093,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, nla_put_failure: nlmsg_free(skb); err_free_txskb: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); ieee80211_free_txskb(hw, my_skb); data->tx_failed++; } @@ -1347,7 +1347,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, } if (data->idle && !data->tmp_chan) { - wiphy_debug(hw->wiphy, "Trying to TX when idle - reject\n"); + wiphy_dbg(hw->wiphy, "Trying to TX when idle - reject\n"); ieee80211_free_txskb(hw, skb); return; } @@ -1408,7 +1408,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, static int mac80211_hwsim_start(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); data->started = true; return 0; } @@ -1419,16 +1419,16 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw) struct mac80211_hwsim_data *data = hw->priv; data->started = false; tasklet_hrtimer_cancel(&data->beacon_timer); - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); } static int mac80211_hwsim_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), - vif->addr); + wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), + vif->addr); hwsim_set_magic(vif); vif->cab_queue = 0; @@ -1447,9 +1447,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw, bool newp2p) { newtype = ieee80211_iftype_p2p(newtype, newp2p); - wiphy_debug(hw->wiphy, - "%s (old type=%d, new type=%d, mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), + wiphy_dbg(hw->wiphy, + "%s (old type=%d, new type=%d, mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), newtype, vif->addr); hwsim_check_magic(vif); @@ -1465,9 +1465,9 @@ static int mac80211_hwsim_change_interface(struct ieee80211_hw *hw, static void mac80211_hwsim_remove_interface( struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - wiphy_debug(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", - __func__, ieee80211_vif_type_p2p(vif), - vif->addr); + wiphy_dbg(hw->wiphy, "%s (type=%d mac_addr=%pM)\n", + __func__, ieee80211_vif_type_p2p(vif), + vif->addr); hwsim_check_magic(vif); hwsim_clear_magic(vif); } @@ -1589,23 +1589,23 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) int idx; if (conf->chandef.chan) - wiphy_debug(hw->wiphy, - "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n", - __func__, - conf->chandef.chan->center_freq, - conf->chandef.center_freq1, - conf->chandef.center_freq2, - hwsim_chanwidths[conf->chandef.width], - !!(conf->flags & IEEE80211_CONF_IDLE), - !!(conf->flags & IEEE80211_CONF_PS), - smps_modes[conf->smps_mode]); + wiphy_dbg(hw->wiphy, + "%s (freq=%d(%d - %d)/%s idle=%d ps=%d smps=%s)\n", + __func__, + conf->chandef.chan->center_freq, + conf->chandef.center_freq1, + conf->chandef.center_freq2, + hwsim_chanwidths[conf->chandef.width], + !!(conf->flags & IEEE80211_CONF_IDLE), + !!(conf->flags & IEEE80211_CONF_PS), + smps_modes[conf->smps_mode]); else - wiphy_debug(hw->wiphy, - "%s (freq=0 idle=%d ps=%d smps=%s)\n", - __func__, - !!(conf->flags & IEEE80211_CONF_IDLE), - !!(conf->flags & IEEE80211_CONF_PS), - smps_modes[conf->smps_mode]); + wiphy_dbg(hw->wiphy, + "%s (freq=0 idle=%d ps=%d smps=%s)\n", + __func__, + !!(conf->flags & IEEE80211_CONF_IDLE), + !!(conf->flags & IEEE80211_CONF_PS), + smps_modes[conf->smps_mode]); data->idle = !!(conf->flags & IEEE80211_CONF_IDLE); @@ -1659,7 +1659,7 @@ static void mac80211_hwsim_configure_filter(struct ieee80211_hw *hw, { struct mac80211_hwsim_data *data = hw->priv; - wiphy_debug(hw->wiphy, "%s\n", __func__); + wiphy_dbg(hw->wiphy, "%s\n", __func__); data->rx_filter = 0; if (*total_flags & FIF_ALLMULTI) @@ -1688,25 +1688,25 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, hwsim_check_magic(vif); - wiphy_debug(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n", - __func__, changed, vif->addr); + wiphy_dbg(hw->wiphy, "%s(changed=0x%x vif->addr=%pM)\n", + __func__, changed, vif->addr); if (changed & BSS_CHANGED_BSSID) { - wiphy_debug(hw->wiphy, "%s: BSSID changed: %pM\n", - __func__, info->bssid); + wiphy_dbg(hw->wiphy, "%s: BSSID changed: %pM\n", + __func__, info->bssid); memcpy(vp->bssid, info->bssid, ETH_ALEN); } if (changed & BSS_CHANGED_ASSOC) { - wiphy_debug(hw->wiphy, " ASSOC: assoc=%d aid=%d\n", - info->assoc, info->aid); + wiphy_dbg(hw->wiphy, " ASSOC: assoc=%d aid=%d\n", + info->assoc, info->aid); vp->assoc = info->assoc; vp->aid = info->aid; } if (changed & BSS_CHANGED_BEACON_ENABLED) { - wiphy_debug(hw->wiphy, " BCN EN: %d (BI=%u)\n", - info->enable_beacon, info->beacon_int); + wiphy_dbg(hw->wiphy, " BCN EN: %d (BI=%u)\n", + info->enable_beacon, info->beacon_int); vp->bcn_en = info->enable_beacon; if (data->started && !hrtimer_is_queued(&data->beacon_timer.timer) && @@ -1725,8 +1725,8 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, ieee80211_iterate_active_interfaces_atomic( data->hw, IEEE80211_IFACE_ITER_NORMAL, mac80211_hwsim_bcn_en_iter, &count); - wiphy_debug(hw->wiphy, " beaconing vifs remaining: %u", - count); + wiphy_dbg(hw->wiphy, " beaconing vifs remaining: %u", + count); if (count == 0) { tasklet_hrtimer_cancel(&data->beacon_timer); data->beacon_int = 0; @@ -1735,31 +1735,31 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, } if (changed & BSS_CHANGED_ERP_CTS_PROT) { - wiphy_debug(hw->wiphy, " ERP_CTS_PROT: %d\n", - info->use_cts_prot); + wiphy_dbg(hw->wiphy, " ERP_CTS_PROT: %d\n", + info->use_cts_prot); } if (changed & BSS_CHANGED_ERP_PREAMBLE) { - wiphy_debug(hw->wiphy, " ERP_PREAMBLE: %d\n", - info->use_short_preamble); + wiphy_dbg(hw->wiphy, " ERP_PREAMBLE: %d\n", + info->use_short_preamble); } if (changed & BSS_CHANGED_ERP_SLOT) { - wiphy_debug(hw->wiphy, " ERP_SLOT: %d\n", info->use_short_slot); + wiphy_dbg(hw->wiphy, " ERP_SLOT: %d\n", info->use_short_slot); } if (changed & BSS_CHANGED_HT) { - wiphy_debug(hw->wiphy, " HT: op_mode=0x%x\n", - info->ht_operation_mode); + wiphy_dbg(hw->wiphy, " HT: op_mode=0x%x\n", + info->ht_operation_mode); } if (changed & BSS_CHANGED_BASIC_RATES) { - wiphy_debug(hw->wiphy, " BASIC_RATES: 0x%llx\n", - (unsigned long long) info->basic_rates); + wiphy_dbg(hw->wiphy, " BASIC_RATES: 0x%llx\n", + (unsigned long long) info->basic_rates); } if (changed & BSS_CHANGED_TXPOWER) - wiphy_debug(hw->wiphy, " TX Power: %d dBm\n", info->txpower); + wiphy_dbg(hw->wiphy, " TX Power: %d dBm\n", info->txpower); } static int mac80211_hwsim_sta_add(struct ieee80211_hw *hw, @@ -1813,11 +1813,11 @@ static int mac80211_hwsim_conf_tx( struct ieee80211_vif *vif, u16 queue, const struct ieee80211_tx_queue_params *params) { - wiphy_debug(hw->wiphy, - "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n", - __func__, queue, - params->txop, params->cw_min, - params->cw_max, params->aifs); + wiphy_dbg(hw->wiphy, + "%s (queue=%d txop=%d cw_min=%d cw_max=%d aifs=%d)\n", + __func__, queue, + params->txop, params->cw_min, + params->cw_max, params->aifs); return 0; } @@ -1981,7 +1981,7 @@ static void hw_scan_work(struct work_struct *work) .aborted = false, }; - wiphy_debug(hwsim->hw->wiphy, "hw scan complete\n"); + wiphy_dbg(hwsim->hw->wiphy, "hw scan complete\n"); ieee80211_scan_completed(hwsim->hw, &info); hwsim->hw_scan_request = NULL; hwsim->hw_scan_vif = NULL; @@ -1990,8 +1990,8 @@ static void hw_scan_work(struct work_struct *work) return; } - wiphy_debug(hwsim->hw->wiphy, "hw scan %d MHz\n", - req->channels[hwsim->scan_chan_idx]->center_freq); + wiphy_dbg(hwsim->hw->wiphy, "hw scan %d MHz\n", + req->channels[hwsim->scan_chan_idx]->center_freq); hwsim->tmp_chan = req->channels[hwsim->scan_chan_idx]; if (hwsim->tmp_chan->flags & (IEEE80211_CHAN_NO_IR | @@ -2060,7 +2060,7 @@ static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw, memset(hwsim->survey_data, 0, sizeof(hwsim->survey_data)); mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim hw_scan request\n"); + wiphy_dbg(hw->wiphy, "hwsim hw_scan request\n"); ieee80211_queue_delayed_work(hwsim->hw, &hwsim->hw_scan, 0); @@ -2075,7 +2075,7 @@ static void mac80211_hwsim_cancel_hw_scan(struct ieee80211_hw *hw, .aborted = true, }; - wiphy_debug(hw->wiphy, "hwsim cancel_hw_scan\n"); + wiphy_dbg(hw->wiphy, "hwsim cancel_hw_scan\n"); cancel_delayed_work_sync(&hwsim->hw_scan); @@ -2096,11 +2096,11 @@ static void mac80211_hwsim_sw_scan(struct ieee80211_hw *hw, mutex_lock(&hwsim->mutex); if (hwsim->scanning) { - printk(KERN_DEBUG "two hwsim sw_scans detected!\n"); + pr_debug("two hwsim sw_scans detected!\n"); goto out; } - printk(KERN_DEBUG "hwsim sw_scan request, prepping stuff\n"); + pr_debug("hwsim sw_scan request, prepping stuff\n"); memcpy(hwsim->scan_addr, mac_addr, ETH_ALEN); hwsim->scanning = true; @@ -2117,7 +2117,7 @@ static void mac80211_hwsim_sw_scan_complete(struct ieee80211_hw *hw, mutex_lock(&hwsim->mutex); - printk(KERN_DEBUG "hwsim sw_scan_complete\n"); + pr_debug("hwsim sw_scan_complete\n"); hwsim->scanning = false; eth_zero_addr(hwsim->scan_addr); @@ -2131,7 +2131,7 @@ static void hw_roc_start(struct work_struct *work) mutex_lock(&hwsim->mutex); - wiphy_debug(hwsim->hw->wiphy, "hwsim ROC begins\n"); + wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC begins\n"); hwsim->tmp_chan = hwsim->roc_chan; ieee80211_ready_on_channel(hwsim->hw); @@ -2151,7 +2151,7 @@ static void hw_roc_done(struct work_struct *work) hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); - wiphy_debug(hwsim->hw->wiphy, "hwsim ROC expired\n"); + wiphy_dbg(hwsim->hw->wiphy, "hwsim ROC expired\n"); } static int mac80211_hwsim_roc(struct ieee80211_hw *hw, @@ -2172,8 +2172,8 @@ static int mac80211_hwsim_roc(struct ieee80211_hw *hw, hwsim->roc_duration = duration; mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n", - chan->center_freq, duration); + wiphy_dbg(hw->wiphy, "hwsim ROC (%d MHz, %d ms)\n", + chan->center_freq, duration); ieee80211_queue_delayed_work(hw, &hwsim->roc_start, HZ/50); return 0; @@ -2190,7 +2190,7 @@ static int mac80211_hwsim_croc(struct ieee80211_hw *hw) hwsim->tmp_chan = NULL; mutex_unlock(&hwsim->mutex); - wiphy_debug(hw->wiphy, "hwsim ROC canceled\n"); + wiphy_dbg(hw->wiphy, "hwsim ROC canceled\n"); return 0; } @@ -2199,20 +2199,20 @@ static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { hwsim_set_chanctx_magic(ctx); - wiphy_debug(hw->wiphy, - "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); return 0; } static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { - wiphy_debug(hw->wiphy, - "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); hwsim_check_chanctx_magic(ctx); hwsim_clear_chanctx_magic(ctx); } @@ -2222,10 +2222,10 @@ static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw, u32 changed) { hwsim_check_chanctx_magic(ctx); - wiphy_debug(hw->wiphy, - "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", - ctx->def.chan->center_freq, ctx->def.width, - ctx->def.center_freq1, ctx->def.center_freq2); + wiphy_dbg(hw->wiphy, + "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", + ctx->def.chan->center_freq, ctx->def.width, + ctx->def.center_freq1, ctx->def.center_freq2); } static int mac80211_hwsim_assign_vif_chanctx(struct ieee80211_hw *hw, @@ -2479,7 +2479,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ops = &mac80211_hwsim_mchan_ops; hw = ieee80211_alloc_hw_nm(sizeof(*data), ops, param->hwname); if (!hw) { - printk(KERN_DEBUG "mac80211_hwsim: ieee80211_alloc_hw failed\n"); + pr_debug("mac80211_hwsim: ieee80211_alloc_hw failed\n"); err = -ENOMEM; goto failed; } @@ -2507,7 +2507,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, data->dev->driver = &mac80211_hwsim_driver.driver; err = device_bind_driver(data->dev); if (err != 0) { - printk(KERN_DEBUG "mac80211_hwsim: device_bind_driver failed (%d)\n", + pr_debug("mac80211_hwsim: device_bind_driver failed (%d)\n", err); goto failed_bind; } @@ -2698,12 +2698,12 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, err = ieee80211_register_hw(hw); if (err < 0) { - printk(KERN_DEBUG "mac80211_hwsim: ieee80211_register_hw failed (%d)\n", + pr_debug("mac80211_hwsim: ieee80211_register_hw failed (%d)\n", err); goto failed_hw; } - wiphy_debug(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr); + wiphy_dbg(hw->wiphy, "hwaddr %pM registered\n", hw->wiphy->perm_addr); if (param->reg_alpha2) { data->alpha2[0] = param->reg_alpha2[0]; @@ -3067,7 +3067,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, return 0; err: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); out: dev_kfree_skb(skb); return -EINVAL; @@ -3098,7 +3098,7 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2, hwsim_register_wmediumd(net, info->snd_portid); - printk(KERN_DEBUG "mac80211_hwsim: received a REGISTER, " + pr_debug("mac80211_hwsim: received a REGISTER, " "switching to wmediumd mode with pid %d\n", info->snd_portid); return 0; @@ -3387,7 +3387,7 @@ static int __init hwsim_init_netlink(void) return 0; failure: - printk(KERN_DEBUG "mac80211_hwsim: error occurred in %s\n", __func__); + pr_debug("mac80211_hwsim: error occurred in %s\n", __func__); return -EINVAL; } @@ -3578,7 +3578,7 @@ module_init(init_mac80211_hwsim); static void __exit exit_mac80211_hwsim(void) { - printk(KERN_DEBUG "mac80211_hwsim: unregister radios\n"); + pr_debug("mac80211_hwsim: unregister radios\n"); hwsim_exit_netlink(); -- GitLab From a6bcda44843c6dfced0fb973e2607c2a98addfa9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 19 Sep 2017 11:52:43 +0200 Subject: [PATCH 0187/1507] cfg80211: remove unused function ieee80211_data_from_8023() This function hasn't been used since the removal of iwmc3200wifi in 2012. It also appears to have a bug when qos=True, since then it'll copy uninitialized stack memory to the SKB. Just remove the function entirely. Reported-by: Jouni Malinen Signed-off-by: Johannes Berg --- Documentation/driver-api/80211/cfg80211.rst | 3 - include/net/cfg80211.h | 13 --- net/wireless/util.c | 115 -------------------- 3 files changed, 131 deletions(-) diff --git a/Documentation/driver-api/80211/cfg80211.rst b/Documentation/driver-api/80211/cfg80211.rst index 8ffac57e1f5b7..eeab91b59457e 100644 --- a/Documentation/driver-api/80211/cfg80211.rst +++ b/Documentation/driver-api/80211/cfg80211.rst @@ -299,9 +299,6 @@ Data path helpers .. kernel-doc:: include/net/cfg80211.h :functions: ieee80211_data_to_8023 -.. kernel-doc:: include/net/cfg80211.h - :functions: ieee80211_data_from_8023 - .. kernel-doc:: include/net/cfg80211.h :functions: ieee80211_amsdu_to_8023s diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index aa9d993e519a6..cc1996081463c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4346,19 +4346,6 @@ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype); } -/** - * ieee80211_data_from_8023 - convert an 802.3 frame to 802.11 - * @skb: the 802.3 frame - * @addr: the device MAC address - * @iftype: the virtual interface type - * @bssid: the network bssid (used only for iftype STATION and ADHOC) - * @qos: build 802.11 QoS data frame - * Return: 0 on success, or a negative error code. - */ -int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, const u8 *bssid, - bool qos); - /** * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame * diff --git a/net/wireless/util.c b/net/wireless/util.c index 4aab793c2f006..7dcdf67cba29a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -529,121 +529,6 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); -int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr, - enum nl80211_iftype iftype, - const u8 *bssid, bool qos) -{ - struct ieee80211_hdr hdr; - u16 hdrlen, ethertype; - __le16 fc; - const u8 *encaps_data; - int encaps_len, skip_header_bytes; - int nh_pos, h_pos; - int head_need; - - if (unlikely(skb->len < ETH_HLEN)) - return -EINVAL; - - nh_pos = skb_network_header(skb) - skb->data; - h_pos = skb_transport_header(skb) - skb->data; - - /* convert Ethernet header to proper 802.11 header (based on - * operation mode) */ - ethertype = (skb->data[12] << 8) | skb->data[13]; - fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); - - switch (iftype) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_P2P_GO: - fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); - /* DA BSSID SA */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, addr, ETH_ALEN); - memcpy(hdr.addr3, skb->data + ETH_ALEN, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_CLIENT: - fc |= cpu_to_le16(IEEE80211_FCTL_TODS); - /* BSSID SA DA */ - memcpy(hdr.addr1, bssid, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, skb->data, ETH_ALEN); - hdrlen = 24; - break; - case NL80211_IFTYPE_OCB: - case NL80211_IFTYPE_ADHOC: - /* DA SA BSSID */ - memcpy(hdr.addr1, skb->data, ETH_ALEN); - memcpy(hdr.addr2, skb->data + ETH_ALEN, ETH_ALEN); - memcpy(hdr.addr3, bssid, ETH_ALEN); - hdrlen = 24; - break; - default: - return -EOPNOTSUPP; - } - - if (qos) { - fc |= cpu_to_le16(IEEE80211_STYPE_QOS_DATA); - hdrlen += 2; - } - - hdr.frame_control = fc; - hdr.duration_id = 0; - hdr.seq_ctrl = 0; - - skip_header_bytes = ETH_HLEN; - if (ethertype == ETH_P_AARP || ethertype == ETH_P_IPX) { - encaps_data = bridge_tunnel_header; - encaps_len = sizeof(bridge_tunnel_header); - skip_header_bytes -= 2; - } else if (ethertype >= ETH_P_802_3_MIN) { - encaps_data = rfc1042_header; - encaps_len = sizeof(rfc1042_header); - skip_header_bytes -= 2; - } else { - encaps_data = NULL; - encaps_len = 0; - } - - skb_pull(skb, skip_header_bytes); - nh_pos -= skip_header_bytes; - h_pos -= skip_header_bytes; - - head_need = hdrlen + encaps_len - skb_headroom(skb); - - if (head_need > 0 || skb_cloned(skb)) { - head_need = max(head_need, 0); - if (head_need) - skb_orphan(skb); - - if (pskb_expand_head(skb, head_need, 0, GFP_ATOMIC)) - return -ENOMEM; - } - - if (encaps_data) { - memcpy(skb_push(skb, encaps_len), encaps_data, encaps_len); - nh_pos += encaps_len; - h_pos += encaps_len; - } - - memcpy(skb_push(skb, hdrlen), &hdr, hdrlen); - - nh_pos += hdrlen; - h_pos += hdrlen; - - /* Update skb pointers to various headers since this modified frame - * is going to go through Linux networking code that may potentially - * need things like pointer to IP header. */ - skb_reset_mac_header(skb); - skb_set_network_header(skb, nh_pos); - skb_set_transport_header(skb, h_pos); - - return 0; -} -EXPORT_SYMBOL(ieee80211_data_from_8023); - static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) -- GitLab From 65026002d69de006e273749bb799d3b01b757eb0 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 18 Aug 2017 15:31:41 +0300 Subject: [PATCH 0188/1507] nl80211: add an option to allow MFP without requiring it The user space can now allow the kernel to associate to an AP that requires MFP or that doesn't have MFP enabled in the same NL80211_CMD_CONNECT command, by using a new NL80211_MFP_OPTIONAL flag. The driver / firmware will decide whether to use it or not. Include a feature bit to advertise support for NL80211_MFP_OPTIONAL. This allows new user space to run on old kernels and know that it cannot use the new attribute if it isn't supported. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 13 +++++++++++-- net/wireless/nl80211.c | 8 +++++++- 2 files changed, 18 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 76404d8a8863d..59ba6ca66a0d0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1407,8 +1407,12 @@ enum nl80211_commands { * * @NL80211_ATTR_USE_MFP: Whether management frame protection (IEEE 802.11w) is * used for the association (&enum nl80211_mfp, represented as a u32); - * this attribute can be used - * with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests + * this attribute can be used with %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_CONNECT requests. %NL80211_MFP_OPTIONAL is not allowed for + * %NL80211_CMD_ASSOCIATE since user space SME is expected and hence, it + * must have decided whether to use management frame protection or not. + * Setting %NL80211_MFP_OPTIONAL with a %NL80211_CMD_CONNECT request will + * let the driver (or the firmware) decide whether to use MFP or not. * * @NL80211_ATTR_STA_FLAGS2: Attribute containing a * &struct nl80211_sta_flag_update. @@ -3947,10 +3951,12 @@ enum nl80211_key_type { * enum nl80211_mfp - Management frame protection state * @NL80211_MFP_NO: Management frame protection not used * @NL80211_MFP_REQUIRED: Management frame protection required + * @NL80211_MFP_OPTIONAL: Management frame protection is optional */ enum nl80211_mfp { NL80211_MFP_NO, NL80211_MFP_REQUIRED, + NL80211_MFP_OPTIONAL, }; enum nl80211_wpa_versions { @@ -4923,6 +4929,8 @@ enum nl80211_feature_flags { * the first probe request in each channel at rate of at least 5.5Mbps. * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports * probe request tx deferral and suppression + * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL + * value in %NL80211_ATTR_USE_MFP. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4949,6 +4957,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP, NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, + NL80211_EXT_FEATURE_MFP_OPTIONAL, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2e6f5f4065f98..1e39ba3cfd060 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8952,8 +8952,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_USE_MFP]) { connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); + if (connect.mfp == NL80211_MFP_OPTIONAL && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_MFP_OPTIONAL)) + return -EOPNOTSUPP; + if (connect.mfp != NL80211_MFP_REQUIRED && - connect.mfp != NL80211_MFP_NO) + connect.mfp != NL80211_MFP_NO && + connect.mfp != NL80211_MFP_OPTIONAL) return -EINVAL; } else { connect.mfp = NL80211_MFP_NO; -- GitLab From 0551968add53777fddd18f4ffb4e3bbc1f646d79 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Sep 2017 11:54:44 +0200 Subject: [PATCH 0189/1507] Revert "genirq: Restrict effective affinity to interrupts actually using it" This reverts commit 74def747bcd09692bdbf8c6a15350795b0f11ca8. The change to the helper function is only correct for the /proc/irq/ readout usage, but breaks the existing x86 usage of that function. Reported-by: Yanko Kaneti Signed-off-by: Thomas Gleixner Cc: Marc Zyngier --- include/linux/irq.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/include/linux/irq.h b/include/linux/irq.h index b99a784635ff5..d4728bf6a537c 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -783,10 +783,7 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) static inline struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - if (!cpumask_empty(d->common->effective_affinity)) - return d->common->effective_affinity; - - return d->common->affinity; + return d->common->effective_affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) -- GitLab From 544e3bf4f0e8278400f19ca7918a3cdf2548b4eb Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 Sep 2017 14:22:08 +0200 Subject: [PATCH 0190/1507] reset: Restrict RESET_HSDK to ARC_SOC_HSDK or COMPILE_TEST The HSDK reset driver is only useful when building for an ARC HSDK platform. While at it, drop the "default n", as that is the default. Fixes: e0be864f14240cb1 ("ARC: reset: introduce HSDKv1 reset driver") Signed-off-by: Geert Uytterhoeven [p.zabel@pengutronix.de: rebased, renamed RESET_HSDK_V1 to RESET_HSDK] Signed-off-by: Philipp Zabel --- drivers/reset/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index a7c7d5a8c089d..e2baecbb9dd3a 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -37,7 +37,7 @@ config RESET_BERLIN config RESET_HSDK bool "Synopsys HSDK Reset Driver" depends on HAS_IOMEM - default n + depends on ARC_SOC_HSDK || COMPILE_TEST help This enables the reset controller driver for HSDK board. -- GitLab From d405fd8cc807c045b23bc2df4a5ab6b85df614f3 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sat, 5 Aug 2017 11:44:36 +0300 Subject: [PATCH 0191/1507] mac80211: recalculate some sta parameters after insertion Sometimes a station is added already in ASSOC state. For example, in AP mode, when a client station didn't get assoc resp and sends an assoc req again. If a station is inserted when its state is ASSOC or higher, the min chandef and allow_p2p_go_ps should be recalculated again after the insertion. Before this patch the recalculation happened only in sta_info_move_state which occurs before the insertion of the sta and thus even though it calls ieee80211_recalc_min_chandef/_p2p_go_ps_allowed functions, since sdata->local->sta_list is still empty at this point, it doesn't do anything. Signed-off-by: Gregory Greenman Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 57 +++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 25 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 69615016d5bf6..ffcd25c4908cc 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -515,6 +515,31 @@ static int sta_info_insert_drv_state(struct ieee80211_local *local, return err; } +static void +ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + bool allow_p2p_go_ps = sdata->vif.p2p; + struct sta_info *sta; + + rcu_read_lock(); + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata || + !test_sta_flag(sta, WLAN_STA_ASSOC)) + continue; + if (!sta->sta.support_p2p_ps) { + allow_p2p_go_ps = false; + break; + } + } + rcu_read_unlock(); + + if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { + sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); + } +} + /* * should be called with sta_mtx locked * this function replaces the mutex lock @@ -561,6 +586,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) goto out_remove; set_sta_flag(sta, WLAN_STA_INSERTED); + + if (sta->sta_state >= IEEE80211_STA_ASSOC) { + ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); + } + /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); @@ -1788,31 +1820,6 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); -static void -ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_local *local = sdata->local; - bool allow_p2p_go_ps = sdata->vif.p2p; - struct sta_info *sta; - - rcu_read_lock(); - list_for_each_entry_rcu(sta, &local->sta_list, list) { - if (sdata != sta->sdata || - !test_sta_flag(sta, WLAN_STA_ASSOC)) - continue; - if (!sta->sta.support_p2p_ps) { - allow_p2p_go_ps = false; - break; - } - } - rcu_read_unlock(); - - if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { - sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_P2P_PS); - } -} - int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { -- GitLab From 1bd773c077deeeb2d9ced1fdb6d846169b8e7e4a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Richard=20Sch=C3=BCtz?= Date: Thu, 7 Sep 2017 17:47:43 +0200 Subject: [PATCH 0192/1507] wireless: set correct mandatory rate flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to IEEE Std 802.11-2016 (16.2.3.4 Long PHY SIGNAL field) all of the following rates are mandatory for a HR/DSSS PHY: 1 Mb/s, 2 Mb/s, 5.5 Mb/s and 11 Mb/s. Set IEEE80211_RATE_MANDATORY_B flag for all of these instead of just 1 Mb/s to correctly reflect this. Signed-off-by: Richard Schütz [johannes: use switch statement] Signed-off-by: Johannes Berg --- net/wireless/util.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 7dcdf67cba29a..7a1fcc6ee0606 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -157,32 +157,30 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) case NL80211_BAND_2GHZ: want = 7; for (i = 0; i < sband->n_bitrates; i++) { - if (sband->bitrates[i].bitrate == 10) { + switch (sband->bitrates[i].bitrate) { + case 10: + case 20: + case 55: + case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate == 20 || - sband->bitrates[i].bitrate == 55 || - sband->bitrates[i].bitrate == 110 || - sband->bitrates[i].bitrate == 60 || - sband->bitrates[i].bitrate == 120 || - sband->bitrates[i].bitrate == 240) { + break; + case 60: + case 120: + case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; - } - - if (sband->bitrates[i].bitrate != 10 && - sband->bitrates[i].bitrate != 20 && - sband->bitrates[i].bitrate != 55 && - sband->bitrates[i].bitrate != 110) + /* fall through */ + default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; + break; + } } - WARN_ON(want != 0 && want != 3 && want != 6); + WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ -- GitLab From 2bc84526d174a2a89c76438f049fc03ac259a159 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 6 Sep 2017 16:44:35 -0600 Subject: [PATCH 0193/1507] Makefile: kselftest and kselftest-clean fail for make O=dir case kselftest and kselftest-clean targets fail when object directory is specified to relocate objects. Fix it so it can find the source tree to build from. make O=/tmp/kselftest_top kselftest make[1]: Entering directory '/tmp/kselftest_top' make[2]: Entering directory '/tmp/kselftest_top' make[2]: *** tools/testing/selftests: No such file or directory. Stop. make[2]: Leaving directory '/tmp/kselftest_top' ./linux-kselftest/Makefile:1185: recipe for target 'kselftest' failed make[1]: *** [kselftest] Error 2 make[1]: Leaving directory '/tmp/kselftest_top' Makefile:145: recipe for target 'sub-make' failed make: *** [sub-make] Error 2 Signed-off-by: Shuah Khan Acked-by: Masahiro Yamada --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 64cbc66cebcaa..9a70578922d3e 100644 --- a/Makefile +++ b/Makefile @@ -1172,11 +1172,11 @@ headers_check: headers_install PHONY += kselftest kselftest: - $(Q)$(MAKE) -C tools/testing/selftests run_tests + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests PHONY += kselftest-clean kselftest-clean: - $(Q)$(MAKE) -C tools/testing/selftests clean + $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean PHONY += kselftest-merge kselftest-merge: -- GitLab From 8050ef2b83a18f628f9501af958fbff39443d58d Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 6 Sep 2017 18:36:22 -0600 Subject: [PATCH 0194/1507] selftests: lib.mk: kselftest and kselftest-clean fail for make O=dir case kselftest and kselftest-clean targets fail when object directory is specified to relocate objects. Main Makefile make O= path clears the built-in defines LINK.c, COMPILE.S, LINK.S, and RM that are used in lib.mk to build and clean targets. Define them. Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 4665463779f5f..266d3ed4bb410 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -7,6 +7,7 @@ OUTPUT := $(shell pwd) endif TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) @@ -62,6 +63,11 @@ endef emit_tests: $(EMIT_TESTS) +# define if isn't already. It is undefined in make O= case. +ifeq ($(RM),) +RM := rm -f +endif + define CLEAN $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef @@ -69,6 +75,15 @@ endef clean: $(CLEAN) +# When make O= with kselftest target from main level +# the following aren't defined. +# +ifneq ($(KBUILD_SRC),) +LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c +LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) +endif + $(OUTPUT)/%:%.c $(LINK.c) $^ $(LDLIBS) -o $@ -- GitLab From 52fd1d082398b928a86d4fdf33c9f3abe1bf7914 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 7 Sep 2017 19:57:43 -0600 Subject: [PATCH 0195/1507] selftests: Makefile: clear LDFLAGS for make O=dir use-case kselftest target fails when object directory is specified to relocate objects. Inherited "LDFLAGS = -m" fails the test builds. Clear it. Signed-off-by: Shuah Khan --- tools/testing/selftests/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 26ce4f7168be5..f4368db011ea2 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -52,6 +52,10 @@ override LDFLAGS = override MAKEFLAGS = endif +ifneq ($(KBUILD_SRC),) +override LDFLAGS = +endif + BUILD := $(O) ifndef BUILD BUILD := $(KBUILD_OUTPUT) -- GitLab From e0a5696a23290c31c5ac2c76f0e7fe50a12c1fc6 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 7 Sep 2017 20:04:26 -0600 Subject: [PATCH 0196/1507] selftests: lib.mk: fix test executable status check to use full path Fix test executable status check to use full path for make O=dir case,m when tests are relocated to user specified object directory. Without the full path, this check fails to find the file and fails the test. Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 266d3ed4bb410..fd1cbbbca8d7b 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -21,7 +21,7 @@ define RUN_TESTS test_num=`echo $$test_num+1 | bc`; \ echo "selftests: $$BASENAME_TEST"; \ echo "========================================"; \ - if [ ! -x $$BASENAME_TEST ]; then \ + if [ ! -x $$TEST ]; then \ echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\ echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \ else \ -- GitLab From e2fb65594cae9a016fab4639a5d22a914f1e16c8 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 8 Sep 2017 16:05:50 -0600 Subject: [PATCH 0197/1507] selftests: watchdog: fix to use TEST_GEN_PROGS and remove clean TEST_PROGS should be used for test scripts that don't ned to be built. Use TEST_GEN_PROGS instead which is intended for test executables. Remove clean target and let the common clean take care of cleaning. Signed-off-by: Shuah Khan --- tools/testing/selftests/watchdog/Makefile | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/testing/selftests/watchdog/Makefile b/tools/testing/selftests/watchdog/Makefile index f863c664e3d14..ee068511fd0bc 100644 --- a/tools/testing/selftests/watchdog/Makefile +++ b/tools/testing/selftests/watchdog/Makefile @@ -1,8 +1,3 @@ -TEST_PROGS := watchdog-test - -all: $(TEST_PROGS) +TEST_GEN_PROGS := watchdog-test include ../lib.mk - -clean: - rm -fr $(TEST_PROGS) -- GitLab From be16a244c199983656e58ddb10d80c67197e502f Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 11 Sep 2017 13:06:33 -0600 Subject: [PATCH 0198/1507] selftests: lib.mk: add TEST_CUSTOM_PROGS to allow custom test run/install Some tests such as sync can't use generic build rules in lib.mk and require custom rules. Currently there is no provision to allow custom builds and test such as sync use TEST_PROGS which is reserved for test shell scripts. Add TEST_CUSTOM_PROGS variable to lib.mk to run and install custom tests built by individual test make files. Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index fd1cbbbca8d7b..b4699c71aee4f 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -6,6 +6,12 @@ ifeq (0,$(MAKELEVEL)) OUTPUT := $(shell pwd) endif +# The following are built by lib.mk common compile rules. +# TEST_CUSTOM_PROGS should be used by tests that require +# custom build rule and prevent common build rule use. +# TEST_PROGS are for test shell scripts. +# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests +# and install targets. Common clean doesn't touch them. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) @@ -31,7 +37,7 @@ define RUN_TESTS endef run_tests: all - $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS)) + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ @@ -39,10 +45,10 @@ define INSTALL_RULE echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ + @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ + echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ fi endef @@ -54,7 +60,7 @@ else endif define EMIT_TESTS - @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \ BASENAME_TEST=`basename $$TEST`; \ echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; -- GitLab From 38f7251852a0cd47f34af4a6f84df0fadafa8ac7 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 11 Sep 2017 13:46:44 -0600 Subject: [PATCH 0199/1507] selftests: sync: use TEST_CUSTOM_PROGS instead of TEST_PROGS lib.mk var TEST_CUSTOM_PROGS is for tests that need custom build rules. TEST_PROGS is used for test shell scripts. Fix it to use TEST_CUSTOM_PROGS. lib.mk will run and install them. Signed-off-by: Shuah Khan --- tools/testing/selftests/sync/Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 4981c6b6d050e..43db80b71e808 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -2,9 +2,11 @@ CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra CFLAGS += -I../../../../usr/include/ LDFLAGS += -pthread -TEST_PROGS = sync_test +# lib.mk TEST_CUSTOM_PROGS var is for custome tests that need special +# build rules. lib.mk will run and install them. +TEST_CUSTOM_PROGS = sync_test -all: $(TEST_PROGS) +all: $(TEST_CUSTOM_PROGS) include ../lib.mk -- GitLab From b2fc6ade9fe2118591e7f51e21b51f65e36f138f Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 11 Sep 2017 14:14:41 -0600 Subject: [PATCH 0200/1507] selftests: sync: kselftest and kselftest-clean fail for make O=dir case sync test fails to build when object directory is specified to relocate object files. Fix it to specify the correct path. Fix clean target to remove objects. Also include simplified logic to use TEST_CUSTOM_PROGS in build and clean targets instead of hard-coding the test name each time. Signed-off-by: Shuah Khan --- tools/testing/selftests/sync/Makefile | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 43db80b71e808..8e04d0afcbd7f 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -2,14 +2,16 @@ CFLAGS += -O2 -g -std=gnu89 -pthread -Wall -Wextra CFLAGS += -I../../../../usr/include/ LDFLAGS += -pthread -# lib.mk TEST_CUSTOM_PROGS var is for custome tests that need special +.PHONY: all clean + +include ../lib.mk + +# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special # build rules. lib.mk will run and install them. -TEST_CUSTOM_PROGS = sync_test +TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test all: $(TEST_CUSTOM_PROGS) -include ../lib.mk - OBJS = sync_test.o sync.o TESTS += sync_alloc.o @@ -20,6 +22,16 @@ TESTS += sync_stress_parallelism.o TESTS += sync_stress_consumer.o TESTS += sync_stress_merge.o -sync_test: $(OBJS) $(TESTS) +OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS)) +TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS)) + +$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) + $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) + +$(OBJS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ + +$(TESTS): $(OUTPUT)/%.o: %.c + $(CC) -c $^ -o $@ -EXTRA_CLEAN := sync_test $(OBJS) $(TESTS) +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) -- GitLab From 1a940687e424080a6ed285f2de8b2f0d018edf3e Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 11 Sep 2017 19:03:11 -0600 Subject: [PATCH 0201/1507] selftests: lib.mk: copy test scripts and test files for make O=dir run For make O=dir run_tests to work, test scripts, test files, and other dependencies need to be copied over to the object directory. Running tests from the object directory is necessary to avoid making the source tree dirty. Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index b4699c71aee4f..f65886af7c0ca 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -37,7 +37,18 @@ define RUN_TESTS endef run_tests: all +ifneq ($(KBUILD_SRC),) + @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then + @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT) + fi + @if [ "X$(TEST_PROGS)" != "X" ]; then + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS)) + else + $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS)) + fi +else $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) +endif define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ -- GitLab From 6af1de2e4ec49635905aaed31d073a0d92c8d3bf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 6 Sep 2017 14:58:53 +0200 Subject: [PATCH 0202/1507] ath10k: mark PM functions as __maybe_unused When CONFIG_PM_SLEEP is disabled, we get a compile-time warning: drivers/net/wireless/ath/ath10k/pci.c:3417:12: error: 'ath10k_pci_pm_resume' defined but not used [-Werror=unused-function] static int ath10k_pci_pm_resume(struct device *dev) ^~~~~~~~~~~~~~~~~~~~ drivers/net/wireless/ath/ath10k/pci.c:3401:12: error: 'ath10k_pci_pm_suspend' defined but not used [-Werror=unused-function] static int ath10k_pci_pm_suspend(struct device *dev) Rather than fixing the #ifdef, this just marks both functions as __maybe_unused, which is a more robust way to do this. Fixes: 32faa3f0ee50 ("ath10k: add the PCI PM core suspend/resume ops") Signed-off-by: Arnd Bergmann Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath10k/pci.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index bc1633945a564..195dafb981314 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3396,9 +3396,7 @@ static void ath10k_pci_remove(struct pci_dev *pdev) MODULE_DEVICE_TABLE(pci, ath10k_pci_id_table); -#ifdef CONFIG_PM - -static int ath10k_pci_pm_suspend(struct device *dev) +static __maybe_unused int ath10k_pci_pm_suspend(struct device *dev) { struct ath10k *ar = dev_get_drvdata(dev); int ret; @@ -3414,7 +3412,7 @@ static int ath10k_pci_pm_suspend(struct device *dev) return ret; } -static int ath10k_pci_pm_resume(struct device *dev) +static __maybe_unused int ath10k_pci_pm_resume(struct device *dev) { struct ath10k *ar = dev_get_drvdata(dev); int ret; @@ -3433,7 +3431,6 @@ static int ath10k_pci_pm_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(ath10k_pci_pm_ops, ath10k_pci_pm_suspend, ath10k_pci_pm_resume); -#endif static struct pci_driver ath10k_pci_driver = { .name = "ath10k_pci", -- GitLab From 2e1c42391ff2556387b3cb6308b24f6f65619feb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 21 Sep 2017 16:58:48 +0200 Subject: [PATCH 0203/1507] USB: core: harden cdc_parse_cdc_header Andrey Konovalov reported a possible out-of-bounds problem for the cdc_parse_cdc_header function. He writes: It looks like cdc_parse_cdc_header() doesn't validate buflen before accessing buffer[1], buffer[2] and so on. The only check present is while (buflen > 0). So fix this issue up by properly validating the buffer length matches what the descriptor says it is. Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 4c38ea41ae969..371a07d874a37 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -2069,6 +2069,10 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, elength = 1; goto next_desc; } + if ((buflen < elength) || (elength < 3)) { + dev_err(&intf->dev, "invalid descriptor buffer length\n"); + break; + } if (buffer[1] != USB_DT_CS_INTERFACE) { dev_err(&intf->dev, "skipping garbage\n"); goto next_desc; -- GitLab From 51a9a8284e43642fc3e85810fd54f4c245d23a14 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 18 Sep 2017 10:03:12 +0100 Subject: [PATCH 0204/1507] x86/xen: clean up clang build warning In the case where sizeof(maddr) != sizeof(long) p is initialized and never read and clang throws a warning on this. Move declaration of p to clean up the clang build warning: warning: Value stored to 'p' during its initialization is never read Signed-off-by: Colin Ian King Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- arch/x86/include/asm/xen/hypercall.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9606688caa4be..e089c1675a7c6 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -552,13 +552,13 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { - u32 *p = (u32 *) &desc; - mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; mcl->args[1] = *(unsigned long *)&desc; } else { + u32 *p = (u32 *)&desc; + mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; mcl->args[2] = *p++; -- GitLab From 127b8e2692b6c145955bb71e482ca1bc6ce10027 Mon Sep 17 00:00:00 2001 From: Gabriel Fernandez Date: Tue, 19 Sep 2017 13:44:06 +0200 Subject: [PATCH 0205/1507] dt-bindings: clk: stm32h7: fix clock-cell size The clock-cell size is 1 on stm32h7 plaform. Signed-off-by: Gabriel Fernandez Fixes: 3e4d618b0722 ("clk: stm32h7: Add stm32h743 clock driver") Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt index a135504c7d571..cac24ee10b72e 100644 --- a/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt +++ b/Documentation/devicetree/bindings/clock/st,stm32h7-rcc.txt @@ -32,7 +32,7 @@ Example: compatible = "st,stm32h743-rcc", "st,stm32-rcc"; reg = <0x58024400 0x400>; #reset-cells = <1>; - #clock-cells = <2>; + #clock-cells = <1>; clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s_ckin>; st,syscfg = <&pwrcfg>; -- GitLab From 4ba72fc080ad44a5c1e93449ec070cd4d331803f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 21 Sep 2017 22:34:54 +0200 Subject: [PATCH 0206/1507] drm/sun4i: cec: Enable back CEC-pin framework Now that the cec-pin framework has been merged, we can remove the safeguard that were preventing the CEC part of the sun4i HDMI driver and actually start to use it. Signed-off-by: Hans Verkuil Signed-off-by: Maxime Ripard --- drivers/gpu/drm/sun4i/Kconfig | 2 +- drivers/gpu/drm/sun4i/sun4i_hdmi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig index 06f05302ee75e..882d85db90539 100644 --- a/drivers/gpu/drm/sun4i/Kconfig +++ b/drivers/gpu/drm/sun4i/Kconfig @@ -26,7 +26,7 @@ config DRM_SUN4I_HDMI_CEC bool "Allwinner A10 HDMI CEC Support" depends on DRM_SUN4I_HDMI select CEC_CORE - depends on CEC_PIN + select CEC_PIN help Choose this option if you have an Allwinner SoC with an HDMI controller and want to use CEC. diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index 1457750988da4..a1f8cba251a24 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -15,7 +15,7 @@ #include #include -#include +#include #define SUN4I_HDMI_CTRL_REG 0x004 #define SUN4I_HDMI_CTRL_ENABLE BIT(31) -- GitLab From a4fd4a724d6c30ad671046d83be2e9be2f11d275 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 21 Sep 2017 16:02:05 -0400 Subject: [PATCH 0207/1507] usb-storage: fix bogus hardware error messages for ATA pass-thru devices Ever since commit a621bac3044e ("scsi_lib: correctly retry failed zero length REQ_TYPE_FS commands"), people have been getting bogus error messages for USB disk drives using ATA pass-thru. For example: [ 1344.880193] sd 6:0:0:0: [sdb] Attached SCSI disk [ 1345.069152] sd 6:0:0:0: [sdb] tag#0 FAILED Result: hostbyte=DID_ERROR driverbyte=DRIVER_SENSE [ 1345.069159] sd 6:0:0:0: [sdb] tag#0 Sense Key : Hardware Error [current] [descriptor] [ 1345.069162] sd 6:0:0:0: [sdb] tag#0 Add. Sense: No additional sense information [ 1345.069168] sd 6:0:0:0: [sdb] tag#0 CDB: ATA command pass through(16) 85 06 20 00 00 00 00 00 00 00 00 00 00 00 e5 00 [ 1345.172252] sd 6:0:0:0: [sdb] tag#0 FAILED Result: hostbyte=DID_ERROR driverbyte=DRIVER_SENSE [ 1345.172258] sd 6:0:0:0: [sdb] tag#0 Sense Key : Hardware Error [current] [descriptor] [ 1345.172261] sd 6:0:0:0: [sdb] tag#0 Add. Sense: No additional sense information [ 1345.172266] sd 6:0:0:0: [sdb] tag#0 CDB: ATA command pass through(12)/Blank a1 06 20 da 00 00 4f c2 00 b0 00 00 These messages can be quite annoying, because programs like udisks2 provoke them every 10 minutes or so. Other programs can also have this effect, such as those in smartmontools. I don't fully understand how that commit induced the SCSI core to log these error messages, but the underlying cause for them is code added to usb-storage by commit f1a0743bc0e7 ("USB: storage: When a device returns no sense data, call it a Hardware Error"). At the time it was necessary to do this, in order to prevent an infinite retry loop with some not-so-great mass storage devices. However, the ATA pass-thru protocol uses SCSI sense data to return command status values, and some devices always report Check Condition status for ATA pass-thru commands to ensure that the host retrieves the sense data, even if the command succeeded. This violates the USB mass-storage protocol (Check Condition status is supposed to mean the command failed), but we can't help that. This patch attempts to mitigate the problem of these bogus error reports by changing usb-storage. The HARDWARE ERROR sense key will be inserted only for commands that aren't ATA pass-thru. Thanks to Ewan Milne for pointing out that this mechanism was present in usb-storage. 8 years after writing it, I had completely forgotten its existence. Signed-off-by: Alan Stern Tested-by: Kris Lindgren Ref: https://bugzilla.redhat.com/show_bug.cgi?id=1351305 CC: Ewan D. Milne CC: Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/transport.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 1a59f335b063e..a3ccb899df60c 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -834,13 +834,25 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us) if (result == USB_STOR_TRANSPORT_GOOD) { srb->result = SAM_STAT_GOOD; srb->sense_buffer[0] = 0x0; + } + + /* + * ATA-passthru commands use sense data to report + * the command completion status, and often devices + * return Check Condition status when nothing is + * wrong. + */ + else if (srb->cmnd[0] == ATA_16 || + srb->cmnd[0] == ATA_12) { + /* leave the data alone */ + } /* * If there was a problem, report an unspecified * hardware error to prevent the higher layers from * entering an infinite retry loop. */ - } else { + else { srb->result = DID_ERROR << 16; if ((sshdr.response_code & 0x72) == 0x72) srb->sense_buffer[1] = HARDWARE_ERROR; -- GitLab From 113f6eb6d50cfa5e2a1cdcf1678b12661fa272ab Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 21 Sep 2017 15:59:30 -0400 Subject: [PATCH 0208/1507] usb-storage: unusual_devs entry to fix write-access regression for Seagate external drives Kris Lindgren reports that without the NO_WP_DETECT flag, his Seagate external disk drive fails all write accesses. This regresssion dates back approximately to the start of the 4.x kernel releases. Signed-off-by: Alan Stern Reported-by: Kris Lindgren CC: Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/unusual_devs.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 5a70c33ef0e06..eb06d88b41d69 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1459,6 +1459,13 @@ UNUSUAL_DEV( 0x0bc2, 0x3010, 0x0000, 0x0000, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_SANE_SENSE ), +/* Reported by Kris Lindgren */ +UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999, + "Seagate", + "External", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT ), + UNUSUAL_DEV( 0x0d49, 0x7310, 0x0000, 0x9999, "Maxtor", "USB to SATA", -- GitLab From fd085bb1766d6a598f53af2308374a546a49775a Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 19 Sep 2017 18:47:40 +0300 Subject: [PATCH 0209/1507] stm class: Fix a use-after-free For reasons unknown, the stm_source removal path uses device_destroy() to kill the underlying device object. Because device_destroy() uses devt to look for the device to destroy and the fact that stm_source devices don't have one (or all have the same one), it just picks the first device in the class, which may well be the wrong one. That is, loading stm_console and stm_heartbeat and then removing both will die in dereferencing a freed object. Since this should have been device_unregister() in the first place, use it instead of device_destroy(). Signed-off-by: Alexander Shishkin Fixes: 7bd1d4093c2 ("stm class: Introduce an abstraction for System Trace Module devices") Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/stm/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 9414900575d86..f129869e05a9b 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -1119,7 +1119,7 @@ void stm_source_unregister_device(struct stm_source_data *data) stm_source_link_drop(src); - device_destroy(&stm_source_class, src->dev.devt); + device_unregister(&src->dev); } EXPORT_SYMBOL_GPL(stm_source_unregister_device); -- GitLab From 920ce7c33db25cf4acb4ade3ae8c93bd23dfd730 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 19 Sep 2017 18:47:41 +0300 Subject: [PATCH 0210/1507] intel_th: pci: Add Cedar Fork PCH support This adds Intel(R) Trace Hub PCI ID for Cedar Fork PCH. Signed-off-by: Alexander Shishkin Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index bc9cebc305261..00ee60d9789e6 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -158,6 +158,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9da6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Cedar Fork PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x18e1), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; -- GitLab From 24600840c74112ad04a9ddd99d7d7f731dcaa1cb Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 19 Sep 2017 18:47:42 +0300 Subject: [PATCH 0211/1507] intel_th: pci: Add Lewisburg PCH support This adds Intel(R) Trace Hub PCI ID for Lewisburg PCH. Signed-off-by: Alexander Shishkin Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 00ee60d9789e6..c2a2ce8ee5410 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -143,6 +143,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x19e1), .driver_data = (kernel_ulong_t)0, }, + { + /* Lewisburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa1a6), + .driver_data = (kernel_ulong_t)0, + }, { /* Gemini Lake */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e), -- GitLab From 33c150c2ee4a65a59190a124b45d05b1abf9478e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 21 Sep 2017 23:41:47 -0700 Subject: [PATCH 0212/1507] vmbus: don't acquire the mutex in vmbus_hvsock_device_unregister() Due to commit 54a66265d675 ("Drivers: hv: vmbus: Fix rescind handling"), we need this patch to resolve the below deadlock: after we get the mutex in vmbus_hvsock_device_unregister() and call vmbus_device_unregister() -> device_unregister() -> ... -> device_release() -> vmbus_device_release(), we'll get a deadlock, because vmbus_device_release() tries to get the same mutex. Signed-off-by: Dexuan Cui Cc: K. Y. Srinivasan Cc: Haiyang Zhang Cc: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Cc: stable@vger.kernel.org (4.13 and above) Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 060df71c2e8b7..bcbb031f72631 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -936,14 +936,10 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) void vmbus_hvsock_device_unregister(struct vmbus_channel *channel) { - mutex_lock(&vmbus_connection.channel_mutex); - BUG_ON(!is_hvsock_channel(channel)); channel->rescind = true; vmbus_device_unregister(channel->device_obj); - - mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_hvsock_device_unregister); -- GitLab From 549e658a0919e355a2b2144dc380b3729bef7f3e Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Thu, 21 Sep 2017 23:41:48 -0700 Subject: [PATCH 0213/1507] Drivers: hv: fcopy: restore correct transfer length Till recently the expected length of bytes read by the daemon did depend on the context. It was either hv_start_fcopy or hv_do_fcopy. The daemon had a buffer size of two pages, which was much larger than needed. Now the expected length of bytes read by the daemon changed slightly. For START_FILE_COPY it is still the size of hv_start_fcopy. But for WRITE_TO_FILE and the other operations it is as large as the buffer that arrived via vmbus. In case of WRITE_TO_FILE that is slightly larger than a struct hv_do_fcopy. Since the buffer in the daemon was still larger everything was fine. Currently, the daemon reads only what is actually needed. The new buffer layout is as large as a struct hv_do_fcopy, for the WRITE_TO_FILE operation. Since the kernel expects a slightly larger size, hvt_op_read will return -EINVAL because the daemon will read slightly less than expected. Address this by restoring the expected buffer size in case of WRITE_TO_FILE. Fixes: 'c7e490fc23eb ("Drivers: hv: fcopy: convert to hv_utils_transport")' Fixes: '3f2baa8a7d2e ("Tools: hv: update buffer handling in hv_fcopy_daemon")' Signed-off-by: Olaf Hering Signed-off-by: K. Y. Srinivasan Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hv_fcopy.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index daa75bd41f867..2364281d8593e 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -170,6 +170,10 @@ static void fcopy_send_data(struct work_struct *dummy) out_src = smsg_out; break; + case WRITE_TO_FILE: + out_src = fcopy_transaction.fcopy_msg; + out_len = sizeof(struct hv_do_fcopy); + break; default: out_src = fcopy_transaction.fcopy_msg; out_len = fcopy_transaction.recv_len; -- GitLab From 44889942b6eb356eab27ce25fe10701adfec7776 Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Fri, 22 Sep 2017 07:53:15 +0200 Subject: [PATCH 0214/1507] KVM: nVMX: fix HOST_CR3/HOST_CR4 cache For nested virt we maintain multiple VMCS that can run on a vCPU. So it is incorrect to keep vmcs_host_cr3 and vmcs_host_cr4, whose purpose is caching the value of the rarely changing HOST_CR3 and HOST_CR4 VMCS fields, in vCPU-wide data structures. Hyper-V nested on KVM runs into this consistently for me with PCID enabled. CR3 is updated with a new value, unlikely(cr3 != vmx->host_state.vmcs_host_cr3) fires, and the currently loaded VMCS is updated. Then we switch from L2 to L1 and the next exit reverts CR3 to its old value. Fixes: d6e41f1151fe ("x86/mm, KVM: Teach KVM's VMX code that CR3 isn't a constant") Signed-off-by: Ladi Prosek Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0726ca7a1b029..c83d28b0ab056 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -200,6 +200,8 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ struct list_head loaded_vmcss_on_cpu_link; }; @@ -600,8 +602,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -5178,12 +5178,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -9274,15 +9274,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the -- GitLab From e001fa78d44d0b5c7b1498d1e4a038740efa3b1e Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 15 Sep 2017 15:26:14 +1000 Subject: [PATCH 0215/1507] KVM: PPC: Book3S HV: Check for updated HDSISR on P9 HDSI exception On POWER9 DD2.1 and below, sometimes on a Hypervisor Data Storage Interrupt (HDSI) the HDSISR is not be updated at all. To work around this we put a canary value into the HDSISR before returning to a guest and then check for this canary when we take a HDSI. If we find the canary on a HDSI, we know the hardware didn't update the HDSISR. In this case we return to the guest to retake the HDSI which should correctly update the HDSISR the second time HDSI entry. After talking to Paulus we've applied this workaround to all POWER9 CPUs. The workaround of returning to the guest shouldn't ever be triggered on well behaving CPU. The extra instructions should have negligible performance impact. Signed-off-by: Michael Neuling Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 17936f82d3c78..ec69fa45d5a2f 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1121,6 +1121,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) BEGIN_FTR_SECTION mtspr SPRN_PPR, r0 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + +/* Move canary into DSISR to check for later */ +BEGIN_FTR_SECTION + li r0, 0x7fff + mtspr SPRN_HDSISR, r0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) @@ -1956,9 +1963,14 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) kvmppc_hdsi: ld r3, VCPU_KVM(r9) lbz r0, KVM_RADIX(r3) - cmpwi r0, 0 mfspr r4, SPRN_HDAR mfspr r6, SPRN_HDSISR +BEGIN_FTR_SECTION + /* Look for DSISR canary. If we find it, retry instruction */ + cmpdi r6, 0x7fff + beq 6f +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) + cmpwi r0, 0 bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */ /* HPTE not found fault or protection fault? */ andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h -- GitLab From e87be9b29c22852ec300826e3b1d551b00c1eb7a Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 14 Sep 2017 14:30:43 +0200 Subject: [PATCH 0216/1507] mmc: tmio: remove broken and noisy debug macro Some change for v4.14 broke the debug output for TMIO. But since it was not helpful to me and too noisy for my taste anyhow, let's just remove it instead of fixing it. We'll find something better if we'd need it... Signed-off-by: Wolfram Sang Signed-off-by: Ulf Hansson --- drivers/mmc/host/tmio_mmc_core.c | 47 -------------------------------- 1 file changed, 47 deletions(-) diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 12cf8288d6635..a7293e186e03f 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -129,50 +129,6 @@ static int tmio_mmc_next_sg(struct tmio_mmc_host *host) #define CMDREQ_TIMEOUT 5000 -#ifdef CONFIG_MMC_DEBUG - -#define STATUS_TO_TEXT(a, status, i) \ - do { \ - if ((status) & TMIO_STAT_##a) { \ - if ((i)++) \ - printk(KERN_DEBUG " | "); \ - printk(KERN_DEBUG #a); \ - } \ - } while (0) - -static void pr_debug_status(u32 status) -{ - int i = 0; - - pr_debug("status: %08x = ", status); - STATUS_TO_TEXT(CARD_REMOVE, status, i); - STATUS_TO_TEXT(CARD_INSERT, status, i); - STATUS_TO_TEXT(SIGSTATE, status, i); - STATUS_TO_TEXT(WRPROTECT, status, i); - STATUS_TO_TEXT(CARD_REMOVE_A, status, i); - STATUS_TO_TEXT(CARD_INSERT_A, status, i); - STATUS_TO_TEXT(SIGSTATE_A, status, i); - STATUS_TO_TEXT(CMD_IDX_ERR, status, i); - STATUS_TO_TEXT(STOPBIT_ERR, status, i); - STATUS_TO_TEXT(ILL_FUNC, status, i); - STATUS_TO_TEXT(CMD_BUSY, status, i); - STATUS_TO_TEXT(CMDRESPEND, status, i); - STATUS_TO_TEXT(DATAEND, status, i); - STATUS_TO_TEXT(CRCFAIL, status, i); - STATUS_TO_TEXT(DATATIMEOUT, status, i); - STATUS_TO_TEXT(CMDTIMEOUT, status, i); - STATUS_TO_TEXT(RXOVERFLOW, status, i); - STATUS_TO_TEXT(TXUNDERRUN, status, i); - STATUS_TO_TEXT(RXRDY, status, i); - STATUS_TO_TEXT(TXRQ, status, i); - STATUS_TO_TEXT(ILL_ACCESS, status, i); - printk("\n"); -} - -#else -#define pr_debug_status(s) do { } while (0) -#endif - static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable) { struct tmio_mmc_host *host = mmc_priv(mmc); @@ -762,9 +718,6 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS); ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask; - pr_debug_status(status); - pr_debug_status(ireg); - /* Clear the status except the interrupt status */ sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ); -- GitLab From c51b46dd5b9950436b6b1f8189e93e1ad380cee1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 20 Sep 2017 22:19:57 +0100 Subject: [PATCH 0217/1507] staging: rtl8723bs: add missing range check on id The value of the u8 id needs to be upper bounds checked to ensure the cam_cache array on the adapter dvobj is not indexed outside of the allowed range of 0..TOTAL_CAM_ENTRY-1. This can currently occur if id is >= TOTAL_CAM_ENTRY when calling write_cam_from_cache. Fix this by adding an upper range check. Detected by CoverityScan, CID#1428464 ("Use of untrusted scalar value") Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver") Signed-off-by: Colin Ian King Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/os_dep/rtw_proc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c index 92277457aba4e..ce1dd6f9036fd 100644 --- a/drivers/staging/rtl8723bs/os_dep/rtw_proc.c +++ b/drivers/staging/rtl8723bs/os_dep/rtw_proc.c @@ -311,6 +311,8 @@ static ssize_t proc_set_cam(struct file *file, const char __user *buffer, size_t if (num < 2) return count; + if (id >= TOTAL_CAM_ENTRY) + return -EINVAL; if (strcmp("c", cmd) == 0) { _clear_cam_entry(adapter, id); -- GitLab From ec14121931a24f8d3678b8a9c408adee3b21d465 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 20 Sep 2017 18:34:18 +0100 Subject: [PATCH 0218/1507] staging: rtl8723bs: avoid null pointer dereference on pmlmepriv There is a check to see if pmlmepriv is null before vfree'ing pmlmepriv->free_bss_buf hence implying pmlmepriv could potenially be null. However, a previous call to rtw_free_mlme_priv_ie_data can also dereference pmlmepriv, so move this call so that it is only called if pmlmepriv non-null. Detected by CoverityScan, CID#1077739 ("Dereference before null check") Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver") Signed-off-by: Colin Ian King Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 6b778206a1a36..cb8a95aabd6c2 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -119,9 +119,8 @@ void rtw_free_mlme_priv_ie_data(struct mlme_priv *pmlmepriv) void _rtw_free_mlme_priv(struct mlme_priv *pmlmepriv) { - rtw_free_mlme_priv_ie_data(pmlmepriv); - if (pmlmepriv) { + rtw_free_mlme_priv_ie_data(pmlmepriv); if (pmlmepriv->free_bss_buf) { vfree(pmlmepriv->free_bss_buf); } -- GitLab From 6ae033689d7b1a419def78e8e990b0eab8bb6419 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 18 Sep 2017 15:16:08 +0300 Subject: [PATCH 0219/1507] mmc: sdhci-pci: Fix voltage switch for some Intel host controllers Some Intel host controllers (e.g. CNP) use an ACPI device-specific method to ensure correct voltage switching. Fix voltage switch for those, by adding a call to the DSM. Signed-off-by: Adrian Hunter Cc: stable@vger.kernel.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-pci-core.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index bbaddf18a1b3c..d0ccc6729fd29 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -392,6 +392,7 @@ static const struct sdhci_pci_fixes sdhci_intel_pch_sdio = { enum { INTEL_DSM_FNS = 0, + INTEL_DSM_V18_SWITCH = 3, INTEL_DSM_DRV_STRENGTH = 9, INTEL_DSM_D3_RETUNE = 10, }; @@ -557,6 +558,19 @@ static void intel_hs400_enhanced_strobe(struct mmc_host *mmc, sdhci_writel(host, val, INTEL_HS400_ES_REG); } +static void sdhci_intel_voltage_switch(struct sdhci_host *host) +{ + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct intel_host *intel_host = sdhci_pci_priv(slot); + struct device *dev = &slot->chip->pdev->dev; + u32 result = 0; + int err; + + err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result); + pr_debug("%s: %s DSM error %d result %u\n", + mmc_hostname(host->mmc), __func__, err, result); +} + static const struct sdhci_ops sdhci_intel_byt_ops = { .set_clock = sdhci_set_clock, .set_power = sdhci_intel_set_power, @@ -565,6 +579,7 @@ static const struct sdhci_ops sdhci_intel_byt_ops = { .reset = sdhci_reset, .set_uhs_signaling = sdhci_set_uhs_signaling, .hw_reset = sdhci_pci_hw_reset, + .voltage_switch = sdhci_intel_voltage_switch, }; static void byt_read_dsm(struct sdhci_pci_slot *slot) -- GitLab From c9adcdbc653b52e4be834f535eefec833f9ca6b1 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 21 Sep 2017 14:03:29 +0800 Subject: [PATCH 0220/1507] ALSA: pcm: Fix structure definition for X32 ABI X32 ABI uses the 64bit timespec in addition to 64bit alignment of 64bit values. We have added compat ABI for these ioctls, but this patch adds one missing padding into 'struct snd_pcm_mmap_status_x32' to fix incompatibilities. Signed-off-by: Baolin Wang Signed-off-by: Takashi Iwai --- sound/core/pcm_compat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index 3a1cc7b97e468..b719d0bd833ec 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -547,6 +547,7 @@ struct snd_pcm_mmap_status_x32 { u32 pad2; /* alignment */ struct timespec tstamp; s32 suspended_state; + s32 pad3; struct timespec audio_tstamp; } __packed; -- GitLab From bfc81a8bc18e3c4ba0cbaa7666ff76be2f998991 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 22 Sep 2017 16:18:53 +0200 Subject: [PATCH 0221/1507] ALSA: usb-audio: Check out-of-bounds access by corrupted buffer descriptor When a USB-audio device receives a maliciously adjusted or corrupted buffer descriptor, the USB-audio driver may access an out-of-bounce value at its parser. This was detected by syzkaller, something like: BUG: KASAN: slab-out-of-bounds in usb_audio_probe+0x27b2/0x2ab0 Read of size 1 at addr ffff88006b83a9e8 by task kworker/0:1/24 CPU: 0 PID: 24 Comm: kworker/0:1 Not tainted 4.14.0-rc1-42251-gebb2c2437d80 #224 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Workqueue: usb_hub_wq hub_event Call Trace: __dump_stack lib/dump_stack.c:16 dump_stack+0x292/0x395 lib/dump_stack.c:52 print_address_description+0x78/0x280 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 kasan_report+0x22f/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x19/0x20 mm/kasan/report.c:427 snd_usb_create_streams sound/usb/card.c:248 usb_audio_probe+0x27b2/0x2ab0 sound/usb/card.c:605 usb_probe_interface+0x35d/0x8e0 drivers/usb/core/driver.c:361 really_probe drivers/base/dd.c:413 driver_probe_device+0x610/0xa00 drivers/base/dd.c:557 __device_attach_driver+0x230/0x290 drivers/base/dd.c:653 bus_for_each_drv+0x161/0x210 drivers/base/bus.c:463 __device_attach+0x26e/0x3d0 drivers/base/dd.c:710 device_initial_probe+0x1f/0x30 drivers/base/dd.c:757 bus_probe_device+0x1eb/0x290 drivers/base/bus.c:523 device_add+0xd0b/0x1660 drivers/base/core.c:1835 usb_set_configuration+0x104e/0x1870 drivers/usb/core/message.c:1932 generic_probe+0x73/0xe0 drivers/usb/core/generic.c:174 usb_probe_device+0xaf/0xe0 drivers/usb/core/driver.c:266 really_probe drivers/base/dd.c:413 driver_probe_device+0x610/0xa00 drivers/base/dd.c:557 __device_attach_driver+0x230/0x290 drivers/base/dd.c:653 bus_for_each_drv+0x161/0x210 drivers/base/bus.c:463 __device_attach+0x26e/0x3d0 drivers/base/dd.c:710 device_initial_probe+0x1f/0x30 drivers/base/dd.c:757 bus_probe_device+0x1eb/0x290 drivers/base/bus.c:523 device_add+0xd0b/0x1660 drivers/base/core.c:1835 usb_new_device+0x7b8/0x1020 drivers/usb/core/hub.c:2457 hub_port_connect drivers/usb/core/hub.c:4903 hub_port_connect_change drivers/usb/core/hub.c:5009 port_event drivers/usb/core/hub.c:5115 hub_event+0x194d/0x3740 drivers/usb/core/hub.c:5195 process_one_work+0xc7f/0x1db0 kernel/workqueue.c:2119 worker_thread+0x221/0x1850 kernel/workqueue.c:2253 kthread+0x3a1/0x470 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:431 This patch adds the checks of out-of-bounce accesses at appropriate places and bails out when it goes out of the given buffer. Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: Signed-off-by: Takashi Iwai --- sound/usb/card.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/sound/usb/card.c b/sound/usb/card.c index 3dc36d9135502..23d1d23aefec3 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -221,6 +221,7 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) struct usb_interface_descriptor *altsd; void *control_header; int i, protocol; + int rest_bytes; /* find audiocontrol interface */ host_iface = &usb_ifnum_to_if(dev, ctrlif)->altsetting[0]; @@ -235,6 +236,15 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) return -EINVAL; } + rest_bytes = (void *)(host_iface->extra + host_iface->extralen) - + control_header; + + /* just to be sure -- this shouldn't hit at all */ + if (rest_bytes <= 0) { + dev_err(&dev->dev, "invalid control header\n"); + return -EINVAL; + } + switch (protocol) { default: dev_warn(&dev->dev, @@ -245,11 +255,21 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif) case UAC_VERSION_1: { struct uac1_ac_header_descriptor *h1 = control_header; + if (rest_bytes < sizeof(*h1)) { + dev_err(&dev->dev, "too short v1 buffer descriptor\n"); + return -EINVAL; + } + if (!h1->bInCollection) { dev_info(&dev->dev, "skipping empty audio interface (v1)\n"); return -EINVAL; } + if (rest_bytes < h1->bLength) { + dev_err(&dev->dev, "invalid buffer length (v1)\n"); + return -EINVAL; + } + if (h1->bLength < sizeof(*h1) + h1->bInCollection) { dev_err(&dev->dev, "invalid UAC_HEADER (v1)\n"); return -EINVAL; -- GitLab From c4fa6c43ce4b427350cfbb659436bfe3d9e09a1d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 21 Sep 2017 09:54:13 -0400 Subject: [PATCH 0222/1507] cgroup: Reinit cgroup_taskset structure before cgroup_migrate_execute() returns The cgroup_taskset structure within the larger cgroup_mgctx structure is supposed to be used once and then discarded. That is not really the case in the hotplug code path: cpuset_hotplug_workfn() - cgroup_transfer_tasks() - cgroup_migrate() - cgroup_migrate_add_task() - cgroup_migrate_execute() In this case, the cgroup_migrate() function is called multiple time with the same cgroup_mgctx structure to transfer the tasks from one cgroup to another one-by-one. The second time cgroup_migrate() is called, the cgroup_taskset will be in an incorrect state and so may cause the system to panic. For example, [ 150.888410] Faulting instruction address: 0xc0000000001db648 [ 150.888414] Oops: Kernel access of bad area, sig: 11 [#1] [ 150.888417] SMP NR_CPUS=2048 [ 150.888417] NUMA [ 150.888419] pSeries : [ 150.888545] NIP [c0000000001db648] cpuset_can_attach+0x58/0x1b0 [ 150.888548] LR [c0000000001db638] cpuset_can_attach+0x48/0x1b0 [ 150.888551] Call Trace: [ 150.888554] [c0000005f65cb940] [c0000000001db638] cpuset_can_attach+0x48/0x1b 0 (unreliable) [ 150.888559] [c0000005f65cb9a0] [c0000000001cff04] cgroup_migrate_execute+0xc4/0x4b0 [ 150.888563] [c0000005f65cba20] [c0000000001d7d14] cgroup_transfer_tasks+0x1d4/0x370 [ 150.888568] [c0000005f65cbb70] [c0000000001ddcb0] cpuset_hotplug_workfn+0x710/0x8f0 [ 150.888572] [c0000005f65cbc80] [c00000000012032c] process_one_work+0x1ac/0x4d0 [ 150.888576] [c0000005f65cbd20] [c0000000001206f8] worker_thread+0xa8/0x5b0 [ 150.888580] [c0000005f65cbdc0] [c0000000001293f8] kthread+0x168/0x1b0 [ 150.888584] [c0000005f65cbe30] [c00000000000b368] ret_from_kernel_thread+0x5c/0x74 To allow reuse of the cgroup_mgctx structure, some fields in that structure are now re-initialized at the end of cgroup_migrate_execute() function call so that the structure can be reused again in a later iteration without causing problem. This bug was introduced in the commit e595cd706982 ("group: track migration context in cgroup_mgctx") in 4.11. This commit moves the cgroup_taskset initialization out of cgroup_migrate(). The commit 10467270fb3 ("cgroup: don't call migration methods if there are no tasks to migrate") helped, but did not completely resolve the problem. Fixes: e595cd706982bff0211e6fafe5a108421e747fbc ("group: track migration context in cgroup_mgctx") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v4.11+ --- kernel/cgroup/cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd452380..44857278eb8aa 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } -- GitLab From 786de92b3cb26012d3d0f00ee37adf14527f35c4 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 22 Sep 2017 11:56:49 -0400 Subject: [PATCH 0223/1507] USB: uas: fix bug in handling of alternate settings The uas driver has a subtle bug in the way it handles alternate settings. The uas_find_uas_alt_setting() routine returns an altsetting value (the bAlternateSetting number in the descriptor), but uas_use_uas_driver() then treats that value as an index to the intf->altsetting array, which it isn't. Normally this doesn't cause any problems because the various alternate settings have bAlternateSetting values 0, 1, 2, ..., so the value is equal to the index in the array. But this is not guaranteed, and Andrey Konovalov used the syzkaller fuzzer with KASAN to get a slab-out-of-bounds error by violating this assumption. This patch fixes the bug by making uas_find_uas_alt_setting() return a pointer to the altsetting entry rather than either the value or the index. Pointers are less subject to misinterpretation. Signed-off-by: Alan Stern Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov CC: Oliver Neukum CC: Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/uas-detect.h | 15 ++++++++------- drivers/usb/storage/uas.c | 10 +++++----- 2 files changed, 13 insertions(+), 12 deletions(-) diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index f58caa9e6a27e..a155cd02bce24 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -9,7 +9,8 @@ static int uas_is_interface(struct usb_host_interface *intf) intf->desc.bInterfaceProtocol == USB_PR_UAS); } -static int uas_find_uas_alt_setting(struct usb_interface *intf) +static struct usb_host_interface *uas_find_uas_alt_setting( + struct usb_interface *intf) { int i; @@ -17,10 +18,10 @@ static int uas_find_uas_alt_setting(struct usb_interface *intf) struct usb_host_interface *alt = &intf->altsetting[i]; if (uas_is_interface(alt)) - return alt->desc.bAlternateSetting; + return alt; } - return -ENODEV; + return NULL; } static int uas_find_endpoints(struct usb_host_interface *alt, @@ -58,14 +59,14 @@ static int uas_use_uas_driver(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); struct usb_hcd *hcd = bus_to_hcd(udev->bus); unsigned long flags = id->driver_info; - int r, alt; - + struct usb_host_interface *alt; + int r; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) + if (!alt) return 0; - r = uas_find_endpoints(&intf->altsetting[alt], eps); + r = uas_find_endpoints(alt, eps); if (r < 0) return 0; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index cfb1e3bbd4347..63cf981ed81cf 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -873,14 +873,14 @@ MODULE_DEVICE_TABLE(usb, uas_usb_ids); static int uas_switch_interface(struct usb_device *udev, struct usb_interface *intf) { - int alt; + struct usb_host_interface *alt; alt = uas_find_uas_alt_setting(intf); - if (alt < 0) - return alt; + if (!alt) + return -ENODEV; - return usb_set_interface(udev, - intf->altsetting[0].desc.bInterfaceNumber, alt); + return usb_set_interface(udev, alt->desc.bInterfaceNumber, + alt->desc.bAlternateSetting); } static int uas_configure_endpoints(struct uas_dev_info *devinfo) -- GitLab From 6e76c01e71551cb221c1f3deacb9dcd9a7346784 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 21 Sep 2017 16:12:01 -0400 Subject: [PATCH 0224/1507] USB: gadgetfs: fix copy_to_user while holding spinlock The gadgetfs driver as a long-outstanding FIXME, regarding a call of copy_to_user() made while holding a spinlock. This patch fixes the issue by dropping the spinlock and using the dev->udc_usage mechanism introduced by another recent patch to guard against status changes while the lock isn't held. Signed-off-by: Alan Stern Reported-by: Andrey Konovalov CC: Acked-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 684900fcfe24c..956b3dc7c3a4d 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -983,11 +983,14 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); -// FIXME don't call this with the spinlock held ... + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; + spin_lock_irq(&dev->lock); + --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } -- GitLab From 520b72fc64debf8a86c3853b8e486aa5982188f0 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 21 Sep 2017 13:23:58 -0400 Subject: [PATCH 0225/1507] USB: gadgetfs: Fix crash caused by inadequate synchronization The gadgetfs driver (drivers/usb/gadget/legacy/inode.c) was written before the UDC and composite frameworks were adopted; it is a legacy driver. As such, it expects that once bound to a UDC controller, it will not be unbound until it unregisters itself. However, the UDC framework does unbind function drivers while they are still registered. When this happens, it can cause the gadgetfs driver to misbehave or crash. For example, userspace can cause a crash by opening the device file and doing an ioctl call before setting up a configuration (found by Andrey Konovalov using the syzkaller fuzzer). This patch adds checks and synchronization to prevent these bad behaviors. It adds a udc_usage counter that the driver increments at times when it is using a gadget interface without holding the private spinlock. The unbind routine waits for this counter to go to 0 before returning, thereby ensuring that the UDC is no longer in use. The patch also adds a check in the dev_ioctl() routine to make sure the driver is bound to a UDC before dereferencing the gadget pointer, and it makes destroy_ep_files() synchronize with the endpoint I/O routines, to prevent the user from accessing an endpoint data structure after it has been removed. Signed-off-by: Alan Stern Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov CC: Acked-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/legacy/inode.c | 41 +++++++++++++++++++++++++++---- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 956b3dc7c3a4d..5c28bee327e15 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -28,7 +28,7 @@ #include #include #include - +#include #include #include @@ -116,6 +116,7 @@ enum ep0_state { struct dev_data { spinlock_t lock; refcount_t count; + int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; @@ -513,9 +514,9 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } - spin_unlock(&epdata->dev->lock); usb_ep_free_request(ep, req); + spin_unlock(&epdata->dev->lock); put_ep(epdata); } @@ -939,9 +940,11 @@ ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { + ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); + --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; @@ -1134,6 +1137,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; + ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; @@ -1145,6 +1149,7 @@ ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) GFP_KERNEL); } spin_lock_irq(&dev->lock); + --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else @@ -1246,9 +1251,21 @@ static long dev_ioctl (struct file *fd, unsigned code, unsigned long value) struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; - if (gadget->ops->ioctl) + spin_lock_irq(&dev->lock); + if (dev->state == STATE_DEV_OPENED || + dev->state == STATE_DEV_UNBOUND) { + /* Not bound to a UDC */ + } else if (gadget->ops->ioctl) { + ++dev->udc_usage; + spin_unlock_irq(&dev->lock); + ret = gadget->ops->ioctl (gadget, code, value); + spin_lock_irq(&dev->lock); + --dev->udc_usage; + } + spin_unlock_irq(&dev->lock); + return ret; } @@ -1466,10 +1483,12 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) if (value < 0) break; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); + --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; @@ -1493,8 +1512,12 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) req->length = value; req->zero = value < w_length; + ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); + spin_lock(&dev->lock); + --dev->udc_usage; + spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; @@ -1521,21 +1544,24 @@ static void destroy_ep_files (struct dev_data *dev) /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); + spin_unlock_irq (&dev->lock); + dentry = ep->dentry; ep->dentry = NULL; parent = d_inode(dentry->d_parent); /* break link to controller */ + mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; + mutex_unlock(&ep->lock); + wake_up (&ep->wait); put_ep (ep); - spin_unlock_irq (&dev->lock); - /* break link to dcache */ inode_lock(parent); d_delete (dentry); @@ -1606,6 +1632,11 @@ gadgetfs_unbind (struct usb_gadget *gadget) spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; + while (dev->udc_usage > 0) { + spin_unlock_irq(&dev->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dev->lock); + } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); -- GitLab From 1fbbb78f25d1291274f320462bf6908906f538db Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 21 Sep 2017 13:22:00 -0400 Subject: [PATCH 0226/1507] USB: g_mass_storage: Fix deadlock when driver is unbound As a holdover from the old g_file_storage gadget, the g_mass_storage legacy gadget driver attempts to unregister itself when its main operating thread terminates (if it hasn't been unregistered already). This is not strictly necessary; it was never more than an attempt to have the gadget fail cleanly if something went wrong and the main thread was killed. However, now that the UDC core manages gadget drivers independently of UDC drivers, this scheme doesn't work any more. A simple test: modprobe dummy-hcd modprobe g-mass-storage file=... rmmod dummy-hcd ends up in a deadlock with the following backtrace: sysrq: SysRq : Show Blocked State task PC stack pid father file-storage D 0 1130 2 0x00000000 Call Trace: __schedule+0x53e/0x58c schedule+0x6e/0x77 schedule_preempt_disabled+0xd/0xf __mutex_lock.isra.1+0x129/0x224 ? _raw_spin_unlock_irqrestore+0x12/0x14 __mutex_lock_slowpath+0x12/0x14 mutex_lock+0x28/0x2b usb_gadget_unregister_driver+0x29/0x9b [udc_core] usb_composite_unregister+0x10/0x12 [libcomposite] msg_cleanup+0x1d/0x20 [g_mass_storage] msg_thread_exits+0xd/0xdd7 [g_mass_storage] fsg_main_thread+0x1395/0x13d6 [usb_f_mass_storage] ? __schedule+0x573/0x58c kthread+0xd9/0xdb ? do_set_interface+0x25c/0x25c [usb_f_mass_storage] ? init_completion+0x1e/0x1e ret_from_fork+0x19/0x24 rmmod D 0 1155 683 0x00000000 Call Trace: __schedule+0x53e/0x58c schedule+0x6e/0x77 schedule_timeout+0x26/0xbc ? __schedule+0x573/0x58c do_wait_for_common+0xb3/0x128 ? usleep_range+0x81/0x81 ? wake_up_q+0x3f/0x3f wait_for_common+0x2e/0x45 wait_for_completion+0x17/0x19 fsg_common_put+0x34/0x81 [usb_f_mass_storage] fsg_free_inst+0x13/0x1e [usb_f_mass_storage] usb_put_function_instance+0x1a/0x25 [libcomposite] msg_unbind+0x2a/0x42 [g_mass_storage] __composite_unbind+0x4a/0x6f [libcomposite] composite_unbind+0x12/0x14 [libcomposite] usb_gadget_remove_driver+0x4f/0x77 [udc_core] usb_del_gadget_udc+0x52/0xcc [udc_core] dummy_udc_remove+0x27/0x2c [dummy_hcd] platform_drv_remove+0x1d/0x31 device_release_driver_internal+0xe9/0x16d device_release_driver+0x11/0x13 bus_remove_device+0xd2/0xe2 device_del+0x19f/0x221 ? selinux_capable+0x22/0x27 platform_device_del+0x21/0x63 platform_device_unregister+0x10/0x1a cleanup+0x20/0x817 [dummy_hcd] SyS_delete_module+0x10c/0x197 ? ____fput+0xd/0xf ? task_work_run+0x55/0x62 ? prepare_exit_to_usermode+0x65/0x75 do_fast_syscall_32+0x86/0xc3 entry_SYSENTER_32+0x4e/0x7c What happens is that removing the dummy-hcd driver causes the UDC core to unbind the gadget driver, which it does while holding the udc_lock mutex. The unbind routine in g_mass_storage tells the main thread to exit and waits for it to terminate. But as mentioned above, when the main thread exits it tries to unregister the mass-storage function driver. Via the composite framework this ends up calling usb_gadget_unregister_driver(), which tries to acquire the udc_lock mutex. The result is deadlock. The simplest way to fix the problem is not to be so clever: The main thread doesn't have to unregister the function driver. The side effects won't be so terrible; if the gadget is still attached to a USB host when the main thread is killed, it will appear to the host as though the gadget's firmware has crashed -- a reasonably accurate interpretation, and an all-too-common occurrence for USB mass-storage devices. In fact, the code to unregister the driver when the main thread exits is specific to g-mass-storage; it is not used when f-mass-storage is included as a function in a larger composite device. Therefore the entire mechanism responsible for this (the fsg_operations structure with its ->thread_exits method, the fsg_common_set_ops() routine, and the msg_thread_exits() callback routine) can all be eliminated. Even the msg_registered bitflag can be removed, because now the driver is unregistered in only one place rather than in two places. Signed-off-by: Alan Stern CC: Acked-by: Felipe Balbi Acked-by: Michal Nazarewicz Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_mass_storage.c | 27 +++++--------------- drivers/usb/gadget/function/f_mass_storage.h | 14 ---------- drivers/usb/gadget/legacy/mass_storage.c | 26 +++---------------- 3 files changed, 10 insertions(+), 57 deletions(-) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index d6bd0244b008a..5153e29870c39 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -307,8 +307,6 @@ struct fsg_common { struct completion thread_notifier; struct task_struct *thread_task; - /* Callback functions. */ - const struct fsg_operations *ops; /* Gadget's private data. */ void *private_data; @@ -2438,6 +2436,7 @@ static void handle_exception(struct fsg_common *common) static int fsg_main_thread(void *common_) { struct fsg_common *common = common_; + int i; /* * Allow the thread to be killed by a signal, but set the signal mask @@ -2476,21 +2475,16 @@ static int fsg_main_thread(void *common_) common->thread_task = NULL; spin_unlock_irq(&common->lock); - if (!common->ops || !common->ops->thread_exits - || common->ops->thread_exits(common) < 0) { - int i; + /* Eject media from all LUNs */ - down_write(&common->filesem); - for (i = 0; i < ARRAY_SIZE(common->luns); i++) { - struct fsg_lun *curlun = common->luns[i]; - if (!curlun || !fsg_lun_is_open(curlun)) - continue; + down_write(&common->filesem); + for (i = 0; i < ARRAY_SIZE(common->luns); i++) { + struct fsg_lun *curlun = common->luns[i]; + if (curlun && fsg_lun_is_open(curlun)) fsg_lun_close(curlun); - curlun->unit_attention_data = SS_MEDIUM_NOT_PRESENT; - } - up_write(&common->filesem); } + up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ complete_and_exit(&common->thread_notifier, 0); @@ -2681,13 +2675,6 @@ void fsg_common_remove_luns(struct fsg_common *common) } EXPORT_SYMBOL_GPL(fsg_common_remove_luns); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops) -{ - common->ops = ops; -} -EXPORT_SYMBOL_GPL(fsg_common_set_ops); - void fsg_common_free_buffers(struct fsg_common *common) { _fsg_common_free_buffers(common->buffhds, common->fsg_num_buffers); diff --git a/drivers/usb/gadget/function/f_mass_storage.h b/drivers/usb/gadget/function/f_mass_storage.h index d3902313b8ac4..dc05ca0c43596 100644 --- a/drivers/usb/gadget/function/f_mass_storage.h +++ b/drivers/usb/gadget/function/f_mass_storage.h @@ -60,17 +60,6 @@ struct fsg_module_parameters { struct fsg_common; /* FSF callback functions */ -struct fsg_operations { - /* - * Callback function to call when thread exits. If no - * callback is set or it returns value lower then zero MSF - * will force eject all LUNs it operates on (including those - * marked as non-removable or with prevent_medium_removal flag - * set). - */ - int (*thread_exits)(struct fsg_common *common); -}; - struct fsg_lun_opts { struct config_group group; struct fsg_lun *lun; @@ -142,9 +131,6 @@ void fsg_common_remove_lun(struct fsg_lun *lun); void fsg_common_remove_luns(struct fsg_common *common); -void fsg_common_set_ops(struct fsg_common *common, - const struct fsg_operations *ops); - int fsg_common_create_lun(struct fsg_common *common, struct fsg_lun_config *cfg, unsigned int id, const char *name, const char **name_pfx); diff --git a/drivers/usb/gadget/legacy/mass_storage.c b/drivers/usb/gadget/legacy/mass_storage.c index e99ab57ee3e58..fcba59782f265 100644 --- a/drivers/usb/gadget/legacy/mass_storage.c +++ b/drivers/usb/gadget/legacy/mass_storage.c @@ -107,15 +107,6 @@ static unsigned int fsg_num_buffers = CONFIG_USB_GADGET_STORAGE_NUM_BUFFERS; FSG_MODULE_PARAMETERS(/* no prefix */, mod_data); -static unsigned long msg_registered; -static void msg_cleanup(void); - -static int msg_thread_exits(struct fsg_common *common) -{ - msg_cleanup(); - return 0; -} - static int msg_do_config(struct usb_configuration *c) { struct fsg_opts *opts; @@ -154,9 +145,6 @@ static struct usb_configuration msg_config_driver = { static int msg_bind(struct usb_composite_dev *cdev) { - static const struct fsg_operations ops = { - .thread_exits = msg_thread_exits, - }; struct fsg_opts *opts; struct fsg_config config; int status; @@ -173,8 +161,6 @@ static int msg_bind(struct usb_composite_dev *cdev) if (status) goto fail; - fsg_common_set_ops(opts->common, &ops); - status = fsg_common_set_cdev(opts->common, cdev, config.can_stall); if (status) goto fail_set_cdev; @@ -256,18 +242,12 @@ MODULE_LICENSE("GPL"); static int __init msg_init(void) { - int ret; - - ret = usb_composite_probe(&msg_driver); - set_bit(0, &msg_registered); - - return ret; + return usb_composite_probe(&msg_driver); } module_init(msg_init); -static void msg_cleanup(void) +static void __exit msg_cleanup(void) { - if (test_and_clear_bit(0, &msg_registered)) - usb_composite_unregister(&msg_driver); + usb_composite_unregister(&msg_driver); } module_exit(msg_cleanup); -- GitLab From 0d0970eef3b03ef08b19da5bc3044410731cf38f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 20 Sep 2017 16:24:32 -0500 Subject: [PATCH 0227/1507] objtool: Handle another GCC stack pointer adjustment bug The kbuild bot reported the following warning with GCC 4.4 and a randconfig: net/socket.o: warning: objtool: compat_sock_ioctl()+0x1083: stack state mismatch: cfa1=7+160 cfa2=-1+0 This is caused by another GCC non-optimization, where it backs up and restores the stack pointer for no apparent reason: 2f91: 48 89 e0 mov %rsp,%rax 2f94: 4c 89 e7 mov %r12,%rdi 2f97: 4c 89 f6 mov %r14,%rsi 2f9a: ba 20 00 00 00 mov $0x20,%edx 2f9f: 48 89 c4 mov %rax,%rsp This issue would have been happily ignored before the following commit: dd88a0a0c861 ("objtool: Handle GCC stack pointer adjustment bug") But now that objtool is paying attention to such stack pointer writes to/from a register, it needs to understand them properly. In this case that means recognizing that the "mov %rsp, %rax" instruction is potentially a backup of the stack pointer. Reported-by: kbuild test robot Signed-off-by: Josh Poimboeuf Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dmitriy Vyukov Cc: Linus Torvalds Cc: Matthias Kaehlcke Cc: Miguel Bernal Marin Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: dd88a0a0c861 ("objtool: Handle GCC stack pointer adjustment bug") Link: http://lkml.kernel.org/r/8c7aa8e9a36fbbb6655d9d8e7cea58958c912da8.1505942196.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/arch/x86/decode.c | 6 ++--- tools/objtool/check.c | 43 ++++++++++++++++++++++----------- 2 files changed, 32 insertions(+), 17 deletions(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0e8c8ec4fd4e6..0f22768c0d4d0 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -208,14 +208,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; case 0x89: - if (rex == 0x48 && modrm == 0xe5) { + if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) { - /* mov %rsp, %rbp */ + /* mov %rsp, reg */ *type = INSN_STACK; op->src.type = OP_SRC_REG; op->src.reg = CFI_SP; op->dest.type = OP_DEST_REG; - op->dest.reg = CFI_BP; + op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b]; break; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f744617c9946d..a0c518ecf0851 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1203,24 +1203,39 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state) switch (op->src.type) { case OP_SRC_REG: - if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) { + if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP && + cfa->base == CFI_SP && + regs[CFI_BP].base == CFI_CFA && + regs[CFI_BP].offset == -cfa->offset) { + + /* mov %rsp, %rbp */ + cfa->base = op->dest.reg; + state->bp_scratch = false; + } - if (cfa->base == CFI_SP && - regs[CFI_BP].base == CFI_CFA && - regs[CFI_BP].offset == -cfa->offset) { + else if (op->src.reg == CFI_SP && + op->dest.reg == CFI_BP && state->drap) { - /* mov %rsp, %rbp */ - cfa->base = op->dest.reg; - state->bp_scratch = false; - } + /* drap: mov %rsp, %rbp */ + regs[CFI_BP].base = CFI_BP; + regs[CFI_BP].offset = -state->stack_size; + state->bp_scratch = false; + } - else if (state->drap) { + else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { - /* drap: mov %rsp, %rbp */ - regs[CFI_BP].base = CFI_BP; - regs[CFI_BP].offset = -state->stack_size; - state->bp_scratch = false; - } + /* + * mov %rsp, %reg + * + * This is needed for the rare case where GCC + * does: + * + * mov %rsp, %rax + * ... + * mov %rax, %rsp + */ + state->vals[op->dest.reg].base = CFI_CFA; + state->vals[op->dest.reg].offset = -state->stack_size; } else if (op->dest.reg == cfa->base) { -- GitLab From f5caf621ee357279e759c0911daf6d55c7d36f03 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 20 Sep 2017 16:24:33 -0500 Subject: [PATCH 0228/1507] x86/asm: Fix inline asm call constraints for Clang For inline asm statements which have a CALL instruction, we list the stack pointer as a constraint to convince GCC to ensure the frame pointer is set up first: static inline void foo() { register void *__sp asm(_ASM_SP); asm("call bar" : "+r" (__sp)) } Unfortunately, that pattern causes Clang to corrupt the stack pointer. The fix is easy: convert the stack pointer register variable to a global variable. It should be noted that the end result is different based on the GCC version. With GCC 6.4, this patch has exactly the same result as before: defconfig defconfig-nofp distro distro-nofp before 9820389 9491555 8816046 8516940 after 9820389 9491555 8816046 8516940 With GCC 7.2, however, GCC's behavior has changed. It now changes its behavior based on the conversion of the register variable to a global. That somehow convinces it to *always* set up the frame pointer before inserting *any* inline asm. (Therefore, listing the variable as an output constraint is a no-op and is no longer necessary.) It's a bit overkill, but the performance impact should be negligible. And in fact, there's a nice improvement with frame pointers disabled: defconfig defconfig-nofp distro distro-nofp before 9796316 9468236 9076191 8790305 after 9796957 9464267 9076381 8785949 So in summary, while listing the stack pointer as an output constraint is no longer necessary for newer versions of GCC, it's still needed for older versions. Suggested-by: Andrey Ryabinin Reported-by: Matthias Kaehlcke Signed-off-by: Josh Poimboeuf Cc: Alexander Potapenko Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dmitriy Vyukov Cc: Linus Torvalds Cc: Miguel Bernal Marin Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/3db862e970c432ae823cf515c52b54fec8270e0e.1505942196.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/alternative.h | 3 +-- arch/x86/include/asm/asm.h | 11 +++++++++++ arch/x86/include/asm/mshyperv.h | 10 ++++------ arch/x86/include/asm/paravirt_types.h | 14 +++++++------- arch/x86/include/asm/preempt.h | 15 +++++---------- arch/x86/include/asm/processor.h | 6 ++---- arch/x86/include/asm/rwsem.h | 4 ++-- arch/x86/include/asm/uaccess.h | 4 ++-- arch/x86/include/asm/xen/hypercall.h | 5 ++--- arch/x86/kvm/emulate.c | 3 +-- arch/x86/kvm/vmx.c | 3 +-- arch/x86/mm/fault.c | 3 +-- tools/objtool/Documentation/stack-validation.txt | 6 +++--- 13 files changed, 42 insertions(+), 45 deletions(-) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 1b020381ab389..c096624137ae8 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -218,10 +218,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ { \ - register void *__sp asm(_ASM_SP); \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ - : output, "+r" (__sp) \ + : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input); \ } diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 676ee5807d864..c1eadbaf1115a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -132,4 +132,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif +#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned int __asm_call_sp asm("esp"); +#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 63cc96f064dc4..738503e1f80c1 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -179,7 +179,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) u64 input_address = input ? virt_to_phys(input) : 0; u64 output_address = output ? virt_to_phys(output) : 0; u64 hv_status; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 if (!hv_hypercall_pg) @@ -187,7 +186,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("mov %4, %%r8\n" "call *%5" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input_address) : "r" (output_address), "m" (hv_hypercall_pg) : "cc", "memory", "r8", "r9", "r10", "r11"); @@ -202,7 +201,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("call *%7" : "=A" (hv_status), - "+c" (input_address_lo), "+r" (__sp) + "+c" (input_address_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input_address_hi), "D"(output_address_hi), "S"(output_address_lo), @@ -224,12 +223,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) { u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 { __asm__ __volatile__("call *%4" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input1) : "m" (hv_hypercall_pg) : "cc", "r8", "r9", "r10", "r11"); @@ -242,7 +240,7 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) __asm__ __volatile__ ("call *%5" : "=A"(hv_status), "+c"(input1_lo), - "+r"(__sp) + ASM_CALL_CONSTRAINT : "A" (control), "b" (input1_hi), "m" (hv_hypercall_pg) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 42873edd9f9d2..280d94c36dada 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -459,8 +459,8 @@ int paravirt_disable_iospace(void); */ #ifdef CONFIG_X86_32 #define PVOP_VCALL_ARGS \ - unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \ - register void *__sp asm("esp") + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) @@ -480,8 +480,8 @@ int paravirt_disable_iospace(void); /* [re]ax isn't an arg, but the return val */ #define PVOP_VCALL_ARGS \ unsigned long __edi = __edi, __esi = __esi, \ - __edx = __edx, __ecx = __ecx, __eax = __eax; \ - register void *__sp asm("rsp") + __edx = __edx, __ecx = __ecx, __eax = __eax; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) @@ -532,7 +532,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -542,7 +542,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -569,7 +569,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index ec1f3c6511506..4f44505dbf870 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -100,19 +100,14 @@ static __always_inline bool should_resched(int preempt_offset) #ifdef CONFIG_PREEMPT extern asmlinkage void ___preempt_schedule(void); -# define __preempt_schedule() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \ -}) +# define __preempt_schedule() \ + asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void ___preempt_schedule_notrace(void); -# define __preempt_schedule_notrace() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \ -}) +# define __preempt_schedule_notrace() \ + asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT) + extern asmlinkage void preempt_schedule_notrace(void); #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3fa26a61eabce..b390ff76e58fd 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -677,8 +677,6 @@ static inline void sync_core(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ - register void *__sp asm(_ASM_SP); - #ifdef CONFIG_X86_32 asm volatile ( "pushfl\n\t" @@ -686,7 +684,7 @@ static inline void sync_core(void) "pushl $1f\n\t" "iret\n\t" "1:" - : "+r" (__sp) : : "memory"); + : ASM_CALL_CONSTRAINT : : "memory"); #else unsigned int tmp; @@ -703,7 +701,7 @@ static inline void sync_core(void) "iretq\n\t" UNWIND_HINT_RESTORE "1:" - : "=&r" (tmp), "+r" (__sp) : : "cc", "memory"); + : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory"); #endif } diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index a34e0d4b957d6..7116b7931c7b8 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -103,7 +103,6 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) ({ \ long tmp; \ struct rw_semaphore* ret; \ - register void *__sp asm(_ASM_SP); \ \ asm volatile("# beginning down_write\n\t" \ LOCK_PREFIX " xadd %1,(%4)\n\t" \ @@ -114,7 +113,8 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) " call " slow_path "\n" \ "1:\n" \ "# ending down_write" \ - : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \ + : "+m" (sem->count), "=d" (tmp), \ + "=a" (ret), ASM_CALL_CONSTRAINT \ : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \ : "memory", "cc"); \ ret; \ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 184eb9894dae3..78e8fcc87d4c6 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -166,11 +166,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ - register void *__sp asm(_ASM_SP); \ __chk_user_ptr(ptr); \ might_fault(); \ asm volatile("call __get_user_%P4" \ - : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \ + : "=a" (__ret_gu), "=r" (__val_gu), \ + ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9606688caa4be..128a1a0b14505 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -113,10 +113,9 @@ extern struct { char _entry[32]; } hypercall_page[]; register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \ register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \ register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \ - register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \ - register void *__sp asm(_ASM_SP); + register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; -#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp) +#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT #define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1) #define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2) #define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 16bf6655aa858..f23f13403f330 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5296,7 +5296,6 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) @@ -5304,7 +5303,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [fastop]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06c0c6d0541e9..6ee237f509dc7 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9036,7 +9036,6 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) { u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - register void *__sp asm(_ASM_SP); if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { @@ -9065,7 +9064,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif - "+r"(__sp) + ASM_CALL_CONSTRAINT : [entry]"r"(entry), [ss]"i"(__KERNEL_DS), diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b836a7274e123..39567b5c33da3 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -806,7 +806,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { - register void *__sp asm("rsp"); unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *); /* * We're likely to be running with very little stack space @@ -821,7 +820,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" - : "+r" (__sp) + : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 6a1af43862df7..3995735a878fe 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -194,10 +194,10 @@ they mean, and suggestions for how to fix them. If it's a GCC-compiled .c file, the error may be because the function uses an inline asm() statement which has a "call" instruction. An asm() statement with a call instruction must declare the use of the - stack pointer in its output operand. For example, on x86_64: + stack pointer in its output operand. On x86_64, this means adding + the ASM_CALL_CONSTRAINT as an output constraint: - register void *__sp asm("rsp"); - asm volatile("call func" : "+r" (__sp)); + asm volatile("call func" : ASM_CALL_CONSTRAINT); Otherwise the stack frame may not get created before the call. -- GitLab From af2e658fc08a397b10352265e50b83f27e25d73e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 22 Sep 2017 12:32:35 +0300 Subject: [PATCH 0229/1507] as3645a: Use ams,input-max-microamp as documented in DT bindings DT bindings document the property "ams,input-max-microamp" that limits the chip's maximum input current. The driver and the DTS however used "peak-current-limit" property. Fix this by using the property documented in DT binding documentation. Signed-off-by: Sakari Ailus Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- arch/arm/boot/dts/omap3-n950-n9.dtsi | 2 +- drivers/leds/leds-as3645a.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index cb47ae79a5f9e..b86fc83a5a65d 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -273,7 +273,7 @@ flash { flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; - peak-current-limit = <1750000>; + ams,input-max-microamp = <1750000>; }; indicator { led-max-microamp = <10000>; diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index bbbbe08982332..e3f89c6130d28 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -534,7 +534,7 @@ static int as3645a_parse_node(struct as3645a *flash, of_property_read_u32(flash->flash_node, "voltage-reference", &cfg->voltage_reference); - of_property_read_u32(flash->flash_node, "peak-current-limit", + of_property_read_u32(flash->flash_node, "ams,input-max-microamp", &cfg->peak); cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak); -- GitLab From 75f9f7279e874ff95d1abe4613abc0826c9a8dcc Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 22 Sep 2017 12:32:36 +0300 Subject: [PATCH 0230/1507] dt: bindings: as3645a: Use LED number to refer to LEDs Use integers (reg property) to tell the number of the LED to the driver instead of the node name. While both of these approaches are currently used by the LED bindings, using integers will require less driver changes for ACPI support. Additionally, it will make possible LED naming using chip and LED node names, effectively making the label property most useful for human-readable names only. Signed-off-by: Sakari Ailus Acked-by: Rob Herring Signed-off-by: Jacek Anaszewski --- .../devicetree/bindings/leds/ams,as3645a.txt | 28 ++++++++++++------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/leds/ams,as3645a.txt b/Documentation/devicetree/bindings/leds/ams,as3645a.txt index 12c5ef26ec739..fdc40e354a64d 100644 --- a/Documentation/devicetree/bindings/leds/ams,as3645a.txt +++ b/Documentation/devicetree/bindings/leds/ams,as3645a.txt @@ -15,11 +15,14 @@ Required properties compatible : Must be "ams,as3645a". reg : The I2C address of the device. Typically 0x30. +#address-cells : 1 +#size-cells : 0 -Required properties of the "flash" child node -============================================= +Required properties of the flash child node (0) +=============================================== +reg: 0 flash-timeout-us: Flash timeout in microseconds. The value must be in the range [100000, 850000] and divisible by 50000. flash-max-microamp: Maximum flash current in microamperes. Has to be @@ -33,20 +36,21 @@ ams,input-max-microamp: Maximum flash controller input current. The and divisible by 50000. -Optional properties of the "flash" child node -============================================= +Optional properties of the flash child node +=========================================== label : The label of the flash LED. -Required properties of the "indicator" child node -================================================= +Required properties of the indicator child node (1) +=================================================== +reg: 1 led-max-microamp: Maximum indicator current. The allowed values are 2500, 5000, 7500 and 10000. -Optional properties of the "indicator" child node -================================================= +Optional properties of the indicator child node +=============================================== label : The label of the indicator LED. @@ -55,16 +59,20 @@ Example ======= as3645a@30 { + #address-cells: 1 + #size-cells: 0 reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; ams,input-max-microamp = <1750000>; label = "as3645a:flash"; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; label = "as3645a:indicator"; }; -- GitLab From e626c325277531db15314b80610d1f5a1c2637b2 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 22 Sep 2017 12:32:37 +0300 Subject: [PATCH 0231/1507] as3645a: Use integer numbers for parsing LEDs Use integer numbers for LEDs, 0 is the flash and 1 is the indicator. Signed-off-by: Sakari Ailus Acked-by: Pavel Machek Signed-off-by: Jacek Anaszewski --- arch/arm/boot/dts/omap3-n950-n9.dtsi | 8 ++++++-- drivers/leds/leds-as3645a.c | 26 ++++++++++++++++++++++++-- 2 files changed, 30 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index b86fc83a5a65d..1b0bd72945f21 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -267,15 +267,19 @@ &i2c2 { clock-frequency = <400000>; as3645a@30 { + #address-cells = <1>; + #size-cells = <0>; reg = <0x30>; compatible = "ams,as3645a"; - flash { + flash@0 { + reg = <0x0>; flash-timeout-us = <150000>; flash-max-microamp = <320000>; led-max-microamp = <60000>; ams,input-max-microamp = <1750000>; }; - indicator { + indicator@1 { + reg = <0x1>; led-max-microamp = <10000>; }; }; diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index e3f89c6130d28..605e0c64e974d 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -112,6 +112,10 @@ #define AS_PEAK_mA_TO_REG(a) \ ((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250) +/* LED numbers for Devicetree */ +#define AS_LED_FLASH 0 +#define AS_LED_INDICATOR 1 + enum as_mode { AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT, AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT, @@ -491,10 +495,29 @@ static int as3645a_parse_node(struct as3645a *flash, struct device_node *node) { struct as3645a_config *cfg = &flash->cfg; + struct device_node *child; const char *name; int rval; - flash->flash_node = of_get_child_by_name(node, "flash"); + for_each_child_of_node(node, child) { + u32 id = 0; + + of_property_read_u32(child, "reg", &id); + + switch (id) { + case AS_LED_FLASH: + flash->flash_node = of_node_get(child); + break; + case AS_LED_INDICATOR: + flash->indicator_node = of_node_get(child); + break; + default: + dev_warn(&flash->client->dev, + "unknown LED %u encountered, ignoring\n", id); + break; + } + } + if (!flash->flash_node) { dev_err(&flash->client->dev, "can't find flash node\n"); return -ENODEV; @@ -538,7 +561,6 @@ static int as3645a_parse_node(struct as3645a *flash, &cfg->peak); cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak); - flash->indicator_node = of_get_child_by_name(node, "indicator"); if (!flash->indicator_node) { dev_warn(&flash->client->dev, "can't find indicator node\n"); -- GitLab From 12c4b878e71fa8b65bc479b2460765c7d1d81a26 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 22 Sep 2017 12:32:38 +0300 Subject: [PATCH 0232/1507] as3645a: Unregister indicator LED on device unbind The indicator LED was registered in probe but was not removed in driver remove callback. Fix this. Signed-off-by: Sakari Ailus Signed-off-by: Jacek Anaszewski --- drivers/leds/leds-as3645a.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index 605e0c64e974d..9a257f9693009 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -743,6 +743,7 @@ static int as3645a_remove(struct i2c_client *client) as3645a_set_control(flash, AS_MODE_EXT_TORCH, false); v4l2_flash_release(flash->vf); + v4l2_flash_release(flash->vfind); led_classdev_flash_unregister(&flash->fled); led_classdev_unregister(&flash->iled_cdev); -- GitLab From 28585a832602747cbfa88ad8934013177a3aae38 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 22 Sep 2017 14:10:22 -0700 Subject: [PATCH 0233/1507] rcu: Allow for page faults in NMI handlers A number of architecture invoke rcu_irq_enter() on exception entry in order to allow RCU read-side critical sections in the exception handler when the exception is from an idle or nohz_full CPU. This works, at least unless the exception happens in an NMI handler. In that case, rcu_nmi_enter() would already have exited the extended quiescent state, which would mean that rcu_irq_enter() would (incorrectly) cause RCU to think that it is again in an extended quiescent state. This will in turn result in lockdep splats in response to later RCU read-side critical sections. This commit therefore causes rcu_irq_enter() and rcu_irq_exit() to take no action if there is an rcu_nmi_enter() in effect, thus avoiding the unscheduled return to RCU quiescent state. This in turn should make the kernel safe for on-demand RCU voyeurism. Link: http://lkml.kernel.org/r/20170922211022.GA18084@linux.vnet.ibm.com Cc: stable@vger.kernel.org Fixes: 0be964be0 ("module: Sanitize RCU usage and locking") Reported-by: Steven Rostedt Signed-off-by: Paul E. McKenney Signed-off-by: Steven Rostedt (VMware) --- kernel/rcu/tree.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 51d4c3acf32d4..63bee8e1b193e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -888,6 +888,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1020,6 +1025,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && -- GitLab From 9aadde91b3c035413c806619beb3e3ef6e697953 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 22 Sep 2017 17:22:19 -0400 Subject: [PATCH 0234/1507] extable: Consolidate *kernel_text_address() functions The functionality between kernel_text_address() and _kernel_text_address() is the same except that _kernel_text_address() does a little more (that function needs a rename, but that can be done another time). Instead of having duplicate code in both, simply have _kernel_text_address() calls kernel_text_address() instead. This is marked for stable because there's an RCU bug that can happen if one of these functions gets called while RCU is not watching. That fix depends on this fix to keep from having to write the fix twice. Cc: stable@vger.kernel.org Fixes: 0be964be0 ("module: Sanitize RCU usage and locking") Acked-by: Paul E. McKenney Signed-off-by: Steven Rostedt (VMware) --- kernel/extable.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412401a1b..a7024a494fafc 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. -- GitLab From e8cac8b1d10589be45671a5ade0926a639b543b7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 22 Sep 2017 17:36:32 -0400 Subject: [PATCH 0235/1507] extable: Enable RCU if it is not watching in kernel_text_address() If kernel_text_address() is called when RCU is not watching, it can cause an RCU bug because is_module_text_address(), the is_kprobe_*insn_slot() and is_bpf_text_address() functions require the use of RCU. Only enable RCU if it is not currently watching before it calls is_module_text_address(). The use of rcu_nmi_enter() is used to enable RCU because kernel_text_address() can happen pretty much anywhere (like an NMI), and even from within an NMI. It is called via save_stack_trace() that can be called by any WARN() or tracing function, which can happen while RCU is not watching (for example, going to or coming from idle, or during CPU take down or bring up). Cc: stable@vger.kernel.org Fixes: 0be964be0 ("module: Sanitize RCU usage and locking") Acked-by: Paul E. McKenney Signed-off-by: Steven Rostedt (VMware) --- kernel/extable.c | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) diff --git a/kernel/extable.c b/kernel/extable.c index a7024a494fafc..9aa1cc41ecf79 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -119,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* -- GitLab From 15516c89acce948debc4c598e03c3fee53045797 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 21 Sep 2017 13:00:21 -0400 Subject: [PATCH 0236/1507] tracing: Remove RCU work arounds from stack tracer Currently the stack tracer calls rcu_irq_enter() to make sure RCU is watching when it records a stack trace. But if the stack tracer is triggered while tracing inside of a rcu_irq_enter(), calling rcu_irq_enter() unconditionally can be problematic. The reason for having rcu_irq_enter() in the first place has been fixed from within the saving of the stack trace code, and there's no reason for doing it in the stack tracer itself. Just remove it. Cc: stable@vger.kernel.org Fixes: 0be964be0 ("module: Sanitize RCU usage and locking") Acked-by: Paul E. McKenney Suggested-by: "Paul E. McKenney" Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67cbc7114..49cb41412eece 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } -- GitLab From 05cf97e7a619fc7ede81ee6bb8ebfa7531b633f5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 22 Sep 2017 01:01:11 +0200 Subject: [PATCH 0237/1507] cnic: Fix an error handling path in 'cnic_alloc_bnx2x_resc()' All the error handling paths 'goto error', except this one. We should also go to error in this case, or some resources will be leaking. Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/cnic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index cec94bbb2ea5a..8bc126a156e80 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1278,7 +1278,7 @@ static int cnic_alloc_bnx2x_resc(struct cnic_dev *dev) ret = cnic_alloc_dma(dev, kwq_16_dma, pages, 0); if (ret) - return -ENOMEM; + goto error; n = CNIC_PAGE_SIZE / CNIC_KWQ16_DATA_SIZE; for (i = 0, j = 0; i < cp->max_cid_space; i++) { -- GitLab From 5c346525d3591cb032eca86d0f904cc01f1069ff Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 21 Sep 2017 18:00:36 -0600 Subject: [PATCH 0238/1507] net: qualcomm: rmnet: Fix rcu splat in rmnet_is_real_dev_registered Xiaolong reported a suspicious rcu_dereference_check in the device unregister notifier callback. Since we do not dereference the rx_handler_data, it's ok to just check for the value of the pointer. Note that this section is already protected by rtnl_lock. [ 101.364846] WARNING: suspicious RCU usage [ 101.365654] 4.13.0-rc6-01701-gceed73a #1 Not tainted [ 101.370873] ----------------------------- [ 101.372472] drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c:57 suspicious rcu_dereference_check() usage! [ 101.374427] [ 101.374427] other info that might help us debug this: [ 101.374427] [ 101.387491] [ 101.387491] rcu_scheduler_active = 2, debug_locks = 1 [ 101.389368] 1 lock held by trinity-main/2809: [ 101.390736] #0: (rtnl_mutex){+.+.+.}, at: [<8146085b>] rtnl_lock+0xf/0x11 [ 101.395482] [ 101.395482] stack backtrace: [ 101.396948] CPU: 0 PID: 2809 Comm: trinity-main Not tainted 4.13.0-rc6-01701-gceed73a #1 [ 101.398857] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.3-20161025_171302-gandalf 04/01/2014 [ 101.401079] Call Trace: [ 101.401656] dump_stack+0xa1/0xeb [ 101.402871] lockdep_rcu_suspicious+0xc7/0xd0 [ 101.403665] rmnet_is_real_dev_registered+0x40/0x4e [ 101.405199] rmnet_config_notify_cb+0x2c/0x142 [ 101.406344] ? wireless_nlevent_flush+0x47/0x71 [ 101.407385] notifier_call_chain+0x2d/0x47 [ 101.408645] raw_notifier_call_chain+0xc/0xe [ 101.409882] call_netdevice_notifiers_info+0x41/0x49 [ 101.411402] call_netdevice_notifiers+0xc/0xe [ 101.412713] rollback_registered_many+0x268/0x36e [ 101.413702] rollback_registered+0x39/0x56 [ 101.414965] unregister_netdevice_queue+0x79/0x88 [ 101.415908] unregister_netdev+0x16/0x1d Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation") Signed-off-by: Subash Abhinov Kasiviswanathan Reported-by: kernel test robot Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 98f22551eb455..1e33aea59f505 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -51,10 +51,7 @@ struct rmnet_walk_data { static int rmnet_is_real_dev_registered(const struct net_device *real_dev) { - rx_handler_func_t *rx_handler; - - rx_handler = rcu_dereference(real_dev->rx_handler); - return (rx_handler == rmnet_rx_handler); + return rcu_access_pointer(real_dev->rx_handler) == rmnet_rx_handler; } /* Needs rtnl lock */ -- GitLab From ab5348c9c23cd253f5902980d2d8fe067dc24c82 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Wed, 26 Jul 2017 22:27:05 -0400 Subject: [PATCH 0239/1507] security: fix description of values returned by cap_inode_need_killpriv cap_inode_need_killpriv returns 1 if security.capability exists and has a value and inode_killpriv() is required, 0 otherwise. Fix the description of the return value to reflect this. Signed-off-by: Stefan Berger Reviewed-by: Serge Hallyn Signed-off-by: James Morris --- security/commoncap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/security/commoncap.c b/security/commoncap.c index 7abebd782d5e0..123426900d25b 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -300,10 +300,10 @@ static inline void bprm_clear_caps(struct linux_binprm *bprm) * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should - * inode_killpriv() be invoked or the change rejected? + * inode_killpriv() be invoked or the change rejected. * - * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and - * -ve to deny the change. + * Returns 1 if security.capability has a value, meaning inode_killpriv() + * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { -- GitLab From c2a9c4bf034ab7415ec272c4c86f1c0b796f80e6 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Thu, 17 Aug 2017 23:04:21 +0530 Subject: [PATCH 0240/1507] tpm: vtpm: constify vio_device_id vio_device_id are not supposed to change at runtime. All functions working with vio_device_id provided by work with const vio_device_id. So mark the non-const structs as const. Signed-off-by: Arvind Yadav Reviewed-by: Jason Gunthorpe Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- drivers/char/tpm/tpm_ibmvtpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index f01d083eced2f..d2ce46bd24719 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -32,7 +32,7 @@ static const char tpm_ibmvtpm_driver_name[] = "tpm_ibmvtpm"; -static struct vio_device_id tpm_ibmvtpm_device_table[] = { +static const struct vio_device_id tpm_ibmvtpm_device_table[] = { { "IBM,vtpm", "IBM,vtpm"}, { "", "" } }; -- GitLab From e1ec650f9ae7d1e66f77bf14c86e4e9dc629a4d5 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Thu, 6 Jul 2017 23:18:39 +0530 Subject: [PATCH 0241/1507] tpm: tpm_crb: constify acpi_device_id. acpi_device_id are not supposed to change at runtime. All functions working with acpi_device_id provided by work with const acpi_device_id. So mark the non-const structs as const. File size before: text data bss dec hex filename 4198 608 0 4806 12c6 drivers/char/tpm/tpm_crb.o File size After adding 'const': text data bss dec hex filename 4262 520 0 4782 12ae drivers/char/tpm/tpm_crb.o Signed-off-by: Arvind Yadav Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- drivers/char/tpm/tpm_crb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index a4ac63a21d8a0..8f0a98dea327a 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -665,7 +665,7 @@ static const struct dev_pm_ops crb_pm = { SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL) }; -static struct acpi_device_id crb_device_ids[] = { +static const struct acpi_device_id crb_device_ids[] = { {"MSFT0101", 0}, {"", 0}, }; -- GitLab From 5d0e4d78149b9745ea34848e950e734f7db3b95f Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Tue, 27 Jun 2017 12:27:23 +0200 Subject: [PATCH 0242/1507] Documentation: tpm: add powered-while-suspended binding documentation Add a new powered-while-suspended property to control the behavior of the TPM suspend/resume. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Sonny Rao Reviewed-by: Jason Gunthorpe Reviewed-by: Jarkko Sakkinen Acked-by: Rob Herring Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt index 8cb638b7e89c3..85c8216fc3358 100644 --- a/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt +++ b/Documentation/devicetree/bindings/security/tpm/tpm-i2c.txt @@ -8,6 +8,12 @@ Required properties: the firmware event log - linux,sml-size : size of the memory allocated for the firmware event log +Optional properties: + +- powered-while-suspended: present when the TPM is left powered on between + suspend and resume (makes the suspend/resume + callbacks do nothing). + Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C) ---------------------------------------------------------- -- GitLab From 9f3fc7bcddcb51234e23494531f93ab60475e1c3 Mon Sep 17 00:00:00 2001 From: Hamza Attak Date: Mon, 14 Aug 2017 19:09:16 +0100 Subject: [PATCH 0243/1507] tpm: replace msleep() with usleep_range() in TPM 1.2/2.0 generic drivers The patch simply replaces all msleep function calls with usleep_range calls in the generic drivers. Tested with an Infineon TPM 1.2, using the generic tpm-tis module, for a thousand PCR extends, we see results going from 1m57s unpatched to 40s with the new patch. We obtain similar results when using the original and patched tpm_infineon driver, which is also part of the patch. Similarly with a STM TPM 2.0, using the CRB driver, it takes about 20ms per extend unpatched and around 7ms with the new patch. Note that the PCR consistency is untouched with this patch, each TPM has been tested with 10 million extends and the aggregated PCR value is continuously verified to be correct. As an extension of this work, this could potentially and easily be applied to other vendor's drivers. Still, these changes are not included in the proposed patch as they are untested. Signed-off-by: Hamza Attak Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- drivers/char/tpm/tpm-interface.c | 10 +++++----- drivers/char/tpm/tpm.h | 9 ++++++++- drivers/char/tpm/tpm2-cmd.c | 2 +- drivers/char/tpm/tpm_infineon.c | 6 +++--- drivers/char/tpm/tpm_tis_core.c | 8 ++++---- 5 files changed, 21 insertions(+), 14 deletions(-) diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index fe597e6c55c40..1d6729be4cd63 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -455,7 +455,7 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, goto out; } - msleep(TPM_TIMEOUT); /* CHECK */ + tpm_msleep(TPM_TIMEOUT); rmb(); } while (time_before(jiffies, stop)); @@ -970,7 +970,7 @@ int tpm_do_selftest(struct tpm_chip *chip) dev_info( &chip->dev, HW_ERR "TPM command timed out during continue self test"); - msleep(delay_msec); + tpm_msleep(delay_msec); continue; } @@ -985,7 +985,7 @@ int tpm_do_selftest(struct tpm_chip *chip) } if (rc != TPM_WARN_DOING_SELFTEST) return rc; - msleep(delay_msec); + tpm_msleep(delay_msec); } while (--loops > 0); return rc; @@ -1085,7 +1085,7 @@ int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout, } } else { do { - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); status = chip->ops->status(chip); if ((status & mask) == mask) return 0; @@ -1150,7 +1150,7 @@ int tpm_pm_suspend(struct device *dev) */ if (rc != TPM_WARN_RETRY) break; - msleep(TPM_TIMEOUT_RETRY); + tpm_msleep(TPM_TIMEOUT_RETRY); } if (rc) diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 04fbff2edbf38..2d5466a72e40f 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -50,7 +50,8 @@ enum tpm_const { enum tpm_timeout { TPM_TIMEOUT = 5, /* msecs */ - TPM_TIMEOUT_RETRY = 100 /* msecs */ + TPM_TIMEOUT_RETRY = 100, /* msecs */ + TPM_TIMEOUT_RANGE_US = 300 /* usecs */ }; /* TPM addresses */ @@ -527,6 +528,12 @@ int tpm_pm_resume(struct device *dev); int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout, wait_queue_head_t *queue, bool check_cancel); +static inline void tpm_msleep(unsigned int delay_msec) +{ + usleep_range(delay_msec * 1000, + (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US); +}; + struct tpm_chip *tpm_chip_find_get(int chip_num); __must_check int tpm_try_get_ops(struct tpm_chip *chip); void tpm_put_ops(struct tpm_chip *chip); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index f7f34b2aa9819..e1a41b788f081 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -899,7 +899,7 @@ static int tpm2_do_selftest(struct tpm_chip *chip) if (rc != TPM2_RC_TESTING) break; - msleep(delay_msec); + tpm_msleep(delay_msec); } return rc; diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c index 3b1b9f9322d55..d8f10047fbbaf 100644 --- a/drivers/char/tpm/tpm_infineon.c +++ b/drivers/char/tpm/tpm_infineon.c @@ -191,7 +191,7 @@ static int wait(struct tpm_chip *chip, int wait_for_bit) /* check the status-register if wait_for_bit is set */ if (status & 1 << wait_for_bit) break; - msleep(TPM_MSLEEP_TIME); + tpm_msleep(TPM_MSLEEP_TIME); } if (i == TPM_MAX_TRIES) { /* timeout occurs */ if (wait_for_bit == STAT_XFE) @@ -226,7 +226,7 @@ static void tpm_wtx(struct tpm_chip *chip) wait_and_send(chip, TPM_CTRL_WTX); wait_and_send(chip, 0x00); wait_and_send(chip, 0x00); - msleep(TPM_WTX_MSLEEP_TIME); + tpm_msleep(TPM_WTX_MSLEEP_TIME); } static void tpm_wtx_abort(struct tpm_chip *chip) @@ -237,7 +237,7 @@ static void tpm_wtx_abort(struct tpm_chip *chip) wait_and_send(chip, 0x00); wait_and_send(chip, 0x00); number_of_wtx = 0; - msleep(TPM_WTX_MSLEEP_TIME); + tpm_msleep(TPM_WTX_MSLEEP_TIME); } static int tpm_inf_recv(struct tpm_chip *chip, u8 * buf, size_t count) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index b617b2eeb080a..63bc6c3b949e5 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -51,7 +51,7 @@ static int wait_startup(struct tpm_chip *chip, int l) if (access & TPM_ACCESS_VALID) return 0; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); return -1; } @@ -117,7 +117,7 @@ static int request_locality(struct tpm_chip *chip, int l) do { if (check_locality(chip, l)) return l; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); } return -1; @@ -164,7 +164,7 @@ static int get_burstcount(struct tpm_chip *chip) burstcnt = (value >> 8) & 0xFFFF; if (burstcnt) return burstcnt; - msleep(TPM_TIMEOUT); + tpm_msleep(TPM_TIMEOUT); } while (time_before(jiffies, stop)); return -EBUSY; } @@ -396,7 +396,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) priv->irq = irq; chip->flags |= TPM_CHIP_FLAG_IRQ; if (!priv->irq_tested) - msleep(1); + tpm_msleep(1); if (!priv->irq_tested) disable_interrupts(chip); priv->irq_tested = true; -- GitLab From fb154e0e0a95249459df054241a9e8f4cca56062 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Fri, 24 Feb 2017 20:35:16 +0100 Subject: [PATCH 0244/1507] tpm: ibmvtpm: simplify crq initialization and document crq format The crq is passed in registers and is the same on BE and LE hosts. However, current implementation allocates a structure on-stack to represent the crq, initializes the members swapping them to BE, and loads the structure swapping it from BE. This is pointless and causes GCC warnings about ununitialized members. Get rid of the structure and the warnings. Signed-off-by: Michal Suchanek Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen Signed-off-by: James Morris --- drivers/char/tpm/tpm_ibmvtpm.c | 96 +++++++++++++++++++++------------- 1 file changed, 60 insertions(+), 36 deletions(-) diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index d2ce46bd24719..25f6e2665385d 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -39,19 +39,63 @@ static const struct vio_device_id tpm_ibmvtpm_device_table[] = { MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table); /** + * + * ibmvtpm_send_crq_word - Send a CRQ request + * @vdev: vio device struct + * @w1: pre-constructed first word of tpm crq (second word is reserved) + * + * Return: + * 0 - Success + * Non-zero - Failure + */ +static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1) +{ + return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, 0); +} + +/** + * * ibmvtpm_send_crq - Send a CRQ request * * @vdev: vio device struct - * @w1: first word - * @w2: second word + * @valid: Valid field + * @msg: Type field + * @len: Length field + * @data: Data field + * + * The ibmvtpm crq is defined as follows: + * + * Byte | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 + * ----------------------------------------------------------------------- + * Word0 | Valid | Type | Length | Data + * ----------------------------------------------------------------------- + * Word1 | Reserved + * ----------------------------------------------------------------------- + * + * Which matches the following structure (on bigendian host): + * + * struct ibmvtpm_crq { + * u8 valid; + * u8 msg; + * __be16 len; + * __be32 data; + * __be64 reserved; + * } __attribute__((packed, aligned(8))); + * + * However, the value is passed in a register so just compute the numeric value + * to load into the register avoiding byteswap altogether. Endian only affects + * memory loads and stores - registers are internally represented the same. * * Return: - * 0 -Sucess + * 0 (H_SUCCESS) - Success * Non-zero - Failure */ -static int ibmvtpm_send_crq(struct vio_dev *vdev, u64 w1, u64 w2) +static int ibmvtpm_send_crq(struct vio_dev *vdev, + u8 valid, u8 msg, u16 len, u32 data) { - return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, w2); + u64 w1 = ((u64)valid << 56) | ((u64)msg << 48) | ((u64)len << 32) | + (u64)data; + return ibmvtpm_send_crq_word(vdev, w1); } /** @@ -109,8 +153,6 @@ static int tpm_ibmvtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count) static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); - struct ibmvtpm_crq crq; - __be64 *word = (__be64 *)&crq; int rc, sig; if (!ibmvtpm->rtce_buf) { @@ -137,10 +179,6 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) spin_lock(&ibmvtpm->rtce_lock); ibmvtpm->res_len = 0; memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count); - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_TPM_COMMAND; - crq.len = cpu_to_be16(count); - crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle); /* * set the processing flag before the Hcall, since we may get the @@ -148,8 +186,9 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) */ ibmvtpm->tpm_processing_cmd = true; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]), - be64_to_cpu(word[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND, + count, ibmvtpm->rtce_dma_handle); if (rc != H_SUCCESS) { dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); rc = 0; @@ -182,15 +221,10 @@ static u8 tpm_ibmvtpm_status(struct tpm_chip *chip) */ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) { - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_GET_RTCE_BUFFER_SIZE, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc); @@ -210,15 +244,10 @@ static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm) */ static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm) { - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_GET_VERSION; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_GET_VERSION, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_get_version failed rc=%d\n", rc); @@ -238,7 +267,7 @@ static int ibmvtpm_crq_send_init_complete(struct ibmvtpm_dev *ibmvtpm) { int rc; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_COMP_CMD, 0); + rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_COMP_CMD); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_send_init_complete failed rc=%d\n", rc); @@ -258,7 +287,7 @@ static int ibmvtpm_crq_send_init(struct ibmvtpm_dev *ibmvtpm) { int rc; - rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_CMD, 0); + rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "ibmvtpm_crq_send_init failed rc=%d\n", rc); @@ -340,15 +369,10 @@ static int tpm_ibmvtpm_suspend(struct device *dev) { struct tpm_chip *chip = dev_get_drvdata(dev); struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev); - struct ibmvtpm_crq crq; - u64 *buf = (u64 *) &crq; int rc = 0; - crq.valid = (u8)IBMVTPM_VALID_CMD; - crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND; - - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]), - cpu_to_be64(buf[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, + IBMVTPM_VALID_CMD, VTPM_PREPARE_TO_SUSPEND, 0, 0); if (rc != H_SUCCESS) dev_err(ibmvtpm->dev, "tpm_ibmvtpm_suspend failed rc=%d\n", rc); -- GitLab From 656f083116a4799d8c0194976b8a2d66bf306538 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:44 +0200 Subject: [PATCH 0245/1507] x86/fpu: Rename copyin_to_xsaves()/copyout_from_xsaves() to copy_user_to_xstate()/copy_xstate_to_user() The 'copyin/copyout' nomenclature needlessly departs from what the modern FPU code uses, which is: copy_fpregs_to_fpstate() copy_fpstate_to_sigframe() copy_fregs_to_user() copy_fxregs_to_kernel() copy_fxregs_to_user() copy_kernel_to_fpregs() copy_kernel_to_fregs() copy_kernel_to_fxregs() copy_kernel_to_xregs() copy_user_to_fregs() copy_user_to_fxregs() copy_user_to_xregs() copy_xregs_to_kernel() copy_xregs_to_user() I.e. according to this pattern, the following rename should be done: copyin_to_xsaves() -> copy_user_to_xstate() copyout_from_xsaves() -> copy_xstate_to_user() or, if we want to be pedantic, denote that that the user-space format is ptrace: copyin_to_xsaves() -> copy_user_ptrace_to_xstate() copyout_from_xsaves() -> copy_xstate_to_user_ptrace() But I'd suggest the shorter, non-pedantic name. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-2-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/regset.c | 4 ++-- arch/x86/kernel/fpu/signal.c | 2 +- arch/x86/kernel/fpu/xstate.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1b2799e0699a4..a1baa17e97480 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,8 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, +int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, +int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16841e37..165d0545c9242 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -92,7 +92,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + ret = copy_xstate_to_user(pos, count, kbuf, ubuf, xsave); } else { fpstate_sanitize_xstate(fpu); /* @@ -132,7 +132,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_write(fpu); if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); + ret = copy_user_to_xstate(kbuf, ubuf, xsave); else ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c230b4c4..b1fe9a1fc4e0e 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -324,7 +324,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, + err = copy_user_to_xstate(NULL, buf_fx, &fpu->state.xsave); } else { err = __copy_from_user(&fpu->state.xsave, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1efb12d7..e7bb41723eaad 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -951,7 +951,7 @@ static inline int xstate_copyout(unsigned int pos, unsigned int count, * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, +int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave) { unsigned int offset, size; @@ -1023,7 +1023,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, +int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave) { unsigned int offset, size; -- GitLab From f0d4f30a7fd299587840a028655285a87f334904 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:45 +0200 Subject: [PATCH 0246/1507] x86/fpu: Split copy_xstate_to_user() into copy_xstate_to_kernel() & copy_xstate_to_user() copy_xstate_to_user() is a weird API - in part due to a bad API inherited from the regset APIs. But don't propagate that bad API choice into the FPU code - so as a first step split the API into kernel and user buffer handling routines. (Also split the xstate_copyout() internal helper.) The split API is a dumb duplication that should be obviously correct, the real splitting will be done in the next patch. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-3-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 +- arch/x86/kernel/fpu/regset.c | 5 +- arch/x86/kernel/fpu/xstate.c | 110 ++++++++++++++++++++++++++++-- 3 files changed, 109 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index a1baa17e97480..92dc8ca141242 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,8 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave); +int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); +int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 165d0545c9242..b6d12d66d04b9 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -92,7 +92,10 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_read(fpu); if (using_compacted_format()) { - ret = copy_xstate_to_user(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(pos, count, kbuf, ubuf, xsave); + else + ret = copy_xstate_to_user(pos, count, kbuf, ubuf, xsave); } else { fpstate_sanitize_xstate(fpu); /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index e7bb41723eaad..38561539cb992 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -924,10 +924,106 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline int +__copy_xstate_to_kernel(unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf, + const void *data, const int start_pos, + const int end_pos) +{ + if ((count == 0) || (pos < start_pos)) + return 0; + + if (end_pos < 0 || pos < end_pos) { + unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + + if (kbuf) { + memcpy(kbuf + pos, data, copy); + } else { + if (__copy_to_user(ubuf + pos, data, copy)) + return -EFAULT; + } + } + return 0; +} + +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, + void __user *ubuf, struct xregs_state *xsave) +{ + unsigned int offset, size; + int ret, i; + struct xstate_header header; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(pos != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, &header, 0, count); + + if (ret) + return ret; + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, src, 0, count); + + if (ret) + return ret; + + if (offset + size >= count) + break; + } + + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); + + if (ret) + return ret; + + return 0; +} + +static inline int +__copy_xstate_to_user(unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf, + const void *data, const int start_pos, + const int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; @@ -977,7 +1073,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); + ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, &header, 0, count); if (ret) return ret; @@ -992,7 +1088,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, src, 0, count); if (ret) return ret; @@ -1009,7 +1105,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); + ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); if (ret) return ret; -- GitLab From 4d981cf2d96f29cdfa7d4972c8b377fe7baa9c4c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:46 +0200 Subject: [PATCH 0247/1507] x86/fpu: Remove 'ubuf' parameter from the copy_xstate_to_kernel() APIs The 'ubuf' parameter is unused in the _kernel() side of the API, remove it. This simplifies the code and makes it easier to think about. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-4-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 2 +- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/xstate.c | 21 ++++++--------------- 3 files changed, 8 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 92dc8ca141242..c762574a245fa 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,7 +48,7 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); +int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave); int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b6d12d66d04b9..34e74adf9d5d9 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -93,7 +93,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (using_compacted_format()) { if (kbuf) - ret = copy_xstate_to_kernel(pos, count, kbuf, ubuf, xsave); + ret = copy_xstate_to_kernel(pos, count, kbuf, xsave); else ret = copy_xstate_to_user(pos, count, kbuf, ubuf, xsave); } else { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 38561539cb992..71d3bda2b8984 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -926,7 +926,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ static inline int __copy_xstate_to_kernel(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, + void *kbuf, const void *data, const int start_pos, const int end_pos) { @@ -936,12 +936,7 @@ __copy_xstate_to_kernel(unsigned int pos, unsigned int count, if (end_pos < 0 || pos < end_pos) { unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; - } + memcpy(kbuf + pos, data, copy); } return 0; } @@ -953,8 +948,7 @@ __copy_xstate_to_kernel(unsigned int pos, unsigned int count, * It supports partial copy but pos always starts from zero. This is called * from xstateregs_get() and there we check the CPU has XSAVES. */ -int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave) { unsigned int offset, size; int ret, i; @@ -979,8 +973,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_kernel(offset, size, kbuf, &header, 0, count); if (ret) return ret; @@ -994,8 +987,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, src, 0, count); - + ret = __copy_xstate_to_kernel(offset, size, kbuf, src, 0, count); if (ret) return ret; @@ -1011,8 +1003,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_kernel(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_kernel(offset, size, kbuf, xstate_fx_sw_bytes, 0, count); if (ret) return ret; -- GitLab From a69c158fb3e7a91220f55029bf222a4e678d16e9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:47 +0200 Subject: [PATCH 0248/1507] x86/fpu: Remove 'kbuf' parameter from the copy_xstate_to_user() APIs The 'kbuf' parameter is unused in the _user() side of the API, remove it. This simplifies the code and makes it easier to think about. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-5-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 2 +- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/xstate.c | 25 +++++++------------------ 3 files changed, 9 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index c762574a245fa..65bd68c30cd09 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -49,7 +49,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave); -int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf, struct xregs_state *xsave); +int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, struct xregs_state *xsave); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 34e74adf9d5d9..fd6dbdd8fde63 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -95,7 +95,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (kbuf) ret = copy_xstate_to_kernel(pos, count, kbuf, xsave); else - ret = copy_xstate_to_user(pos, count, kbuf, ubuf, xsave); + ret = copy_xstate_to_user(pos, count, ubuf, xsave); } else { fpstate_sanitize_xstate(fpu); /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 71d3bda2b8984..2d8f3344875d5 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1011,10 +1011,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, stru } static inline int -__copy_xstate_to_user(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +__copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, const void *data, const int start_pos, const int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; @@ -1022,12 +1019,8 @@ __copy_xstate_to_user(unsigned int pos, unsigned int count, if (end_pos < 0 || pos < end_pos) { unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; - } + if (__copy_to_user(ubuf + pos, data, copy)) + return -EFAULT; } return 0; } @@ -1038,8 +1031,7 @@ __copy_xstate_to_user(unsigned int pos, unsigned int count, * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, struct xregs_state *xsave) { unsigned int offset, size; int ret, i; @@ -1064,8 +1056,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(offset, size, ubuf, &header, 0, count); if (ret) return ret; @@ -1079,8 +1070,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, src, 0, count); - + ret = __copy_xstate_to_user(offset, size, ubuf, src, 0, count); if (ret) return ret; @@ -1096,8 +1086,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_user(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(offset, size, ubuf, xstate_fx_sw_bytes, 0, count); if (ret) return ret; -- GitLab From d7eda6c99cc75f1c41d67abf988f37a10045a370 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:48 +0200 Subject: [PATCH 0249/1507] x86/fpu: Clean up parameter order in the copy_xstate_to_*() APIs Parameter ordering is weird: int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave); int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, struct xregs_state *xsave); 'pos' and 'count', which are attributes of the destination buffer, are listed before the destination buffer itself ... List them after the primary arguments instead. This makes the code more similar to regular memcpy() variant APIs. No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-6-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/regset.c | 4 ++-- arch/x86/kernel/fpu/xstate.c | 25 ++++++++++++------------- 3 files changed, 16 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 65bd68c30cd09..e4430b84939d1 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,8 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave); -int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, struct xregs_state *xsave); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int pos, unsigned int count); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int pos, unsigned int count); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index fd6dbdd8fde63..ec1404194b658 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -93,9 +93,9 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (using_compacted_format()) { if (kbuf) - ret = copy_xstate_to_kernel(pos, count, kbuf, xsave); + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); else - ret = copy_xstate_to_user(pos, count, ubuf, xsave); + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 2d8f3344875d5..0a299468510f9 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -925,10 +925,9 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * the source data pointer or increment pos, count, kbuf, and ubuf. */ static inline int -__copy_xstate_to_kernel(unsigned int pos, unsigned int count, - void *kbuf, - const void *data, const int start_pos, - const int end_pos) +__copy_xstate_to_kernel(void *kbuf, + const void *data, + unsigned int pos, unsigned int count, const int start_pos, const int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; @@ -948,7 +947,7 @@ __copy_xstate_to_kernel(unsigned int pos, unsigned int count, * It supports partial copy but pos always starts from zero. This is called * from xstateregs_get() and there we check the CPU has XSAVES. */ -int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, struct xregs_state *xsave) +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int pos, unsigned int count) { unsigned int offset, size; int ret, i; @@ -973,7 +972,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, stru offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_kernel(offset, size, kbuf, &header, 0, count); + ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, 0, count); if (ret) return ret; @@ -987,7 +986,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, stru offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_kernel(offset, size, kbuf, src, 0, count); + ret = __copy_xstate_to_kernel(kbuf, src, offset, size, 0, count); if (ret) return ret; @@ -1003,7 +1002,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, stru offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_kernel(offset, size, kbuf, xstate_fx_sw_bytes, 0, count); + ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, 0, count); if (ret) return ret; @@ -1011,7 +1010,7 @@ int copy_xstate_to_kernel(unsigned int pos, unsigned int count, void *kbuf, stru } static inline int -__copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, const void *data, const int start_pos, const int end_pos) +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, const int start_pos, const int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; @@ -1031,7 +1030,7 @@ __copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, c * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int pos, unsigned int count) { unsigned int offset, size; int ret, i; @@ -1056,7 +1055,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_user(offset, size, ubuf, &header, 0, count); + ret = __copy_xstate_to_user(ubuf, &header, offset, size, 0, count); if (ret) return ret; @@ -1070,7 +1069,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_user(offset, size, ubuf, src, 0, count); + ret = __copy_xstate_to_user(ubuf, src, offset, size, 0, count); if (ret) return ret; @@ -1086,7 +1085,7 @@ int copy_xstate_to_user(unsigned int pos, unsigned int count, void __user *ubuf, offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_user(offset, size, ubuf, xstate_fx_sw_bytes, 0, count); + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, 0, count); if (ret) return ret; -- GitLab From becb2bb72ff906cc0d2bac3ee9574f694364823b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:49 +0200 Subject: [PATCH 0250/1507] x86/fpu: Clean up the parameter definitions of copy_xstate_to_*() Remove pointless 'const' of non-pointer input parameter. Remove unnecessary parenthesis that shows uncertainty about arithmetic operator precedence. Clarify copy_xstate_to_user() description. No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-7-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0a299468510f9..9647e7256179d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -927,13 +927,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline int __copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int pos, unsigned int count, const int start_pos, const int end_pos) + unsigned int pos, unsigned int count, int start_pos, int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + unsigned int copy = end_pos < 0 ? count : min(count, end_pos - pos); memcpy(kbuf + pos, data, copy); } @@ -1010,13 +1010,13 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po } static inline int -__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, const int start_pos, const int end_pos) +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, int start_pos, int end_pos) { if ((count == 0) || (pos < start_pos)) return 0; if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + unsigned int copy = end_pos < 0 ? count : min(count, end_pos - pos); if (__copy_to_user(ubuf + pos, data, copy)) return -EFAULT; @@ -1026,7 +1026,7 @@ __copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, uns /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -- GitLab From 8a5b731889cbf004b406d988dc591c8a7aac773e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:50 +0200 Subject: [PATCH 0251/1507] x86/fpu: Remove the 'start_pos' parameter from the __copy_xstate_to_*() functions 'start_pos' is always 0, so remove it and remove the pointless check of 'pos < 0' which can not ever be true as 'pos' is unsigned ... No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-8-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 9647e7256179d..1f50fdaf4c5a6 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -927,9 +927,9 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline int __copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int pos, unsigned int count, int start_pos, int end_pos) + unsigned int pos, unsigned int count, int end_pos) { - if ((count == 0) || (pos < start_pos)) + if (!count) return 0; if (end_pos < 0 || pos < end_pos) { @@ -972,7 +972,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, 0, count); + ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, count); if (ret) return ret; @@ -986,7 +986,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_kernel(kbuf, src, offset, size, 0, count); + ret = __copy_xstate_to_kernel(kbuf, src, offset, size, count); if (ret) return ret; @@ -1002,7 +1002,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, 0, count); + ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, count); if (ret) return ret; @@ -1010,9 +1010,9 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po } static inline int -__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, int start_pos, int end_pos) +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, int end_pos) { - if ((count == 0) || (pos < start_pos)) + if (!count) return 0; if (end_pos < 0 || pos < end_pos) { @@ -1055,7 +1055,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_user(ubuf, &header, offset, size, 0, count); + ret = __copy_xstate_to_user(ubuf, &header, offset, size, count); if (ret) return ret; @@ -1069,7 +1069,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_user(ubuf, src, offset, size, 0, count); + ret = __copy_xstate_to_user(ubuf, src, offset, size, count); if (ret) return ret; @@ -1085,7 +1085,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, 0, count); + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, count); if (ret) return ret; -- GitLab From 56583c9a1400fe1935edd55b24b4fbbc779b59cb Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:51 +0200 Subject: [PATCH 0252/1507] x86/fpu: Clarify parameter names in the copy_xstate_to_*() methods Right now there's a confusing mixture of 'offset' and 'size' parameters: - __copy_xstate_to_*() input parameter 'end_pos' not not really an offset, but the full size of the copy to be performed. - input parameter 'count' to copy_xstate_to_*() shadows that of __copy_xstate_to_*()'s 'count' parameter name - but the roles are different: the first one is the total number of bytes to be copied, while the second one is a partial copy size. To unconfuse all this, use a consistent set of parameter names: - 'size' is the partial copy size within a single xstate component - 'size_total' is the total copy requested - 'offset_start' is the requested starting offset. - 'offset' is the offset within an xstate component. No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-9-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 +-- arch/x86/kernel/fpu/xstate.c | 44 +++++++++++++++---------------- 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index e4430b84939d1..fed6617a1079b 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -48,8 +48,8 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int pos, unsigned int count); -int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int pos, unsigned int count); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1f50fdaf4c5a6..c13083579655a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -927,15 +927,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline int __copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int pos, unsigned int count, int end_pos) + unsigned int offset, unsigned int size, int size_total) { - if (!count) + if (!size) return 0; - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = end_pos < 0 ? count : min(count, end_pos - pos); + if (size_total < 0 || offset < size_total) { + unsigned int copy = size_total < 0 ? size : min(size, size_total - offset); - memcpy(kbuf + pos, data, copy); + memcpy(kbuf + offset, data, copy); } return 0; } @@ -947,7 +947,7 @@ __copy_xstate_to_kernel(void *kbuf, * It supports partial copy but pos always starts from zero. This is called * from xstateregs_get() and there we check the CPU has XSAVES. */ -int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int pos, unsigned int count) +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -956,7 +956,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -972,7 +972,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, count); + ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); if (ret) return ret; @@ -986,11 +986,11 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_kernel(kbuf, src, offset, size, count); + ret = __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); if (ret) return ret; - if (offset + size >= count) + if (offset + size >= size_total) break; } @@ -1002,7 +1002,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, count); + ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1010,15 +1010,15 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int po } static inline int -__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, unsigned int count, int end_pos) +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, int size_total) { - if (!count) + if (!size) return 0; - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = end_pos < 0 ? count : min(count, end_pos - pos); + if (size_total < 0 || offset < size_total) { + unsigned int copy = size_total < 0 ? size : min(size, size_total - offset); - if (__copy_to_user(ubuf + pos, data, copy)) + if (__copy_to_user(ubuf + offset, data, copy)) return -EFAULT; } return 0; @@ -1030,7 +1030,7 @@ __copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int pos, uns * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int pos, unsigned int count) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -1039,7 +1039,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -1055,7 +1055,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_user(ubuf, &header, offset, size, count); + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -1069,11 +1069,11 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = __copy_xstate_to_user(ubuf, src, offset, size, count); + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - if (offset + size >= count) + if (offset + size >= size_total) break; } @@ -1085,7 +1085,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, count); + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; -- GitLab From 6ff15f8db7eaf29ef5ead6afbec9b25485fe8703 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:52 +0200 Subject: [PATCH 0253/1507] x86/fpu: Change 'size_total' parameter to unsigned and standardize the size checks in copy_xstate_to_*() 'size_total' is derived from an unsigned input parameter - and then converted to 'int' and checked for negative ranges: if (size_total < 0 || offset < size_total) { This conversion and the checks are unnecessary obfuscation, reject overly large requested copy sizes outright and simplify the underlying code. Reported-by: Rik van Riel Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-10-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c13083579655a..b18c5457065ab 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -925,15 +925,11 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * the source data pointer or increment pos, count, kbuf, and ubuf. */ static inline int -__copy_xstate_to_kernel(void *kbuf, - const void *data, - unsigned int offset, unsigned int size, int size_total) +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if (!size) - return 0; - - if (size_total < 0 || offset < size_total) { - unsigned int copy = size_total < 0 ? size : min(size, size_total - offset); + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); memcpy(kbuf + offset, data, copy); } @@ -986,12 +982,13 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of offset = xstate_offsets[i]; size = xstate_sizes[i]; + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= size_total) - break; } } @@ -1010,13 +1007,13 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of } static inline int -__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, int size_total) +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) { if (!size) return 0; - if (size_total < 0 || offset < size_total) { - unsigned int copy = size_total < 0 ? size : min(size, size_total - offset); + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); if (__copy_to_user(ubuf + offset, data, copy)) return -EFAULT; @@ -1069,12 +1066,13 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i offset = xstate_offsets[i]; size = xstate_sizes[i]; + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= size_total) - break; } } -- GitLab From 8c0817f4a3188ac5485ce14f96f12a175800b881 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:53 +0200 Subject: [PATCH 0254/1507] x86/fpu: Simplify __copy_xstate_to_kernel() return values __copy_xstate_to_kernel() can only return 0 (because kernel copies cannot fail), simplify the code throughout. No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-11-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b18c5457065ab..00c3b41c3cf1a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -924,7 +924,7 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int +static inline void __copy_xstate_to_kernel(void *kbuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) { @@ -933,7 +933,6 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, memcpy(kbuf + offset, data, copy); } - return 0; } /* @@ -946,8 +945,8 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; - int ret, i; struct xstate_header header; + int i; /* * Currently copy_regset_to_user() starts from pos 0: @@ -968,9 +967,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); - if (ret) - return ret; + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); for (i = 0; i < XFEATURE_MAX; i++) { /* @@ -986,9 +983,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of if (offset + size > size_total) break; - ret = __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); - if (ret) - return ret; + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } } @@ -999,9 +994,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); - if (ret) - return ret; + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); return 0; } -- GitLab From 79fecc2b7506f29fb91becc65e8788e5ae7eba9f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:54 +0200 Subject: [PATCH 0255/1507] x86/fpu: Split copy_user_to_xstate() into copy_kernel_to_xstate() & copy_user_to_xstate() Similar to: x86/fpu: Split copy_xstate_to_user() into copy_xstate_to_kernel() & copy_xstate_to_user() No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-12-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 +- arch/x86/kernel/fpu/regset.c | 10 +++-- arch/x86/kernel/fpu/xstate.c | 66 ++++++++++++++++++++++++++++++- 3 files changed, 74 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index fed6617a1079b..79af79dbcab67 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -50,6 +50,6 @@ const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); -int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave); +int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); +int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index ec1404194b658..cb45dd81d6170 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -134,10 +134,14 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, fpu__activate_fpstate_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copy_user_to_xstate(kbuf, ubuf, xsave); - else + if (boot_cpu_has(X86_FEATURE_XSAVES)) { + if (kbuf) + ret = copy_kernel_to_xstate(kbuf, ubuf, xsave); + else + ret = copy_user_to_xstate(kbuf, ubuf, xsave); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + } /* * In case of failure, mark all states as init: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 00c3b41c3cf1a..1ad25d1b80561 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1084,7 +1084,71 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set() and + * there we check the CPU has XSAVES and a whole standard-sized buffer + * exists. + */ +int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, + struct xregs_state *xsave) +{ + unsigned int offset, size; + int i; + u64 xfeatures; + u64 allowed_features; + + offset = offsetof(struct xregs_state, header); + size = sizeof(xfeatures); + + if (kbuf) { + memcpy(&xfeatures, kbuf + offset, size); + } else { + if (__copy_from_user(&xfeatures, ubuf + offset, size)) + return -EFAULT; + } + + /* + * Reject if the user sets any disabled or supervisor features: + */ + allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + + if (xfeatures & ~allowed_features) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + if (kbuf) { + memcpy(dst, kbuf + offset, size); + } else { + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; + } + } + } + + /* + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: + */ + xsave->header.xfeatures |= xfeatures; + + return 0; +} + +/* + * Convert from a ptrace standard-format user-space buffer to kernel XSAVES format * and copy to the target thread. This is called from xstateregs_set() and * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. -- GitLab From 59dffa4edba1f15b2bfdbe608aca1efe664c674c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:55 +0200 Subject: [PATCH 0256/1507] x86/fpu: Remove 'ubuf' parameter from the copy_kernel_to_xstate() API No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-13-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 2 +- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/xstate.c | 17 +++-------------- 3 files changed, 5 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 79af79dbcab67..f10889bc0c88f 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -50,6 +50,6 @@ const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); -int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); +int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave); int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index cb45dd81d6170..785302c75f386 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -136,7 +136,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (boot_cpu_has(X86_FEATURE_XSAVES)) { if (kbuf) - ret = copy_kernel_to_xstate(kbuf, ubuf, xsave); + ret = copy_kernel_to_xstate(kbuf, xsave); else ret = copy_user_to_xstate(kbuf, ubuf, xsave); } else { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1ad25d1b80561..71cc8d367fdd1 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1089,8 +1089,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. */ -int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave) { unsigned int offset, size; int i; @@ -1100,12 +1099,7 @@ int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, offset = offsetof(struct xregs_state, header); size = sizeof(xfeatures); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; - } + memcpy(&xfeatures, kbuf + offset, size); /* * Reject if the user sets any disabled or supervisor features: @@ -1124,12 +1118,7 @@ int copy_kernel_to_xstate(const void *kbuf, const void __user *ubuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + memcpy(dst, kbuf + offset, size); } } -- GitLab From 7b9094c688f807c110a2dab6f6edc5876bfa7b0b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:56 +0200 Subject: [PATCH 0257/1507] x86/fpu: Remove 'kbuf' parameter from the copy_user_to_xstate() API No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-14-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 2 +- arch/x86/kernel/fpu/regset.c | 2 +- arch/x86/kernel/fpu/signal.c | 11 ++++------- arch/x86/kernel/fpu/xstate.c | 19 +++++-------------- 4 files changed, 11 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index f10889bc0c88f..4ceb90740d802 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -51,5 +51,5 @@ int using_compacted_format(void); int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave); -int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, struct xregs_state *xsave); +int copy_user_to_xstate(const void __user *ubuf, struct xregs_state *xsave); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 785302c75f386..caf723f317373 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -138,7 +138,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (kbuf) ret = copy_kernel_to_xstate(kbuf, xsave); else - ret = copy_user_to_xstate(kbuf, ubuf, xsave); + ret = copy_user_to_xstate(ubuf, xsave); } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index b1fe9a1fc4e0e..2c685b492fd6f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -323,13 +323,10 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ fpu__drop(fpu); - if (using_compacted_format()) { - err = copy_user_to_xstate(NULL, buf_fx, - &fpu->state.xsave); - } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); - } + if (using_compacted_format()) + err = copy_user_to_xstate(buf_fx, &fpu->state.xsave); + else + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); if (err || __copy_from_user(&env, buf, sizeof(env))) { fpstate_init(&fpu->state); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 71cc8d367fdd1..b1f3e4dae2e36 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1142,8 +1142,7 @@ int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave) * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. */ -int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_user_to_xstate(const void __user *ubuf, struct xregs_state *xsave) { unsigned int offset, size; int i; @@ -1153,12 +1152,8 @@ int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, offset = offsetof(struct xregs_state, header); size = sizeof(xfeatures); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(&xfeatures, ubuf + offset, size)) + return -EFAULT; /* * Reject if the user sets any disabled or supervisor features: @@ -1177,12 +1172,8 @@ int copy_user_to_xstate(const void *kbuf, const void __user *ubuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } -- GitLab From 6d7f7da5533a3f841eeb1d9657257c9367924274 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:57 +0200 Subject: [PATCH 0258/1507] x86/fpu: Flip the parameter order in copy_*_to_xstate() Make it more consistent with regular memcpy() semantics, where the destination argument comes first. No change in functionality. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-15-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 ++-- arch/x86/kernel/fpu/regset.c | 4 ++-- arch/x86/kernel/fpu/signal.c | 2 +- arch/x86/kernel/fpu/xstate.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 4ceb90740d802..579ac2358e63b 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -50,6 +50,6 @@ const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); -int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave); -int copy_user_to_xstate(const void __user *ubuf, struct xregs_state *xsave); +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); #endif diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index caf723f317373..19a7385a912cc 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -136,9 +136,9 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (boot_cpu_has(X86_FEATURE_XSAVES)) { if (kbuf) - ret = copy_kernel_to_xstate(kbuf, xsave); + ret = copy_kernel_to_xstate(xsave, kbuf); else - ret = copy_user_to_xstate(ubuf, xsave); + ret = copy_user_to_xstate(xsave, ubuf); } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 2c685b492fd6f..2d682dac35d4c 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -324,7 +324,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpu__drop(fpu); if (using_compacted_format()) - err = copy_user_to_xstate(buf_fx, &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); else err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b1f3e4dae2e36..0ef35040d0ad0 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1089,7 +1089,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. */ -int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; @@ -1142,7 +1142,7 @@ int copy_kernel_to_xstate(const void *kbuf, struct xregs_state *xsave) * there we check the CPU has XSAVES and a whole standard-sized buffer * exists. */ -int copy_user_to_xstate(const void __user *ubuf, struct xregs_state *xsave) +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) { unsigned int offset, size; int i; -- GitLab From b3a163081c28d1a4d1ad76259a9d93b34a82f1da Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:58 +0200 Subject: [PATCH 0259/1507] x86/fpu: Simplify fpu->fpregs_active use The fpregs_active() inline function is pretty pointless - in almost all the callsites it can be replaced with a direct fpu->fpregs_active access. Do so and eliminate the extra layer of obfuscation. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-16-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 17 +---------------- arch/x86/kernel/fpu/core.c | 2 +- arch/x86/kernel/fpu/signal.c | 9 +++++---- arch/x86/mm/pkeys.c | 2 +- 4 files changed, 8 insertions(+), 22 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 554cdb205d175..b223c57dd5dc3 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -542,21 +542,6 @@ static inline void fpregs_activate(struct fpu *fpu) trace_x86_fpu_regs_activated(fpu); } -/* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int fpregs_active(void) -{ - return current->thread.fpu.fpregs_active; -} - /* * FPU state switching for scheduling. * @@ -617,7 +602,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpregs_active()) + if (!fpu->fpregs_active) fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f070c2df..bad57248e5a03 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -367,7 +367,7 @@ void fpu__current_fpstate_write_end(void) * registers may still be out of date. Update them with * an XRSTOR if they are active. */ - if (fpregs_active()) + if (fpu->fpregs_active) copy_kernel_to_fpregs(&fpu->state); /* diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 2d682dac35d4c..684025654d0cc 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -155,7 +155,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +171,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->fpregs_active || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +190,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 2dab69a706ec0..e2c23472233e0 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -45,7 +45,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - fpregs_active() && + current->thread.fpu.fpregs_active && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; -- GitLab From a10b6a16cdad88170f546d008c77453cddf918e6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 14:59:59 +0200 Subject: [PATCH 0260/1507] x86/fpu: Make the fpu state change in fpu__clear() scheduler-atomic Do this temporarily only, to make it easier to change the FPU state machine, in particular this change couples the fpu->fpregs_active and fpu->fpstate_active states: they are only set/cleared together (as far as the scheduler sees them). This will be removed by later patches. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-17-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index bad57248e5a03..b7dc3833d41a9 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -462,9 +462,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { + preempt_disable(); fpu__activate_curr(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } -- GitLab From b6aa85558d7e7b18fc3470d2bc1731d2205dd275 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:00 +0200 Subject: [PATCH 0261/1507] x86/fpu: Split the state handling in fpu__drop() Prepare fpu__drop() to use fpu->fpregs_active. There are two distinct usecases for fpu__drop() in this context: exit_thread() when called for 'current' in exit(), and when called for another task in fork(). This patch does not change behavior, it only adds a couple of debug checks and structures the code to make the ->fpregs_active change more obviously correct. All the complications will be removed later on. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-18-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index b7dc3833d41a9..815dfba7781a6 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -414,12 +414,19 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); + + if (fpu->fpregs_active) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + if (fpu->fpregs_active) + fpregs_deactivate(fpu); + } + } else { + WARN_ON_FPU(fpu->fpregs_active); } fpu->fpstate_active = 0; -- GitLab From f1c8cd0176078c7bcafdc89cac447cab672a0b5e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:01 +0200 Subject: [PATCH 0262/1507] x86/fpu: Change fpu->fpregs_active users to fpu->fpstate_active We want to simplify the FPU state machine by eliminating fpu->fpregs_active, and we can do that because the two state flags (::fpregs_active and ::fpstate_active) are set essentially together. The old lazy FPU switching code used to make a distinction - but there's no lazy switching code anymore, we always switch in an 'eager' fashion. Do this by first changing all substantial uses of fpu->fpregs_active to fpu->fpstate_active and adding a few debug checks to double check our assumption is correct. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-19-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 4 +++- arch/x86/kernel/fpu/core.c | 16 ++++++++++------ arch/x86/kernel/fpu/signal.c | 4 +++- arch/x86/mm/pkeys.c | 3 +-- 4 files changed, 17 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index b223c57dd5dc3..7fa676f93ac1d 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -556,7 +556,9 @@ static inline void fpregs_activate(struct fpu *fpu) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpregs_active) { + WARN_ON_FPU(old_fpu->fpregs_active != old_fpu->fpstate_active); + + if (old_fpu->fpstate_active) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 815dfba7781a6..eab2446224025 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->fpstate_active) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->fpstate_active) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -147,8 +147,10 @@ void fpu__save(struct fpu *fpu) WARN_ON_FPU(fpu != ¤t->thread.fpu); preempt_disable(); + WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); + trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->fpstate_active) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -262,11 +264,12 @@ EXPORT_SYMBOL_GPL(fpu__activate_curr); */ void fpu__activate_fpstate_read(struct fpu *fpu) { + WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); /* * If fpregs are active (in the current CPU), then * copy them to the fpstate: */ - if (fpu->fpregs_active) { + if (fpu->fpstate_active) { fpu__save(fpu); } else { if (!fpu->fpstate_active) { @@ -362,12 +365,13 @@ void fpu__current_fpstate_write_end(void) { struct fpu *fpu = ¤t->thread.fpu; + WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); /* * 'fpu' now has an updated copy of the state, but the * registers may still be out of date. Update them with * an XRSTOR if they are active. */ - if (fpu->fpregs_active) + if (fpu->fpstate_active) copy_kernel_to_fpregs(&fpu->state); /* @@ -417,7 +421,7 @@ void fpu__drop(struct fpu *fpu) if (fpu == ¤t->thread.fpu) { WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); - if (fpu->fpregs_active) { + if (fpu->fpstate_active) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 684025654d0cc..a88083ba7f8bd 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -171,7 +171,9 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpu->fpregs_active || using_compacted_format()) { + WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); + + if (fpu->fpstate_active || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index e2c23472233e0..4d24269c071f4 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -18,7 +18,6 @@ #include /* boot_cpu_has, ... */ #include /* vma_pkey() */ -#include /* fpregs_active() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - current->thread.fpu.fpregs_active && + current->thread.fpu.fpstate_active && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; -- GitLab From 6cf4edbe0526db311a28734609da888fdfcb3604 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:02 +0200 Subject: [PATCH 0263/1507] x86/fpu: Decouple fpregs_activate()/fpregs_deactivate() from fpu->fpregs_active The fpregs_activate()/fpregs_deactivate() are currently called in such a pattern: if (!fpu->fpregs_active) fpregs_activate(fpu); ... if (fpu->fpregs_active) fpregs_deactivate(fpu); But note that it's actually safe to call them without checking the flag first. This further decouples the fpu->fpregs_active flag from actual FPU logic. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-20-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 7 +------ arch/x86/kernel/fpu/core.c | 3 +-- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 7fa676f93ac1d..42a601673c090 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -526,8 +526,6 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - WARN_ON_FPU(!fpu->fpregs_active); - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); @@ -535,8 +533,6 @@ static inline void fpregs_deactivate(struct fpu *fpu) static inline void fpregs_activate(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpregs_active); - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); @@ -604,8 +600,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpu->fpregs_active) - fpregs_activate(fpu); + fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eab2446224025..01a47e9edfb45 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,8 +426,7 @@ void fpu__drop(struct fpu *fpu) asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); - if (fpu->fpregs_active) - fpregs_deactivate(fpu); + fpregs_deactivate(fpu); } } else { WARN_ON_FPU(fpu->fpregs_active); -- GitLab From 99dc26bda233ee722bbd370bddf20beece3ffb93 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:03 +0200 Subject: [PATCH 0264/1507] x86/fpu: Remove struct fpu::fpregs_active The previous changes paved the way for the removal of the fpu::fpregs_active state flag - we now only have the fpu::fpstate_active and fpu::last_cpu fields left. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-21-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 5 ----- arch/x86/include/asm/fpu/types.h | 23 ----------------------- arch/x86/include/asm/trace/fpu.h | 5 +---- arch/x86/kernel/fpu/core.c | 9 --------- arch/x86/kernel/fpu/signal.c | 2 -- 5 files changed, 1 insertion(+), 43 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 42a601673c090..629e7abcd6c99 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -526,14 +526,12 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } @@ -552,8 +550,6 @@ static inline void fpregs_activate(struct fpu *fpu) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - WARN_ON_FPU(old_fpu->fpregs_active != old_fpu->fpstate_active); - if (old_fpu->fpstate_active) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; @@ -561,7 +557,6 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ - old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); } else old_fpu->last_cpu = -1; diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 3c80f5b9c09d8..0c314a397cf52 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -298,29 +298,6 @@ struct fpu { */ unsigned char fpstate_active; - /* - * @fpregs_active: - * - * This flag determines whether a given context is actively - * loaded into the FPU's registers and that those registers - * represent the task's current FPU state. - * - * Note the interaction with fpstate_active: - * - * # task does not use the FPU: - * fpstate_active == 0 - * - * # task uses the FPU and regs are active: - * fpstate_active == 1 && fpregs_active == 1 - * - * # the regs are inactive but still match fpstate: - * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu - * - * The third state is what we use for the lazy restore optimization - * on lazy-switching CPUs. - */ - unsigned char fpregs_active; - /* * @state: * diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 342e59789fcdc..da565aae9fd25 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -12,7 +12,6 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpregs_active) __field(bool, fpstate_active) __field(u64, xfeatures) __field(u64, xcomp_bv) @@ -20,16 +19,14 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_fast_assign( __entry->fpu = fpu; - __entry->fpregs_active = fpu->fpregs_active; __entry->fpstate_active = fpu->fpstate_active; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpregs_active, __entry->fpstate_active, __entry->xfeatures, __entry->xcomp_bv diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 01a47e9edfb45..93103a909c471 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -147,8 +147,6 @@ void fpu__save(struct fpu *fpu) WARN_ON_FPU(fpu != ¤t->thread.fpu); preempt_disable(); - WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); - trace_x86_fpu_before_save(fpu); if (fpu->fpstate_active) { if (!copy_fpregs_to_fpstate(fpu)) { @@ -191,7 +189,6 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) @@ -264,7 +261,6 @@ EXPORT_SYMBOL_GPL(fpu__activate_curr); */ void fpu__activate_fpstate_read(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); /* * If fpregs are active (in the current CPU), then * copy them to the fpstate: @@ -365,7 +361,6 @@ void fpu__current_fpstate_write_end(void) { struct fpu *fpu = ¤t->thread.fpu; - WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); /* * 'fpu' now has an updated copy of the state, but the * registers may still be out of date. Update them with @@ -419,8 +414,6 @@ void fpu__drop(struct fpu *fpu) preempt_disable(); if (fpu == ¤t->thread.fpu) { - WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); - if (fpu->fpstate_active) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" @@ -428,8 +421,6 @@ void fpu__drop(struct fpu *fpu) _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } - } else { - WARN_ON_FPU(fpu->fpregs_active); } fpu->fpstate_active = 0; diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a88083ba7f8bd..629106e51a297 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -171,8 +171,6 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - WARN_ON_FPU(fpu->fpstate_active != fpu->fpregs_active); - if (fpu->fpstate_active || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) -- GitLab From 0852b374173bb57f870d78e6c6839c77b339be5f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Sat, 23 Sep 2017 15:00:04 +0200 Subject: [PATCH 0265/1507] x86/fpu: Add FPU state copying quirk to handle XRSTOR failure on Intel Skylake CPUs On Skylake CPUs I noticed that XRSTOR is unable to deal with states created by copyout_from_xsaves() if the xstate has only SSE/YMM state, and no FP state. That is, xfeatures had XFEATURE_MASK_SSE set, but not XFEATURE_MASK_FP. The reason is that part of the SSE/YMM state lives in the MXCSR and MXCSR_FLAGS fields of the FP state. Ensure that whenever we copy SSE or YMM state around, the MXCSR and MXCSR_FLAGS fields are also copied around. Signed-off-by: Rik van Riel Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170210085445.0f1cc708@annuminas.surriel.com Link: http://lkml.kernel.org/r/20170923130016.21448-22-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/types.h | 3 +++ arch/x86/kernel/fpu/xstate.c | 42 ++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 0c314a397cf52..71db45ca88708 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -68,6 +68,9 @@ struct fxregs_state { /* Default value for fxregs_state.mxcsr: */ #define MXCSR_DEFAULT 0x1f80 +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + /* * Software based FPU emulation state. This is arbitrary really, * it matches the x87 format to make it easier to understand: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0ef35040d0ad0..41c52256bdce6 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -920,6 +920,23 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, } #endif /* ! CONFIG_ARCH_HAS_PKEYS */ +/* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return 0; + + if (xfeatures & XFEATURE_MASK_FP) + return 0; + + return 1; +} + /* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. @@ -988,6 +1005,12 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ @@ -1070,6 +1093,12 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ @@ -1122,6 +1151,12 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) } } + if (xfeatures_mxcsr_quirk(xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1177,6 +1212,13 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) } } + if (xfeatures_mxcsr_quirk(xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': -- GitLab From 4f8cef59bad29344aca0e2e6b0ad18dadd078fd0 Mon Sep 17 00:00:00 2001 From: kbuild test robot Date: Sat, 23 Sep 2017 15:00:05 +0200 Subject: [PATCH 0266/1507] x86/fpu: Fix boolreturn.cocci warnings arch/x86/kernel/fpu/xstate.c:931:9-10: WARNING: return of 0/1 in function 'xfeatures_mxcsr_quirk' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Generated by: scripts/coccinelle/misc/boolreturn.cocci Signed-off-by: Fengguang Wu Signed-off-by: Thomas Gleixner Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Yu-cheng Yu Cc: kbuild-all@01.org Cc: tipbuild@zytor.com Link: http://lkml.kernel.org/r/20170306004553.GA25764@lkp-wsm-ep1 Link: http://lkml.kernel.org/r/20170923130016.21448-23-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 41c52256bdce6..fda1109cc3553 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -929,12 +929,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) { if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) - return 0; + return false; if (xfeatures & XFEATURE_MASK_FP) - return 0; + return false; - return 1; + return true; } /* -- GitLab From 03eaec81ac09814817e9f0307d572ffe8365f980 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Sat, 23 Sep 2017 15:00:06 +0200 Subject: [PATCH 0267/1507] x86/fpu: Turn WARN_ON() in context switch into WARN_ON_FPU() copy_xregs_to_kernel checks if the alternatives have been already patched. This WARN_ON() is always executed in every context switch. All the other checks in fpu internal.h are WARN_ON_FPU(), but this one is plain WARN_ON(). I assume it was forgotten to switch it. So switch it to WARN_ON_FPU() too to avoid some unnecessary code in the context switch, and a potentially expensive cache line miss for the global variable. Signed-off-by: Andi Kleen Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170329062605.4970-1-andi@firstfloor.org Link: http://lkml.kernel.org/r/20170923130016.21448-24-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 629e7abcd6c99..2dca7c65319cd 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -350,7 +350,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u32 hmask = mask >> 32; int err; - WARN_ON(!alternatives_patched); + WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); -- GitLab From 245a396a9b1a67ac5c3228737c261b3e48708a2a Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 23 Sep 2017 08:06:18 +0200 Subject: [PATCH 0268/1507] iio: adc: twl4030: Fix an error handling path in 'twl4030_madc_probe()' If 'devm_regulator_get()' fails, we should go through the existing error handling path instead of returning directly, as done is all the other error handling paths in this function. Fixes: 7cc97d77ee8a ("iio: adc: twl4030: Fix ADC[3:6] readings") Signed-off-by: Christophe JAILLET Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/twl4030-madc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index bd3d37fc21442..252f5890311ee 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -887,8 +887,10 @@ static int twl4030_madc_probe(struct platform_device *pdev) /* Enable 3v1 bias regulator for MADC[3:6] */ madc->usb3v1 = devm_regulator_get(madc->dev, "vusb3v1"); - if (IS_ERR(madc->usb3v1)) - return -ENODEV; + if (IS_ERR(madc->usb3v1)) { + ret = -ENODEV; + goto err_i2c; + } ret = regulator_enable(madc->usb3v1); if (ret) -- GitLab From 7f70be6e4025db0551e6863e7eb9cca07122695c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 23 Sep 2017 08:06:19 +0200 Subject: [PATCH 0269/1507] iio: adc: twl4030: Disable the vusb3v1 rugulator in the error handling path of 'twl4030_madc_probe()' Commit 7cc97d77ee8a has introduced a call to 'regulator_disable()' in the .remove function. So we should also have such a call in the .probe function in case of error after a successful 'regulator_enable()' call. Add a new label for that and use it. Fixes: 7cc97d77ee8a ("iio: adc: twl4030: Fix ADC[3:6] readings") Signed-off-by: Christophe JAILLET Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/twl4030-madc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index 252f5890311ee..0c86fbb3033e4 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -899,11 +899,13 @@ static int twl4030_madc_probe(struct platform_device *pdev) ret = iio_device_register(iio_dev); if (ret) { dev_err(&pdev->dev, "could not register iio device\n"); - goto err_i2c; + goto err_usb3v1; } return 0; +err_usb3v1: + regulator_disable(madc->usb3v1); err_i2c: twl4030_madc_set_current_generator(madc, 0, 0); err_current_generator: -- GitLab From 53063846affd27def6f96e13a9fb80b9a3c2d126 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 23 Sep 2017 08:06:20 +0200 Subject: [PATCH 0270/1507] iio: adc: twl4030: Return an error if we can not enable the vusb3v1 regulator in 'twl4030_madc_probe()' If we can not enable the regulator, go through the error handling path instead of silently continuing. Fixes: 7cc97d77ee8a ("iio: adc: twl4030: Fix ADC[3:6] readings") Signed-off-by: Christophe JAILLET Signed-off-by: Jonathan Cameron --- drivers/iio/adc/twl4030-madc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c index 0c86fbb3033e4..28df096e84ec8 100644 --- a/drivers/iio/adc/twl4030-madc.c +++ b/drivers/iio/adc/twl4030-madc.c @@ -893,8 +893,10 @@ static int twl4030_madc_probe(struct platform_device *pdev) } ret = regulator_enable(madc->usb3v1); - if (ret) + if (ret) { dev_err(madc->dev, "could not enable 3v1 bias regulator\n"); + goto err_i2c; + } ret = iio_device_register(iio_dev); if (ret) { -- GitLab From 0a56eabc4e3f730782e4a9f3af4f60aa03a8a849 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 18 Sep 2017 12:05:30 +0200 Subject: [PATCH 0271/1507] iio: trigger: stm32-timer: preset shouldn't be buffered Currently, setting preset value (ARR) will update directly 'Auto reload value' only on 1st write access. But then, ARPE is set. This makes ARR a shadow register. Preset value should be updated upon each write request: ensure ARPE is 0. This fixes successive writes to preset attribute. Fixes: 4adec7da0536 ("iio: stm32 trigger: Add quadrature encoder device") Signed-off-by: Fabrice Gasnier Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/trigger/stm32-timer-trigger.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index a9bc5b603b86f..4cec28af3ecfe 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -681,8 +681,9 @@ static ssize_t stm32_count_set_preset(struct iio_dev *indio_dev, if (ret) return ret; + /* TIMx_ARR register shouldn't be buffered (ARPE=0) */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_write(priv->regmap, TIM_ARR, preset); - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, TIM_CR1_ARPE); return len; } -- GitLab From b7a9776c1f9443326632486fcbd82dca82f8511e Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 18 Sep 2017 12:05:31 +0200 Subject: [PATCH 0272/1507] iio: trigger: stm32-timer: fix a corner case to write preset Balance timer start routine that sets ARPE: clear it in stop routine. This fixes a corner case, when timer is used successively as trigger (with sampling_frequency start/stop routines), then as a counter (with preset). Fixes: 93fbe91b5521 ("iio: Add STM32 timer trigger driver") Signed-off-by: Fabrice Gasnier Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/trigger/stm32-timer-trigger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 4cec28af3ecfe..a30ba6e1dfec5 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -174,6 +174,7 @@ static void stm32_timer_stop(struct stm32_timer_trigger *priv) clk_disable(priv->clk); /* Stop timer */ + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0); regmap_write(priv->regmap, TIM_PSC, 0); regmap_write(priv->regmap, TIM_ARR, 0); -- GitLab From 4fb840c95f82652cece7352be9080884cafb92a0 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 18 Sep 2017 18:24:15 +0200 Subject: [PATCH 0273/1507] iio: adc: stm32: fix bad error check on max_channels Fix a bad error check when counting 'st,adc-channels' array elements. This is seen when all channels are in use simultaneously. Fixes: 64ad7f643 ("iio: adc: stm32: introduce compatible data cfg") Signed-off-by: Fabrice Gasnier Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/stm32-adc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 6bc602891f2f0..e93244bc3edd8 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1656,7 +1656,7 @@ static int stm32_adc_chan_of_init(struct iio_dev *indio_dev) num_channels = of_property_count_u32_elems(node, "st,adc-channels"); if (num_channels < 0 || - num_channels >= adc_info->max_channels) { + num_channels > adc_info->max_channels) { dev_err(&indio_dev->dev, "Bad st,adc-channels?\n"); return num_channels < 0 ? num_channels : -EINVAL; } -- GitLab From 0964e40947a630a2a6f724e968246992f97bcf1c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 22 Aug 2017 15:33:00 +0200 Subject: [PATCH 0274/1507] iio: adc: mcp320x: Fix oops on module unload The driver calls spi_get_drvdata() in its ->remove hook even though it has never called spi_set_drvdata(). Stack trace for posterity: Unable to handle kernel NULL pointer dereference at virtual address 00000220 Internal error: Oops: 5 [#1] SMP ARM [<8072f564>] (mutex_lock) from [<7f1400d0>] (iio_device_unregister+0x24/0x7c [industrialio]) [<7f1400d0>] (iio_device_unregister [industrialio]) from [<7f15e020>] (mcp320x_remove+0x20/0x30 [mcp320x]) [<7f15e020>] (mcp320x_remove [mcp320x]) from [<8055a8cc>] (spi_drv_remove+0x2c/0x44) [<8055a8cc>] (spi_drv_remove) from [<805087bc>] (__device_release_driver+0x98/0x134) [<805087bc>] (__device_release_driver) from [<80509180>] (driver_detach+0xdc/0xe0) [<80509180>] (driver_detach) from [<8050823c>] (bus_remove_driver+0x5c/0xb0) [<8050823c>] (bus_remove_driver) from [<80509ab0>] (driver_unregister+0x38/0x58) [<80509ab0>] (driver_unregister) from [<7f15e69c>] (mcp320x_driver_exit+0x14/0x1c [mcp320x]) [<7f15e69c>] (mcp320x_driver_exit [mcp320x]) from [<801a78d0>] (SyS_delete_module+0x184/0x1d0) [<801a78d0>] (SyS_delete_module) from [<80108100>] (ret_fast_syscall+0x0/0x1c) Fixes: f5ce4a7a9291 ("iio: adc: add driver for MCP3204/08 12-bit ADC") Cc: Oskar Andero Signed-off-by: Lukas Wunner Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/mcp320x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c index 634717ae12f35..45d043c9a888e 100644 --- a/drivers/iio/adc/mcp320x.c +++ b/drivers/iio/adc/mcp320x.c @@ -312,6 +312,7 @@ static int mcp320x_probe(struct spi_device *spi) indio_dev->name = spi_get_device_id(spi)->name; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &mcp320x_info; + spi_set_drvdata(spi, indio_dev); chip_info = &mcp320x_chip_infos[spi_get_device_id(spi)->driver_data]; indio_dev->channels = chip_info->channels; -- GitLab From e6f4794371ee7cce1339e7ca9542f1e703c5f84a Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 22 Aug 2017 15:33:00 +0200 Subject: [PATCH 0275/1507] iio: adc: mcp320x: Fix readout of negative voltages Commit f686a36b4b79 ("iio: adc: mcp320x: Add support for mcp3301") returns a signed voltage from mcp320x_adc_conversion() but neglects that the caller interprets a negative return value as failure. Only mcp3301 (and the upcoming mcp3550/1/3) is affected as the other chips are incapable of measuring negative voltages. Fix and while at it, add mcp3301 to the list of supported chips at the top of the file. Fixes: f686a36b4b79 ("iio: adc: mcp320x: Add support for mcp3301") Cc: Andrea Galbusera Signed-off-by: Lukas Wunner Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/mcp320x.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c index 45d043c9a888e..071dd23a33d9f 100644 --- a/drivers/iio/adc/mcp320x.c +++ b/drivers/iio/adc/mcp320x.c @@ -17,6 +17,8 @@ * MCP3204 * MCP3208 * ------------ + * 13 bit converter + * MCP3301 * * Datasheet can be found here: * http://ww1.microchip.com/downloads/en/DeviceDoc/21293C.pdf mcp3001 @@ -96,7 +98,7 @@ static int mcp320x_channel_to_tx_data(int device_index, } static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, - bool differential, int device_index) + bool differential, int device_index, int *val) { int ret; @@ -117,19 +119,25 @@ static int mcp320x_adc_conversion(struct mcp320x *adc, u8 channel, switch (device_index) { case mcp3001: - return (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + *val = (adc->rx_buf[0] << 5 | adc->rx_buf[1] >> 3); + return 0; case mcp3002: case mcp3004: case mcp3008: - return (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + *val = (adc->rx_buf[0] << 2 | adc->rx_buf[1] >> 6); + return 0; case mcp3201: - return (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + *val = (adc->rx_buf[0] << 7 | adc->rx_buf[1] >> 1); + return 0; case mcp3202: case mcp3204: case mcp3208: - return (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + *val = (adc->rx_buf[0] << 4 | adc->rx_buf[1] >> 4); + return 0; case mcp3301: - return sign_extend32((adc->rx_buf[0] & 0x1f) << 8 | adc->rx_buf[1], 12); + *val = sign_extend32((adc->rx_buf[0] & 0x1f) << 8 + | adc->rx_buf[1], 12); + return 0; default: return -EINVAL; } @@ -150,12 +158,10 @@ static int mcp320x_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: ret = mcp320x_adc_conversion(adc, channel->address, - channel->differential, device_index); - + channel->differential, device_index, val); if (ret < 0) goto out; - *val = ret; ret = IIO_VAL_INT; break; -- GitLab From 4b1f0c31f96c45e8521dd84aae50f2aa4aecfb7b Mon Sep 17 00:00:00 2001 From: Colin Parker Date: Mon, 28 Aug 2017 16:21:39 -0700 Subject: [PATCH 0276/1507] IIO: BME280: Updates to Humidity readings need ctrl_reg write! The ctrl_reg register needs to be written after any write to the humidity registers. The value written to the ctrl_reg register does not necessarily need to change, but a write operation must occur. The regmap_update_bits functions will not write to a register if the register value matches the value to be written. This saves unnecessary bus operations. The change in this patch forces a bus write during the chip_config operation by switching to regmap_write_bits. This will fix issues where the Humidity Sensor Oversampling bits are not updated after initialization. Signed-off-by: Colin Parker Acked-by: Andreas Klinger Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index d82b788374b61..e442c5248427a 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -558,7 +558,7 @@ static int bmp280_chip_config(struct bmp280_data *data) u8 osrs = BMP280_OSRS_TEMP_X(data->oversampling_temp + 1) | BMP280_OSRS_PRESS_X(data->oversampling_press + 1); - ret = regmap_update_bits(data->regmap, BMP280_REG_CTRL_MEAS, + ret = regmap_write_bits(data->regmap, BMP280_REG_CTRL_MEAS, BMP280_OSRS_TEMP_MASK | BMP280_OSRS_PRESS_MASK | BMP280_MODE_MASK, -- GitLab From 7fc10de8d49a748c476532c9d8e8fe19e548dd67 Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Tue, 5 Sep 2017 15:14:45 +0300 Subject: [PATCH 0277/1507] iio: ad_sigma_delta: Implement a dedicated reset function Since most of the SD ADCs have the option of reseting the serial interface by sending a number of SCLKs with CS = 0 and DIN = 1, a dedicated function that can do this is usefull. Needed for the patch: iio: ad7793: Fix the serial interface reset Signed-off-by: Dragos Bogdan Acked-by: Lars-Peter Clausen Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad_sigma_delta.c | 28 ++++++++++++++++++++++++++ include/linux/iio/adc/ad_sigma_delta.h | 3 +++ 2 files changed, 31 insertions(+) diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index d10bd0c97233f..22c4c17cd9969 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -177,6 +177,34 @@ int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, } EXPORT_SYMBOL_GPL(ad_sd_read_reg); +/** + * ad_sd_reset() - Reset the serial interface + * + * @sigma_delta: The sigma delta device + * @reset_length: Number of SCLKs with DIN = 1 + * + * Returns 0 on success, an error code otherwise. + **/ +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length) +{ + uint8_t *buf; + unsigned int size; + int ret; + + size = DIV_ROUND_UP(reset_length, 8); + buf = kcalloc(size, sizeof(*buf), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + memset(buf, 0xff, size); + ret = spi_write(sigma_delta->spi, buf, size); + kfree(buf); + + return ret; +} +EXPORT_SYMBOL_GPL(ad_sd_reset); + static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, unsigned int mode, unsigned int channel) { diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 5ba430cc9a873..1fc7abd28b0b0 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -111,6 +111,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg, unsigned int size, unsigned int *val); +int ad_sd_reset(struct ad_sigma_delta *sigma_delta, + unsigned int reset_length); + int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, -- GitLab From 7ee3b7ebcb74714df6d94c8f500f307e1ee5dda5 Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Tue, 5 Sep 2017 15:16:13 +0300 Subject: [PATCH 0278/1507] iio: ad7793: Fix the serial interface reset The serial interface can be reset by writing 32 consecutive 1s to the device. 'ret' was initialized correctly but its value was overwritten when ad7793_check_platform_data() was called. Since a dedicated reset function is present now, it should be used instead. Fixes: 2edb769d246e ("iio:ad7793: Add support for the ad7798 and ad7799") Signed-off-by: Dragos Bogdan Acked-by: Lars-Peter Clausen Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad7793.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c index e6706a09e100d..47c3d7f329004 100644 --- a/drivers/iio/adc/ad7793.c +++ b/drivers/iio/adc/ad7793.c @@ -257,7 +257,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, unsigned int vref_mv) { struct ad7793_state *st = iio_priv(indio_dev); - int i, ret = -1; + int i, ret; unsigned long long scale_uv; u32 id; @@ -266,7 +266,7 @@ static int ad7793_setup(struct iio_dev *indio_dev, return ret; /* reset the serial interface */ - ret = spi_write(st->sd.spi, (u8 *)&ret, sizeof(ret)); + ret = ad_sd_reset(&st->sd, 32); if (ret < 0) goto out; usleep_range(500, 2000); /* Wait for at least 500us */ -- GitLab From 3d62c78a6eb9a7d67bace9622b66ad51e81c5f9b Mon Sep 17 00:00:00 2001 From: Matt Fornero Date: Tue, 5 Sep 2017 16:34:10 +0200 Subject: [PATCH 0279/1507] iio: core: Return error for failed read_reg If an IIO device returns an error code for a read access via debugfs, it is currently ignored by the IIO core (other than emitting an error message). Instead, return this error code to user space, so upper layers can detect it correctly. Signed-off-by: Matt Fornero Signed-off-by: Lars-Peter Clausen Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 17ec4cee51dc0..a47428b4d31be 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -310,8 +310,10 @@ static ssize_t iio_debugfs_read_reg(struct file *file, char __user *userbuf, ret = indio_dev->info->debugfs_reg_access(indio_dev, indio_dev->cached_reg_addr, 0, &val); - if (ret) + if (ret) { dev_err(indio_dev->dev.parent, "%s: read failed\n", __func__); + return ret; + } len = snprintf(buf, sizeof(buf), "0x%X\n", val); -- GitLab From f790923f146140a261ad211e5baf75d169f16fb2 Mon Sep 17 00:00:00 2001 From: Stefan Popa Date: Thu, 14 Sep 2017 16:50:28 +0300 Subject: [PATCH 0280/1507] staging: iio: ad7192: Fix - use the dedicated reset function avoiding dma from stack. Depends on: 691c4b95d1 ("iio: ad_sigma_delta: Implement a dedicated reset function") SPI host drivers can use DMA to transfer data, so the buffer should be properly allocated. Keeping it on the stack could cause an undefined behavior. The dedicated reset function solves this issue. Signed-off-by: Stefan Popa Acked-by: Lars-Peter Clausen Acked-by: Michael Hennerich Cc: Signed-off-by: Jonathan Cameron --- drivers/staging/iio/adc/ad7192.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index d11c6de9c777f..6150d2780e22c 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -223,11 +223,9 @@ static int ad7192_setup(struct ad7192_state *st, struct iio_dev *indio_dev = spi_get_drvdata(st->sd.spi); unsigned long long scale_uv; int i, ret, id; - u8 ones[6]; /* reset the serial interface */ - memset(&ones, 0xFF, 6); - ret = spi_write(st->sd.spi, &ones, 6); + ret = ad_sd_reset(&st->sd, 48); if (ret < 0) goto out; usleep_range(500, 1000); /* Wait for at least 500us */ -- GitLab From e19b205be43d11bff638cad4487008c48d21c103 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 24 Sep 2017 16:38:56 -0700 Subject: [PATCH 0281/1507] Linux 4.14-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 64cbc66cebcaa..d1119941261c3 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Fearless Coyote # *DOCUMENTATION* -- GitLab From 5f3d862a736398e7068fa67142133f1713fdee8c Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Mon, 18 Sep 2017 09:41:45 +0200 Subject: [PATCH 0282/1507] qxl: fix framebuffer unpinning qxl_plane_cleanup_fb() unpins the just activated framebuffer instead of the old one. Oops. Fix it. Cc: Gabriel Krisman Bertazi Fixes: 1277eed5fecb8830c8cc414ad70c1ef640464bc0 Signed-off-by: Gerd Hoffmann Reviewed-by: Gabriel Krisman Bertazi Link: http://patchwork.freedesktop.org/patch/msgid/20170918074145.2257-1-kraxel@redhat.com --- drivers/gpu/drm/qxl/qxl_display.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index e1dd05423e862..afbf50d0c08fa 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -702,14 +702,15 @@ static void qxl_plane_cleanup_fb(struct drm_plane *plane, struct drm_gem_object *obj; struct qxl_bo *user_bo; - if (!plane->state->fb) { - /* we never executed prepare_fb, so there's nothing to + if (!old_state->fb) { + /* + * we never executed prepare_fb, so there's nothing to * unpin. */ return; } - obj = to_qxl_framebuffer(plane->state->fb)->obj; + obj = to_qxl_framebuffer(old_state->fb)->obj; user_bo = gem_to_qxl_bo(obj); qxl_bo_unpin(user_bo); } -- GitLab From 814fb7bb7db5433757d76f4c4502c96fc53b0b5e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 23 Sep 2017 15:00:07 +0200 Subject: [PATCH 0283/1507] x86/fpu: Don't let userspace set bogus xcomp_bv On x86, userspace can use the ptrace() or rt_sigreturn() system calls to set a task's extended state (xstate) or "FPU" registers. ptrace() can set them for another task using the PTRACE_SETREGSET request with NT_X86_XSTATE, while rt_sigreturn() can set them for the current task. In either case, registers can be set to any value, but the kernel assumes that the XSAVE area itself remains valid in the sense that the CPU can restore it. However, in the case where the kernel is using the uncompacted xstate format (which it does whenever the XSAVES instruction is unavailable), it was possible for userspace to set the xcomp_bv field in the xstate_header to an arbitrary value. However, all bits in that field are reserved in the uncompacted case, so when switching to a task with nonzero xcomp_bv, the XRSTOR instruction failed with a #GP fault. This caused the WARN_ON_FPU(err) in copy_kernel_to_xregs() to be hit. In addition, since the error is otherwise ignored, the FPU registers from the task previously executing on the CPU were leaked. Fix the bug by checking that the user-supplied value of xcomp_bv is 0 in the uncompacted case, and returning an error otherwise. The reason for validating xcomp_bv rather than simply overwriting it with 0 is that we want userspace to see an error if it (incorrectly) provides an XSAVE area in compacted format rather than in uncompacted format. Note that as before, in case of error we clear the task's FPU state. This is perhaps non-ideal, especially for PTRACE_SETREGSET; it might be better to return an error before changing anything. But it seems the "clear on error" behavior is fine for now, and it's a little tricky to do otherwise because it would mean we couldn't simply copy the full userspace state into kernel memory in one __copy_from_user(). This bug was found by syzkaller, which hit the above-mentioned WARN_ON_FPU(): WARNING: CPU: 1 PID: 0 at ./arch/x86/include/asm/fpu/internal.h:373 __switch_to+0x5b5/0x5d0 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.13.0 #453 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff9ba2bc8e42c0 task.stack: ffffa78cc036c000 RIP: 0010:__switch_to+0x5b5/0x5d0 RSP: 0000:ffffa78cc08bbb88 EFLAGS: 00010082 RAX: 00000000fffffffe RBX: ffff9ba2b8bf2180 RCX: 00000000c0000100 RDX: 00000000ffffffff RSI: 000000005cb10700 RDI: ffff9ba2b8bf36c0 RBP: ffffa78cc08bbbd0 R08: 00000000929fdf46 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000000 R12: ffff9ba2bc8e42c0 R13: 0000000000000000 R14: ffff9ba2b8bf3680 R15: ffff9ba2bf5d7b40 FS: 00007f7e5cb10700(0000) GS:ffff9ba2bf400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004005cc CR3: 0000000079fd5000 CR4: 00000000001406e0 Call Trace: Code: 84 00 00 00 00 00 e9 11 fd ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 e7 fa ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 c2 fa ff ff <0f> ff 66 0f 1f 84 00 00 00 00 00 e9 d4 fc ff ff 66 66 2e 0f 1f Here is a C reproducer. The expected behavior is that the program spin forever with no output. However, on a buggy kernel running on a processor with the "xsave" feature but without the "xsaves" feature (e.g. Sandy Bridge through Broadwell for Intel), within a second or two the program reports that the xmm registers were corrupted, i.e. were not restored correctly. With CONFIG_X86_DEBUG_FPU=y it also hits the above kernel warning. #define _GNU_SOURCE #include #include #include #include #include #include #include #include int main(void) { int pid = fork(); uint64_t xstate[512]; struct iovec iov = { .iov_base = xstate, .iov_len = sizeof(xstate) }; if (pid == 0) { bool tracee = true; for (int i = 0; i < sysconf(_SC_NPROCESSORS_ONLN) && tracee; i++) tracee = (fork() != 0); uint32_t xmm0[4] = { [0 ... 3] = tracee ? 0x00000000 : 0xDEADBEEF }; asm volatile(" movdqu %0, %%xmm0\n" " mov %0, %%rbx\n" "1: movdqu %%xmm0, %0\n" " mov %0, %%rax\n" " cmp %%rax, %%rbx\n" " je 1b\n" : "+m" (xmm0) : : "rax", "rbx", "xmm0"); printf("BUG: xmm registers corrupted! tracee=%d, xmm0=%08X%08X%08X%08X\n", tracee, xmm0[0], xmm0[1], xmm0[2], xmm0[3]); } else { usleep(100000); ptrace(PTRACE_ATTACH, pid, 0, 0); wait(NULL); ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov); xstate[65] = -1; ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov); ptrace(PTRACE_CONT, pid, 0, 0); wait(NULL); } return 1; } Note: the program only tests for the bug using the ptrace() system call. The bug can also be reproduced using the rt_sigreturn() system call, but only when called from a 32-bit program, since for 64-bit programs the kernel restores the FPU state from the signal frame by doing XRSTOR directly from userspace memory (with proper error checking). Reported-by: Dmitry Vyukov Signed-off-by: Eric Biggers Reviewed-by: Kees Cook Reviewed-by: Rik van Riel Acked-by: Dave Hansen Cc: [v3.17+] Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Fixes: 0b29643a5843 ("x86/xsaves: Change compacted format xsave area header") Link: http://lkml.kernel.org/r/20170922174156.16780-2-ebiggers3@gmail.com Link: http://lkml.kernel.org/r/20170923130016.21448-25-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/regset.c | 4 ++++ arch/x86/kernel/fpu/signal.c | 9 +++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 19a7385a912cc..c764f74053223 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -141,6 +141,10 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, ret = copy_user_to_xstate(xsave, ubuf); } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + + /* xcomp_bv must be 0 when using uncompacted format */ + if (!ret && xsave->header.xcomp_bv) + ret = -EINVAL; } /* diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 629106e51a297..da68ea1c3a442 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -324,11 +324,16 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ fpu__drop(fpu); - if (using_compacted_format()) + if (using_compacted_format()) { err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); - else + } else { err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + /* xcomp_bv must be 0 when using uncompacted format */ + if (!err && state_size > offsetof(struct xregs_state, header) && fpu->state.xsave.header.xcomp_bv) + err = -EINVAL; + } + if (err || __copy_from_user(&env, buf, sizeof(env))) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); -- GitLab From d5c8028b4788f62b31fb79a331b3ad3e041fa366 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 23 Sep 2017 15:00:09 +0200 Subject: [PATCH 0284/1507] x86/fpu: Reinitialize FPU registers if restoring FPU state fails Userspace can change the FPU state of a task using the ptrace() or rt_sigreturn() system calls. Because reserved bits in the FPU state can cause the XRSTOR instruction to fail, the kernel has to carefully validate that no reserved bits or other invalid values are being set. Unfortunately, there have been bugs in this validation code. For example, we were not checking that the 'xcomp_bv' field in the xstate_header was 0. As-is, such bugs are exploitable to read the FPU registers of other processes on the system. To do so, an attacker can create a task, assign to it an invalid FPU state, then spin in a loop and monitor the values of the FPU registers. Because the task's FPU registers are not being restored, sometimes the FPU registers will have the values from another process. This is likely to continue to be a problem in the future because the validation done by the CPU instructions like XRSTOR is not immediately visible to kernel developers. Nor will invalid FPU states ever be encountered during ordinary use --- they will only be seen during fuzzing or exploits. There can even be reserved bits outside the xstate_header which are easy to forget about. For example, the MXCSR register contains reserved bits, which were not validated by the KVM_SET_XSAVE ioctl until commit a575813bfe4b ("KVM: x86: Fix load damaged SSEx MXCSR register"). Therefore, mitigate this class of vulnerability by restoring the FPU registers from init_fpstate if restoring from the task's state fails. We actually used to do this, but it was (perhaps unwisely) removed by commit 9ccc27a5d297 ("x86/fpu: Remove error return values from copy_kernel_to_*regs() functions"). This new patch is also a bit different. First, it only clears the registers, not also the bad in-memory state; this is simpler and makes it easier to make the mitigation cover all callers of __copy_kernel_to_fpregs(). Second, it does the register clearing in an exception handler so that no extra instructions are added to context switches. In fact, we *remove* instructions, since previously we were always zeroing the register containing 'err' even if CONFIG_X86_DEBUG_FPU was disabled. Signed-off-by: Eric Biggers Reviewed-by: Rik van Riel Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170922174156.16780-4-ebiggers3@gmail.com Link: http://lkml.kernel.org/r/20170923130016.21448-27-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 51 +++++++++-------------------- arch/x86/mm/extable.c | 24 ++++++++++++++ 2 files changed, 39 insertions(+), 36 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 2dca7c65319cd..cf290d424e48d 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -120,20 +120,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); err; \ }) -#define check_insn(insn, output, input...) \ -({ \ - int err; \ +#define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ + : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { @@ -153,20 +144,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - int err; - if (IS_ENABLED(CONFIG_X86_32)) { - err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ - err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); } } - /* Copying from a kernel buffer to FPU registers should never fail: */ - WARN_ON_FPU(err); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) @@ -183,9 +170,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) static inline void copy_kernel_to_fregs(struct fregs_state *fx) { - int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - - WARN_ON_FPU(err); + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) @@ -281,18 +266,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ -#define XSTATE_XRESTORE(st, lmask, hmask, err) \ +#define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ - "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ + : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -336,7 +316,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ WARN_ON_FPU(err); } @@ -365,12 +348,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err; - - XSTATE_XRESTORE(xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ - WARN_ON_FPU(err); + XSTATE_XRESTORE(xstate, lmask, hmask); } /* diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index c076f710de4cb..c3521e2be3961 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -2,6 +2,7 @@ #include #include +#include #include #include @@ -78,6 +79,29 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_refcount); +/* + * Handler for when we fail to restore a task's FPU state. We should never get + * here because the FPU state of a task using the FPU (task->thread.fpu.state) + * should always be valid. However, past bugs have allowed userspace to set + * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). + * These caused XRSTOR to fail when switching to the task, leaking the FPU + * registers of the task previously executing on the CPU. Mitigate this class + * of vulnerability by restoring from the initial state (essentially, zeroing + * out all the FPU registers) if we can't restore from the task's FPU state. + */ +bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + + WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", + (void *)instruction_pointer(regs)); + + __copy_kernel_to_fpregs(&init_fpstate, -1); + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fprestore); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { -- GitLab From 10430364ebb562311ba6a6efa74e0c2298007912 Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Tue, 29 Aug 2017 23:47:11 +0530 Subject: [PATCH 0285/1507] x86/numachip: Add const and __initconst to numachip2_clockevent Make this const as it is only used during a copy operation and add __initconst as this usage is during the initialization phase. Signed-off-by: Bhumika Goyal Signed-off-by: Thomas Gleixner Cc: julia.lawall@lip6.fr Cc: daniel.lezcano@linaro.org Link: http://lkml.kernel.org/r/1504030631-10812-1-git-send-email-bhumirks@gmail.com --- drivers/clocksource/numachip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/numachip.c b/drivers/clocksource/numachip.c index 6a20dc8b253f4..9a7d7f0f23fea 100644 --- a/drivers/clocksource/numachip.c +++ b/drivers/clocksource/numachip.c @@ -43,7 +43,7 @@ static int numachip2_set_next_event(unsigned long delta, struct clock_event_devi return 0; } -static struct clock_event_device numachip2_clockevent = { +static const struct clock_event_device numachip2_clockevent __initconst = { .name = "numachip2", .rating = 400, .set_next_event = numachip2_set_next_event, -- GitLab From a3c4fb7c9c2ebfd50b8c60f6c069932bb319bc37 Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Mon, 4 Sep 2017 10:32:15 +0200 Subject: [PATCH 0286/1507] x86/mm: Fix fault error path using unsafe vma pointer commit 7b2d0dbac489 ("x86/mm/pkeys: Pass VMA down in to fault signal generation code") passes down a vma pointer to the error path, but that is done once the mmap_sem is released when calling mm_fault_error() from __do_page_fault(). This is dangerous as the vma structure is no more safe to be used once the mmap_sem has been released. As only the protection key value is required in the error processing, we could just pass down this value. Fix it by passing a pointer to a protection key value down to the fault signal generation code. The use of a pointer allows to keep the check generating a warning message in fill_sig_info_pkey() when the vma was not known. If the pointer is valid, the protection value can be accessed by deferencing the pointer. [ tglx: Made *pkey u32 as that's the type which is passed in siginfo ] Fixes: 7b2d0dbac489 ("x86/mm/pkeys: Pass VMA down in to fault signal generation code") Signed-off-by: Laurent Dufour Signed-off-by: Thomas Gleixner Cc: linux-mm@kvack.org Cc: Dave Hansen Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1504513935-12742-1-git-send-email-ldufour@linux.vnet.ibm.com --- arch/x86/mm/fault.c | 47 +++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 39567b5c33da3..e2baeaa053a5b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -192,8 +192,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, - struct vm_area_struct *vma) +static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) @@ -209,7 +208,7 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * valid VMA, so we should never reach this without a * valid VMA. */ - if (!vma) { + if (!pkey) { WARN_ONCE(1, "PKU fault with no VMA passed in"); info->si_pkey = 0; return; @@ -219,13 +218,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * absolutely guranteed to be 100% accurate because of * the race explained above. */ - info->si_pkey = vma_pkey(vma); + info->si_pkey = *pkey; } static void force_sig_info_fault(int si_signo, int si_code, unsigned long address, - struct task_struct *tsk, struct vm_area_struct *vma, - int fault) + struct task_struct *tsk, u32 *pkey, int fault) { unsigned lsb = 0; siginfo_t info; @@ -240,7 +238,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, vma); + fill_sig_info_pkey(si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -762,8 +760,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; unsigned long flags; int sig; - /* No context means no VMA to pass down */ - struct vm_area_struct *vma = NULL; /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF)) { @@ -788,7 +784,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, /* XXX: hwpoison faults will set the wrong code. */ force_sig_info_fault(signal, si_code, address, - tsk, vma, 0); + tsk, NULL, 0); } /* @@ -896,8 +892,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - int si_code) + unsigned long address, u32 *pkey, int si_code) { struct task_struct *tsk = current; @@ -945,7 +940,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_PF; - force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0); + force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0); return; } @@ -958,9 +953,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, u32 *pkey) { - __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR); + __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR); } static void @@ -968,6 +963,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma, int si_code) { struct mm_struct *mm = current->mm; + u32 pkey; + + if (vma) + pkey = vma_pkey(vma); /* * Something tried to access memory that isn't in our memory map.. @@ -975,7 +974,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, */ up_read(&mm->mmap_sem); - __bad_area_nosemaphore(regs, error_code, address, vma, si_code); + __bad_area_nosemaphore(regs, error_code, address, + (vma) ? &pkey : NULL, si_code); } static noinline void @@ -1018,7 +1018,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, - struct vm_area_struct *vma, unsigned int fault) + u32 *pkey, unsigned int fault) { struct task_struct *tsk = current; int code = BUS_ADRERR; @@ -1045,13 +1045,12 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, code = BUS_MCEERR_AR; } #endif - force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault); + force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - unsigned int fault) + unsigned long address, u32 *pkey, unsigned int fault) { if (fatal_signal_pending(current) && !(error_code & PF_USER)) { no_context(regs, error_code, address, 0, 0); @@ -1075,9 +1074,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) - do_sigbus(regs, error_code, address, vma, fault); + do_sigbus(regs, error_code, address, pkey, fault); else if (fault & VM_FAULT_SIGSEGV) - bad_area_nosemaphore(regs, error_code, address, vma); + bad_area_nosemaphore(regs, error_code, address, pkey); else BUG(); } @@ -1267,6 +1266,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, struct mm_struct *mm; int fault, major = 0; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + u32 pkey; tsk = current; mm = tsk->mm; @@ -1467,9 +1467,10 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, return; } + pkey = vma_pkey(vma); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, vma, fault); + mm_fault_error(regs, error_code, address, &pkey, fault); return; } -- GitLab From 7d7099433d9eaaa5a989a55f1fa354c16a3ad297 Mon Sep 17 00:00:00 2001 From: Sean Fu Date: Mon, 11 Sep 2017 08:33:21 +0800 Subject: [PATCH 0287/1507] x86/sysfs: Fix off-by-one error in loop termination An off-by-one error in loop terminantion conditions in create_setup_data_nodes() will lead to memory leak when create_setup_data_node() failed. Signed-off-by: Sean Fu Signed-off-by: Thomas Gleixner Link: http://lkml.kernel.org/r/1505090001-1157-1-git-send-email-fxinrong@gmail.com --- arch/x86/kernel/ksysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4b0592ca9e47b..8c1cc08f514f4 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent) return 0; out_clean_nodes: - for (j = i - 1; j > 0; j--) + for (j = i - 1; j >= 0; j--) cleanup_setup_data_node(*(kobjp + j)); kfree(kobjp); out_setup_data_kobj: -- GitLab From 5ac751d9e6b187c4a0000879d6598eb2292db949 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 12 Sep 2017 19:40:00 +0300 Subject: [PATCH 0288/1507] x86: Don't cast away the __user in __get_user_asm_u64() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Don't cast away the __user in __get_user_asm_u64() on x86-32. Prevents sparse getting upset. Signed-off-by: Ville Syrjälä Signed-off-by: Thomas Gleixner Cc: Benjamin LaHaise Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20170912164000.13745-1-ville.syrjala@linux.intel.com --- arch/x86/include/asm/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 78e8fcc87d4c6..4b892917edeb7 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -337,7 +337,7 @@ do { \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=r" (retval), "=&A"(x) \ - : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ + : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) -- GitLab From b09c146f8f63c0e03adba74df76bf9c2be466fec Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 8 Sep 2017 17:34:47 -0400 Subject: [PATCH 0289/1507] perf/x86/intel/cstate: Add missing CPU IDs Skylake server uses the same C-state residency events as Sandy Bridge. Denverton and Gemini lake use the same C-state residency events as Apollo Lake. Signed-off-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: ak@linux.intel.com Cc: peterz@infradead.org Cc: piotr.luc@intel.com Cc: harry.pan@intel.com Cc: srinivas.pandruvada@linux.intel.com Link: http://lkml.kernel.org/r/20170908213449.6224-1-kan.liang@intel.com --- arch/x86/events/intel/cstate.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4cf100ff2a374..72db0664a53df 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), @@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); -- GitLab From 1aaccc40a1864053da26605b0297be16dd52641e Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 8 Sep 2017 17:34:48 -0400 Subject: [PATCH 0290/1507] perf/x86/msr: Add missing CPU IDs Goldmont, Glodmont plus and Xeon Phi have MSR_SMI_COUNT as well. Signed-off-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: ak@linux.intel.com Cc: peterz@infradead.org Cc: piotr.luc@intel.com Cc: harry.pan@intel.com Cc: srinivas.pandruvada@linux.intel.com Link: http://lkml.kernel.org/r/20170908213449.6224-2-kan.liang@intel.com --- arch/x86/events/msr.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 4bb3ec69e8ea1..06723671ae4e9 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -63,6 +63,14 @@ static bool test_intel(int idx) case INTEL_FAM6_ATOM_SILVERMONT1: case INTEL_FAM6_ATOM_SILVERMONT2: case INTEL_FAM6_ATOM_AIRMONT: + + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_DENVERTON: + + case INTEL_FAM6_ATOM_GEMINI_LAKE: + + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; -- GitLab From 450a97893559354b927c935f39ee11126f01f520 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 8 Sep 2017 17:34:49 -0400 Subject: [PATCH 0291/1507] perf/x86/intel/rapl: Add missing CPU IDs DENVERTON and GEMINI_LAKE support same RAPL counters as Apollo Lake. Signed-off-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: ak@linux.intel.com Cc: peterz@infradead.org Cc: piotr.luc@intel.com Cc: harry.pan@intel.com Cc: srinivas.pandruvada@linux.intel.com Link: http://lkml.kernel.org/r/20170908213449.6224-3-kan.liang@intel.com --- arch/x86/events/intel/rapl.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 8e2457cb6b4a4..005908ee9333f 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init), {}, }; -- GitLab From 57999d1107c1e60c2ca7088f2ac0f819e2f554b3 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 22 Sep 2017 23:43:25 +0300 Subject: [PATCH 0292/1507] USB: devio: Prevent integer overflow in proc_do_submiturb() There used to be an integer overflow check in proc_do_submiturb() but we removed it. It turns out that it's still required. The uurb->buffer_length variable is a signed integer and it's controlled by the user. It can lead to an integer overflow when we do: num_sgs = DIV_ROUND_UP(uurb->buffer_length, USB_SG_SIZE); If we strip away the macro then that line looks like this: num_sgs = (uurb->buffer_length + USB_SG_SIZE - 1) / USB_SG_SIZE; ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ It's the first addition which can overflow. Fixes: 1129d270cbfb ("USB: Increase usbfs transfer limit") Cc: stable Signed-off-by: Dan Carpenter Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 318bb3b966879..e9326f31db8d4 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -140,6 +140,9 @@ module_param(usbfs_memory_mb, uint, 0644); MODULE_PARM_DESC(usbfs_memory_mb, "maximum MB allowed for usbfs buffers (0 = no limit)"); +/* Hard limit, necessary to avoid arithmetic overflow */ +#define USBFS_XFER_MAX (UINT_MAX / 2 - 1000000) + static atomic64_t usbfs_memory_usage; /* Total memory currently allocated */ /* Check whether it's okay to allocate more memory for a transfer */ @@ -1460,6 +1463,8 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb USBDEVFS_URB_ZERO_PACKET | USBDEVFS_URB_NO_INTERRUPT)) return -EINVAL; + if ((unsigned int)uurb->buffer_length >= USBFS_XFER_MAX) + return -EINVAL; if (uurb->buffer_length > 0 && !uurb->buffer) return -EINVAL; if (!(uurb->type == USBDEVFS_URB_TYPE_CONTROL && -- GitLab From fa1ed74eb1c233be6131ec92df21ab46499a15b6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 22 Sep 2017 23:43:46 +0300 Subject: [PATCH 0293/1507] USB: devio: Don't corrupt user memory The user buffer has "uurb->buffer_length" bytes. If the kernel has more information than that, we should truncate it instead of writing past the end of the user's buffer. I added a WARN_ONCE() to help the user debug the issue. Reported-by: Alan Stern Cc: stable Signed-off-by: Dan Carpenter Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/devio.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e9326f31db8d4..4664e543cf2f8 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1576,7 +1576,11 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb totlen += isopkt[u].length; } u *= sizeof(struct usb_iso_packet_descriptor); - uurb->buffer_length = totlen; + if (totlen <= uurb->buffer_length) + uurb->buffer_length = totlen; + else + WARN_ONCE(1, "uurb->buffer_length is too short %d vs %d", + totlen, uurb->buffer_length); break; default: -- GitLab From 8fec9355a968ad240f3a2e9ad55b823cf1cc52ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 22 Sep 2017 22:18:18 +0200 Subject: [PATCH 0294/1507] USB: cdc-wdm: ignore -EPIPE from GetEncapsulatedResponse MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will forward errors to userspace after turning most of them into -EIO. But all status codes are not equal. The -EPIPE (stall) in particular can be seen more as a result of normal USB signaling than an actual error. The state is automatically cleared by the USB core without intervention from either driver or userspace. And most devices and firmwares will never trigger a stall as a result of GetEncapsulatedResponse. This is in fact a requirement for CDC WDM devices. Quoting from section 7.1 of the CDC WMC spec revision 1.1: The function shall not return STALL in response to GetEncapsulatedResponse. But this driver is also handling GetEncapsulatedResponse on behalf of the qmi_wwan and cdc_mbim drivers. Unfortunately the relevant specs are not as clear wrt stall. So some QMI and MBIM devices *will* occasionally stall, causing the GetEncapsulatedResponse to return an -EPIPE status. Translating this into -EIO for userspace has proven to be harmful. Treating it as an empty read is safer, making the driver behave as if the device was conforming to the CDC WDM spec. There have been numerous reports of issues related to -EPIPE errors from some newer CDC MBIM devices in particular, like for example the Fibocom L831-EAU. Testing on this device has shown that the issues go away if we simply ignore the -EPIPE status. Similar handling of -EPIPE is already known from e.g. usb_get_string() The -EPIPE log message is still kept to let us track devices with this unexpected behaviour, hoping that it attracts attention from firmware developers. Cc: Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100938 Reported-and-tested-by: Christian Ehrig Reported-and-tested-by: Patrick Chilton Reported-and-tested-by: Andreas Böhler Signed-off-by: Bjørn Mork Acked-by: Oliver Neukum Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/cdc-wdm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 5aacea1978a5f..3e865dbf878c7 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -190,8 +190,10 @@ static void wdm_in_callback(struct urb *urb) /* * only set a new error if there is no previous error. * Errors are only cleared during read/open + * Avoid propagating -EPIPE (stall) to userspace since it is + * better handled as an empty read */ - if (desc->rerr == 0) + if (desc->rerr == 0 && status != -EPIPE) desc->rerr = status; if (length + desc->length > desc->wMaxCommand) { -- GitLab From 29b46dfb136cdbeece542b3f01115237e43f2855 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 11 Sep 2017 10:10:15 -0700 Subject: [PATCH 0295/1507] perf/x86/intel/uncore: Correct num_boxes for IIO and IRP There are 6 IIO/IRP boxes for CBDMA, PCIe0-2, MCP 0 and MCP 1 separately. Correct the num_boxes. Signed-off-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: ak@linux.intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: acme@kernel.org Link: http://lkml.kernel.org/r/1505149816-12580-1-git-send-email-kan.liang@intel.com --- arch/x86/events/intel/uncore_snbep.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index db1fe377e6dd9..a7196818416a5 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = { static struct intel_uncore_type skx_uncore_iio = { .name = "iio", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IIO0_MSR_PMON_CTL0, .perf_ctr = SKX_IIO0_MSR_PMON_CTR0, @@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = { static struct intel_uncore_type skx_uncore_irp = { .name = "irp", .num_counters = 2, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IRP0_MSR_PMON_CTL0, .perf_ctr = SKX_IRP0_MSR_PMON_CTR0, -- GitLab From 0add53713b1c07a1c71e27a20e21eb7c180b4e7b Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 19 Sep 2017 16:40:21 +0200 Subject: [PATCH 0296/1507] microblaze: Add missing kvm_para.h to Kbuild Running make allmodconfig;make is throwing compilation error: CC kernel/watchdog.o In file included from ./include/linux/kvm_para.h:4:0, from kernel/watchdog.c:29: ./include/uapi/linux/kvm_para.h:32:26: fatal error: asm/kvm_para.h: No such file or directory #include ^ compilation terminated. make[1]: *** [kernel/watchdog.o] Error 1 make: *** [kernel/watchdog.o] Error 2 Reported-by: Michal Hocko Suggested-by: Geert Uytterhoeven Signed-off-by: Michal Simek Fixes: 83f0124ad81e87b ("microblaze: remove asm-generic wrapper headers") Reviewed-by: Tobias Klauser Tested-by: Michal Hocko --- arch/microblaze/include/uapi/asm/Kbuild | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index e77a596f3f1ef..06609ca361150 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ generic-y += fcntl.h generic-y += ioctl.h generic-y += ioctls.h generic-y += ipcbuf.h +generic-y += kvm_para.h generic-y += mman.h generic-y += msgbuf.h generic-y += param.h -- GitLab From 64c99853baca40e2f06038c4a926009edd14c7c3 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 21 Sep 2017 00:29:36 +0200 Subject: [PATCH 0297/1507] microblaze: Cocci spatch "vma_pages" Use vma_pages function on vma object instead of explicit computation. Found by coccinelle spatch "api/vma_pages.cocci" Signed-off-by: Thomas Meyer Signed-off-by: Michal Simek --- arch/microblaze/kernel/dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index e45ada8fb0066..94700c5270a91 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -165,7 +165,7 @@ int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma, unsigned long attrs) { #ifdef CONFIG_MMU - unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; unsigned long pfn; -- GitLab From 428dbf156cc5a8f9994d1f1a5c79373d15476f3c Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 18 Sep 2017 10:53:29 -0600 Subject: [PATCH 0298/1507] arch: change default endian for microblaze Fix the default for microblaze. Michal Simek mentioned default for microblaze should be CPU_LITTLE_ENDIAN. Fixes : commit 206d3642d8ee ("arch/microblaze: add choice for endianness and update Makefile") Signed-off-by: Babu Moger Cc: Michal Simek Signed-off-by: Michal Simek --- arch/microblaze/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9d26abdf0dc1c..4f798aa671ddd 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -39,7 +39,7 @@ config MICROBLAZE # Endianness selection choice prompt "Endianness selection" - default CPU_BIG_ENDIAN + default CPU_LITTLE_ENDIAN help microblaze architectures can be configured for either little or big endian formats. Be sure to select the appropriate mode. -- GitLab From 89975bd335f37b96ffd3cc24b9effb1fa25e7788 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 20 Sep 2017 16:41:34 -0300 Subject: [PATCH 0299/1507] perf tools: Get all of tools/{arch,include}/ in the MANIFEST Now that I'm switching the container builds from using a local volume pointing to the kernel repository with the perf sources, instead getting a detached tarball to be able to use a container cluster, some places broke because I forgot to put some of the required files in tools/perf/MANIFEST, namely some bitsperlong.h files. So, to fix it do the same as for tools/build/ and pack the whole tools/arch/ directory. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-wmenpjfjsobwdnfde30qqncj@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 87 ++------------------------------------------- 1 file changed, 2 insertions(+), 85 deletions(-) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 62072822dc85d..627b7cada1442 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,34 +1,8 @@ tools/perf -tools/arch/alpha/include/asm/barrier.h -tools/arch/arm/include/asm/barrier.h -tools/arch/arm64/include/asm/barrier.h -tools/arch/ia64/include/asm/barrier.h -tools/arch/mips/include/asm/barrier.h -tools/arch/powerpc/include/asm/barrier.h -tools/arch/s390/include/asm/barrier.h -tools/arch/sh/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier.h -tools/arch/sparc/include/asm/barrier_32.h -tools/arch/sparc/include/asm/barrier_64.h -tools/arch/tile/include/asm/barrier.h -tools/arch/x86/include/asm/barrier.h -tools/arch/x86/include/asm/cmpxchg.h -tools/arch/x86/include/asm/cpufeatures.h -tools/arch/x86/include/asm/disabled-features.h -tools/arch/x86/include/asm/required-features.h -tools/arch/x86/include/uapi/asm/svm.h -tools/arch/x86/include/uapi/asm/vmx.h -tools/arch/x86/include/uapi/asm/kvm.h -tools/arch/x86/include/uapi/asm/kvm_perf.h -tools/arch/x86/lib/memcpy_64.S -tools/arch/x86/lib/memset_64.S -tools/arch/s390/include/uapi/asm/kvm_perf.h -tools/arch/s390/include/uapi/asm/sie.h -tools/arch/xtensa/include/asm/barrier.h +tools/arch tools/scripts tools/build -tools/arch/x86/include/asm/atomic.h -tools/arch/x86/include/asm/rmwcc.h +tools/include tools/lib/traceevent tools/lib/api tools/lib/bpf @@ -42,60 +16,3 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c -tools/include/asm/alternative-asm.h -tools/include/asm/atomic.h -tools/include/asm/barrier.h -tools/include/asm/bug.h -tools/include/asm-generic/atomic-gcc.h -tools/include/asm-generic/barrier.h -tools/include/asm-generic/bitops/arch_hweight.h -tools/include/asm-generic/bitops/atomic.h -tools/include/asm-generic/bitops/const_hweight.h -tools/include/asm-generic/bitops/__ffs.h -tools/include/asm-generic/bitops/__ffz.h -tools/include/asm-generic/bitops/__fls.h -tools/include/asm-generic/bitops/find.h -tools/include/asm-generic/bitops/fls64.h -tools/include/asm-generic/bitops/fls.h -tools/include/asm-generic/bitops/hweight.h -tools/include/asm-generic/bitops.h -tools/include/linux/atomic.h -tools/include/linux/bitops.h -tools/include/linux/compiler.h -tools/include/linux/compiler-gcc.h -tools/include/linux/coresight-pmu.h -tools/include/linux/bug.h -tools/include/linux/filter.h -tools/include/linux/hash.h -tools/include/linux/kernel.h -tools/include/linux/list.h -tools/include/linux/log2.h -tools/include/uapi/asm-generic/fcntl.h -tools/include/uapi/asm-generic/ioctls.h -tools/include/uapi/asm-generic/mman-common.h -tools/include/uapi/asm-generic/mman.h -tools/include/uapi/drm/drm.h -tools/include/uapi/drm/i915_drm.h -tools/include/uapi/linux/bpf.h -tools/include/uapi/linux/bpf_common.h -tools/include/uapi/linux/fcntl.h -tools/include/uapi/linux/hw_breakpoint.h -tools/include/uapi/linux/kvm.h -tools/include/uapi/linux/mman.h -tools/include/uapi/linux/perf_event.h -tools/include/uapi/linux/sched.h -tools/include/uapi/linux/stat.h -tools/include/uapi/linux/vhost.h -tools/include/uapi/sound/asound.h -tools/include/linux/poison.h -tools/include/linux/rbtree.h -tools/include/linux/rbtree_augmented.h -tools/include/linux/refcount.h -tools/include/linux/string.h -tools/include/linux/stringify.h -tools/include/linux/types.h -tools/include/linux/err.h -tools/include/linux/bitmap.h -tools/include/linux/time64.h -tools/arch/*/include/uapi/asm/mman.h -tools/arch/*/include/uapi/asm/perf_regs.h -- GitLab From 549a3976523c69a0245c0a310210c824a0b26e35 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 13 Sep 2017 09:38:23 +0200 Subject: [PATCH 0300/1507] tools include: Sync kernel ABI headers with tooling headers Time for a sync with ABI/uapi headers with the upcoming v4.14 kernel. None of the ABI changes require any source code level changes to our existing in-kernel tooling code: - tools/arch/s390/include/uapi/asm/kvm.h: New KVM_S390_VM_TOD_EXT ABI, not used by in-kernel tooling. - tools/arch/x86/include/asm/cpufeatures.h: tools/arch/x86/include/asm/disabled-features.h: New PCID, SME and VGIF x86 CPU feature bits defined. - tools/include/asm-generic/hugetlb_encode.h: tools/include/uapi/asm-generic/mman-common.h: tools/include/uapi/linux/mman.h: Two new madvise() flags, plus a hugetlb system call mmap flags restructuring/extension changes. - tools/include/uapi/drm/drm.h: tools/include/uapi/drm/i915_drm.h: New drm_syncobj_create flags definitions, new drm_syncobj_wait and drm_syncobj_array ABIs. DRM_I915_PERF_* calls and a new I915_PARAM_HAS_EXEC_FENCE_ARRAY ABI for the Intel driver. - tools/include/uapi/linux/bpf.h: New bpf_sock fields (::mark and ::priority), new XDP_REDIRECT action, new kvm_ppc_smmu_info fields (::data_keys, instr_keys) Signed-off-by: Ingo Molnar Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Taeung Song Cc: Wang Nan Cc: Yao Jin Link: http://lkml.kernel.org/r/20170913073823.lxmi4c7ejqlfabjx@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/s390/include/uapi/asm/kvm.h | 6 +++ tools/arch/x86/include/asm/cpufeatures.h | 2 + .../arch/x86/include/asm/disabled-features.h | 4 +- tools/include/asm-generic/hugetlb_encode.h | 34 +++++++++++++ tools/include/uapi/asm-generic/mman-common.h | 14 ++--- tools/include/uapi/drm/drm.h | 22 ++++++++ tools/include/uapi/drm/i915_drm.h | 51 ++++++++++++++++++- tools/include/uapi/linux/bpf.h | 32 +++++++----- tools/include/uapi/linux/kvm.h | 3 +- tools/include/uapi/linux/mman.h | 24 ++++++++- 10 files changed, 164 insertions(+), 28 deletions(-) create mode 100644 tools/include/asm-generic/hugetlb_encode.h diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 69d09c39bbcd0..cd7359e23d869 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req { /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 +#define KVM_S390_VM_TOD_EXT 2 + +struct kvm_s390_vm_tod_clock { + __u8 epoch_idx; + __u64 tod; +}; /* kvm attributes for KVM_S390_VM_CPU_MODEL */ /* processor related attributes are r/w */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 8ea315a11fe0d..2519c6c801c91 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -196,6 +196,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ @@ -287,6 +288,7 @@ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dff775af7cd6..c10c9128f54e6 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -21,11 +21,13 @@ # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) # define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) # define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +# define DISABLE_PCID 0 #else # define DISABLE_VME 0 # define DISABLE_K6_MTRR 0 # define DISABLE_CYRIX_ARR 0 # define DISABLE_CENTAUR_MCR 0 +# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31)) #endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -49,7 +51,7 @@ #define DISABLED_MASK1 0 #define DISABLED_MASK2 0 #define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) -#define DISABLED_MASK4 0 +#define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 0 diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h new file mode 100644 index 0000000000000..e4732d3c29982 --- /dev/null +++ b/tools/include/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 8c27db0c5c08c..203268f9231e1 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 101593ab10ac7..97677cd6964db 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -700,6 +700,7 @@ struct drm_prime_handle { struct drm_syncobj_create { __u32 handle; +#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0) __u32 flags; }; @@ -718,6 +719,24 @@ struct drm_syncobj_handle { __u32 pad; }; +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +struct drm_syncobj_wait { + __u64 handles; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + +struct drm_syncobj_array { + __u64 handles; + __u32 count_handles; + __u32 pad; +}; + #if defined(__cplusplus) } #endif @@ -840,6 +859,9 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy) #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle) #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle) +#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait) +#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array) +#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array) /** * Device specific ioctls should only be in their respective headers diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7ccbd6a2bbe07..6598fb76d2c27 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_CONTEXT_GETPARAM 0x34 #define DRM_I915_GEM_CONTEXT_SETPARAM 0x35 #define DRM_I915_PERF_OPEN 0x36 +#define DRM_I915_PERF_ADD_CONFIG 0x37 +#define DRM_I915_PERF_REMOVE_CONFIG 0x38 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param) #define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param) +#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config) +#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_HAS_EXEC_BATCH_FIRST 48 +/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of + * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY. + */ +#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49 + typedef struct drm_i915_getparam { __s32 param; /* @@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 { __u64 rsvd2; }; +struct drm_i915_gem_exec_fence { + /** + * User's handle for a drm_syncobj to wait on or signal. + */ + __u32 handle; + +#define I915_EXEC_FENCE_WAIT (1<<0) +#define I915_EXEC_FENCE_SIGNAL (1<<1) + __u32 flags; +}; + struct drm_i915_gem_execbuffer2 { /** * List of gem_exec_object2 structs @@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 { __u32 DR1; __u32 DR4; __u32 num_cliprects; - /** This is a struct drm_clip_rect *cliprects */ + /** + * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY + * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a + * struct drm_i915_gem_exec_fence *fences. + */ __u64 cliprects_ptr; #define I915_EXEC_RING_MASK (7<<0) #define I915_EXEC_DEFAULT (0<<0) @@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 { * element). */ #define I915_EXEC_BATCH_FIRST (1<<18) -#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1)) + +/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr + * define an array of i915_gem_exec_fence structures which specify a set of + * dma fences to wait upon or signal. + */ +#define I915_EXEC_FENCE_ARRAY (1<<19) + +#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1)) #define I915_EXEC_CONTEXT_ID_MASK (0xffffffff) #define i915_execbuffer2_set_context_id(eb2, context) \ @@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; +/** + * Structure to upload perf dynamic configuration into the kernel. + */ +struct drm_i915_perf_oa_config { + /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + char uuid[36]; + + __u32 n_mux_regs; + __u32 n_boolean_regs; + __u32 n_flex_regs; + + __u64 __user mux_regs_ptr; + __u64 __user boolean_regs_ptr; + __u64 __user flex_regs_ptr; +}; + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e571409..43ab5c402f98f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -632,7 +637,7 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -753,20 +758,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6cd63c18708ae..8388875874118 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index 81d8edf11789a..a937480d7cd34 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -1,7 +1,8 @@ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H -#include +#include +#include #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ -- GitLab From f1e52f14a69386ac460a8d700df0647a631cf595 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Sep 2017 15:41:44 -0300 Subject: [PATCH 0301/1507] perf evsel: Fix attr.exclude_kernel setting for default cycles:p Yet another fix for probing the max attr.precise_ip setting: it is not enough settting attr.exclude_kernel for !root users, as they _can_ profile the kernel if the kernel.perf_event_paranoid sysctl is set to -1, so check that as well. Testing it: As non root: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = 2 $ perf record sleep 1 $ perf evlist -v cycles:uppp: ..., exclude_kernel: 1, ... precise_ip: 3, ... Now as non-root, but with kernel.perf_event_paranoid set set to the most permissive value, -1: $ sysctl kernel.perf_event_paranoid kernel.perf_event_paranoid = -1 $ perf record sleep 1 $ perf evlist -v cycles:ppp: ..., exclude_kernel: 0, ... precise_ip: 3, ... $ I.e. non-root, default kernel.perf_event_paranoid: :uppp modifier = not allowed to sample the kernel, non-root, most permissible kernel.perf_event_paranoid: :ppp = allowed to sample the kernel. In both cases, use the highest available precision: attr.precise_ip = 3. Reported-and-Tested-by: Ingo Molnar Cc: Adrian Hunter Cc: Andy Lutomirski Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: d37a36979077 ("perf evsel: Fix attr.exclude_kernel setting for default cycles:p") Link: http://lkml.kernel.org/n/tip-nj2qkf75xsd6pw6hhjzfqqdx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4bb89373eb528..0dccdb89572cd 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) return evsel; } +static bool perf_event_can_profile_kernel(void) +{ + return geteuid() == 0 || perf_event_paranoid() == -1; +} + struct perf_evsel *perf_evsel__new_cycles(bool precise) { struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = geteuid() != 0, + .exclude_kernel = !perf_event_can_profile_kernel(), }; struct perf_evsel *evsel; -- GitLab From 44d8143340a99b167c74365e844516b73523c087 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Sep 2017 13:57:40 -0700 Subject: [PATCH 0302/1507] KEYS: fix cred refcount leak in request_key_auth_new() In request_key_auth_new(), if key_alloc() or key_instantiate_and_link() were to fail, we would leak a reference to the 'struct cred'. Currently this can only happen if key_alloc() fails to allocate memory. But it still should be fixed, as it is a more severe bug waiting to happen. Fix it by cleaning things up to use a helper function which frees a 'struct request_key_auth' correctly. Fixes: d84f4f992cbd ("CRED: Inaugurate COW credentials") Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/request_key_auth.c | 68 +++++++++++++++----------------- 1 file changed, 31 insertions(+), 37 deletions(-) diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index afe9d22ab3611..69d6b3b35470c 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -120,6 +120,18 @@ static void request_key_auth_revoke(struct key *key) } } +static void free_request_key_auth(struct request_key_auth *rka) +{ + if (!rka) + return; + key_put(rka->target_key); + key_put(rka->dest_keyring); + if (rka->cred) + put_cred(rka->cred); + kfree(rka->callout_info); + kfree(rka); +} + /* * Destroy an instantiation authorisation token key. */ @@ -129,15 +141,7 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); - if (rka->cred) { - put_cred(rka->cred); - rka->cred = NULL; - } - - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); + free_request_key_auth(rka); } /* @@ -151,22 +155,17 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, const struct cred *cred = current->cred; struct key *authkey = NULL; char desc[20]; - int ret; + int ret = -ENOMEM; kenter("%d,", target->serial); /* allocate a auth record */ - rka = kmalloc(sizeof(*rka), GFP_KERNEL); - if (!rka) { - kleave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); - } + rka = kzalloc(sizeof(*rka), GFP_KERNEL); + if (!rka) + goto error; rka->callout_info = kmalloc(callout_len, GFP_KERNEL); - if (!rka->callout_info) { - kleave(" = -ENOMEM"); - kfree(rka); - return ERR_PTR(-ENOMEM); - } + if (!rka->callout_info) + goto error_free_rka; /* see if the calling process is already servicing the key request of * another process */ @@ -176,8 +175,12 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ - if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) - goto auth_key_revoked; + if (test_bit(KEY_FLAG_REVOKED, + &cred->request_key_auth->flags)) { + up_read(&cred->request_key_auth->sem); + ret = -EKEYREVOKED; + goto error_free_rka; + } irka = cred->request_key_auth->payload.data[0]; rka->cred = get_cred(irka->cred); @@ -205,32 +208,23 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); - goto error_alloc; + goto error_free_rka; } /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) - goto error_inst; + goto error_put_authkey; kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage)); return authkey; -auth_key_revoked: - up_read(&cred->request_key_auth->sem); - kfree(rka->callout_info); - kfree(rka); - kleave("= -EKEYREVOKED"); - return ERR_PTR(-EKEYREVOKED); - -error_inst: +error_put_authkey: key_revoke(authkey); key_put(authkey); -error_alloc: - key_put(rka->target_key); - key_put(rka->dest_keyring); - kfree(rka->callout_info); - kfree(rka); +error_free_rka: + free_request_key_auth(rka); +error: kleave("= %d", ret); return ERR_PTR(ret); } -- GitLab From f7b48cf08fa63a68b59c2894806ee478216d7f91 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Sep 2017 13:57:41 -0700 Subject: [PATCH 0303/1507] KEYS: don't revoke uninstantiated key in request_key_auth_new() If key_instantiate_and_link() were to fail (which fortunately isn't possible currently), the call to key_revoke(authkey) would crash with a NULL pointer dereference in request_key_auth_revoke() because the key has not yet been instantiated. Fix this by removing the call to key_revoke(). key_put() is sufficient, as it's not possible for an uninstantiated authkey to have been used for anything yet. Fixes: b5f545c880a2 ("[PATCH] keys: Permit running process to instantiate keys") Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/request_key_auth.c | 1 - 1 file changed, 1 deletion(-) diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index 69d6b3b35470c..e356075ed2f81 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -220,7 +220,6 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, return authkey; error_put_authkey: - key_revoke(authkey); key_put(authkey); error_free_rka: free_request_key_auth(rka); -- GitLab From 884bee0215fcc239b30c062c37ca29077005e064 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:36:12 -0700 Subject: [PATCH 0304/1507] KEYS: fix key refcount leak in keyctl_assume_authority() In keyctl_assume_authority(), if keyctl_change_reqkey_auth() were to fail, we would leak the reference to the 'authkey'. Currently this can only happen if prepare_creds() fails to allocate memory. But it still should be fixed, as it is a more severe bug waiting to happen. This patch also moves the read of 'authkey->serial' to before the reference to the authkey is dropped. Doing the read after dropping the reference is very fragile because it assumes we still hold another reference to the key. (Which we do, in current->cred->request_key_auth, but there's no reason not to write it in the "obviously correct" way.) Fixes: d84f4f992cbd ("CRED: Inaugurate COW credentials") Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/keyctl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ab0b337c84b4c..562f7fe287a0d 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1406,11 +1406,9 @@ long keyctl_assume_authority(key_serial_t id) } ret = keyctl_change_reqkey_auth(authkey); - if (ret < 0) - goto error; + if (ret == 0) + ret = authkey->serial; key_put(authkey); - - ret = authkey->serial; error: return ret; } -- GitLab From 7fc0786d956d9e59b68d282be9b156179846ea3d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:36:31 -0700 Subject: [PATCH 0305/1507] KEYS: fix key refcount leak in keyctl_read_key() In keyctl_read_key(), if key_permission() were to return an error code other than EACCES, we would leak a the reference to the key. This can't actually happen currently because key_permission() can only return an error code other than EACCES if security_key_permission() does, only SELinux and Smack implement that hook, and neither can return an error code other than EACCES. But it should still be fixed, as it is a bug waiting to happen. Fixes: 29db91906340 ("[PATCH] Keys: Add LSM hooks for key management [try #3]") Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/keyctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 562f7fe287a0d..aa1d11a291361 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -771,7 +771,7 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) if (ret == 0) goto can_read_key; if (ret != -EACCES) - goto error; + goto error2; /* we can't; see if it's searchable from this process's keyrings * - we automatically take account of the fact that it may be -- GitLab From e645016abc803dafc75e4b8f6e4118f088900ffb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:36:45 -0700 Subject: [PATCH 0306/1507] KEYS: fix writing past end of user-supplied buffer in keyring_read() Userspace can call keyctl_read() on a keyring to get the list of IDs of keys in the keyring. But if the user-supplied buffer is too small, the kernel would write the full list anyway --- which will corrupt whatever userspace memory happened to be past the end of the buffer. Fix it by only filling the space that is available. Fixes: b2a4df200d57 ("KEYS: Expand the capacity of a keyring") Cc: [v3.13+] Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/keyring.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/security/keys/keyring.c b/security/keys/keyring.c index de81793f99207..94f038967c170 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -423,7 +423,7 @@ static void keyring_describe(const struct key *keyring, struct seq_file *m) } struct keyring_read_iterator_context { - size_t qty; + size_t buflen; size_t count; key_serial_t __user *buffer; }; @@ -435,9 +435,9 @@ static int keyring_read_iterator(const void *object, void *data) int ret; kenter("{%s,%d},,{%zu/%zu}", - key->type->name, key->serial, ctx->count, ctx->qty); + key->type->name, key->serial, ctx->count, ctx->buflen); - if (ctx->count >= ctx->qty) + if (ctx->count >= ctx->buflen) return 1; ret = put_user(key->serial, ctx->buffer); @@ -472,16 +472,12 @@ static long keyring_read(const struct key *keyring, return 0; /* Calculate how much data we could return */ - ctx.qty = nr_keys * sizeof(key_serial_t); - if (!buffer || !buflen) - return ctx.qty; - - if (buflen > ctx.qty) - ctx.qty = buflen; + return nr_keys * sizeof(key_serial_t); /* Copy the IDs of the subscribed keys into the buffer */ ctx.buffer = (key_serial_t __user *)buffer; + ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { -- GitLab From 237bbd29f7a049d310d907f4b2716a7feef9abf3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:37:03 -0700 Subject: [PATCH 0307/1507] KEYS: prevent creating a different user's keyrings It was possible for an unprivileged user to create the user and user session keyrings for another user. For example: sudo -u '#3000' sh -c 'keyctl add keyring _uid.4000 "" @u keyctl add keyring _uid_ses.4000 "" @u sleep 15' & sleep 1 sudo -u '#4000' keyctl describe @u sudo -u '#4000' keyctl describe @us This is problematic because these "fake" keyrings won't have the right permissions. In particular, the user who created them first will own them and will have full access to them via the possessor permissions, which can be used to compromise the security of a user's keys: -4: alswrv-----v------------ 3000 0 keyring: _uid.4000 -5: alswrv-----v------------ 3000 0 keyring: _uid_ses.4000 Fix it by marking user and user session keyrings with a flag KEY_FLAG_UID_KEYRING. Then, when searching for a user or user session keyring by name, skip all keyrings that don't have the flag set. Fixes: 69664cf16af4 ("keys: don't generate user and user session keyrings unless they're accessed") Cc: [v2.6.26+] Signed-off-by: Eric Biggers Signed-off-by: David Howells --- include/linux/key.h | 2 ++ security/keys/internal.h | 2 +- security/keys/key.c | 2 ++ security/keys/keyring.c | 23 ++++++++++++++--------- security/keys/process_keys.c | 6 ++++-- 5 files changed, 23 insertions(+), 12 deletions(-) diff --git a/include/linux/key.h b/include/linux/key.h index 0441141851206..e315e16b6ff8a 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -187,6 +187,7 @@ struct key { #define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */ #define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 10 /* set if key should not be removed */ +#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */ /* the key type and key description string * - the desc is used to match a key against search criteria @@ -243,6 +244,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */ #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ +#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); diff --git a/security/keys/internal.h b/security/keys/internal.h index 1c02c65470384..503adbae7b0dd 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -141,7 +141,7 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx); extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx); -extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check); +extern struct key *find_keyring_by_name(const char *name, bool uid_keyring); extern int install_user_keyrings(void); extern int install_thread_keyring_to_cred(struct cred *); diff --git a/security/keys/key.c b/security/keys/key.c index 83da68d98b40b..e5c0896c3a8ff 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -302,6 +302,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; + if (flags & KEY_ALLOC_UID_KEYRING) + key->flags |= 1 << KEY_FLAG_UID_KEYRING; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 94f038967c170..4fa82a8a9c0e6 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1097,15 +1097,15 @@ key_ref_t find_key_to_update(key_ref_t keyring_ref, /* * Find a keyring with the specified name. * - * All named keyrings in the current user namespace are searched, provided they - * grant Search permission directly to the caller (unless this check is - * skipped). Keyrings whose usage points have reached zero or who have been - * revoked are skipped. + * Only keyrings that have nonzero refcount, are not revoked, and are owned by a + * user in the current user namespace are considered. If @uid_keyring is %true, + * the keyring additionally must have been allocated as a user or user session + * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ -struct key *find_keyring_by_name(const char *name, bool skip_perm_check) +struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct key *keyring; int bucket; @@ -1133,10 +1133,15 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check) if (strcmp(keyring->description, name) != 0) continue; - if (!skip_perm_check && - key_permission(make_key_ref(keyring, 0), - KEY_NEED_SEARCH) < 0) - continue; + if (uid_keyring) { + if (!test_bit(KEY_FLAG_UID_KEYRING, + &keyring->flags)) + continue; + } else { + if (key_permission(make_key_ref(keyring, 0), + KEY_NEED_SEARCH) < 0) + continue; + } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 86bced9fdbdf2..293d3598153bf 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -77,7 +77,8 @@ int install_user_keyrings(void) if (IS_ERR(uid_keyring)) { uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); @@ -94,7 +95,8 @@ int install_user_keyrings(void) session_keyring = keyring_alloc(buf, user->uid, INVALID_GID, cred, user_keyring_perm, - KEY_ALLOC_IN_QUOTA, + KEY_ALLOC_UID_KEYRING | + KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); -- GitLab From 37863c43b2c6464f252862bf2e9768264e961678 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:37:23 -0700 Subject: [PATCH 0308/1507] KEYS: prevent KEYCTL_READ on negative key Because keyctl_read_key() looks up the key with no permissions requested, it may find a negatively instantiated key. If the key is also possessed, we went ahead and called ->read() on the key. But the key payload will actually contain the ->reject_error rather than the normal payload. Thus, the kernel oopses trying to read the user_key_payload from memory address (int)-ENOKEY = 0x00000000ffffff82. Fortunately the payload data is stored inline, so it shouldn't be possible to abuse this as an arbitrary memory read primitive... Reproducer: keyctl new_session keyctl request2 user desc '' @s keyctl read $(keyctl show | awk '/user: desc/ {print $1}') It causes a crash like the following: BUG: unable to handle kernel paging request at 00000000ffffff92 IP: user_read+0x33/0xa0 PGD 36a54067 P4D 36a54067 PUD 0 Oops: 0000 [#1] SMP CPU: 0 PID: 211 Comm: keyctl Not tainted 4.14.0-rc1 #337 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-20170228_101828-anatol 04/01/2014 task: ffff90aa3b74c3c0 task.stack: ffff9878c0478000 RIP: 0010:user_read+0x33/0xa0 RSP: 0018:ffff9878c047bee8 EFLAGS: 00010246 RAX: 0000000000000001 RBX: ffff90aa3d7da340 RCX: 0000000000000017 RDX: 0000000000000000 RSI: 00000000ffffff82 RDI: ffff90aa3d7da340 RBP: ffff9878c047bf00 R08: 00000024f95da94f R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f58ece69740(0000) GS:ffff90aa3e200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000ffffff92 CR3: 0000000036adc001 CR4: 00000000003606f0 Call Trace: keyctl_read_key+0xac/0xe0 SyS_keyctl+0x99/0x120 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x7f58ec787bb9 RSP: 002b:00007ffc8d401678 EFLAGS: 00000206 ORIG_RAX: 00000000000000fa RAX: ffffffffffffffda RBX: 00007ffc8d402800 RCX: 00007f58ec787bb9 RDX: 0000000000000000 RSI: 00000000174a63ac RDI: 000000000000000b RBP: 0000000000000004 R08: 00007ffc8d402809 R09: 0000000000000020 R10: 0000000000000000 R11: 0000000000000206 R12: 00007ffc8d402800 R13: 00007ffc8d4016e0 R14: 0000000000000000 R15: 0000000000000000 Code: e5 41 55 49 89 f5 41 54 49 89 d4 53 48 89 fb e8 a4 b4 ad ff 85 c0 74 09 80 3d b9 4c 96 00 00 74 43 48 8b b3 20 01 00 00 4d 85 ed <0f> b7 5e 10 74 29 4d 85 e4 74 24 4c 39 e3 4c 89 e2 4c 89 ef 48 RIP: user_read+0x33/0xa0 RSP: ffff9878c047bee8 CR2: 00000000ffffff92 Fixes: 61ea0c0ba904 ("KEYS: Skip key state checks when checking for possession") Cc: [v3.13+] Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/keyctl.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index aa1d11a291361..365ff85d7e271 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -766,6 +766,11 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) key = key_ref_to_ptr(key_ref); + if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) { + ret = -ENOKEY; + goto error2; + } + /* see if we can read it directly */ ret = key_permission(key_ref, KEY_NEED_READ); if (ret == 0) -- GitLab From 8f674565d405a8c0b36ee531849df87f43e72ed5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:37:39 -0700 Subject: [PATCH 0309/1507] KEYS: reset parent each time before searching key_user_tree In key_user_lookup(), if there is no key_user for the given uid, we drop key_user_lock, allocate a new key_user, and search the tree again. But we failed to set 'parent' to NULL at the beginning of the second search. If the tree were to be empty for the second search, the insertion would be done with an invalid 'parent', scribbling over freed memory. Fortunately this can't actually happen currently because the tree always contains at least the root_key_user. But it still should be fixed to make the code more robust. Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/key.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/keys/key.c b/security/keys/key.c index e5c0896c3a8ff..eb914a838840d 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -54,10 +54,10 @@ void __key_check(const struct key *key) struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; - struct rb_node *parent = NULL; - struct rb_node **p; + struct rb_node *parent, **p; try_again: + parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); -- GitLab From 4aa68e07d845562561f5e73c04aa521376e95252 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Sep 2017 11:38:29 -0700 Subject: [PATCH 0310/1507] KEYS: restrict /proc/keys by credentials at open time When checking for permission to view keys whilst reading from /proc/keys, we should use the credentials with which the /proc/keys file was opened. This is because, in a classic type of exploit, it can be possible to bypass checks for the *current* credentials by passing the file descriptor to a suid program. Following commit 34dbbcdbf633 ("Make file credentials available to the seqfile interfaces") we can finally fix it. So let's do it. Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/proc.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/security/keys/proc.c b/security/keys/proc.c index bf08d02b6646a..de834309d1002 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -187,7 +187,7 @@ static int proc_keys_show(struct seq_file *m, void *v) struct keyring_search_context ctx = { .index_key.type = key->type, .index_key.description = key->description, - .cred = current_cred(), + .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, @@ -207,11 +207,7 @@ static int proc_keys_show(struct seq_file *m, void *v) } } - /* check whether the current task is allowed to view the key (assuming - * non-possession) - * - the caller holds a spinlock, and thus the RCU read lock, making our - * access to __current_cred() safe - */ + /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; -- GitLab From e007ce9c59bddd1e67b94bc29036d920f5c5428a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Sep 2017 13:57:42 -0700 Subject: [PATCH 0311/1507] KEYS: use kmemdup() in request_key_auth_new() kmemdup() is preferred to kmalloc() followed by memcpy(). Signed-off-by: Eric Biggers Signed-off-by: David Howells --- security/keys/request_key_auth.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index e356075ed2f81..6ebf1af8fce96 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -163,9 +163,10 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, rka = kzalloc(sizeof(*rka), GFP_KERNEL); if (!rka) goto error; - rka->callout_info = kmalloc(callout_len, GFP_KERNEL); + rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); if (!rka->callout_info) goto error_free_rka; + rka->callout_len = callout_len; /* see if the calling process is already servicing the key request of * another process */ @@ -196,8 +197,6 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, rka->target_key = key_get(target); rka->dest_keyring = key_get(dest_keyring); - memcpy(rka->callout_info, callout_info, callout_len); - rka->callout_len = callout_len; /* allocate the auth key */ sprintf(desc, "%x", target->serial); -- GitLab From c74aef2d06a9f59cece89093eecc552933cba72a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 17:48:06 +0200 Subject: [PATCH 0312/1507] futex: Fix pi_state->owner serialization There was a reported suspicion about a race between exit_pi_state_list() and put_pi_state(). The same report mentioned the comment with put_pi_state() said it should be called with hb->lock held, and it no longer is in all places. As it turns out, the pi_state->owner serialization is indeed broken. As per the new rules: 734009e96d19 ("futex: Change locking rules") pi_state->owner should be serialized by pi_state->pi_mutex.wait_lock. For the sites setting pi_state->owner we already hold wait_lock (where required) but exit_pi_state_list() and put_pi_state() were not and raced on clearing it. Fixes: 734009e96d19 ("futex: Change locking rules") Reported-by: Gratian Crisan Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: dvhart@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20170922154806.jd3ffltfk24m4o4y@hirez.programming.kicks-ass.net --- kernel/futex.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf054920..0518a0bfc746b 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); -- GitLab From 2827a418ca1b23e432e62c9b3d0e7cf3255dfe88 Mon Sep 17 00:00:00 2001 From: Alexandru Moise <00moses.alexander00@gmail.com> Date: Tue, 19 Sep 2017 22:04:12 +0200 Subject: [PATCH 0313/1507] genirq: Check __free_irq() return value for NULL __free_irq() can return a NULL irqaction for example when trying to free already-free IRQ, but the callsite unconditionally dereferences the returned pointer. Fix this by adding a check and return NULL. Signed-off-by: Alexandru Moise <00moses.alexander00@gmail.com> Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20170919200412.GA29985@gmail.com --- kernel/irq/manage.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52b08060..d00132b5c325b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; -- GitLab From 02a4843618fb35f847cf8c31cd3893873aa0edde Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 13 Sep 2017 09:17:57 -0400 Subject: [PATCH 0314/1507] brd: fix overflow in __brd_direct_access The code in __brd_direct_access multiplies the pgoff variable by page size and divides it by 512. It can cause overflow on 32-bit architectures. The overflow happens if we create ramdisk larger than 4G and use it as a sparse device. This patch replaces multiplication and division with multiplication by the number of sectors per page. Reviewed-by: Dan Williams Signed-off-by: Mikulas Patocka Fixes: 1647b9b959c7 ("brd: add dax_operations support") Cc: stable@vger.kernel.org # 4.12+ Signed-off-by: Jens Axboe --- drivers/block/brd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index bbd0d186cfc00..2d7178f7754ed 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -342,7 +342,7 @@ static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff, if (!brd) return -ENODEV; - page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512); + page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT); if (!page) return -ENOSPC; *kaddr = page_address(page); -- GitLab From f507b54dccfd8000c517d740bc45f20c74532d18 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 Sep 2017 13:54:35 +0200 Subject: [PATCH 0315/1507] bsg-lib: don't free job in bsg_prepare_job The job structure is allocated as part of the request, so we should not free it in the error path of bsg_prepare_job. Signed-off-by: Christoph Hellwig Cc: stable@vger.kernel.org Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/bsg-lib.c | 1 - 1 file changed, 1 deletion(-) diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c82408c7cc3c9..dbddff8174e57 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -154,7 +154,6 @@ static int bsg_prepare_job(struct device *dev, struct request *req) failjob_rls_rqst_payload: kfree(job->request_payload.sg_list); failjob_rls_job: - kfree(job); return -ENOMEM; } -- GitLab From 1dae69bedeeca0b57e441eae491fbd38049c0b47 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 5 May 2017 22:25:18 -0400 Subject: [PATCH 0316/1507] nbd: ignore non-nbd ioctl's In testing we noticed that nbd would spew if you ran a fio job against the raw device itself. This is because fio calls a block device specific ioctl, however the block layer will first pass this back to the driver ioctl handler in case the driver wants to do something special. Since the device was setup using netlink this caused us to spew every time fio called this ioctl. Since we don't have special handling, just error out for any non-nbd specific ioctl's that come in. This fixes the spew. Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2aa87cbdede0e..3684e21d543f2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1194,6 +1194,12 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* The block layer will pass back some non-nbd ioctls in case we have + * special handling for them, but we don't so just return an error. + */ + if (_IOC_TYPE(cmd) != 0xab) + return -EINVAL; + mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with -- GitLab From 5acb3cc2c2e9d3020a4fee43763c6463767f1572 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 20 Sep 2017 13:12:20 -0600 Subject: [PATCH 0317/1507] blktrace: Fix potential deadlock between delete & sysfs ops The lockdep code had reported the following unsafe locking scenario: CPU0 CPU1 ---- ---- lock(s_active#228); lock(&bdev->bd_mutex/1); lock(s_active#228); lock(&bdev->bd_mutex); *** DEADLOCK *** The deadlock may happen when one task (CPU1) is trying to delete a partition in a block device and another task (CPU0) is accessing tracing sysfs file (e.g. /sys/block/dm-1/trace/act_mask) in that partition. The s_active isn't an actual lock. It is a reference count (kn->count) on the sysfs (kernfs) file. Removal of a sysfs file, however, require a wait until all the references are gone. The reference count is treated like a rwsem using lockdep instrumentation code. The fact that a thread is in the sysfs callback method or in the ioctl call means there is a reference to the opended sysfs or device file. That should prevent the underlying block structure from being removed. Instead of using bd_mutex in the block_device structure, a new blk_trace_mutex is now added to the request_queue structure to protect access to the blk_trace structure. Suggested-by: Christoph Hellwig Signed-off-by: Waiman Long Acked-by: Steven Rostedt (VMware) Fix typo in patch subject line, and prune a comment detailing how the code used to work. Signed-off-by: Jens Axboe --- block/blk-core.c | 3 +++ include/linux/blkdev.h | 1 + kernel/trace/blktrace.c | 18 ++++++++++++------ 3 files changed, 16 insertions(+), 6 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index aebe676225e6f..048be4aa60244 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) kobject_init(&q->kobj, &blk_queue_ktype); +#ifdef CONFIG_BLK_DEV_IO_TRACE + mutex_init(&q->blk_trace_mutex); +#endif mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 460294bb0fa52..02fa42d24b52f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -551,6 +551,7 @@ struct request_queue { int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace *blk_trace; + struct mutex blk_trace_mutex; #endif /* * for flush operations diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b45b73be..45a3928544ce5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: -- GitLab From e5313c141b49c1b1af43d1ca81398185d66ad1a6 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 20 Sep 2017 14:24:34 -0700 Subject: [PATCH 0318/1507] loop: remove union of use_aio and ref in struct loop_cmd When the request is completed, lo_complete_rq() checks cmd->use_aio. However, if this is in fact an aio request, cmd->use_aio will have already been reused as cmd->ref by lo_rw_aio*. Fix it by not using a union. On x86_64, there's a hole after the union anyways, so this doesn't make struct loop_cmd any bigger. Fixes: 92d773324b7e ("block/loop: fix use after free") Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- drivers/block/loop.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/block/loop.h b/drivers/block/loop.h index f68c1d50802fd..1f39567029938 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -67,10 +67,8 @@ struct loop_device { struct loop_cmd { struct kthread_work work; struct request *rq; - union { - bool use_aio; /* use AIO interface to handle I/O */ - atomic_t ref; /* only for aio */ - }; + bool use_aio; /* use AIO interface to handle I/O */ + atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; -- GitLab From 56b7103a06083b8ce1160f8289460ba2f584e182 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 16:27:26 -0700 Subject: [PATCH 0319/1507] nvme-fc: remove use of FC-specific error codes The FC-NVME transport used the FC-specific error codes in cases where it had to fabricate an error to go back up stack. Instead of using the FC-specific values, now use a generic value (NVME_SC_INTERNAL). Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d2e882c0f4968..9100779b58c9e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1376,7 +1376,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); else if (freq->status) - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); /* * For the linux implementation, if we have an unsuccesful @@ -1404,7 +1404,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) */ if (freq->transferred_length != be32_to_cpu(op->cmd_iu.data_len)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result.u64 = 0; @@ -1421,7 +1421,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) freq->transferred_length || op->rsp_iu.status_code || sqe->common.command_id != cqe->command_id)) { - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } result = cqe->result; @@ -1429,7 +1429,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) break; default: - status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1); + status = cpu_to_le16(NVME_SC_INTERNAL << 1); goto done; } -- GitLab From 29b3d26ecc8046838de88205b7c4b182ac27ff65 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 16:27:27 -0700 Subject: [PATCH 0320/1507] nvmet-fc: remove use of FC-specific error codes The FC-NVME target transport used the FC-specific error codes in return codes when the transport or lldd failed. Instead of using the FC-specific values, now use a generic value (NVME_SC_INTERNAL). Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fc.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 421e43bf1dd78..088f07250d760 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1910,8 +1910,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, spin_lock_irqsave(&fod->flock, flags); fod->writedataactive = false; spin_unlock_irqrestore(&fod->flock, flags); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ { fcpreq->fcp_error = ret; fcpreq->transferred_length = 0; @@ -1929,8 +1928,7 @@ __nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort) /* if in the middle of an io and we need to tear down */ if (abort) { if (fcpreq->op == NVMET_FCOP_WRITEDATA) { - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return true; } @@ -1968,8 +1966,7 @@ nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod) fod->abort = true; spin_unlock(&fod->flock); - nvmet_req_complete(&fod->req, - NVME_SC_FC_TRANSPORT_ERROR); + nvmet_req_complete(&fod->req, NVME_SC_INTERNAL); return; } -- GitLab From fc9608e8b4dc3c2545fa0bc5d3eef158ca56ccf8 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 16:27:28 -0700 Subject: [PATCH 0321/1507] nvmet-fcloop: remove use of FC-specific error codes The FC-NVME transport loopback test module used the FC-specific error codes in cases where it emulated a transport abort case. Instead of using the FC-specific values, now use a generic value (NVME_SC_INTERNAL). Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fcloop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1cb9847ec2611..1fd1afbb8b2a2 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -576,7 +576,7 @@ fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport, tfcp_req->aborted = true; spin_unlock(&tfcp_req->reqlock); - tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED; + tfcp_req->status = NVME_SC_INTERNAL; /* * nothing more to do. If io wasn't active, the transport should -- GitLab From 8e009ce84683fa124b23ff5cb7fd87c48b331b88 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 16:27:29 -0700 Subject: [PATCH 0322/1507] lpfc: remove use of FC-specific error codes The lpfc driver uses the FC-specific error when it needed to return an error to the FC-NVME transport. Convert to use a generic value instead. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/scsi/lpfc/lpfc_nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 79ba3ce063a4f..23bdb1ca106e4 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -884,7 +884,7 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn, wcqe->total_data_placed); nCmd->transferred_length = 0; nCmd->rcv_rsplen = 0; - nCmd->status = NVME_SC_FC_TRANSPORT_ERROR; + nCmd->status = NVME_SC_INTERNAL; } } -- GitLab From 39a550d2d9eaee8b618084e6011441eac6a2a3b7 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 14 Sep 2017 11:30:15 -0700 Subject: [PATCH 0323/1507] qla2xxx: remove use of FC-specific error codes The qla2xxx driver uses the FC-specific error when it needed to return an error to the FC-NVME transport. Convert to use a generic value instead. Signed-off-by: James Smart Acked-by: Himanshu Madhani Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/scsi/qla2xxx/qla_nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 1f59e7a74c7b7..6b33a1f24f561 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -180,7 +180,7 @@ static void qla_nvme_sp_done(void *ptr, int res) goto rel; if (unlikely(res == QLA_FUNCTION_FAILED)) - fd->status = NVME_SC_FC_TRANSPORT_ERROR; + fd->status = NVME_SC_INTERNAL; else fd->status = 0; -- GitLab From c98cb3bd882119e7e1a7c8df2f1eacfcc701450b Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 16:27:25 -0700 Subject: [PATCH 0324/1507] nvme.h: remove FC transport-specific error values The NVM express group recinded the reserved range for the transport. Remove the FC-centric values that had been defined. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 87723c86f136f..2440be32be1de 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1127,19 +1127,6 @@ enum { NVME_SC_UNWRITTEN_BLOCK = 0x287, NVME_SC_DNR = 0x4000, - - - /* - * FC Transport-specific error status values for NVME commands - * - * Transport-specific status code values must be in the range 0xB0..0xBF - */ - - /* Generic FC failure - catchall */ - NVME_SC_FC_TRANSPORT_ERROR = 0x00B0, - - /* I/O failure due to FC ABTS'd */ - NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1, }; struct nvme_completion { -- GitLab From d85cf207499e6740ab9c490ff4f360af5c432d23 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 13:20:23 -0700 Subject: [PATCH 0325/1507] nvme: add transport SGL definitions Add transport SGL defintions from NVMe TP 4008, required for the final NVMe-FC standard. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2440be32be1de..9310ce77d8e1f 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -471,12 +471,14 @@ enum nvme_opcode { * * @NVME_SGL_FMT_ADDRESS: absolute address of the data block * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation * request subtype */ enum { NVME_SGL_FMT_ADDRESS = 0x00, NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_TRANSPORT_A = 0x0A, NVME_SGL_FMT_INVALIDATE = 0x0f, }; @@ -490,12 +492,16 @@ enum { * * For struct nvme_keyed_sgl_desc: * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + * + * Transport-specific SGL types: + * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor */ enum { NVME_SGL_FMT_DATA_DESC = 0x00, NVME_SGL_FMT_SEG_DESC = 0x02, NVME_SGL_FMT_LAST_SEG_DESC = 0x03, NVME_KEY_SGL_FMT_DATA_DESC = 0x04, + NVME_TRANSPORT_SGL_DATA_DESC = 0x05, }; struct nvme_sgl_desc { -- GitLab From d9d34c0b2327e85da0ad1476575264fe957fc6ef Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 13:20:24 -0700 Subject: [PATCH 0326/1507] nvme-fc: use transport-specific sgl format Sync with NVM Express spec change and FC-NVME 1.18. FC transport sets SGL type to Transport SGL Data Block Descriptor and subtype to transport-specific value 0x0A. Removed the warn-on's on the PRP fields. They are unneeded. They were to check for values from the upper layer that weren't set right, and for the most part were fine. But, with Async events, which reuse the same structure and 2nd time issued the SGL overlay converted them to the Transport SGL values - the warn-on's were errantly firing. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9100779b58c9e..af075e9989449 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1989,16 +1989,17 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, * as well as those by FC-NVME spec. */ WARN_ON_ONCE(sqe->common.metadata); - WARN_ON_ONCE(sqe->common.dptr.prp1); - WARN_ON_ONCE(sqe->common.dptr.prp2); sqe->common.flags |= NVME_CMD_SGL_METABUF; /* - * format SQE DPTR field per FC-NVME rules - * type=data block descr; subtype=offset; - * offset is currently 0. + * format SQE DPTR field per FC-NVME rules: + * type=0x5 Transport SGL Data Block Descriptor + * subtype=0xA Transport-specific value + * address=0 + * length=length of the data series */ - sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET; + sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) | + NVME_SGL_FMT_TRANSPORT_A; sqe->rw.dptr.sgl.length = cpu_to_le32(data_len); sqe->rw.dptr.sgl.addr = 0; -- GitLab From deb61742e060d4447712598bc11bb50f8b2e51dd Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 11 Sep 2017 16:16:53 -0700 Subject: [PATCH 0327/1507] nvmet-fc: fix failing max io queue connections fc transport is treating NVMET_NR_QUEUES as maximum queue count, e.g. admin queue plus NVMET_NR_QUEUES-1 io queues. But NVMET_NR_QUEUES is the number of io queues, so maximum queue count is really NVMET_NR_QUEUES+1. Fix the handling in the target fc transport Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 088f07250d760..c48c83d97e304 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -148,7 +148,7 @@ struct nvmet_fc_tgt_assoc { u32 a_id; struct nvmet_fc_tgtport *tgtport; struct list_head a_list; - struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES]; + struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; struct kref ref; }; @@ -608,7 +608,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, unsigned long flags; int ret; - if (qid >= NVMET_NR_QUEUES) + if (qid > NVMET_NR_QUEUES) return NULL; queue = kzalloc((sizeof(*queue) + @@ -888,7 +888,7 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) int i; spin_lock_irqsave(&tgtport->lock, flags); - for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) { + for (i = NVMET_NR_QUEUES; i >= 0; i--) { queue = assoc->queues[i]; if (queue) { if (!nvmet_fc_tgt_q_get(queue)) -- GitLab From 161b8be2bd6abad250d4b3f674bdd5480f15beeb Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 14 Sep 2017 13:54:39 -0400 Subject: [PATCH 0328/1507] nvme-pci: initialize queue memory before interrupts A spurious interrupt before the nvme driver has initialized the completion queue may inadvertently cause the driver to believe it has a completion to process. This may result in a NULL dereference since the nvmeq's tags are not set at this point. The patch initializes the host's CQ memory so that a spurious interrupt isn't mistaken for a real completion. Signed-off-by: Keith Busch Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4a2121335f48a..004018c5dccc3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1313,11 +1313,11 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) if (result < 0) goto release_cq; + nvme_init_queue(nvmeq, qid); result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; - nvme_init_queue(nvmeq, qid); return result; release_sq: @@ -1464,6 +1464,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) return result; nvmeq->cq_vector = 0; + nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { nvmeq->cq_vector = -1; @@ -2156,7 +2157,6 @@ static void nvme_reset_work(struct work_struct *work) if (result) goto out; - nvme_init_queue(dev->queues[0], 0); result = nvme_alloc_admin_tags(dev); if (result) goto out; -- GitLab From d08774738446e77734777adcf5d1045237b4475a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 15 Sep 2017 13:05:38 -0400 Subject: [PATCH 0329/1507] nvme-pci: Print invalid SGL only once The WARN_ONCE macro returns true if the condition is true, not if the warn was raised, so we're printing the scatter list every time it's invalid. This is excessive and makes debugging harder, so this patch prints it just once. Signed-off-by: Keith Busch Reviewed-by: Martin K. Petersen Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 004018c5dccc3..cb73bc8cad3bd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -540,6 +541,20 @@ static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) } #endif +static void nvme_print_sgl(struct scatterlist *sgl, int nents) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + dma_addr_t phys = sg_phys(sg); + pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " + "dma_address:%pad dma_length:%d\n", + i, &phys, sg->offset, sg->length, &sg_dma_address(sg), + sg_dma_len(sg)); + } +} + static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); @@ -622,19 +637,10 @@ static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req) return BLK_STS_OK; bad_sgl: - if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n", - blk_rq_payload_bytes(req), iod->nents)) { - for_each_sg(iod->sg, sg, iod->nents, i) { - dma_addr_t phys = sg_phys(sg); - pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d " - "dma_address:%pad dma_length:%d\n", i, &phys, - sg->offset, sg->length, - &sg_dma_address(sg), - sg_dma_len(sg)); - } - } + WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents), + "Invalid SGL for payload:%d nents:%d\n", + blk_rq_payload_bytes(req), iod->nents); return BLK_STS_IOERR; - } static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, -- GitLab From cd48282cc736377d5abf7c04de8c6ba864ba3794 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 14 Sep 2017 11:03:09 -0700 Subject: [PATCH 0330/1507] nvme: stop aer posting if controller state not live If an nvme async_event command completes, in most cases, a new async event is posted. However, if the controller enters a resetting or reconnecting state, there is nothing to block the scheduled work element from posting the async event again. Nor are there calls from the transport to stop async events when an association dies. In the case of FC, where the association is torn down, the aer must be aborted on the FC link and completes through the normal job completion path. Thus the terminated async event ends up being rescheduled even though the controller isn't in a valid state for the aer, and the reposting gets the transport into a partially torn down data structure. It's possible to hit the scenario on rdma, although much less likely due to an aer completing right as the association is terminated and as the association teardown reclaims the blk requests via nvme_cancel_request() so its immediate, not a link-related action like on FC. Fix by putting controller state checks in both the async event completion routine where it schedules the async event and in the async event work routine before it calls into the transport. It's effectively a "stop_async_events()" behavior. The transport, when it creates a new association with the subsystem will transition the state back to live and is already restarting the async event posting. Signed-off-by: James Smart [hch: remove taking a lock over reading the controller state] Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index acc816b67582f..d470f031e27f5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2590,7 +2590,7 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); spin_lock_irq(&ctrl->lock); - while (ctrl->event_limit > 0) { + while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { int aer_idx = --ctrl->event_limit; spin_unlock_irq(&ctrl->lock); @@ -2677,7 +2677,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, /*FALLTHRU*/ case NVME_SC_ABORT_REQ: ++ctrl->event_limit; - queue_work(nvme_wq, &ctrl->async_event_work); + if (ctrl->state == NVME_CTRL_LIVE) + schedule_work(&ctrl->async_event_work); break; default: break; -- GitLab From 0951338d9677f546e230685d68631dfd3f81cca5 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 7 Sep 2017 13:18:04 -0700 Subject: [PATCH 0331/1507] nvme: allow timed-out ios to retry Currently the nvme_req_needs_retry() applies several checks to see if a retry is allowed. On of those is whether the current time has exceeded the start time of the io plus the timeout length. This check, if an io times out, means there is never a retry allowed for the io. Which means applications see the io failure. Remove this check and allow the io to timeout, like it does on other protocols, and retries to be made. On the FC transport, a frame can be lost for an individual io, and there may be no other errors that escalate for the connection/association. The io will timeout, which causes the transport to escalate into creating a new association, but the io that timed out, due to this retry logic, has already failed back to the application and things are hosed. Signed-off-by: James Smart Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d470f031e27f5..5589f67d2cd8e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -134,8 +134,6 @@ static inline bool nvme_req_needs_retry(struct request *req) return false; if (nvme_req(req)->status & NVME_SC_DNR) return false; - if (jiffies - req->start_time >= req->timeout) - return false; if (nvme_req(req)->retries >= nvme_max_retries) return false; return true; -- GitLab From 8edd11c9ad3a6205eea6de9d02eaf64c681a0658 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Thu, 14 Sep 2017 13:59:28 -0300 Subject: [PATCH 0332/1507] nvme-fabrics: Allow 0 as KATO value Currently, driver code allows user to set 0 as KATO (Keep Alive TimeOut), but this is not being respected. This patch enforces the expected behavior. Signed-off-by: Guilherme G. Piccoli Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fabrics.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 47307752dc65d..555c976cc2ee7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -565,6 +565,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, opts->queue_size = NVMF_DEF_QUEUE_SIZE; opts->nr_io_queues = num_online_cpus(); opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY; + opts->kato = NVME_DEFAULT_KATO; options = o = kstrdup(buf, GFP_KERNEL); if (!options) @@ -655,21 +656,22 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, goto out; } - if (opts->discovery_nqn) { - pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n"); - ret = -EINVAL; - goto out; - } - if (token < 0) { pr_err("Invalid keep_alive_tmo %d\n", token); ret = -EINVAL; goto out; - } else if (token == 0) { + } else if (token == 0 && !opts->discovery_nqn) { /* Allowed for debug */ pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n"); } opts->kato = token; + + if (opts->discovery_nqn && opts->kato) { + pr_err("Discovery controllers cannot accept KATO != 0\n"); + ret = -EINVAL; + goto out; + } + break; case NVMF_OPT_CTRL_LOSS_TMO: if (match_int(args, &token)) { @@ -762,8 +764,6 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, uuid_copy(&opts->host->id, &hostid); out: - if (!opts->discovery_nqn && !opts->kato) - opts->kato = NVME_DEFAULT_KATO; kfree(options); return ret; } -- GitLab From bb1cc74790eb51f52d23c6e5fd9a3bb16030c3d8 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 18 Sep 2017 09:08:29 -0700 Subject: [PATCH 0333/1507] nvmet: implement valid sqhd values in completions To support sqhd, for initiators that are following the spec and paying attention to sqhd vs their sqtail values: - add sqhd to struct nvmet_sq - initialize sqhd to 0 in nvmet_sq_setup - rather than propagate the 0's-based qsize value from the connect message which requires a +1 in every sqhd update, and as nothing else references it, convert to 1's-based value in nvmt_sq/cq_setup() calls. - validate connect message sqsize being non-zero per spec. - updated assign sqhd for every completion that goes back. Also remove handling the NULL sq case in __nvmet_req_complete, as it can't happen with the current code. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Reviewed-by: Max Gurtovoy Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/core.c | 8 ++++---- drivers/nvme/target/fabrics-cmd.c | 9 +++++++-- drivers/nvme/target/nvmet.h | 1 + 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7c23eaf8e5639..c2a768a94235d 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -390,10 +390,9 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (status) nvmet_set_status(req, status); - /* XXX: need to fill in something useful for sq_head */ - req->rsp->sq_head = 0; - if (likely(req->sq)) /* may happen during early failure */ - req->rsp->sq_id = cpu_to_le16(req->sq->qid); + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; + req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); + req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; if (req->ns) @@ -420,6 +419,7 @@ void nvmet_cq_setup(struct nvmet_ctrl *ctrl, struct nvmet_cq *cq, void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, u16 qid, u16 size) { + sq->sqhd = 0; sq->qid = qid; sq->size = size; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 859a66725291d..db3bf6b8bf9ee 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -109,9 +109,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) pr_warn("queue already connected!\n"); return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR; } + if (!sqsize) { + pr_warn("queue size zero!\n"); + return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; + } - nvmet_cq_setup(ctrl, req->cq, qid, sqsize); - nvmet_sq_setup(ctrl, req->sq, qid, sqsize); + /* note: convert queue size from 0's-based value to 1's-based value */ + nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1); + nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1); return 0; } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7d261ab894f47..7b8e20adf7602 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -74,6 +74,7 @@ struct nvmet_sq { struct percpu_ref ref; u16 qid; u16 size; + u16 sqhd; struct completion free_done; struct completion confirm_done; }; -- GitLab From 332391a9935da939319e473b4680e173df75afcf Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Thu, 21 Sep 2017 08:16:29 -0600 Subject: [PATCH 0334/1507] fs: Fix page cache inconsistency when mixing buffered and AIO DIO Currently when mixing buffered reads and asynchronous direct writes it is possible to end up with the situation where we have stale data in the page cache while the new data is already written to disk. This is permanent until the affected pages are flushed away. Despite the fact that mixing buffered and direct IO is ill-advised it does pose a thread for a data integrity, is unexpected and should be fixed. Fix this by deferring completion of asynchronous direct writes to a process context in the case that there are mapped pages to be found in the inode. Later before the completion in dio_complete() invalidate the pages in question. This ensures that after the completion the pages in the written area are either unmapped, or populated with up-to-date data. Also do the same for the iomap case which uses iomap_dio_complete() instead. This has a side effect of deferring the completion to a process context for every AIO DIO that happens on inode that has pages mapped. However since the consensus is that this is ill-advised practice the performance implication should not be a problem. This was based on proposal from Jeff Moyer, thanks! Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Reviewed-by: Jeff Moyer Signed-off-by: Lukas Czerner Signed-off-by: Jens Axboe --- fs/direct-io.c | 49 +++++++++++++++++++++++++++++++++++++++++++------ fs/iomap.c | 29 ++++++++++++++++------------- mm/filemap.c | 10 ++++++++-- 3 files changed, 67 insertions(+), 21 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index 5fa2211e49aee..62cf812ed0e58 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; + int err; /* * AIO submission can race with bio completion to get here while @@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) if (ret == 0) ret = transferred; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (ret > 0 && dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages) { + err = invalidate_inode_pages2_range(dio->inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + ret - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + if (dio->end_io) { - int err; // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); @@ -304,6 +319,7 @@ static void dio_bio_end_aio(struct bio *bio) struct dio *dio = bio->bi_private; unsigned long remaining; unsigned long flags; + bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); @@ -315,7 +331,19 @@ static void dio_bio_end_aio(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - if (dio->result && dio->defer_completion) { + /* + * Defer completion when defer_completion is set or + * when the inode has pages mapped and this is AIO write. + * We need to invalidate those pages because there is a + * chance they contain stale data in the case buffered IO + * went in between AIO submission and completion into the + * same region. + */ + if (dio->result) + defer_completion = dio->defer_completion || + (dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages); + if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); @@ -1210,10 +1238,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && iov_iter_rw(iter) == WRITE && - ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host))) { - retval = dio_set_defer_completion(dio); + if (dio->is_async && iov_iter_rw(iter) == WRITE) { + retval = 0; + if ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host)) + retval = dio_set_defer_completion(dio); + else if (!dio->inode->i_sb->s_dio_done_wq) { + /* + * In case of AIO write racing with buffered read we + * need to defer completion. We can't decide this now, + * however the workqueue needs to be initialized here. + */ + retval = sb_init_dio_done_wq(dio->inode->i_sb); + } if (retval) { /* * We grab i_mutex only for reads so we don't have diff --git a/fs/iomap.c b/fs/iomap.c index 269b24a01f321..8194d30bdca08 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -713,8 +713,24 @@ struct iomap_dio { static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + ret = invalidate_inode_pages2_range(inode->i_mapping, + iocb->ki_pos >> PAGE_SHIFT, + (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + } + if (dio->end_io) { ret = dio->end_io(iocb, dio->error ? dio->error : dio->size, @@ -1042,19 +1058,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ret = iomap_dio_complete(dio); - /* - * Try again to invalidate clean pages which might have been cached by - * non-direct readahead, or faulted in by get_user_pages() if the source - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (iov_iter_rw(iter) == WRITE) { - int err = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(err); - } - return ret; out_free_dio: diff --git a/mm/filemap.c b/mm/filemap.c index 870971e209670..db250d0e05655 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2926,9 +2926,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... + * + * Most of the time we do not need this since dio_complete() will do + * the invalidation for us. However there are some file systems that + * do not end up with dio_complete() being called, so let's not break + * them by removing it completely */ - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); + if (mapping->nrpages) + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); if (written > 0) { pos += written; -- GitLab From f5c156c4c29a3d87176dd6e5c099388e187ec29b Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 21 Sep 2017 12:17:16 -0700 Subject: [PATCH 0335/1507] block: fix a crash caused by wrong API part_stat_show takes a part device not a disk, so we should use part_to_disk. Fixes: d62e26b3ffd2("block: pass in queue to inflight accounting") Cc: Bart Van Assche Cc: Omar Sandoval Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- block/partition-generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/partition-generic.c b/block/partition-generic.c index 86e8fe1adcdb7..88c555db4e5de 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -112,7 +112,7 @@ ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); - struct request_queue *q = dev_to_disk(dev)->queue; + struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; int cpu; -- GitLab From 62e082430ea4bb5b28909ca4375bb683931e22aa Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 20 Sep 2017 07:29:49 -0400 Subject: [PATCH 0336/1507] dm ioctl: fix alignment of event number in the device list The size of struct dm_name_list is different on 32-bit and 64-bit kernels (so "(nl + 1)" differs between 32-bit and 64-bit kernels). This mismatch caused some harmless difference in padding when using 32-bit or 64-bit kernel. Commit 23d70c5e52dd ("dm ioctl: report event number in DM_LIST_DEVICES") added reporting event number in the output of DM_LIST_DEVICES_CMD. This difference in padding makes it impossible for userspace to determine the location of the event number (the location would be different when running on 32-bit and 64-bit kernels). Fix the padding by using offsetof(struct dm_name_list, name) instead of sizeof(struct dm_name_list) to determine the location of entries. Also, the ioctl version number is incremented to 37 so that userspace can use the version number to determine that the event number is present and correctly located. In addition, a global event is now raised when a DM device is created, removed, renamed or when table is swapped, so that the user can monitor for device changes. Reported-by: Eugene Syromiatnikov Fixes: 23d70c5e52dd ("dm ioctl: report event number in DM_LIST_DEVICES") Cc: stable@vger.kernel.org # 4.13 Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-core.h | 1 + drivers/md/dm-ioctl.c | 37 +++++++++++++++++++++++------------ drivers/md/dm.c | 10 ++++++++-- include/uapi/linux/dm-ioctl.h | 4 ++-- 4 files changed, 35 insertions(+), 17 deletions(-) diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 24eddbdf2ab4c..203144762f368 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -149,5 +149,6 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen extern atomic_t dm_global_event_nr; extern wait_queue_head_t dm_global_eventq; +void dm_issue_global_event(void); #endif diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 8756a6850431d..e52676fa9832c 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -477,9 +477,13 @@ static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_si * Round up the ptr to an 8-byte boundary. */ #define ALIGN_MASK 7 +static inline size_t align_val(size_t val) +{ + return (val + ALIGN_MASK) & ~ALIGN_MASK; +} static inline void *align_ptr(void *ptr) { - return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK); + return (void *)align_val((size_t)ptr); } /* @@ -505,7 +509,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ struct hash_cell *hc; size_t len, needed = 0; struct gendisk *disk; - struct dm_name_list *nl, *old_nl = NULL; + struct dm_name_list *orig_nl, *nl, *old_nl = NULL; uint32_t *event_nr; down_write(&_hash_lock); @@ -516,17 +520,15 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ */ for (i = 0; i < NUM_BUCKETS; i++) { list_for_each_entry (hc, _name_buckets + i, name_list) { - needed += sizeof(struct dm_name_list); - needed += strlen(hc->name) + 1; - needed += ALIGN_MASK; - needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK; + needed += align_val(offsetof(struct dm_name_list, name) + strlen(hc->name) + 1); + needed += align_val(sizeof(uint32_t)); } } /* * Grab our output buffer. */ - nl = get_result_buffer(param, param_size, &len); + nl = orig_nl = get_result_buffer(param, param_size, &len); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; @@ -549,11 +551,16 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ strcpy(nl->name, hc->name); old_nl = nl; - event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1); + event_nr = align_ptr(nl->name + strlen(hc->name) + 1); *event_nr = dm_get_event_nr(hc->md); nl = align_ptr(event_nr + 1); } } + /* + * If mismatch happens, security may be compromised due to buffer + * overflow, so it's better to crash. + */ + BUG_ON((char *)nl - (char *)orig_nl != needed); out: up_write(&_hash_lock); @@ -1621,7 +1628,8 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para * which has a variable size, is not used by the function processing * the ioctl. */ -#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 /*----------------------------------------------------------------- * Implementation of open/close/ioctl on the special char @@ -1635,12 +1643,12 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) ioctl_fn fn; } _ioctls[] = { {DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */ - {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all}, + {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all}, {DM_LIST_DEVICES_CMD, 0, list_devices}, - {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create}, - {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove}, - {DM_DEV_RENAME_CMD, 0, dev_rename}, + {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create}, + {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove}, + {DM_DEV_RENAME_CMD, IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename}, {DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend}, {DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status}, {DM_DEV_WAIT_CMD, 0, dev_wait}, @@ -1869,6 +1877,9 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); + if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT) + dm_issue_global_event(); + /* * Copy the results back to userland. */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6e54145969c5c..4be85324f44dc 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -52,6 +52,12 @@ static struct workqueue_struct *deferred_remove_workqueue; atomic_t dm_global_event_nr = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq); +void dm_issue_global_event(void) +{ + atomic_inc(&dm_global_event_nr); + wake_up(&dm_global_eventq); +} + /* * One of these is allocated per bio. */ @@ -1865,9 +1871,8 @@ static void event_callback(void *context) dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj); atomic_inc(&md->event_nr); - atomic_inc(&dm_global_event_nr); wake_up(&md->eventq); - wake_up(&dm_global_eventq); + dm_issue_global_event(); } /* @@ -2283,6 +2288,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) } map = __bind(md, table, &limits); + dm_issue_global_event(); out: mutex_unlock(&md->suspend_lock); diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 412c06a624c83..ccaea525340b9 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -269,9 +269,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 36 +#define DM_VERSION_MINOR 37 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2017-06-09)" +#define DM_VERSION_EXTRA "-ioctl (2017-09-20)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- GitLab From 9789e7e93f2b892098d7684ac8131092aa617814 Mon Sep 17 00:00:00 2001 From: Mengting Zhang Date: Sat, 23 Sep 2017 16:18:14 +0800 Subject: [PATCH 0337/1507] perf report: Fix debug messages with --call-graph option With --call-graph option, perf report can display call chains using type, min percent threshold, optional print limit and order. And the default call-graph parameter is 'graph,0.5,caller,function,percent'. Before this patch, 'perf report --call-graph' shows incorrect debug messages as below: # perf report --call-graph Invalid callchain mode: 0.5 Invalid callchain order: 0.5 Invalid callchain sort key: 0.5 Invalid callchain config key: 0.5 Invalid callchain mode: caller Invalid callchain mode: function Invalid callchain order: function Invalid callchain mode: percent Invalid callchain order: percent Invalid callchain sort key: percent That is because in function __parse_callchain_report_opt(),each field of the call-graph parameter is passed to parse_callchain_{mode,order, sort_key,value} in turn until it meets the matching value. For example, the order field "caller" is passed to parse_callchain_mode() firstly and obviously it doesn't match any mode field. Therefore parse_callchain_mode() will shows the debug message "Invalid callchain mode: caller", which could confuse users. The patch fixes this issue by moving the warning out of the function parse_callchain_{mode,order,sort_key,value}. Signed-off-by: Mengting Zhang Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Krister Johansen Cc: Li Bin Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Cc: Yao Jin Link: http://lkml.kernel.org/r/1506154694-39691-1-git-send-email-zhangmengting@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 510b513e0f01f..be09d77cade02 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } - - pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } - - pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value) callchain_param.branch_callstack = 1; return 0; } - - pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } - - pr_err("Invalid callchain config key: %s\n", value); return -1; } @@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value) return ret; } - if (!strcmp(var, "print-type")) - return parse_callchain_mode(value); - if (!strcmp(var, "order")) - return parse_callchain_order(value); - if (!strcmp(var, "sort-key")) - return parse_callchain_sort_key(value); + if (!strcmp(var, "print-type")){ + int ret; + ret = parse_callchain_mode(value); + if (ret == -1) + pr_err("Invalid callchain mode: %s\n", value); + return ret; + } + if (!strcmp(var, "order")){ + int ret; + ret = parse_callchain_order(value); + if (ret == -1) + pr_err("Invalid callchain order: %s\n", value); + return ret; + } + if (!strcmp(var, "sort-key")){ + int ret; + ret = parse_callchain_sort_key(value); + if (ret == -1) + pr_err("Invalid callchain sort key: %s\n", value); + return ret; + } if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); if (value == endptr) { -- GitLab From 090657c9fb7094e4c1b05c1713d6c2a12ef43dea Mon Sep 17 00:00:00 2001 From: Akemi Yagi Date: Fri, 22 Sep 2017 22:11:53 +0000 Subject: [PATCH 0338/1507] perf tools: Fix syscalltbl build failure The build of kernel v4.14-rc1 for i686 fails on RHEL 6 with the error in tools/perf: util/syscalltbl.c:157: error: expected ';', ',' or ')' before '__maybe_unused' mv: cannot stat `util/.syscalltbl.o.tmp': No such file or directory Fix it by placing/moving: #include outside of #ifdef HAVE_SYSCALL_TABLE block. Signed-off-by: Akemi Yagi Cc: Alan Bartlett Link: http://lkml.kernel.org/r/oq41r8$1v9$1@blaine.gmane.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/syscalltbl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 19e5db90394c2..6eea7cff3d4e9 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -15,9 +15,9 @@ #include "syscalltbl.h" #include +#include #ifdef HAVE_SYSCALL_TABLE -#include #include #include "string2.h" #include "util.h" -- GitLab From 78b1beb0998437107ed144b341fbe1252188916b Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 24 Sep 2017 21:46:29 +0300 Subject: [PATCH 0339/1507] IB/core: Fix typo in the name of the tag-matching cap struct The tag matching functionality is implemented by mlx5 driver by extending XRQ, however this internal kernel information was exposed to user space applications with *xrq* name instead of *tm*. This patch renames *xrq* to *tm* to handle that. Fixes: 8d50505ada72 ("IB/uverbs: Expose XRQ capabilities") Signed-off-by: Leon Romanovsky Reviewed-by: Yishai Hadas Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs_cmd.c | 14 +++++++------- drivers/infiniband/hw/mlx5/main.c | 10 +++++----- include/rdma/ib_verbs.h | 4 ++-- include/uapi/rdma/ib_user_verbs.h | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4ab30d832ac5b..52a2cf2d83aaf 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -3869,15 +3869,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file, resp.raw_packet_caps = attr.raw_packet_caps; resp.response_length += sizeof(resp.raw_packet_caps); - if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps)) + if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps)) goto end; - resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size; - resp.xrq_caps.max_num_tags = attr.xrq_caps.max_num_tags; - resp.xrq_caps.max_ops = attr.xrq_caps.max_ops; - resp.xrq_caps.max_sge = attr.xrq_caps.max_sge; - resp.xrq_caps.flags = attr.xrq_caps.flags; - resp.response_length += sizeof(resp.xrq_caps); + resp.tm_caps.max_rndv_hdr_size = attr.tm_caps.max_rndv_hdr_size; + resp.tm_caps.max_num_tags = attr.tm_caps.max_num_tags; + resp.tm_caps.max_ops = attr.tm_caps.max_ops; + resp.tm_caps.max_sge = attr.tm_caps.max_sge; + resp.tm_caps.flags = attr.tm_caps.flags; + resp.response_length += sizeof(resp.tm_caps); end: err = ib_copy_to_udata(ucore, &resp, resp.response_length); return err; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 05fb4bdff6a0a..d6fbad8f34aa7 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -778,13 +778,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, } if (MLX5_CAP_GEN(mdev, tag_matching)) { - props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; - props->xrq_caps.max_num_tags = + props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE; + props->tm_caps.max_num_tags = (1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1; - props->xrq_caps.flags = IB_TM_CAP_RC; - props->xrq_caps.max_ops = + props->tm_caps.flags = IB_TM_CAP_RC; + props->tm_caps.max_ops = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz); - props->xrq_caps.max_sge = MLX5_TM_MAX_SGE; + props->tm_caps.max_sge = MLX5_TM_MAX_SGE; } if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) { diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bdb1279a415b3..bbb5f54db8820 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -285,7 +285,7 @@ enum ib_tm_cap_flags { IB_TM_CAP_RC = 1 << 0, }; -struct ib_xrq_caps { +struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ @@ -358,7 +358,7 @@ struct ib_device_attr { struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ - struct ib_xrq_caps xrq_caps; + struct ib_tm_caps tm_caps; }; enum ib_mtu { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 9a0b6479fe0c6..d4e0b53bfc75c 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -261,7 +261,7 @@ struct ib_uverbs_ex_query_device_resp { struct ib_uverbs_rss_caps rss_caps; __u32 max_wq_type_rq; __u32 raw_packet_caps; - struct ib_uverbs_tm_caps xrq_caps; + struct ib_uverbs_tm_caps tm_caps; }; struct ib_uverbs_query_port { -- GitLab From 73827a605bbd7cebef4cfd1261e497246a82a0e7 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 24 Sep 2017 21:46:30 +0300 Subject: [PATCH 0340/1507] IB/core: Fix qp_sec use after free access When security_ib_alloc_security fails, qp->qp_sec memory is freed. However ib_destroy_qp still tries to access this memory which result in kernel crash. So its initialized to NULL to avoid such access. Fixes: d291f1a65232 ("IB/core: Enforce PKey security on QPs") Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/core/security.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index 70ad19c4c73e7..88bdafb297f5f 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -432,8 +432,10 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) atomic_set(&qp->qp_sec->error_list_count, 0); init_completion(&qp->qp_sec->error_complete); ret = security_ib_alloc_security(&qp->qp_sec->security); - if (ret) + if (ret) { kfree(qp->qp_sec); + qp->qp_sec = NULL; + } return ret; } -- GitLab From edd31551148c09608feee6b8756ad148d550ee3b Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 24 Sep 2017 21:46:31 +0300 Subject: [PATCH 0341/1507] IB: Correct MR length field to be 64-bit The ib_mr->length represents the length of the MR in bytes as per the IBTA spec 1.3 section 11.2.10.3 (REGISTER PHYSICAL MEMORY REGION). Currently ib_mr->length field is defined as only 32-bits field. This might result into truncation and failed WRs of consumers who registers more than 4GB bytes memory regions and whose WRs accessing such MRs. This patch makes the length 64-bit to avoid such truncation. Cc: Sagi Grimberg Cc: Chuck Lever Cc: Faisal Latif Fixes: 4c67e2bfc8b7 ("IB/core: Introduce new fast registration API") Signed-off-by: Ilya Lesokhin Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/nes/nes_verbs.c | 4 ++-- drivers/infiniband/ulp/iser/iser_memory.c | 2 +- include/rdma/ib_verbs.h | 2 +- net/sunrpc/xprtrdma/frwr_ops.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index f0dc5f4aa177e..442b9bdc0f03b 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -3232,7 +3232,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->ibmr.iova); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX, - mr->ibmr.length); + lower_32_bits(mr->ibmr.length)); set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0); set_wqe_32bit_value(wqe->wqe_words, @@ -3274,7 +3274,7 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr, mr->npages * 8); nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, " - "length: %d, rkey: %0x, pgl_paddr: %llx, " + "length: %lld, rkey: %0x, pgl_paddr: %llx, " "page_list_len: %u, wqe_misc: %x\n", (unsigned long long) mr->ibmr.iova, mr->ibmr.length, diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 9c3e9ab53a415..322209d5ff582 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -154,7 +154,7 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) { int i; - iser_err("page vec npages %d data length %d\n", + iser_err("page vec npages %d data length %lld\n", page_vec->npages, page_vec->fake_mr.length); for (i = 0; i < page_vec->npages; i++) iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index bbb5f54db8820..e8608b2dc844f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1739,7 +1739,7 @@ struct ib_mr { u32 lkey; u32 rkey; u64 iova; - u32 length; + u64 length; unsigned int page_size; bool need_inval; union { diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 5a936a6a31a32..df062e086bdbb 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -401,7 +401,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (unlikely(n != mw->mw_nents)) goto out_mapmr_err; - dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n", + dprintk("RPC: %s: Using frmr %p to map %u segments (%llu bytes)\n", __func__, frmr, mw->mw_nents, mr->length); key = (u8)(mr->rkey & 0x000000FF); -- GitLab From 9c6f42e9254150d2772242d9f8bd8d0b7b7431ff Mon Sep 17 00:00:00 2001 From: Shalom Lagziel Date: Sun, 24 Sep 2017 21:46:32 +0300 Subject: [PATCH 0342/1507] IB/ipoib: Fix sysfs Pkey create<->remove possible deadlock A possible ABBA lock can happen with RTNL and vlan_rwsem. For example: Flow A: Device Flush __ipoib_ib_dev_flush down_read(vlan_rwsem) // Lock A ipoib_flush_ah flush_workqueue(priv->wq) // Wait for completion A work on shared WQ (Mcast carrier) ipoib_mcast_carrier_on_task while (!rtnl_trylock()) // Wait for lock B Flow B: Sysfs PKEY delete ipoib_vlan_delete lock(RTNL) // Lock B down_write(vlan_rwsem) // Wait for lock A This can happen with PKEY creates as well. The solution is to release the RTNL lock in sysfs functions in case it is not possible to lock VLAN RW semaphore and reset the SYS call. Fixes: 69956d83267e ("IB/ipoib: Sync between remove_one to sysfs calls that use rtnl_lock") Signed-off-by: Shalom Lagziel Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 9927cd6b7082b..e01c58edca15c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -141,14 +141,17 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); - if (!priv) { + if (!down_write_trylock(&ppriv->vlan_rwsem)) { rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - return -ENOMEM; + return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); + if (!priv) { + result = -ENOMEM; + goto out; + } /* * First ensure this isn't a duplicate. We check the parent device and @@ -175,7 +178,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) rtnl_unlock(); mutex_unlock(&ppriv->sysfs_mutex); - if (result) { + if (result && priv) { free_netdev(priv->dev); kfree(priv); } @@ -204,7 +207,12 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) return restart_syscall(); } - down_write(&ppriv->vlan_rwsem); + if (!down_write_trylock(&ppriv->vlan_rwsem)) { + rtnl_unlock(); + mutex_unlock(&ppriv->sysfs_mutex); + return restart_syscall(); + } + list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey && priv->child_type == IPOIB_LEGACY_CHILD) { -- GitLab From 7c9d9662103ae1c11acc7bfc47d988466cff23cf Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Sun, 24 Sep 2017 21:46:33 +0300 Subject: [PATCH 0343/1507] IB/ipoib: Fix inconsistency with free_netdev and free_rdma_netdev Call free_rdma_netdev instead of free_netdev each time we want to release a netdevice. This call is also relevant for future freeing of offloaded child interfaces. This patch also adds a missing call for free netdevice when releasing a parent interface that has child interfaces using ipoib_remove_one. Fixes: cd565b4b51e5 ('IB/IPoIB: Support acceleration options callbacks') Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 15 +++++++++++---- drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 10 ++++++++-- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index bac95b509a9b2..dcc77014018db 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2180,6 +2180,7 @@ static struct net_device *ipoib_add_port(const char *format, { struct ipoib_dev_priv *priv; struct ib_port_attr attr; + struct rdma_netdev *rn; int result = -ENOMEM; priv = ipoib_intf_alloc(hca, port, format); @@ -2279,7 +2280,8 @@ static struct net_device *ipoib_add_port(const char *format, ipoib_dev_cleanup(priv->dev); device_init_failed: - free_netdev(priv->dev); + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); alloc_mem_failed: @@ -2328,7 +2330,7 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) return; list_for_each_entry_safe(priv, tmp, dev_list, list) { - struct rdma_netdev *rn = netdev_priv(priv->dev); + struct rdma_netdev *parent_rn = netdev_priv(priv->dev); ib_unregister_event_handler(&priv->event_handler); flush_workqueue(ipoib_workqueue); @@ -2350,10 +2352,15 @@ static void ipoib_remove_one(struct ib_device *device, void *client_data) unregister_netdev(priv->dev); mutex_unlock(&priv->sysfs_mutex); - rn->free_rdma_netdev(priv->dev); + parent_rn->free_rdma_netdev(priv->dev); + + list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) { + struct rdma_netdev *child_rn; - list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) + child_rn = netdev_priv(cpriv->dev); + child_rn->free_rdma_netdev(cpriv->dev); kfree(cpriv); + } kfree(priv); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index e01c58edca15c..55a9b71ed05a7 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -179,7 +179,10 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) mutex_unlock(&ppriv->sysfs_mutex); if (result && priv) { - free_netdev(priv->dev); + struct rdma_netdev *rn; + + rn = netdev_priv(priv->dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); } @@ -232,7 +235,10 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) mutex_unlock(&ppriv->sysfs_mutex); if (dev) { - free_netdev(dev); + struct rdma_netdev *rn; + + rn = netdev_priv(dev); + rn->free_rdma_netdev(priv->dev); kfree(priv); return 0; } -- GitLab From d67bc5d4e3e100d762c0f57ea67f28bc219698a6 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Sun, 24 Sep 2017 21:46:34 +0300 Subject: [PATCH 0344/1507] IB/mlx5: Simplify mlx5_ib_cont_pages The patch simplifies mlx5_ib_cont_pages and fixes the following issues in the original implementation: First issues is related to alignment of the PFNs. After the check base + p != PFN, the alignment of the PFN wasn't checked. So the PFN sequence 0, 1, 1, 2 would result in a page_shift of 13 even though the 3rd PFN is not 8KB aligned. This wasn't actually a bug because it was supported by all the existing mlx5 compatible device, but we don't want to require this support in all future devices. Another issue is because the inner loop didn't advance PFN so the test "if (base + p != pfn)" always failed for SGE with len > (1< Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mem.c | 47 ++++++++++++-------------------- 1 file changed, 17 insertions(+), 30 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c index 914f212e7ef60..f3dbd75a0a968 100644 --- a/drivers/infiniband/hw/mlx5/mem.c +++ b/drivers/infiniband/hw/mlx5/mem.c @@ -50,13 +50,9 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, { unsigned long tmp; unsigned long m; - int i, k; - u64 base = 0; - int p = 0; - int skip; - int mask; - u64 len; - u64 pfn; + u64 base = ~0, p = 0; + u64 len, pfn; + int i = 0; struct scatterlist *sg; int entry; unsigned long page_shift = umem->page_shift; @@ -76,33 +72,24 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, m = find_first_bit(&tmp, BITS_PER_LONG); if (max_page_shift) m = min_t(unsigned long, max_page_shift - page_shift, m); - skip = 1 << m; - mask = skip - 1; - i = 0; + for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) { len = sg_dma_len(sg) >> page_shift; pfn = sg_dma_address(sg) >> page_shift; - for (k = 0; k < len; k++) { - if (!(i & mask)) { - tmp = (unsigned long)pfn; - m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG)); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } else { - if (base + p != pfn) { - tmp = (unsigned long)p; - m = find_first_bit(&tmp, BITS_PER_LONG); - skip = 1 << m; - mask = skip - 1; - base = pfn; - p = 0; - } - } - p++; - i++; + if (base + p != pfn) { + /* If either the offset or the new + * base are unaligned update m + */ + tmp = (unsigned long)(pfn | p); + if (!IS_ALIGNED(tmp, 1 << m)) + m = find_first_bit(&tmp, BITS_PER_LONG); + + base = pfn; + p = 0; } + + p += len; + i += len; } if (i) { -- GitLab From fbcd49838d9094ca45772356e7b33afe4b7c93e7 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Sun, 24 Sep 2017 21:46:35 +0300 Subject: [PATCH 0345/1507] IB/mlx5: Fix NULL deference on mlx5_ib_update_xlt failure mlx5_ib_reg_user_mr called mlx5_ib_dereg_mr in case of MR population failure. This resulted in a NULL dereference as ibmr->device wasn't initialized yet. We address this by adding an internal dereg_mr function that can handle partially initialized MRs, and fixing clean_mr to work on partially initialized MRs. Fixes: ff740aefecb9 ("IB/mlx5: Decouple MR allocation and population flows") Signed-off-by: Ilya Lesokhin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/mr.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 0e2789d9bb4d0..37bbc543847a5 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -47,7 +47,8 @@ enum { #define MLX5_UMR_ALIGN 2048 -static int clean_mr(struct mlx5_ib_mr *mr); +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); static int mr_cache_max_order(struct mlx5_ib_dev *dev); static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr); @@ -1270,8 +1271,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift, update_xlt_flags); + if (err) { - mlx5_ib_dereg_mr(&mr->ibmr); + dereg_mr(dev, mr); return ERR_PTR(err); } } @@ -1356,7 +1358,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, err = mr_umem_get(pd, addr, len, access_flags, &mr->umem, &npages, &page_shift, &ncont, &order); if (err < 0) { - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1410,7 +1412,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); - clean_mr(mr); + clean_mr(dev, mr); return err; } } @@ -1469,9 +1471,8 @@ mlx5_free_priv_descs(struct mlx5_ib_mr *mr) } } -static int clean_mr(struct mlx5_ib_mr *mr) +static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); int allocated_from_cache = mr->allocated_from_cache; int err; @@ -1507,10 +1508,8 @@ static int clean_mr(struct mlx5_ib_mr *mr) return 0; } -int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { - struct mlx5_ib_dev *dev = to_mdev(ibmr->device); - struct mlx5_ib_mr *mr = to_mmr(ibmr); int npages = mr->npages; struct ib_umem *umem = mr->umem; @@ -1539,7 +1538,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) } #endif - clean_mr(mr); + clean_mr(dev, mr); if (umem) { ib_umem_release(umem); @@ -1549,6 +1548,14 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr) return 0; } +int mlx5_ib_dereg_mr(struct ib_mr *ibmr) +{ + struct mlx5_ib_dev *dev = to_mdev(ibmr->device); + struct mlx5_ib_mr *mr = to_mmr(ibmr); + + return dereg_mr(dev, mr); +} + struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg) -- GitLab From fe59493240169a2cc3f445ae5f2a2308fda06b63 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 Sep 2017 14:29:15 +0200 Subject: [PATCH 0346/1507] PCI: Add dummy pci_acs_enabled() for CONFIG_PCI=n build If CONFIG_PCI=n and gcc (e.g. 4.1.2) decides not to inline get_pci_function_alias_group(), the build fails with: drivers/iommu/iommu.o: In function `get_pci_function_alias_group': iommu.c:(.text+0xfdc): undefined reference to `pci_acs_enabled' Due to the various dummies for PCI calls in the CONFIG_PCI=n case, pci_acs_enabled() never called, but not all versions of gcc are smart enough to realize that. While explicitly marking get_pci_function_alias_group() inline would fix the build, this would inflate the code for the CONFIG_PCI=y case, as get_pci_function_alias_group() is a not-so-small function called from two places. Hence fix the issue by introducing a dummy for pci_acs_enabled() instead. Fixes: 0ae349a0f33f ("iommu/qcom: Add qcom_iommu") Signed-off-by: Geert Uytterhoeven Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Williamson --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/pci.h b/include/linux/pci.h index f68c58a93dd04..f4f8ee5a7362e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1685,6 +1685,8 @@ static inline int pci_get_new_domain_nr(void) { return -ENOSYS; } #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) +static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ return false; } #endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ -- GitLab From 9c3340ea7f5dabf88ca096a917cb0ab1f208ef2a Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 11 Sep 2017 19:11:07 -0600 Subject: [PATCH 0347/1507] selftests: futex: copy sub-dir test scripts for make O=dir run For make O=dir run_tests to work, test scripts from sub-directories need to be copied over to the object directory. Running tests from the object directory is necessary to avoid making the source tree dirty. Signed-off-by: Shuah Khan Reviewed-by: Darren Hart (VMware) Signed-off-by: Shuah Khan --- tools/testing/selftests/futex/Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 7c647f619d63f..9358cb210fd54 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -11,10 +11,13 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + if [ -e $$DIR/$(TEST_PROGS) ]; then + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; + fi done override define RUN_TESTS - $(OUTPUT)/run.sh + cd $(OUTPUT); ./run.sh endef override define INSTALL_RULE -- GitLab From 8230b905a6780c60372bf5df7bf5f23041ca3196 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Tue, 12 Sep 2017 08:52:13 -0600 Subject: [PATCH 0348/1507] selftests: mqueue: Use full path to run tests from Makefile Use full path including $(OUTPUT) to run tests from Makefile for normal case when objects reside in the source tree as well as when objects are relocated with make O=dir. In both cases $(OUTPUT) will be set correctly by lib.mk. Signed-off-by: Shuah Khan --- tools/testing/selftests/mqueue/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index 79a664aeb8d76..0f5e347b068d3 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk override define RUN_TESTS - @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" - @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" + $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]" + $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]" endef override define EMIT_TESTS -- GitLab From 1ede053632f6380d7e1dba4d781e5eb78621aa3a Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 18 Sep 2017 17:30:50 -0600 Subject: [PATCH 0349/1507] selftests: Makefile: fix for loops in targets to run silently Fix for loops in targets to run silently to avoid cluttering the test results. Suppresses the following from targets: e.g run from breakpoints for TARGET in breakpoints; do \ BUILD_TARGET=$BUILD/$TARGET; \ mkdir $BUILD_TARGET -p; \ make OUTPUT=$BUILD_TARGET -C $TARGET;\ done; Signed-off-by: Shuah Khan --- tools/testing/selftests/Makefile | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index f4368db011ea2..ff805643b5f72 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -66,32 +66,32 @@ endif export BUILD all: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: - for TARGET in $(TARGETS_HOTPLUG); do \ + @for TARGET in $(TARGETS_HOTPLUG); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; @@ -107,7 +107,7 @@ install: ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @@ -132,7 +132,7 @@ else endif clean: - for TARGET in $(TARGETS); do \ + @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; -- GitLab From 659dbfd8c47adeb03f401d1a1f17091bb63cc5a2 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Mon, 18 Sep 2017 18:46:23 -0600 Subject: [PATCH 0350/1507] selftests: futex: Makefile: fix for loops in targets to run silently Fix for loops in targets to run silently to avoid cluttering the test results. Suppresses the following from targets: for DIR in functional; do \ BUILD_TARGET=./tools/testing/selftests/futex/$DIR; \ mkdir $BUILD_TARGET -p; \ make OUTPUT=$BUILD_TARGET -C $DIR all;\ done ./tools/testing/selftests/futex/run.sh Signed-off-by: Shuah Khan Reviewed-by: Darren Hart (VMware) Signed-off-by: Shuah Khan --- tools/testing/selftests/futex/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 9358cb210fd54..f0c0369ccb797 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -7,7 +7,7 @@ TEST_PROGS := run.sh include ../lib.mk all: - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ @@ -17,7 +17,7 @@ all: done override define RUN_TESTS - cd $(OUTPUT); ./run.sh + @cd $(OUTPUT); ./run.sh endef override define INSTALL_RULE @@ -36,7 +36,7 @@ override define EMIT_TESTS endef override define CLEAN - for DIR in $(SUBDIRS); do \ + @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ -- GitLab From 10859f3855db4c6f10dc7974ff4b3a292f3de8e0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 7 Sep 2017 16:32:46 -0700 Subject: [PATCH 0351/1507] selftests/seccomp: Support glibc 2.26 siginfo_t.h The 2.26 release of glibc changed how siginfo_t is defined, and the earlier work-around to using the kernel definition are no longer needed. The old way needs to stay around for a while, though. Reported-by: Seth Forshee Cc: Andy Lutomirski Cc: Will Drewry Cc: Shuah Khan Cc: linux-kselftest@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Tested-by: Seth Forshee Signed-off-by: Shuah Khan --- tools/testing/selftests/seccomp/seccomp_bpf.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4d6f92a9df6b4..19cd272c234d8 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -6,10 +6,18 @@ */ #include -#include -#define __have_siginfo_t 1 -#define __have_sigval_t 1 -#define __have_sigevent_t 1 + +/* + * glibc 2.26 and later have SIGSYS in siginfo_t. Before that, + * we need to use the kernel's siginfo.h file and trick glibc + * into accepting it. + */ +#if !__GLIBC_PREREQ(2, 26) +# include +# define __have_siginfo_t 1 +# define __have_sigval_t 1 +# define __have_sigevent_t 1 +#endif #include #include @@ -676,7 +684,7 @@ TEST_F_SIGNAL(TRAP, ign, SIGSYS) syscall(__NR_getpid); } -static struct siginfo TRAP_info; +static siginfo_t TRAP_info; static volatile int TRAP_nr; static void TRAP_action(int nr, siginfo_t *info, void *void_context) { -- GitLab From 21aadfa2426d5d199ceb474d0159d079c7f17bfa Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Thu, 21 Sep 2017 17:13:27 +0800 Subject: [PATCH 0352/1507] selftests/memfd: correct run_tests.sh permission to fix the following issue: ------------------ TAP version 13 selftests: run_tests.sh ======================================== selftests: Warning: file run_tests.sh is not executable, correct this. not ok 1..1 selftests: run_tests.sh [FAIL] ------------------ Signed-off-by: Li Zhijian Signed-off-by: Shuah Khan --- tools/testing/selftests/memfd/run_tests.sh | 0 1 file changed, 0 insertions(+), 0 deletions(-) mode change 100644 => 100755 tools/testing/selftests/memfd/run_tests.sh diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh old mode 100644 new mode 100755 -- GitLab From 01db7fbf5487505b887fbd6a03c51f2adc952196 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 21 Sep 2017 13:46:01 -0600 Subject: [PATCH 0353/1507] selftests: timers: set-timer-lat: fix hang when std out/err are redirected do_timer_oneshot() uses select() as a timer with FD_SETSIZE and readfs is cleared with FD_ZERO without FD_SET. When stdout and stderr are redirected, the test hangs in select forever. Fix the problem calling select() with readfds empty and nfds zero. This is sufficient for using select() for timer. With this fix "./set-timer-lat > /dev/null 2>&1" no longer hangs. Signed-off-by: Shuah Khan Acked-by: Greg Hackmann Signed-off-by: Shuah Khan --- tools/testing/selftests/timers/set-timer-lat.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9c92b7bd56410..ea1af5dbc7b6d 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -228,7 +228,6 @@ int do_timer_oneshot(int clock_id, int flags) timer_t tm1; const int interval = 0; struct timeval timeout; - fd_set fds; int err; err = setup_timer(clock_id, flags, interval, &tm1); @@ -237,9 +236,8 @@ int do_timer_oneshot(int clock_id, int flags) memset(&timeout, 0, sizeof(timeout)); timeout.tv_sec = 5; - FD_ZERO(&fds); do { - err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout); + err = select(0, NULL, NULL, NULL, &timeout); } while (err == -1 && errno == EINTR); timer_delete(tm1); -- GitLab From eefd95e1f3d47b90dc768e9ebc77d390c4f34809 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Thu, 21 Sep 2017 13:05:18 -0600 Subject: [PATCH 0354/1507] selftests: timers: set-timer-lat: Fix hang when testing unsupported alarms When timer_create() fails on a bootime or realtime clock, setup_timer() returns 0 as if timer has been set. Callers wait forever for the timer to expire. This hang is seen on a system that doesn't have support for: CLOCK_REALTIME_ALARM ABSTIME missing CAP_WAKE_ALARM? : [UNSUPPORTED] Test hangs waiting for a timer that hasn't been set to expire. Fix setup_timer() to return 1, add handling in callers to detect the unsupported case and return 0 without waiting to not fail the test. Signed-off-by: Shuah Khan --- tools/testing/selftests/timers/set-timer-lat.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index ea1af5dbc7b6d..50da45437daab 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -143,7 +143,8 @@ int setup_timer(int clock_id, int flags, int interval, timer_t *tm1) printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n", clockstring(clock_id), flags ? "ABSTIME":"RELTIME"); - return 0; + /* Indicate timer isn't set, so caller doesn't wait */ + return 1; } printf("%s - timer_create() failed\n", clockstring(clock_id)); return -1; @@ -213,8 +214,9 @@ int do_timer(int clock_id, int flags) int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; while (alarmcount < 5) sleep(1); @@ -231,8 +233,9 @@ int do_timer_oneshot(int clock_id, int flags) int err; err = setup_timer(clock_id, flags, interval, &tm1); + /* Unsupported case - return 0 to not fail the test */ if (err) - return err; + return err == 1 ? 0 : err; memset(&timeout, 0, sizeof(timeout)); timeout.tv_sec = 5; -- GitLab From 10201655b085df8e000822e496e5d4016a167a36 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 19 Sep 2017 07:15:35 -0500 Subject: [PATCH 0355/1507] gfs2: Fix debugfs glocks dump The switch to rhashtables (commit 88ffbf3e03) broke the debugfs glock dump (/sys/kernel/debug/gfs2//glocks) for dumps bigger than a single buffer: the right function for restarting an rhashtable iteration from the beginning of the hash table is rhashtable_walk_enter; rhashtable_walk_stop + rhashtable_walk_start will just resume from the current position. Signed-off-by: Andreas Gruenbacher Signed-off-by: Bob Peterson Cc: stable@vger.kernel.org # v4.3+ --- fs/gfs2/glock.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 98e845b7841bd..11066d8647d29 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1945,13 +1945,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1959,6 +1955,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1970,6 +1967,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } @@ -1980,6 +1978,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -2042,12 +2041,10 @@ static int __gfs2_glocks_open(struct inode *inode, struct file *file, struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } @@ -2063,7 +2060,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } -- GitLab From 115ef3b7e61ac64e32827611a127002672ed3725 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 25 Sep 2017 20:21:54 +0200 Subject: [PATCH 0356/1507] watchdog/hardlockup/perf: Cure UP damage for_each_cpu() unintuitively reports CPU0 as set independend of the actual cpumask content on UP kernels. That leads to a NULL pointer dereference when the cleanup function is invoked and there is no event to clean up. Reported-by: Fengguang Wu Signed-off-by: Thomas Gleixner --- kernel/watchdog_hld.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index b2931154b5f28..204a8cadb7170 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -220,8 +220,13 @@ void hardlockup_detector_perf_cleanup(void) for_each_cpu(cpu, &dead_events_mask) { struct perf_event *event = per_cpu(watchdog_ev, cpu); + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); per_cpu(watchdog_ev, cpu) = NULL; - perf_event_release_kernel(event); } cpumask_clear(&dead_events_mask); } -- GitLab From 8cbd96a6285e8eb65232b5afd3e8d9418453a61c Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 21 Sep 2017 08:13:49 -0700 Subject: [PATCH 0357/1507] nvme: fix sqhd reference when admin queue connect fails Fix bug in sqhd patch. It wasn't the sq that was at risk. In the case where the admin queue connect command fails, the sq->size field is not set. Therefore, this becomes a divide by zero error. Add a quick check to bypass under this failure condition. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index c2a768a94235d..1b208beeef509 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -390,7 +390,8 @@ static void __nvmet_req_complete(struct nvmet_req *req, u16 status) if (status) nvmet_set_status(req, status); - req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; + if (req->sq->size) + req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size; req->rsp->sq_head = cpu_to_le16(req->sq->sqhd); req->rsp->sq_id = cpu_to_le16(req->sq->qid); req->rsp->command_id = req->cmd->common.command_id; -- GitLab From 1a40d97288c6ffea9b355139e88fa62f0e5439f7 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 21 Sep 2017 17:01:36 +0300 Subject: [PATCH 0358/1507] nvme-core: Use nvme_wq to queue async events and fw activation async_event_work might race as it is executed from two different workqueues at the moment. Reviewed-by: Johannes Thumshirn Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5589f67d2cd8e..bb2aad0786373 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2676,7 +2676,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, case NVME_SC_ABORT_REQ: ++ctrl->event_limit; if (ctrl->state == NVME_CTRL_LIVE) - schedule_work(&ctrl->async_event_work); + queue_work(nvme_wq, &ctrl->async_event_work); break; default: break; @@ -2691,7 +2691,7 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, nvme_queue_scan(ctrl); break; case NVME_AER_NOTICE_FW_ACT_STARTING: - schedule_work(&ctrl->fw_act_work); + queue_work(nvme_wq, &ctrl->fw_act_work); break; default: dev_warn(ctrl->device, "async event result %08x\n", result); -- GitLab From 0a960afd60d02808c7f7f36d4aa8a2e07045e1e9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 21 Sep 2017 17:01:37 +0300 Subject: [PATCH 0359/1507] nvme-rdma: give up reconnect if state change fails If we failed to transition to state LIVE after a successful reconnect, then controller deletion already started. In this case there is no point moving forward with reconnect. Reviewed-by: Johannes Thumshirn Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 58983000964be..8441f6b3f617d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -942,7 +942,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); + if (!changed) { + /* state change failure is ok if we're in DELETING state */ + WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING); + return; + } + ctrl->ctrl.nr_reconnects = 0; nvme_start_ctrl(&ctrl->ctrl); -- GitLab From e4d753d7e51c0648b9ee33efeed55d45f362fc3d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 21 Sep 2017 17:01:38 +0300 Subject: [PATCH 0360/1507] nvme-rdma: don't fully stop the controller in error recovery By calling nvme_stop_ctrl on a already failed controller will wait for the scan work to complete (only by identify timeout expiration which is 60 seconds). This is unnecessary when we already know that the controller has failed. Reported-by: Yi Zhang Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 8441f6b3f617d..92a03ff5fb4d4 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -967,7 +967,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, err_work); - nvme_stop_ctrl(&ctrl->ctrl); + nvme_stop_keep_alive(&ctrl->ctrl); if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); -- GitLab From 3688feb582a1bc4e58ad50f5eccfdb90615de27b Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 19 Sep 2017 15:13:11 -0700 Subject: [PATCH 0361/1507] nvmet-fc: on port remove call put outside lock Avoid calling the put routine, as it may traverse to free routines while holding the target lock. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index c48c83d97e304..6850672ad2a2a 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -2530,13 +2530,17 @@ nvmet_fc_remove_port(struct nvmet_port *port) { struct nvmet_fc_tgtport *tgtport = port->priv; unsigned long flags; + bool matched = false; spin_lock_irqsave(&nvmet_fc_tgtlock, flags); if (tgtport->port == port) { - nvmet_fc_tgtport_put(tgtport); + matched = true; tgtport->port = NULL; } spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags); + + if (matched) + nvmet_fc_tgtport_put(tgtport); } static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = { -- GitLab From 0c319d3a144d4b8f1ea2047fd614d2149b68f889 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 19 Sep 2017 16:33:56 -0700 Subject: [PATCH 0362/1507] nvmet-fc: ensure target queue id within range. When searching for queue id's ensure they are within the expected range. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 6850672ad2a2a..58e010bdda3ea 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -783,6 +783,9 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, u16 qid = nvmet_fc_getqueueid(connection_id); unsigned long flags; + if (qid > NVMET_NR_QUEUES) + return NULL; + spin_lock_irqsave(&tgtport->lock, flags); list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { -- GitLab From 6b71f9e1e849f82abb4a8d54ce7f4b1c71f19ac4 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 20 Sep 2017 11:07:26 -0700 Subject: [PATCH 0363/1507] nvmet-fc: sync header templates with comments Comments were incorrect: - defer_rcv was in host port template. moved to target port template - Added Mandatory statements for target port template items Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/nvme-fc-driver.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 9c5cb44808063..a726f96010d59 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -346,11 +346,6 @@ struct nvme_fc_remote_port { * indicating an FC transport Aborted status. * Entrypoint is Mandatory. * - * @defer_rcv: Called by the transport to signal the LLLD that it has - * begun processing of a previously received NVME CMD IU. The LLDD - * is now free to re-use the rcv buffer associated with the - * nvmefc_tgt_fcp_req. - * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -806,11 +801,19 @@ struct nvmet_fc_target_port { * outstanding operation (if there was one) to complete, then will * call the fcp_req_release() callback to return the command's * exchange context back to the LLDD. + * Entrypoint is Mandatory. * * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req * to the LLDD after all operations on the fcp operation are complete. * This may be due to the command completing or upon completion of * abort cleanup. + * Entrypoint is Mandatory. + * + * @defer_rcv: Called by the transport to signal the LLLD that it has + * begun processing of a previously received NVME CMD IU. The LLDD + * is now free to re-use the rcv buffer associated with the + * nvmefc_tgt_fcp_req. + * Entrypoint is Optional. * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. -- GitLab From fddc9923c6d41de9fe7b1f323a3cece53e046c88 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 19 Sep 2017 14:01:50 -0700 Subject: [PATCH 0364/1507] nvme-fcloop: fix port deletes and callbacks Now that there are potentially long delays between when a remoteport or targetport delete calls is made and when the callback occurs (dev_loss_tmo timeout), no longer block in the delete routines and move the final nport puts to the callbacks. Moved the fcloop_nport_get/put/free routines to avoid forward declarations. Ensure port_info structs used in registrations are nulled in case fields are not set (ex: devloss_tmo values). Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/fcloop.c | 102 +++++++++++++---------------------- 1 file changed, 38 insertions(+), 64 deletions(-) diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 1fd1afbb8b2a2..7b75d9de55ab0 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -224,8 +224,6 @@ struct fcloop_nport { struct fcloop_lport *lport; struct list_head nport_list; struct kref ref; - struct completion rport_unreg_done; - struct completion tport_unreg_done; u64 node_name; u64 port_name; u32 port_role; @@ -630,6 +628,32 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport, schedule_work(&inireq->iniwork); } +static void +fcloop_nport_free(struct kref *ref) +{ + struct fcloop_nport *nport = + container_of(ref, struct fcloop_nport, ref); + unsigned long flags; + + spin_lock_irqsave(&fcloop_lock, flags); + list_del(&nport->nport_list); + spin_unlock_irqrestore(&fcloop_lock, flags); + + kfree(nport); +} + +static void +fcloop_nport_put(struct fcloop_nport *nport) +{ + kref_put(&nport->ref, fcloop_nport_free); +} + +static int +fcloop_nport_get(struct fcloop_nport *nport) +{ + return kref_get_unless_zero(&nport->ref); +} + static void fcloop_localport_delete(struct nvme_fc_local_port *localport) { @@ -644,8 +668,7 @@ fcloop_remoteport_delete(struct nvme_fc_remote_port *remoteport) { struct fcloop_rport *rport = remoteport->private; - /* release any threads waiting for the unreg to complete */ - complete(&rport->nport->rport_unreg_done); + fcloop_nport_put(rport->nport); } static void @@ -653,8 +676,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) { struct fcloop_tport *tport = targetport->private; - /* release any threads waiting for the unreg to complete */ - complete(&tport->nport->tport_unreg_done); + fcloop_nport_put(tport->nport); } #define FCLOOP_HW_QUEUES 4 @@ -722,6 +744,7 @@ fcloop_create_local_port(struct device *dev, struct device_attribute *attr, goto out_free_opts; } + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = opts->wwnn; pinfo.port_name = opts->wwpn; pinfo.port_role = opts->roles; @@ -804,32 +827,6 @@ fcloop_delete_local_port(struct device *dev, struct device_attribute *attr, return ret ? ret : count; } -static void -fcloop_nport_free(struct kref *ref) -{ - struct fcloop_nport *nport = - container_of(ref, struct fcloop_nport, ref); - unsigned long flags; - - spin_lock_irqsave(&fcloop_lock, flags); - list_del(&nport->nport_list); - spin_unlock_irqrestore(&fcloop_lock, flags); - - kfree(nport); -} - -static void -fcloop_nport_put(struct fcloop_nport *nport) -{ - kref_put(&nport->ref, fcloop_nport_free); -} - -static int -fcloop_nport_get(struct fcloop_nport *nport) -{ - return kref_get_unless_zero(&nport->ref); -} - static struct fcloop_nport * fcloop_alloc_nport(const char *buf, size_t count, bool remoteport) { @@ -938,6 +935,7 @@ fcloop_create_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -EIO; + memset(&pinfo, 0, sizeof(pinfo)); pinfo.node_name = nport->node_name; pinfo.port_name = nport->port_name; pinfo.port_role = nport->port_role; @@ -979,24 +977,12 @@ __unlink_remote_port(struct fcloop_nport *nport) } static int -__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) +__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport) { - int ret; - if (!rport) return -EALREADY; - init_completion(&nport->rport_unreg_done); - - ret = nvme_fc_unregister_remoteport(rport->remoteport); - if (ret) - return ret; - - wait_for_completion(&nport->rport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvme_fc_unregister_remoteport(rport->remoteport); } static ssize_t @@ -1029,7 +1015,7 @@ fcloop_delete_remote_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); return ret ? ret : count; } @@ -1086,24 +1072,12 @@ __unlink_target_port(struct fcloop_nport *nport) } static int -__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) +__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport) { - int ret; - if (!tport) return -EALREADY; - init_completion(&nport->tport_unreg_done); - - ret = nvmet_fc_unregister_targetport(tport->targetport); - if (ret) - return ret; - - wait_for_completion(&nport->tport_unreg_done); - - fcloop_nport_put(nport); - - return ret; + return nvmet_fc_unregister_targetport(tport->targetport); } static ssize_t @@ -1136,7 +1110,7 @@ fcloop_delete_target_port(struct device *dev, struct device_attribute *attr, if (!nport) return -ENOENT; - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); return ret ? ret : count; } @@ -1223,11 +1197,11 @@ static void __exit fcloop_exit(void) spin_unlock_irqrestore(&fcloop_lock, flags); - ret = __wait_targetport_unreg(nport, tport); + ret = __targetport_unreg(nport, tport); if (ret) pr_warn("%s: Failed deleting target port\n", __func__); - ret = __wait_remoteport_unreg(nport, rport); + ret = __remoteport_unreg(nport, rport); if (ret) pr_warn("%s: Failed deleting remote port\n", __func__); -- GitLab From a08588ea486a5590b50c36f437dc86350271b250 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 21 Sep 2017 23:24:39 -0700 Subject: [PATCH 0365/1507] irqchip/mips-gic: Fix shifts to extract register fields The MIPS GIC driver is incorrectly using __fls to shift registers, intending to shift to the least significant bit of a value based upon its mask but instead shifting off all but the value's top bit. It should actually be using __ffs to shift to the first, not last, bit of the value. Apparently the system I used when testing commit 3680746abd87 ("irqchip: mips-gic: Convert remaining shared reg access to new accessors") and commit b2b2e584ceab ("irqchip: mips-gic: Clean up mti, reserved-cpu-vectors handling") managed to work correctly despite this issue, but not all systems do... Fixes: 3680746abd87 ("irqchip: mips-gic: Convert remaining shared reg access to new accessors") Fixes: b2b2e584ceab ("irqchip: mips-gic: Clean up mti, reserved-cpu-vectors handling") Signed-off-by: Paul Burton Signed-off-by: Thomas Gleixner Cc: Marc Zyngier Cc: Jason Cooper Link: https://lkml.kernel.org/r/20170922062440.23701-2-paul.burton@imgtec.com --- drivers/irqchip/irq-mips-gic.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 40159ac12ac8c..0022b31ad2c5a 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -645,7 +645,7 @@ static int __init gic_of_init(struct device_node *node, /* Find the first available CPU vector. */ i = 0; - reserved = (C_SW0 | C_SW1) >> __fls(C_SW0); + reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0); while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors", i++, &cpu_vec)) reserved |= BIT(cpu_vec); @@ -684,11 +684,11 @@ static int __init gic_of_init(struct device_node *node, gicconfig = read_gic_config(); gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS; - gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS); + gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS); gic_shared_intrs = (gic_shared_intrs + 1) * 8; gic_vpes = gicconfig & GIC_CONFIG_PVPS; - gic_vpes >>= __fls(GIC_CONFIG_PVPS); + gic_vpes >>= __ffs(GIC_CONFIG_PVPS); gic_vpes = gic_vpes + 1; if (cpu_has_veic) { -- GitLab From d9f82930a5b41f28fadb1e4838b877ae528456d3 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 21 Sep 2017 23:24:40 -0700 Subject: [PATCH 0366/1507] irqchip/mips-gic: Use effective affinity to unmask Commit 7778c4b27cbe ("irqchip: mips-gic: Use pcpu_masks to avoid reading GIC_SH_MASK*") adjusted the way we handle masking interrupts to set & clear the interrupt's bit in each pcpu_mask. This allows us to avoid needing to read the GIC mask registers and perform a bitwise and of their values with the pending & pcpu_masks. Unfortunately this didn't quite work for IPIs, which were mapped to a particular CPU/VP during initialisation but never set the affinity or effective_affinity fields of their struct irq_desc. This led to them losing their affinity when gic_unmask_irq() was called for them, and they'd all become affine to cpu0. Fix this by: 1) Setting the effective affinity of interrupts in gic_shared_irq_domain_map(), which is where we actually map an interrupt to a CPU/VP. This ensures that the effective affinity mask is always valid, not just after explicitly setting affinity. 2) Using an interrupt's effective affinity when unmasking it, which prevents gic_unmask_irq() from unintentionally changing which pcpu_mask includes an interrupt. Fixes: 7778c4b27cbe ("irqchip: mips-gic: Use pcpu_masks to avoid reading GIC_SH_MASK*") Signed-off-by: Paul Burton Signed-off-by: Thomas Gleixner Cc: Marc Zyngier Cc: Jason Cooper Link: https://lkml.kernel.org/r/20170922062440.23701-3-paul.burton@imgtec.com --- drivers/irqchip/irq-mips-gic.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 0022b31ad2c5a..c90976d7e53cc 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -175,14 +175,13 @@ static void gic_mask_irq(struct irq_data *d) static void gic_unmask_irq(struct irq_data *d) { - struct cpumask *affinity = irq_data_get_affinity_mask(d); unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq); unsigned int cpu; write_gic_smask(intr); gic_clear_pcpu_masks(intr); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(d)); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); } @@ -420,13 +419,17 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw, unsigned int cpu) { int intr = GIC_HWIRQ_TO_SHARED(hw); + struct irq_data *data; unsigned long flags; + data = irq_get_irq_data(virq); + spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); gic_clear_pcpu_masks(intr); set_bit(intr, per_cpu_ptr(pcpu_masks, cpu)); + irq_data_update_effective_affinity(data, cpumask_of(cpu)); spin_unlock_irqrestore(&gic_lock, flags); return 0; -- GitLab From 7755d83e48397e822aac751b1545f8bcf71d133e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 22 Sep 2017 21:20:41 +0900 Subject: [PATCH 0367/1507] irqdomain: Add __rcu annotations to radix tree accessors Fix various address spaces warning of sparse. kernel/irq/irqdomain.c:1463:14: warning: incorrect type in assignment (different address spaces) kernel/irq/irqdomain.c:1463:14: expected void **slot kernel/irq/irqdomain.c:1463:14: got void [noderef] ** kernel/irq/irqdomain.c:1465:66: warning: incorrect type in argument 2 (different address spaces) kernel/irq/irqdomain.c:1465:66: expected void [noderef] **slot kernel/irq/irqdomain.c:1465:66: got void **slot Signed-off-by: Masahiro Yamada Signed-off-by: Thomas Gleixner Cc: Marc Zyngier Cc: Jason Cooper Link: https://lkml.kernel.org/r/1506082841-11530-1-git-send-email-yamada.masahiro@socionext.com --- kernel/irq/irqdomain.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b7056bb083..ac4644e92b499 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ -- GitLab From c88f0e6b06f4092995688211a631bb436125d77b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 27 Aug 2017 20:25:26 +0800 Subject: [PATCH 0368/1507] scsi: scsi_transport_iscsi: fix the issue that iscsi_if_rx doesn't parse nlmsg properly ChunYu found a kernel crash by syzkaller: [ 651.617875] kasan: CONFIG_KASAN_INLINE enabled [ 651.618217] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 651.618731] general protection fault: 0000 [#1] SMP KASAN [ 651.621543] CPU: 1 PID: 9539 Comm: scsi Not tainted 4.11.0.cov #32 [ 651.621938] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 651.622309] task: ffff880117780000 task.stack: ffff8800a3188000 [ 651.622762] RIP: 0010:skb_release_data+0x26c/0x590 [...] [ 651.627260] Call Trace: [ 651.629156] skb_release_all+0x4f/0x60 [ 651.629450] consume_skb+0x1a5/0x600 [ 651.630705] netlink_unicast+0x505/0x720 [ 651.632345] netlink_sendmsg+0xab2/0xe70 [ 651.633704] sock_sendmsg+0xcf/0x110 [ 651.633942] ___sys_sendmsg+0x833/0x980 [ 651.637117] __sys_sendmsg+0xf3/0x240 [ 651.638820] SyS_sendmsg+0x32/0x50 [ 651.639048] entry_SYSCALL_64_fastpath+0x1f/0xc2 It's caused by skb_shared_info at the end of sk_buff was overwritten by ISCSI_KEVENT_IF_ERROR when parsing nlmsg info from skb in iscsi_if_rx. During the loop if skb->len == nlh->nlmsg_len and both are sizeof(*nlh), ev = nlmsg_data(nlh) will acutally get skb_shinfo(SKB) instead and set a new value to skb_shinfo(SKB)->nr_frags by ev->type. This patch is to fix it by checking nlh->nlmsg_len properly there to avoid over accessing sk_buff. Reported-by: ChunYu Wang Signed-off-by: Xin Long Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 8934f19bce8ea..0190aeff5f7fd 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3689,7 +3689,7 @@ iscsi_if_rx(struct sk_buff *skb) uint32_t group; nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || + if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } -- GitLab From f3a0c7b3fa7cdf6783827c245c62772687f8b3ac Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Sat, 9 Sep 2017 20:37:03 +0800 Subject: [PATCH 0369/1507] MAINTAINERS: Add entry for MediaTek PMIC LED driver Add myself as a maintainer to support existing SoCs and push forward following MediaTek PMICs with LEDs to reuse the driver. Signed-off-by: Sean Wang Signed-off-by: Jacek Anaszewski --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 2281af4b41b6c..22cb6cc91081e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8586,6 +8586,12 @@ M: Sean Wang S: Maintained F: drivers/media/rc/mtk-cir.c +MEDIATEK PMIC LED DRIVER +M: Sean Wang +S: Maintained +F: drivers/leds/leds-mt6323.c +F: Documentation/devicetree/bindings/leds/leds-mt6323.txt + MEDIATEK ETHERNET DRIVER M: Felix Fietkau M: John Crispin -- GitLab From fac1c2040203363eab6c6e86ce883cb71390418f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:15 +0200 Subject: [PATCH 0370/1507] smp/hotplug: Add state diagram Add a state diagram to clarify when which states are ran where. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Cc: max.byungchul.park@gmail.com Link: https://lkml.kernel.org/r/20170920170546.661598270@infradead.org --- include/linux/cpuhotplug.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f24bfb2b9a2dc..477b2e6f60f72 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -3,6 +3,24 @@ #include +/* + * CPU-up CPU-down + * + * BP AP BP AP + * + * OFFLINE OFFLINE + * | ^ + * v | + * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead) + * | AP_OFFLINE + * v (IRQ-off) ,---------------^ + * AP_ONLNE | (stop_machine) + * | TEARDOWN_CPU <- AP_ONLINE_IDLE + * | ^ + * v | + * AP_ACTIVE AP_ACTIVE + */ + enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, -- GitLab From 96abb968549cdefd0964d1f7af0a79f4e6e7f897 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:16 +0200 Subject: [PATCH 0371/1507] smp/hotplug: Allow external multi-instance rollback Currently the rollback of multi-instance states is handled inside cpuhp_invoke_callback(). The problem is that when we want to allow an explicit state change for rollback, we need to return from the function without doing the rollback. Change cpuhp_invoke_callback() to optionally return the multi-instance state, such that rollback can be done from a subsequent call. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Cc: max.byungchul.park@gmail.com Link: https://lkml.kernel.org/r/20170920170546.720361181@infradead.org --- kernel/cpu.c | 47 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 32 insertions(+), 15 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51f..323b71050b54b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -123,13 +123,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -138,6 +141,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int ret, cnt; if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +156,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +166,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -323,7 +338,7 @@ static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); } } @@ -334,7 +349,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, int ret = 0; for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_down(cpu, st); @@ -350,7 +365,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +377,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -428,11 +443,13 @@ static void cpuhp_thread_fun(unsigned int cpu) if (st->cb_state < CPUHP_AP_ONLINE) { local_irq_disable(); ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + st->bringup, st->node, + NULL); local_irq_enable(); } else { ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + st->bringup, st->node, + NULL); } } else if (st->rollback) { BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); @@ -472,7 +489,7 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->cb_state = state; st->single = true; @@ -595,7 +612,7 @@ static int take_cpu_down(void *_param) st->state--; /* Invoke the former CPU_DYING callbacks */ for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -776,7 +793,7 @@ void notify_cpu_starting(unsigned int cpu) rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); } } @@ -1307,9 +1324,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; -- GitLab From 4dddfb5faa6118564b0c54a163353d13882299d8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:17 +0200 Subject: [PATCH 0372/1507] smp/hotplug: Rewrite AP state machine core There is currently no explicit state change on rollback. That is, st->bringup, st->rollback and st->target are not consistent when doing the rollback. Rework the AP state handling to be more coherent. This does mean we have to do a second AP kick-and-wait for rollback, but since rollback is the slow path of a slowpath, this really should not matter. Take this opportunity to simplify the AP thread function to only run a single callback per invocation. This unifies the three single/up/down modes is supports. The looping it used to do for up/down are achieved by retaining should_run and relying on the main smpboot_thread_fn() loop. (I have most of a patch that does the same for the BP state handling, but that's not critical and gets a little complicated because CPUHP_BRINGUP_CPU does the AP handoff from a callback, which gets recursive @st usage, I still have de-fugly that.) [ tglx: Move cpuhp_down_callbacks() et al. into the HOTPLUG_CPU section to avoid gcc complaining about unused functions. Make the HOTPLUG_CPU one piece instead of having two consecutive ifdef sections of the same type. ] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Cc: max.byungchul.park@gmail.com Link: https://lkml.kernel.org/r/20170920170546.769658088@infradead.org --- kernel/cpu.c | 321 +++++++++++++++++++++++++++++++++------------------ 1 file changed, 206 insertions(+), 115 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 323b71050b54b..1139063de5afb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -58,6 +58,7 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; struct completion done; @@ -112,6 +113,14 @@ static bool cpuhp_is_ap_state(enum cpuhp_state state) return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { struct cpuhp_step *sp; @@ -286,7 +295,72 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_completion(&st->done); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { @@ -301,12 +375,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -332,32 +404,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -404,71 +450,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) - return; - st->should_run = false; + if (WARN_ON_ONCE(!st->should_run)) + return; lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ + if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node, - NULL); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node, - NULL); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); + + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); - undo_cpu_down(cpu, st); - st->rollback = false; + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } + +next: lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + + if (!st->should_run) + complete(&st->done); } /* Invoke a single callback on a remote cpu */ @@ -477,6 +542,7 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; @@ -491,48 +557,43 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + st->rollback = false; + st->last = NULL; + + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); lock_map_acquire(&cpuhp_state_lock_map); lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); + + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -693,11 +754,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -716,13 +798,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -737,6 +819,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -744,9 +828,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: @@ -771,11 +854,15 @@ static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -846,7 +933,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1313,6 +1400,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; -- GitLab From 724a86881d03ee5794148e65142e24ed3621be66 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:18 +0200 Subject: [PATCH 0373/1507] smp/hotplug: Callback vs state-machine consistency While the generic callback functions have an 'int' return and thus appear to be allowed to return error, this is not true for all states. Specifically, what used to be STARTING/DYING are ran with IRQs disabled from critical parts of CPU bringup/teardown and are not allowed to fail. Add WARNs to enforce this rule. But since some callbacks are indeed allowed to fail, we have the situation where a state-machine rollback encounters a failure, in this case we're stuck, we can't go forward and we can't go back. Also add a WARN for that case. AFAICT this is a fundamental 'problem' with no real obvious solution. We want the 'prepare' callbacks to allow failure on either up or down. Typically on prepare-up this would be things like -ENOMEM from resource allocations, and the typical usage in prepare-down would be something like -EBUSY to avoid CPUs being taken away. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Cc: max.byungchul.park@gmail.com Link: https://lkml.kernel.org/r/20170920170546.819539119@infradead.org --- kernel/cpu.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 1139063de5afb..d6f1b8c364009 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -202,7 +202,14 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } @@ -659,6 +666,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -672,8 +680,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -876,11 +889,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } -- GitLab From 5f4b55e10645b7371322c800a5ec745cab487a6c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:20 +0200 Subject: [PATCH 0374/1507] smp/hotplug: Differentiate the AP-work lockdep class between up and down With lockdep-crossrelease we get deadlock reports that span cpu-up and cpu-down chains. Such deadlocks cannot possibly happen because cpu-up and cpu-down are globally serialized. CPU0 CPU1 CPU2 cpuhp_up_callbacks: takedown_cpu: cpuhp_thread_fun: cpuhp_state irq_lock_sparse() irq_lock_sparse() wait_for_completion() cpuhp_state complete() Now that we have consistent AP state, we can trivially separate the AP-work class between up and down using st->bringup. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: max.byungchul.park@gmail.com Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Link: https://lkml.kernel.org/r/20170920170546.922524234@infradead.org --- kernel/cpu.c | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index d6f1b8c364009..d5c09985fbb64 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -68,9 +68,26 @@ struct cpuhp_cpu_state { static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -486,7 +503,7 @@ static void cpuhp_thread_fun(unsigned int cpu) if (WARN_ON_ONCE(!st->should_run)) return; - lock_map_acquire(&cpuhp_state_lock_map); + cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; @@ -537,7 +554,7 @@ static void cpuhp_thread_fun(unsigned int cpu) } next: - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_release(bringup); if (!st->should_run) complete(&st->done); @@ -554,8 +571,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls @@ -593,8 +613,11 @@ static int cpuhp_kick_ap_work(unsigned int cpu) enum cpuhp_state prev_state = st->state; int ret; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(st, st->target); -- GitLab From 5ebe7742fff8be5f1359bc50f5d43fb6ff7bd060 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:19 +0200 Subject: [PATCH 0375/1507] smp/hotplug: Differentiate the AP completion between up and down With lockdep-crossrelease we get deadlock reports that span cpu-up and cpu-down chains. Such deadlocks cannot possibly happen because cpu-up and cpu-down are globally serialized. takedown_cpu() irq_lock_sparse() wait_for_completion(&st->done) cpuhp_thread_fun cpuhp_up_callback cpuhp_invoke_callback irq_affinity_online_cpu irq_local_spare() irq_unlock_sparse() complete(&st->done) Now that we have consistent AP state, we can trivially separate the AP completion between up and down using st->bringup. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Acked-by: max.byungchul.park@gmail.com Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Link: https://lkml.kernel.org/r/20170920170546.872472799@infradead.org --- kernel/cpu.c | 49 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 32 insertions(+), 17 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index d5c09985fbb64..6bbe261b851f3 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -46,7 +46,8 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; @@ -61,7 +62,8 @@ struct cpuhp_cpu_state { struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; @@ -130,14 +132,6 @@ static bool cpuhp_is_ap_state(enum cpuhp_state state) return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } -/* - * The former STARTING/DYING states, ran with IRQs disabled and must not fail. - */ -static bool cpuhp_is_atomic_state(enum cpuhp_state state) -{ - return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; -} - static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { struct cpuhp_step *sp; @@ -232,6 +226,26 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -368,7 +382,7 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) smp_mb(); st->should_run = true; wake_up_process(st->thread); - wait_for_completion(&st->done); + wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) @@ -391,7 +405,7 @@ static int bringup_wait_for_ap(unsigned int cpu) struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -464,7 +478,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -557,7 +572,7 @@ static void cpuhp_thread_fun(unsigned int cpu) cpuhp_lock_release(bringup); if (!st->should_run) - complete(&st->done); + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -753,7 +768,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -772,7 +787,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -939,7 +954,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ -- GitLab From 1db49484f21ed0fcdadd0635a3669f5f386546fa Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 20 Sep 2017 19:00:21 +0200 Subject: [PATCH 0376/1507] smp/hotplug: Hotplug state fail injection Add a sysfs file to one-time fail a specific state. This can be used to test the state rollback code paths. Something like this (hotplug-up.sh): #!/bin/bash echo 0 > /debug/sched_debug echo 1 > /debug/tracing/events/cpuhp/enable ALL_STATES=`cat /sys/devices/system/cpu/hotplug/states | cut -d':' -f1` STATES=${1:-$ALL_STATES} for state in $STATES do echo 0 > /sys/devices/system/cpu/cpu1/online echo 0 > /debug/tracing/trace echo Fail state: $state echo $state > /sys/devices/system/cpu/cpu1/hotplug/fail cat /sys/devices/system/cpu/cpu1/hotplug/fail echo 1 > /sys/devices/system/cpu/cpu1/online cat /debug/tracing/trace > hotfail-${state}.trace sleep 1 done Can be used to test for all possible rollback (barring multi-instance) scenarios on CPU-up, CPU-down is a trivial modification of the above. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: bigeasy@linutronix.de Cc: efault@gmx.de Cc: rostedt@goodmis.org Cc: max.byungchul.park@gmail.com Link: https://lkml.kernel.org/r/20170920170546.972581715@infradead.org --- include/linux/cpuhotplug.h | 3 +- kernel/cpu.c | 60 +++++++++++++++++++++++++++++++++++++- 2 files changed, 61 insertions(+), 2 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 477b2e6f60f72..6d508767e1445 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -22,7 +22,8 @@ */ enum cpuhp_state { - CPUHP_OFFLINE, + CPUHP_INVALID = -1, + CPUHP_OFFLINE = 0, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, diff --git a/kernel/cpu.c b/kernel/cpu.c index 6bbe261b851f3..8de11a29e4955 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -52,6 +52,7 @@ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -67,7 +68,9 @@ struct cpuhp_cpu_state { #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = @@ -160,6 +163,15 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; @@ -1805,9 +1817,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; -- GitLab From cdd10c9627496ad25c87ce6394e29752253c69d3 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 22 Sep 2017 15:39:23 +0200 Subject: [PATCH 0377/1507] l2tp: ensure sessions are freed after their PPPOL2TP socket If l2tp_tunnel_delete() or l2tp_tunnel_closeall() deletes a session right after pppol2tp_release() orphaned its socket, then the 'sock' variable of the pppol2tp_session_close() callback is NULL. Yet the session is still used by pppol2tp_release(). Therefore we need to take an extra reference in any case, to prevent l2tp_tunnel_delete() or l2tp_tunnel_closeall() from freeing the session. Since the pppol2tp_session_close() callback is only set if the session is associated to a PPPOL2TP socket and that both l2tp_tunnel_delete() and l2tp_tunnel_closeall() hold the PPPOL2TP socket before calling pppol2tp_session_close(), we're sure that pppol2tp_session_close() and pppol2tp_session_destruct() are paired and called in the right order. So the reference taken by the former will be released by the later. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ppp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 50e3ee9a9d612..bc6e8bfc5be49 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -437,11 +437,11 @@ static void pppol2tp_session_close(struct l2tp_session *session) BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (sock) { + if (sock) inet_shutdown(sock, SEND_SHUTDOWN); - /* Don't let the session go away before our socket does */ - l2tp_session_inc_refcount(session); - } + + /* Don't let the session go away before our socket does */ + l2tp_session_inc_refcount(session); } /* Really kill the session socket. (Called from sock_put() if -- GitLab From b228a94066406b6c456321d69643b0d7ce11cfa6 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 22 Sep 2017 15:39:24 +0200 Subject: [PATCH 0378/1507] l2tp: fix race between l2tp_session_delete() and l2tp_tunnel_closeall() There are several ways to remove L2TP sessions: * deleting a session explicitly using the netlink interface (with L2TP_CMD_SESSION_DELETE), * deleting the session's parent tunnel (either by closing the tunnel's file descriptor or using the netlink interface), * closing the PPPOL2TP file descriptor of a PPP pseudo-wire. In some cases, when these methods are used concurrently on the same session, the session can be removed twice, leading to use-after-free bugs. This patch adds a 'dead' flag, used by l2tp_session_delete() and l2tp_tunnel_closeall() to prevent them from stepping on each other's toes. The session deletion path used when closing a PPPOL2TP file descriptor doesn't need to be adapted. It already has to ensure that a session remains valid for the lifetime of its PPPOL2TP file descriptor. So it takes an extra reference on the session in the ->session_close() callback (pppol2tp_session_close()), which is eventually dropped in the ->sk_destruct() callback of the PPPOL2TP socket (pppol2tp_session_destruct()). Still, __l2tp_session_unhash() and l2tp_session_queue_purge() can be called twice and even concurrently for a given session, but thanks to proper locking and re-initialisation of list fields, this is not an issue. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 6 ++++++ net/l2tp/l2tp_core.h | 1 + 2 files changed, 7 insertions(+) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ee485df73ccdd..d8c2a89a76e18 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1314,6 +1314,9 @@ void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) hlist_del_init(&session->hlist); + if (test_and_set_bit(0, &session->dead)) + goto again; + if (session->ref != NULL) (*session->ref)(session); @@ -1750,6 +1753,9 @@ EXPORT_SYMBOL_GPL(__l2tp_session_unhash); */ int l2tp_session_delete(struct l2tp_session *session) { + if (test_and_set_bit(0, &session->dead)) + return 0; + if (session->ref) (*session->ref)(session); __l2tp_session_unhash(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a305e0c5925a2..70a12df40a5f0 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -76,6 +76,7 @@ struct l2tp_session_cfg { struct l2tp_session { int magic; /* should be * L2TP_SESSION_MAGIC */ + long dead; struct l2tp_tunnel *tunnel; /* back pointer to tunnel * context */ -- GitLab From 910801809b2e40a4baedd080ef5d80b4a180e70e Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 20 Sep 2017 16:58:38 +0200 Subject: [PATCH 0379/1507] security/keys: properly zero out sensitive key material in big_key Error paths forgot to zero out sensitive material, so this patch changes some kfrees into a kzfrees. Signed-off-by: Jason A. Donenfeld Signed-off-by: David Howells Reviewed-by: Eric Biggers Cc: Herbert Xu Cc: Kirill Marinushkin Cc: security@kernel.org Cc: stable@vger.kernel.org --- security/keys/big_key.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 6acb00f6f22cd..507d6fb86a4f9 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -195,7 +195,7 @@ int big_key_preparse(struct key_preparsed_payload *prep) *path = file->f_path; path_get(path); fput(file); - kfree(data); + kzfree(data); } else { /* Just store the data in a buffer */ void *data = kmalloc(datalen, GFP_KERNEL); @@ -211,9 +211,9 @@ int big_key_preparse(struct key_preparsed_payload *prep) err_fput: fput(file); err_enckey: - kfree(enckey); + kzfree(enckey); error: - kfree(data); + kzfree(data); return ret; } @@ -227,7 +227,7 @@ void big_key_free_preparse(struct key_preparsed_payload *prep) path_put(path); } - kfree(prep->payload.data[big_key_data]); + kzfree(prep->payload.data[big_key_data]); } /* @@ -259,7 +259,7 @@ void big_key_destroy(struct key *key) path->mnt = NULL; path->dentry = NULL; } - kfree(key->payload.data[big_key_data]); + kzfree(key->payload.data[big_key_data]); key->payload.data[big_key_data] = NULL; } @@ -328,7 +328,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) err_fput: fput(file); error: - kfree(data); + kzfree(data); } else { ret = datalen; if (copy_to_user(buffer, key->payload.data[big_key_data], -- GitLab From 428490e38b2e352812e0b765d8bceafab0ec441d Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 20 Sep 2017 16:58:39 +0200 Subject: [PATCH 0380/1507] security/keys: rewrite all of big_key crypto This started out as just replacing the use of crypto/rng with get_random_bytes_wait, so that we wouldn't use bad randomness at boot time. But, upon looking further, it appears that there were even deeper underlying cryptographic problems, and that this seems to have been committed with very little crypto review. So, I rewrote the whole thing, trying to keep to the conventions introduced by the previous author, to fix these cryptographic flaws. It makes no sense to seed crypto/rng at boot time and then keep using it like this, when in fact there's already get_random_bytes_wait, which can ensure there's enough entropy and be a much more standard way of generating keys. Since this sensitive material is being stored untrusted, using ECB and no authentication is simply not okay at all. I find it surprising and a bit horrifying that this code even made it past basic crypto review, which perhaps points to some larger issues. This patch moves from using AES-ECB to using AES-GCM. Since keys are uniquely generated each time, we can set the nonce to zero. There was also a race condition in which the same key would be reused at the same time in different threads. A mutex fixes this issue now. So, to summarize, this commit fixes the following vulnerabilities: * Low entropy key generation, allowing an attacker to potentially guess or predict keys. * Unauthenticated encryption, allowing an attacker to modify the cipher text in particular ways in order to manipulate the plaintext, which is is even more frightening considering the next point. * Use of ECB mode, allowing an attacker to trivially swap blocks or compare identical plaintext blocks. * Key re-use. * Faulty memory zeroing. Signed-off-by: Jason A. Donenfeld Reviewed-by: Eric Biggers Signed-off-by: David Howells Cc: Herbert Xu Cc: Kirill Marinushkin Cc: security@kernel.org Cc: stable@vger.kernel.org --- security/keys/Kconfig | 4 +- security/keys/big_key.c | 127 +++++++++++++++++++--------------------- 2 files changed, 60 insertions(+), 71 deletions(-) diff --git a/security/keys/Kconfig b/security/keys/Kconfig index a7a23b5541f85..91eafada3164e 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -45,10 +45,8 @@ config BIG_KEYS bool "Large payload keys" depends on KEYS depends on TMPFS - depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y) select CRYPTO_AES - select CRYPTO_ECB - select CRYPTO_RNG + select CRYPTO_GCM help This option provides support for holding large keys within the kernel (for example Kerberos ticket caches). The data may be stored out to diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 507d6fb86a4f9..e607830b6154c 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -1,5 +1,6 @@ /* Large capacity key type * + * Copyright (C) 2017 Jason A. Donenfeld . All Rights Reserved. * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * @@ -16,10 +17,10 @@ #include #include #include +#include #include #include -#include -#include +#include /* * Layout of key payload words. @@ -49,7 +50,12 @@ enum big_key_op { /* * Key size for big_key data encryption */ -#define ENC_KEY_SIZE 16 +#define ENC_KEY_SIZE 32 + +/* + * Authentication tag length + */ +#define ENC_AUTHTAG_SIZE 16 /* * big_key defined keys take an arbitrary string as the description and an @@ -64,57 +70,62 @@ struct key_type key_type_big_key = { .destroy = big_key_destroy, .describe = big_key_describe, .read = big_key_read, + /* no ->update(); don't add it without changing big_key_crypt() nonce */ }; /* - * Crypto names for big_key data encryption + * Crypto names for big_key data authenticated encryption */ -static const char big_key_rng_name[] = "stdrng"; -static const char big_key_alg_name[] = "ecb(aes)"; +static const char big_key_alg_name[] = "gcm(aes)"; /* - * Crypto algorithms for big_key data encryption + * Crypto algorithms for big_key data authenticated encryption */ -static struct crypto_rng *big_key_rng; -static struct crypto_skcipher *big_key_skcipher; +static struct crypto_aead *big_key_aead; /* - * Generate random key to encrypt big_key data + * Since changing the key affects the entire object, we need a mutex. */ -static inline int big_key_gen_enckey(u8 *key) -{ - return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE); -} +static DEFINE_MUTEX(big_key_aead_lock); /* * Encrypt/decrypt big_key data */ static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key) { - int ret = -EINVAL; + int ret; struct scatterlist sgio; - SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher); - - if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) { + struct aead_request *aead_req; + /* We always use a zero nonce. The reason we can get away with this is + * because we're using a different randomly generated key for every + * different encryption. Notably, too, key_type_big_key doesn't define + * an .update function, so there's no chance we'll wind up reusing the + * key to encrypt updated data. Simply put: one key, one encryption. + */ + u8 zero_nonce[crypto_aead_ivsize(big_key_aead)]; + + aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL); + if (!aead_req) + return -ENOMEM; + + memset(zero_nonce, 0, sizeof(zero_nonce)); + sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0)); + aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); + aead_request_set_ad(aead_req, 0); + + mutex_lock(&big_key_aead_lock); + if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) { ret = -EAGAIN; goto error; } - - skcipher_request_set_tfm(req, big_key_skcipher); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, - NULL, NULL); - - sg_init_one(&sgio, data, datalen); - skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL); - if (op == BIG_KEY_ENC) - ret = crypto_skcipher_encrypt(req); + ret = crypto_aead_encrypt(aead_req); else - ret = crypto_skcipher_decrypt(req); - - skcipher_request_zero(req); - + ret = crypto_aead_decrypt(aead_req); error: + mutex_unlock(&big_key_aead_lock); + aead_request_free(aead_req); return ret; } @@ -146,16 +157,13 @@ int big_key_preparse(struct key_preparsed_payload *prep) * * File content is stored encrypted with randomly generated key. */ - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; - /* prepare aligned data to encrypt */ data = kmalloc(enclen, GFP_KERNEL); if (!data) return -ENOMEM; - memcpy(data, prep->data, datalen); - memset(data + datalen, 0x00, enclen - datalen); /* generate random key */ enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL); @@ -163,13 +171,12 @@ int big_key_preparse(struct key_preparsed_payload *prep) ret = -ENOMEM; goto error; } - - ret = big_key_gen_enckey(enckey); - if (ret) + ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE); + if (unlikely(ret)) goto err_enckey; /* encrypt aligned data */ - ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey); + ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey); if (ret) goto err_enckey; @@ -295,7 +302,7 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) struct file *file; u8 *data; u8 *enckey = (u8 *)key->payload.data[big_key_data]; - size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher)); + size_t enclen = datalen + ENC_AUTHTAG_SIZE; loff_t pos = 0; data = kmalloc(enclen, GFP_KERNEL); @@ -344,47 +351,31 @@ long big_key_read(const struct key *key, char __user *buffer, size_t buflen) */ static int __init big_key_init(void) { - struct crypto_skcipher *cipher; - struct crypto_rng *rng; int ret; - rng = crypto_alloc_rng(big_key_rng_name, 0, 0); - if (IS_ERR(rng)) { - pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng)); - return PTR_ERR(rng); - } - - big_key_rng = rng; - - /* seed RNG */ - ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng)); - if (ret) { - pr_err("Can't reset rng: %d\n", ret); - goto error_rng; - } - /* init block cipher */ - cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(cipher)) { - ret = PTR_ERR(cipher); + big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(big_key_aead)) { + ret = PTR_ERR(big_key_aead); pr_err("Can't alloc crypto: %d\n", ret); - goto error_rng; + return ret; + } + ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE); + if (ret < 0) { + pr_err("Can't set crypto auth tag len: %d\n", ret); + goto free_aead; } - - big_key_skcipher = cipher; ret = register_key_type(&key_type_big_key); if (ret < 0) { pr_err("Can't register type: %d\n", ret); - goto error_cipher; + goto free_aead; } return 0; -error_cipher: - crypto_free_skcipher(big_key_skcipher); -error_rng: - crypto_free_rng(big_key_rng); +free_aead: + crypto_free_aead(big_key_aead); return ret; } -- GitLab From e4d8ae00169f7686e1da5a62e5cf797d12bf8822 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Sep 2017 10:44:36 -0700 Subject: [PATCH 0381/1507] PM / OPP: Call notifier without holding opp_table->lock The notifier callbacks may want to call some OPP helper routines which may try to take the same opp_table->lock again and cause a deadlock. One such usecase was reported by Chanwoo Choi, where calling dev_pm_opp_disable() leads us to the devfreq's OPP notifier handler, which further calls dev_pm_opp_find_freq_floor() and it deadlocks. We don't really need the opp_table->lock to be held across the notifier call though, all we want to make sure is that the 'opp' doesn't get freed while being used from within the notifier chain. We can do it with help of dev_pm_opp_get/put() as well. Let's do it. Cc: 4.11+ # 4.11+ Fixes: 5b650b388844 "PM / OPP: Take kref from _find_opp_table()" Reported-by: Chanwoo Choi Tested-by: Chanwoo Choi Reviewed-by: Stephen Boyd Reviewed-by: Chanwoo Choi Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/base/power/opp/core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index a8cc14fd8ae49..a6de325306933 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -1581,6 +1581,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, opp->available = availability_req; + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + /* Notify the change of the OPP availability */ if (availability_req) blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE, @@ -1589,8 +1592,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq, blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_DISABLE, opp); + dev_pm_opp_put(opp); + goto put_table; + unlock: mutex_unlock(&opp_table->lock); +put_table: dev_pm_opp_put_opp_table(opp_table); return r; } -- GitLab From 675195d0be27391d48d8d23c7c62991505168528 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 20 Sep 2017 08:58:53 +0200 Subject: [PATCH 0382/1507] scsi: scsi_transport_fc: set scsi_target_id upon rescan When an rport is found in the bindings array there is no guarantee that it had been a target port, so we need to call fc_remote_port_rolechg() here to ensure the scsi_target_id is set correctly. Otherwise the port will never be scanned. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Tested-by: Chad Dupuis Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_fc.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index ba9d70f8a6a17..e74fffc32c75c 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2876,7 +2876,6 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, memcpy(&rport->port_name, &ids->port_name, sizeof(rport->port_name)); rport->port_id = ids->port_id; - rport->roles = ids->roles; rport->port_state = FC_PORTSTATE_ONLINE; rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT; @@ -2885,15 +2884,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, fci->f->dd_fcrport_size); spin_unlock_irqrestore(shost->host_lock, flags); - if (ids->roles & FC_PORT_ROLE_FCP_TARGET) { - scsi_target_unblock(&rport->dev, SDEV_RUNNING); - - /* initiate a scan of the target */ - spin_lock_irqsave(shost->host_lock, flags); - rport->flags |= FC_RPORT_SCAN_PENDING; - scsi_queue_work(shost, &rport->scan_work); - spin_unlock_irqrestore(shost->host_lock, flags); - } + fc_remote_port_rolechg(rport, ids->roles); return rport; } } -- GitLab From d477bf3af1e88fe27c893f84136647fe11963198 Mon Sep 17 00:00:00 2001 From: Suniel Mahesh Date: Thu, 21 Sep 2017 19:09:03 +0530 Subject: [PATCH 0383/1507] cpufreq: dt: Fix sysfs duplicate filename creation for platform-device ti-cpufreq and cpufreq-dt-platdev drivers are registering platform-device with same name "cpufreq-dt" using platform_device_register_*() routines. This is leading to build warnings appended below. Providing hardware information to OPP framework along with the platform- device creation should be done by ti-cpufreq driver before cpufreq-dt driver comes into place. This patch add's TI am33xx, am43 and dra7 platforms (which use opp-v2 property) to the blacklist of devices in cpufreq-dt-platform driver to avoid creating platform-device twice and remove build warnings. [ 2.370167] ------------[ cut here ]------------ [ 2.375087] WARNING: CPU: 0 PID: 1 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x58/0x78 [ 2.383112] sysfs: cannot create duplicate filename '/devices/platform/cpufreq-dt' [ 2.391219] Modules linked in: [ 2.394506] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.13.0-next-20170912 #1 [ 2.402006] Hardware name: Generic AM33XX (Flattened Device Tree) [ 2.408437] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 2.416568] [] (show_stack) from [] (dump_stack+0xac/0xe0) [ 2.424165] [] (dump_stack) from [] (__warn+0xd8/0x104) [ 2.431488] [] (__warn) from [] (warn_slowpath_fmt+0x34/0x44) [ 2.439351] [] (warn_slowpath_fmt) from [] (sysfs_warn_dup+0x58/0x78) [ 2.447938] [] (sysfs_warn_dup) from [] (sysfs_create_dir_ns+0x80/0x98) [ 2.456719] [] (sysfs_create_dir_ns) from [] (kobject_add_internal+0x9c/0x2d4) [ 2.466124] [] (kobject_add_internal) from [] (kobject_add+0x4c/0x9c) [ 2.474712] [] (kobject_add) from [] (device_add+0xcc/0x57c) [ 2.482489] [] (device_add) from [] (platform_device_add+0x100/0x220) [ 2.491085] [] (platform_device_add) from [] (platform_device_register_full+0xf4/0x118) [ 2.501305] [] (platform_device_register_full) from [] (ti_cpufreq_init+0x150/0x22c) [ 2.511253] [] (ti_cpufreq_init) from [] (do_one_initcall+0x3c/0x170) [ 2.519838] [] (do_one_initcall) from [] (kernel_init_freeable+0x1fc/0x2c4) [ 2.528974] [] (kernel_init_freeable) from [] (kernel_init+0x8/0x110) [ 2.537565] [] (kernel_init) from [] (ret_from_fork+0x14/0x3c) [ 2.545981] ---[ end trace 2fc00e213c13ab20 ]--- [ 2.551051] ------------[ cut here ]------------ [ 2.555931] WARNING: CPU: 0 PID: 1 at lib/kobject.c:240 kobject_add_internal+0x254/0x2d4 [ 2.564578] kobject_add_internal failed for cpufreq-dt with -EEXIST, don't try to register things with the same name in the same directory. [ 2.577977] Modules linked in: [ 2.581261] CPU: 0 PID: 1 Comm: swapper/0 Tainted: G W 4.13.0-next-20170912 #1 [ 2.590013] Hardware name: Generic AM33XX (Flattened Device Tree) [ 2.596437] [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [ 2.604573] [] (show_stack) from [] (dump_stack+0xac/0xe0) [ 2.612172] [] (dump_stack) from [] (__warn+0xd8/0x104) [ 2.619494] [] (__warn) from [] (warn_slowpath_fmt+0x34/0x44) [ 2.627362] [] (warn_slowpath_fmt) from [] (kobject_add_internal+0x254/0x2d4) [ 2.636666] [] (kobject_add_internal) from [] (kobject_add+0x4c/0x9c) [ 2.645255] [] (kobject_add) from [] (device_add+0xcc/0x57c) [ 2.653027] [] (device_add) from [] (platform_device_add+0x100/0x220) [ 2.661615] [] (platform_device_add) from [] (platform_device_register_full+0xf4/0x118) [ 2.671833] [] (platform_device_register_full) from [] (ti_cpufreq_init+0x150/0x22c) [ 2.681779] [] (ti_cpufreq_init) from [] (do_one_initcall+0x3c/0x170) [ 2.690377] [] (do_one_initcall) from [] (kernel_init_freeable+0x1fc/0x2c4) [ 2.699510] [] (kernel_init_freeable) from [] (kernel_init+0x8/0x110) [ 2.708106] [] (kernel_init) from [] (ret_from_fork+0x14/0x3c) [ 2.716217] ---[ end trace 2fc00e213c13ab21 ]--- Fixes: edeec420de24 (cpufreq: dt-cpufreq: platdev Automatically create device with OPP v2) Signed-off-by: Suniel Mahesh Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq-dt-platdev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 430edadca527a..a753c50e9e412 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -118,6 +118,10 @@ static const struct of_device_id blacklist[] __initconst = { { .compatible = "sigma,tango4", }, + { .compatible = "ti,am33xx", }, + { .compatible = "ti,am43", }, + { .compatible = "ti,dra7", }, + { } }; -- GitLab From a93ad944f4ff9a797abff17c73fc4b1e4a1d9141 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Fri, 22 Sep 2017 15:32:44 -0500 Subject: [PATCH 0384/1507] net: qcom/emac: specify the correct size when mapping a DMA buffer When mapping the RX DMA buffers, the driver was accidentally specifying zero for the buffer length. Under normal circumstances, SWIOTLB does not need to allocate a bounce buffer, so the address is just mapped without checking the size field. This is why the error was not detected earlier. Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver") Cc: stable@vger.kernel.org Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-mac.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 0ea3ca09c6898..3ed9033e56dbe 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -898,7 +898,8 @@ static void emac_mac_rx_descs_refill(struct emac_adapter *adpt, curr_rxbuf->dma_addr = dma_map_single(adpt->netdev->dev.parent, skb->data, - curr_rxbuf->length, DMA_FROM_DEVICE); + adpt->rxbuf_size, DMA_FROM_DEVICE); + ret = dma_mapping_error(adpt->netdev->dev.parent, curr_rxbuf->dma_addr); if (ret) { -- GitLab From 9561475db680f7144d2223a409dd3d7e322aca03 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 11 Sep 2017 09:45:40 +0200 Subject: [PATCH 0385/1507] PCI: Fix race condition with driver_override The driver_override implementation is susceptible to a race condition when different threads are reading vs. storing a different driver override. Add locking to avoid the race condition. This is in close analogy to commit 6265539776a0 ("driver core: platform: fix race condition with driver_override") from Adrian Salido. Fixes: 782a985d7af2 ("PCI: Introduce new device binding path using pci_dev.driver_override") Signed-off-by: Nicolai Stange Signed-off-by: Bjorn Helgaas Cc: stable@vger.kernel.org # v3.16+ --- drivers/pci/pci-sysfs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 1eecfa301f7fb..8e075ea2743ef 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -686,7 +686,7 @@ static ssize_t driver_override_store(struct device *dev, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - char *driver_override, *old = pdev->driver_override, *cp; + char *driver_override, *old, *cp; /* We need to keep extra room for a newline */ if (count >= (PAGE_SIZE - 1)) @@ -700,12 +700,15 @@ static ssize_t driver_override_store(struct device *dev, if (cp) *cp = '\0'; + device_lock(dev); + old = pdev->driver_override; if (strlen(driver_override)) { pdev->driver_override = driver_override; } else { kfree(driver_override); pdev->driver_override = NULL; } + device_unlock(dev); kfree(old); @@ -716,8 +719,12 @@ static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + ssize_t len; - return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override); + device_unlock(dev); + return len; } static DEVICE_ATTR_RW(driver_override); -- GitLab From b776e4b1a990045a7c70798f1f353c3160c26594 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 25 Sep 2017 20:38:45 -0400 Subject: [PATCH 0386/1507] fix a typo in put_compat_shm_info() "uip" misspelled as "up"; unfortunately, the latter happens to be a function and gcc is happy to convert it to void *... Signed-off-by: Al Viro --- ipc/shm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ipc/shm.c b/ipc/shm.c index 1e2b1692ba2c6..badac463e2c8e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1154,7 +1154,7 @@ static int put_compat_shm_info(struct shm_info *ip, info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; - return copy_to_user(up, &info, sizeof(info)); + return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, -- GitLab From cc6f77710a6de6210f9feda7cd53e2f5ee7a7e69 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 18 Sep 2017 09:41:16 -0700 Subject: [PATCH 0387/1507] xfs: don't unconditionally clear the reflink flag on zero-block files If we have speculative cow preallocations hanging around in the cow fork, don't let a truncate operation clear the reflink flag because if we do then there's a chance we'll forget to free those extents when we destroy the incore inode. Reported-by: Amir Goldstein Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_inode.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5599dda4727af..4ec5b7f454013 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1624,10 +1624,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } -- GitLab From 3af423b03435c81036fa710623d3ae92fbe346a3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 18 Sep 2017 09:41:17 -0700 Subject: [PATCH 0388/1507] xfs: evict CoW fork extents when performing finsert/fcollapse When we perform an finsert/fcollapse operation, cancel all the CoW extents for the affected file offset range so that they don't end up pointing to the wrong blocks. Reported-by: Amir Goldstein Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_bmap_util.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index cd9a5400ba4fe..bc6c6e10a9699 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1459,7 +1459,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ -- GitLab From e150dcd459e1b441eaf08f341a986f04e61bf3b8 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Mon, 18 Sep 2017 11:34:16 -0700 Subject: [PATCH 0389/1507] fs/xfs: Use %pS printk format for direct addresses Use the %pS instead of the %pF printk format specifier for printing symbols from direct addresses. This is needed for the ia64, ppc64 and parisc64 architectures. Signed-off-by: Helge Deller Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_error.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index bd786a9ac2c38..eaf86f55b7f21 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -347,7 +347,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); -- GitLab From 64671bafbdd984535aa382bccadd91fbe7be0e80 Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Mon, 18 Sep 2017 11:38:58 -0700 Subject: [PATCH 0390/1507] xfs: kill meaningless variable 'zero' In xfs_file_aio_write_checks(), variable 'zero' is there only to satisfy xfs_zero_eof(), the result of it is ignored. Now, with iomap_zero_range() based xfs_zero_eof(), we can safely pass NULL as the last param of it and kill 'zero'. Signed-off-by: Eryu Guan Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ebdd0bd2b2616..261d83f1db767 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -377,8 +377,6 @@ xfs_file_aio_write_checks( */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { - bool zero = false; - spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { @@ -399,7 +397,7 @@ xfs_file_aio_write_checks( drained_dio = true; goto restart; } - error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else -- GitLab From d20a5e3851969fa685f118a80e4df670255a4e8d Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Mon, 18 Sep 2017 11:39:23 -0700 Subject: [PATCH 0391/1507] xfs: report zeroed or not correctly in xfs_zero_range() The 'did_zero' param of xfs_zero_range() was not passed to iomap_zero_range() correctly. This was introduced by commit 7bb41db3ea16 ("xfs: handle 64-bit length in xfs_iozero"), and found by code inspection. Signed-off-by: Eryu Guan Reviewed-by: Carlos Maiolino Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 261d83f1db767..350b6d43ba23b 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -58,7 +58,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int -- GitLab From 1e6fa688bffc0ff419a4c3e78dbaf7aabfb55183 Mon Sep 17 00:00:00 2001 From: Kenjiro Nakayama Date: Mon, 18 Sep 2017 12:03:56 -0700 Subject: [PATCH 0392/1507] xfs: Output warning message when discard option was enabled even though the device does not support discard In order to using discard function, it is necessary that not only xfs is mounted with discard option, but also the discard function is supported by the device. Current code doesn't output any message when users mount with discard option on unsupported device, so it is difficult to notice that it was not enabled actually. This patch adds the warning message to notice that discard option is not enabled due to unsupported device when the filesystem is mounted. Changes in v2 (Suggested by Brian Foster): - Move the unsupported device check into xfs_fs_fill_super(). - Clear the discard flag when device is unsupported. Signed-off-by: Kenjiro Nakayama Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_super.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c996f4ae4a5f2..584cf2d573bab 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1654,6 +1654,16 @@ xfs_fs_fill_super( "DAX and reflink have not been tested together!"); } + if (mp->m_flags & XFS_MOUNT_DISCARD) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + + if (!blk_queue_discard(q)) { + xfs_warn(mp, "mounting with \"discard\" option, but " + "the device does not support discard"); + mp->m_flags &= ~XFS_MOUNT_DISCARD; + } + } + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, -- GitLab From 60915f83cd1e021a66fc1503a446aef5c772553a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 18 Sep 2017 13:38:46 -0700 Subject: [PATCH 0393/1507] xfs: remove redundant re-initialization of total_nr_pages Variable total_nr_pages is being initialized and then updated with the same value, this latter assignment is redundant and can be removed. Cleans up clang build warning: Value stored to 'total_nr_pages' during its initialization is never read Signed-off-by: Colin Ian King Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_buf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index da14658da3103..2f97c12ca75e4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1258,8 +1258,6 @@ xfs_buf_ioapply_map( int size; int offset; - total_nr_pages = bp->b_page_count; - /* skip the pages in the buffer before the start offset */ page_index = 0; offset = *buf_offset; -- GitLab From f091fb8c344ce13cbf058d304c6cbb042be97058 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 25 Sep 2017 13:47:23 +0200 Subject: [PATCH 0394/1507] scsi: scsi_transport_fc: Also check for NOTPRESENT in fc_remote_port_add() During failover there is a small race window between fc_remote_port_add() and fc_timeout_deleted_rport(); the latter drops the lock after setting the port to NOTPRESENT, so if fc_remote_port_add() is called right at that time it will fail to detect the existing rport and happily adding a new structure, causing rports to get registered twice. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_fc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index e74fffc32c75c..cbd4495d0ff9d 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2739,7 +2739,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, list_for_each_entry(rport, &fc_host->rports, peers) { - if ((rport->port_state == FC_PORTSTATE_BLOCKED) && + if ((rport->port_state == FC_PORTSTATE_BLOCKED || + rport->port_state == FC_PORTSTATE_NOTPRESENT) && (rport->channel == channel)) { switch (fc_host->tgtid_bind_type) { -- GitLab From 6098d7ddd62f532f80ee2a4b01aca500a8e4e9e4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 22 Sep 2017 23:29:18 +0200 Subject: [PATCH 0395/1507] rocker: fix rocker_tlv_put_* functions for KASAN Inlining these functions creates lots of stack variables that each take 64 bytes when KASAN is enabled, leading to this warning about potential stack overflow: drivers/net/ethernet/rocker/rocker_ofdpa.c: In function 'ofdpa_cmd_flow_tbl_add': drivers/net/ethernet/rocker/rocker_ofdpa.c:621:1: error: the frame size of 2752 bytes is larger than 1536 bytes [-Werror=frame-larger-than=] gcc-8 can now consolidate the stack slots itself, but on older versions we get the same behavior by using a temporary variable that holds a copy of the inline function argument. Cc: stable@vger.kernel.org Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker_tlv.h | 48 +++++++++++++++--------- 1 file changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/rocker/rocker_tlv.h b/drivers/net/ethernet/rocker/rocker_tlv.h index a63ef82e7c72d..dfae3c9d57c6d 100644 --- a/drivers/net/ethernet/rocker/rocker_tlv.h +++ b/drivers/net/ethernet/rocker/rocker_tlv.h @@ -139,40 +139,52 @@ rocker_tlv_start(struct rocker_desc_info *desc_info) int rocker_tlv_put(struct rocker_desc_info *desc_info, int attrtype, int attrlen, const void *data); -static inline int rocker_tlv_put_u8(struct rocker_desc_info *desc_info, - int attrtype, u8 value) +static inline int +rocker_tlv_put_u8(struct rocker_desc_info *desc_info, int attrtype, u8 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value); + u8 tmp = value; /* work around GCC PR81715 */ + + return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &tmp); } -static inline int rocker_tlv_put_u16(struct rocker_desc_info *desc_info, - int attrtype, u16 value) +static inline int +rocker_tlv_put_u16(struct rocker_desc_info *desc_info, int attrtype, u16 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value); + u16 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &tmp); } -static inline int rocker_tlv_put_be16(struct rocker_desc_info *desc_info, - int attrtype, __be16 value) +static inline int +rocker_tlv_put_be16(struct rocker_desc_info *desc_info, int attrtype, __be16 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &value); + __be16 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(__be16), &tmp); } -static inline int rocker_tlv_put_u32(struct rocker_desc_info *desc_info, - int attrtype, u32 value) +static inline int +rocker_tlv_put_u32(struct rocker_desc_info *desc_info, int attrtype, u32 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value); + u32 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &tmp); } -static inline int rocker_tlv_put_be32(struct rocker_desc_info *desc_info, - int attrtype, __be32 value) +static inline int +rocker_tlv_put_be32(struct rocker_desc_info *desc_info, int attrtype, __be32 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &value); + __be32 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(__be32), &tmp); } -static inline int rocker_tlv_put_u64(struct rocker_desc_info *desc_info, - int attrtype, u64 value) +static inline int +rocker_tlv_put_u64(struct rocker_desc_info *desc_info, int attrtype, u64 value) { - return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value); + u64 tmp = value; + + return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &tmp); } static inline struct rocker_tlv * -- GitLab From b4391db42308c9940944b5d7be5ca4b78fb88dd0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 22 Sep 2017 23:29:19 +0200 Subject: [PATCH 0396/1507] netlink: fix nla_put_{u8,u16,u32} for KASAN When CONFIG_KASAN is enabled, the "--param asan-stack=1" causes rather large stack frames in some functions. This goes unnoticed normally because CONFIG_FRAME_WARN is disabled with CONFIG_KASAN by default as of commit 3f181b4d8652 ("lib/Kconfig.debug: disable -Wframe-larger-than warnings with KASAN=y"). The kernelci.org build bot however has the warning enabled and that led me to investigate it a little further, as every build produces these warnings: net/wireless/nl80211.c:4389:1: warning: the frame size of 2240 bytes is larger than 2048 bytes [-Wframe-larger-than=] net/wireless/nl80211.c:1895:1: warning: the frame size of 3776 bytes is larger than 2048 bytes [-Wframe-larger-than=] net/wireless/nl80211.c:1410:1: warning: the frame size of 2208 bytes is larger than 2048 bytes [-Wframe-larger-than=] net/bridge/br_netlink.c:1282:1: warning: the frame size of 2544 bytes is larger than 2048 bytes [-Wframe-larger-than=] Most of this problem is now solved in gcc-8, which can consolidate the stack slots for the inline function arguments. On older compilers we can add a workaround by declaring a local variable in each function to pass the inline function argument. Cc: stable@vger.kernel.org Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/net/netlink.h | 73 ++++++++++++++++++++++++++++++++----------- 1 file changed, 55 insertions(+), 18 deletions(-) diff --git a/include/net/netlink.h b/include/net/netlink.h index e51cf5f815977..14c2893930719 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -773,7 +773,10 @@ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { - return nla_put(skb, attrtype, sizeof(u8), &value); + /* temporary variables to work around GCC PR81715 with asan-stack=1 */ + u8 tmp = value; + + return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** @@ -784,7 +787,9 @@ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { - return nla_put(skb, attrtype, sizeof(u16), &value); + u16 tmp = value; + + return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** @@ -795,7 +800,9 @@ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { - return nla_put(skb, attrtype, sizeof(__be16), &value); + __be16 tmp = value; + + return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** @@ -806,7 +813,9 @@ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { - return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, value); + __be16 tmp = value; + + return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** @@ -817,7 +826,9 @@ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { - return nla_put(skb, attrtype, sizeof(__le16), &value); + __le16 tmp = value; + + return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** @@ -828,7 +839,9 @@ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { - return nla_put(skb, attrtype, sizeof(u32), &value); + u32 tmp = value; + + return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** @@ -839,7 +852,9 @@ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { - return nla_put(skb, attrtype, sizeof(__be32), &value); + __be32 tmp = value; + + return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** @@ -850,7 +865,9 @@ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { - return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, value); + __be32 tmp = value; + + return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** @@ -861,7 +878,9 @@ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { - return nla_put(skb, attrtype, sizeof(__le32), &value); + __le32 tmp = value; + + return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** @@ -874,7 +893,9 @@ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(u64), &value, padattr); + u64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** @@ -887,7 +908,9 @@ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(__be64), &value, padattr); + __be64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** @@ -900,7 +923,9 @@ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { - return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, value, + __be64 tmp = value; + + return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } @@ -914,7 +939,9 @@ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(__le64), &value, padattr); + __le64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** @@ -925,7 +952,9 @@ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { - return nla_put(skb, attrtype, sizeof(s8), &value); + s8 tmp = value; + + return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** @@ -936,7 +965,9 @@ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { - return nla_put(skb, attrtype, sizeof(s16), &value); + s16 tmp = value; + + return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** @@ -947,7 +978,9 @@ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { - return nla_put(skb, attrtype, sizeof(s32), &value); + s32 tmp = value; + + return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** @@ -960,7 +993,9 @@ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { - return nla_put_64bit(skb, attrtype, sizeof(s64), &value, padattr); + s64 tmp = value; + + return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** @@ -1010,7 +1045,9 @@ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { - return nla_put_be32(skb, attrtype, addr); + __be32 tmp = addr; + + return nla_put_be32(skb, attrtype, tmp); } /** -- GitLab From 4618e90965f272fe522f2af2523a60d0d4bc78f3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:10 +0200 Subject: [PATCH 0397/1507] x86/fpu: Fix fpu__activate_fpstate_read() and update comments fpu__activate_fpstate_read() can be called for the current task when coredumping - or for stopped tasks when ptrace-ing. Implement this properly in the code and update the comments. This also fixes an incorrect (but harmless) warning introduced by one of the earlier patches. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-28-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 93103a909c471..afd3f2a5c64e9 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -254,18 +254,21 @@ EXPORT_SYMBOL_GPL(fpu__activate_curr); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ void fpu__activate_fpstate_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpstate_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { if (!fpu->fpstate_active) { -- GitLab From 685c930d6e58e31e251ec354f9dca3958a4c5040 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:11 +0200 Subject: [PATCH 0398/1507] x86/fpu: Remove fpu__current_fpstate_write_begin/end() These functions are not used anymore, so remove them. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Bobby Powers Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-29-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 2 - arch/x86/kernel/fpu/core.c | 63 ----------------------------- 2 files changed, 65 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index cf290d424e48d..508e4181c4af1 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -26,8 +26,6 @@ extern void fpu__activate_curr(struct fpu *fpu); extern void fpu__activate_fpstate_read(struct fpu *fpu); extern void fpu__activate_fpstate_write(struct fpu *fpu); -extern void fpu__current_fpstate_write_begin(void); -extern void fpu__current_fpstate_write_end(void); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index afd3f2a5c64e9..b2cdeb3b18609 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -316,69 +316,6 @@ void fpu__activate_fpstate_write(struct fpu *fpu) } } -/* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpu->fpstate_active) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - /* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate -- GitLab From e4a81bfcaae1ebbdc6efe74e8ea563144d90e9a9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 26 Sep 2017 09:43:36 +0200 Subject: [PATCH 0399/1507] x86/fpu: Rename fpu::fpstate_active to fpu::initialized The x86 FPU code used to have a complex state machine where both the FPU registers and the FPU state context could be 'active' (or inactive) independently of each other - which enabled features like lazy FPU restore. Much of this complexity is gone in the current code: now we basically can have FPU-less tasks (kernel threads) that don't use (and save/restore) FPU state at all, plus full FPU users that save/restore directly with no laziness whatsoever. But the fpu::fpstate_active still carries bits of the old complexity - meanwhile this flag has become a simple flag that shows whether the FPU context saving area in the thread struct is initialized and used, or not. Rename it to fpu::initialized to express this simplicity in the name as well. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-30-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/ia32/ia32_signal.c | 2 +- arch/x86/include/asm/fpu/internal.h | 4 ++-- arch/x86/include/asm/fpu/types.h | 6 +++--- arch/x86/include/asm/trace/fpu.h | 8 ++++---- arch/x86/kernel/fpu/core.c | 24 ++++++++++++------------ arch/x86/kernel/fpu/init.c | 2 +- arch/x86/kernel/fpu/regset.c | 6 +++--- arch/x86/kernel/fpu/signal.c | 8 ++++---- arch/x86/kernel/fpu/xstate.c | 2 +- arch/x86/kernel/signal.c | 6 +++--- arch/x86/mm/pkeys.c | 2 +- 11 files changed, 35 insertions(+), 35 deletions(-) diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index e0bb46c028575..0e2a5edbce001 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (fpu->fpstate_active) { + if (fpu->initialized) { unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 508e4181c4af1..b26ae05da18a7 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -527,7 +527,7 @@ static inline void fpregs_activate(struct fpu *fpu) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpstate_active) { + if (old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else @@ -550,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { bool preload = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active; + new_fpu->initialized; if (preload) { if (!fpregs_state_valid(new_fpu, cpu)) diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 71db45ca88708..a1520575d86b8 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -293,13 +293,13 @@ struct fpu { unsigned int last_cpu; /* - * @fpstate_active: + * @initialized: * - * This flag indicates whether this context is active: if the task + * This flag indicates whether this context is initialized: if the task * is not running then we can restore from this context, if the task * is running then we should save into this context. */ - unsigned char fpstate_active; + unsigned char initialized; /* * @state: diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index da565aae9fd25..39f7a27bef130 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -12,22 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpstate_active) + __field(bool, initialized) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; - __entry->fpstate_active = fpu->fpstate_active; + __entry->initialized = fpu->initialized; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpstate_active, + __entry->initialized, __entry->xfeatures, __entry->xcomp_bv ) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index b2cdeb3b18609..c8d6032f04d09 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpstate_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpstate_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpstate_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -191,7 +191,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -240,13 +240,13 @@ void fpu__activate_curr(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } EXPORT_SYMBOL_GPL(fpu__activate_curr); @@ -271,13 +271,13 @@ void fpu__activate_fpstate_read(struct fpu *fpu) if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -303,7 +303,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { + if (fpu->initialized) { /* Invalidate any lazy state: */ __fpu_invalidate_fpregs_state(fpu); } else { @@ -312,7 +312,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } @@ -354,7 +354,7 @@ void fpu__drop(struct fpu *fpu) preempt_disable(); if (fpu == ¤t->thread.fpu) { - if (fpu->fpstate_active) { + if (fpu->initialized) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" @@ -363,7 +363,7 @@ void fpu__drop(struct fpu *fpu) } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c452624c..7affb7e3d9a5b 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index c764f74053223..19e82334e8115 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -16,14 +16,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -380,7 +380,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index da68ea1c3a442..ab2dd24cfea48 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -171,7 +171,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpu->fpstate_active || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; @@ -315,12 +315,12 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); @@ -342,7 +342,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index fda1109cc3553..703e76d027ee5 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -867,7 +867,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e04442345fc09..4e188fda59612 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -263,7 +263,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +279,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +755,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 4d24269c071f4..d7bc0eea20a5e 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -44,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - current->thread.fpu.fpstate_active && + current->thread.fpu.initialized && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; -- GitLab From 7f1487c59b7c6dcb20155f4302985da2659a2997 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:13 +0200 Subject: [PATCH 0400/1507] x86/fpu: Fix stale comments about lazy FPU logic We don't do any lazy restore anymore, what we have are two pieces of optimization: - no-FPU tasks that don't save/restore the FPU context (kernel threads are such) - cached FPU registers maintained via the fpu->last_cpu field. This means that if an FPU task context switches to a non-FPU task then we can maintain the FPU registers as an in-FPU copies (cache), and skip the restoration of them once we switch back to the original FPU-using task. Update all the comments that still referred to old 'lazy' and 'unlazy' concepts. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-31-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c8d6032f04d09..77668d91fdc10 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -205,9 +205,6 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * * We have to do all this with preemption disabled, * mostly because of the FNSAVE case, because in that @@ -285,13 +282,13 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ @@ -304,7 +301,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) WARN_ON_FPU(fpu == ¤t->thread.fpu); if (fpu->initialized) { - /* Invalidate any lazy state: */ + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); -- GitLab From e10078eba69859359ce8644dd423b4132a6a8913 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:14 +0200 Subject: [PATCH 0401/1507] x86/fpu: Simplify and speed up fpu__copy() fpu__copy() has a preempt_disable()/enable() pair, which it had to do to be able to atomically unlazy the current task when doing an FNSAVE. But we don't unlazy tasks anymore, we always do direct saves/restores of FPU context. So remove both the unnecessary critical section, and update the comments. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-32-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 77668d91fdc10..52122dd418aee 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -206,22 +206,13 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); -- GitLab From 2ce03d850b9a2f17d55596ecfa86e72b5687a627 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 15:00:15 +0200 Subject: [PATCH 0402/1507] x86/fpu: Rename fpu__activate_curr() to fpu__initialize() Rename this function to better express that it's all about initializing the FPU state of a task which goes hand in hand with the fpu::initialized field. Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Eric Biggers Cc: Fenghua Yu Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/20170923130016.21448-33-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 2 +- arch/x86/kernel/fpu/core.c | 8 ++++---- arch/x86/kernel/fpu/signal.c | 2 +- arch/x86/kvm/x86.c | 2 +- arch/x86/math-emu/fpu_entry.c | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index b26ae05da18a7..7c980aafb8aa9 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -23,7 +23,7 @@ /* * High level FPU state handling functions: */ -extern void fpu__activate_curr(struct fpu *fpu); +extern void fpu__initialize(struct fpu *fpu); extern void fpu__activate_fpstate_read(struct fpu *fpu); extern void fpu__activate_fpstate_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 52122dd418aee..07db9d94b68bc 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -224,7 +224,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); @@ -237,7 +237,7 @@ void fpu__activate_curr(struct fpu *fpu) fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. @@ -316,7 +316,7 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -392,7 +392,7 @@ void fpu__clear(struct fpu *fpu) */ if (static_cpu_has(X86_FEATURE_FPU)) { preempt_disable(); - fpu__activate_curr(fpu); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); preempt_enable(); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index ab2dd24cfea48..7fa3bdb331e91 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -280,7 +280,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd17b7d9a1076..03869eb7fcd67 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7225,7 +7225,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index d4a7df2205b8d..220638a4cb94e 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -114,7 +114,7 @@ void math_emulate(struct math_emu_info *info) struct desc_struct code_descriptor; struct fpu *fpu = ¤t->thread.fpu; - fpu__activate_curr(fpu); + fpu__initialize(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { -- GitLab From 369a036de206710ff27a66f9bffe78ef657648c3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 23 Sep 2017 13:37:45 +0200 Subject: [PATCH 0403/1507] x86/fpu: Rename fpu__activate_fpstate_read/write() to fpu__prepare_[read|write]() As per the new nomenclature we don't 'activate' the FPU state anymore, we initialize it. So drop the _activate_fpstate name from these functions, which were a bit of a mouthful anyway, and name them: fpu__prepare_read() fpu__prepare_write() Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Eric Biggers Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/internal.h | 4 ++-- arch/x86/kernel/fpu/core.c | 4 ++-- arch/x86/kernel/fpu/regset.c | 12 ++++++------ 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 7c980aafb8aa9..e3221ffa304e3 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -24,8 +24,8 @@ * High level FPU state handling functions: */ extern void fpu__initialize(struct fpu *fpu); -extern void fpu__activate_fpstate_read(struct fpu *fpu); -extern void fpu__activate_fpstate_write(struct fpu *fpu); +extern void fpu__prepare_read(struct fpu *fpu); +extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 07db9d94b68bc..f92a6593de1ec 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(fpu__initialize); * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { if (fpu == ¤t->thread.fpu) { fpu__save(fpu); @@ -283,7 +283,7 @@ void fpu__activate_fpstate_read(struct fpu *fpu) * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 19e82334e8115..ee8d2f0498188 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -38,7 +38,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +55,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,7 +89,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { if (kbuf) @@ -132,7 +132,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); if (boot_cpu_has(X86_FEATURE_XSAVES)) { if (kbuf) @@ -310,7 +310,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -340,7 +340,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) -- GitLab From e63e5d5c15c6b1dba26f7cbd1b1089a1d6155db5 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:04 +0200 Subject: [PATCH 0404/1507] x86/fpu: Introduce validate_xstate_header() Move validation of user-supplied xstate_header into a helper function, in preparation of calling it from both the ptrace and sigreturn syscall paths. The new function also considers it to be an error if *any* reserved bits are set, whereas before we were just clearing most of them silently. This should reduce the chance of bugs that fail to correctly validate user-supplied XSAVE areas. It also will expose any broken userspace programs that set the other reserved bits; this is desirable because such programs will lose compatibility with future CPUs and kernels if those bits are ever used for anything. (There shouldn't be any such programs, and in fact in the case where the compacted format is in use we were already validating xfeatures. But you never know...) Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-2-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fpu/xstate.h | 4 ++++ arch/x86/kernel/fpu/xstate.c | 24 ++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 579ac2358e63b..83fee2469eb76 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -52,4 +52,8 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); + +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +extern int validate_xstate_header(const struct xstate_header *hdr); + #endif diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 703e76d027ee5..2427aeea33b57 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -483,6 +483,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; -- GitLab From cf9df81b139b6ebaec188d73758f02ca3b2110e4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:05 +0200 Subject: [PATCH 0405/1507] x86/fpu: Use validate_xstate_header() to validate the xstate_header in xstateregs_set() Tighten the checks in xstateregs_set(). Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-3-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/regset.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index ee8d2f0498188..b831d5b9de99c 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -141,27 +141,20 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, ret = copy_user_to_xstate(xsave, ubuf); } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* xcomp_bv must be 0 when using uncompacted format */ - if (!ret && xsave->header.xcomp_bv) - ret = -EINVAL; + if (!ret) + ret = validate_xstate_header(&xsave->header); } - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); - /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } -- GitLab From b11e2e18a7fc8eaa3d592c260d50c7129e094ded Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:06 +0200 Subject: [PATCH 0406/1507] x86/fpu: Use validate_xstate_header() to validate the xstate_header in __fpu__restore_sig() Tighten the checks in __fpu__restore_sig() and update comments. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-4-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/signal.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 7fa3bdb331e91..fb639e70048f5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -214,8 +214,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -224,7 +227,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -308,7 +311,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; @@ -329,9 +332,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else { err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); - /* xcomp_bv must be 0 when using uncompacted format */ - if (!err && state_size > offsetof(struct xregs_state, header) && fpu->state.xsave.header.xcomp_bv) - err = -EINVAL; + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { -- GitLab From 80d8ae86b36791a545ca28ddc95133ea59bba6e0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:07 +0200 Subject: [PATCH 0407/1507] x86/fpu: Copy the full state_header in copy_kernel_to_xstate() This is in preparation to verify the full xstate header as supplied by user-space. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-5-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 2427aeea33b57..02591b96bb254 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1148,11 +1148,13 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) int i; u64 xfeatures; u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - memcpy(&xfeatures, kbuf + offset, size); + memcpy(&hdr, kbuf + offset, size); + xfeatures = hdr.xfeatures; /* * Reject if the user sets any disabled or supervisor features: -- GitLab From b89eda482d7849a1c146b6d0a42f4e76369bb08e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:08 +0200 Subject: [PATCH 0408/1507] x86/fpu: Eliminate the 'xfeatures' local variable in copy_kernel_to_xstate() We have this information in the xstate_header. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-6-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 02591b96bb254..c97c4a9db52a8 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1146,7 +1146,6 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; u64 allowed_features; struct xstate_header hdr; @@ -1154,20 +1153,19 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) size = sizeof(hdr); memcpy(&hdr, kbuf + offset, size); - xfeatures = hdr.xfeatures; /* * Reject if the user sets any disabled or supervisor features: */ allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; - if (xfeatures & ~allowed_features) + if (hdr.xfeatures & ~allowed_features) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; @@ -1177,7 +1175,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) } } - if (xfeatures_mxcsr_quirk(xfeatures)) { + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { offset = offsetof(struct fxregs_state, mxcsr); size = MXCSR_AND_FLAGS_SIZE; memcpy(&xsave->i387.mxcsr, kbuf + offset, size); @@ -1192,7 +1190,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } -- GitLab From af95774b3ca080b0e1e651c0fc7680f3444ddda7 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:09 +0200 Subject: [PATCH 0409/1507] x86/fpu: Use validate_xstate_header() to validate the xstate_header in copy_kernel_to_xstate() Tighten the checks in copy_kernel_to_xstate(). Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-7-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c97c4a9db52a8..325db78503358 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1138,15 +1138,12 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i /* * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * and copy to the target thread. This is called from xstateregs_set(). */ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 allowed_features; struct xstate_header hdr; offset = offsetof(struct xregs_state, header); @@ -1154,12 +1151,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) memcpy(&hdr, kbuf + offset, size); - /* - * Reject if the user sets any disabled or supervisor features: - */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; - - if (hdr.xfeatures & ~allowed_features) + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { -- GitLab From af2c4322d986a08a6e793b74b83a62b325019c20 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:10 +0200 Subject: [PATCH 0410/1507] x86/fpu: Copy the full header in copy_user_to_xstate() This is in preparation to verify the full xstate header as supplied by user-space. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-8-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 325db78503358..0cd7b73c25e8e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1199,13 +1199,16 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) int i; u64 xfeatures; u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (__copy_from_user(&xfeatures, ubuf + offset, size)) + if (__copy_from_user(&hdr, ubuf + offset, size)) return -EFAULT; + xfeatures = hdr.xfeatures; + /* * Reject if the user sets any disabled or supervisor features: */ -- GitLab From 3d703477bcfe8bb57079d97198cf1e342fe1fef9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:11 +0200 Subject: [PATCH 0411/1507] x86/fpu: Eliminate the 'xfeatures' local variable in copy_user_to_xstate() We now have this field in hdr.xfeatures. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-9-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 0cd7b73c25e8e..b6d78b78b5c2b 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1197,7 +1197,6 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) { unsigned int offset, size; int i; - u64 xfeatures; u64 allowed_features; struct xstate_header hdr; @@ -1207,20 +1206,18 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) if (__copy_from_user(&hdr, ubuf + offset, size)) return -EFAULT; - xfeatures = hdr.xfeatures; - /* * Reject if the user sets any disabled or supervisor features: */ allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; - if (xfeatures & ~allowed_features) + if (hdr.xfeatures & ~allowed_features) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; @@ -1231,7 +1228,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) } } - if (xfeatures_mxcsr_quirk(xfeatures)) { + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { offset = offsetof(struct fxregs_state, mxcsr); size = MXCSR_AND_FLAGS_SIZE; if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) @@ -1247,7 +1244,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } -- GitLab From 98c0fad9d60e8b2cd47e15b7bee7df343648f5bb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:12 +0200 Subject: [PATCH 0412/1507] x86/fpu: Use validate_xstate_header() to validate the xstate_header in copy_user_to_xstate() Tighten the checks in copy_user_to_xstate(). Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-10-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/xstate.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index b6d78b78b5c2b..f1d5476c90220 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1188,16 +1188,15 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) } /* - * Convert from a ptrace standard-format user-space buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. */ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) { unsigned int offset, size; int i; - u64 allowed_features; struct xstate_header hdr; offset = offsetof(struct xregs_state, header); @@ -1206,12 +1205,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) if (__copy_from_user(&hdr, ubuf + offset, size)) return -EFAULT; - /* - * Reject if the user sets any disabled or supervisor features: - */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; - - if (hdr.xfeatures & ~allowed_features) + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { -- GitLab From 738f48cb5fdd5878d11934f1898aa2bcf1578289 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 24 Sep 2017 12:59:13 +0200 Subject: [PATCH 0413/1507] x86/fpu: Use using_compacted_format() instead of open coded X86_FEATURE_XSAVES This is the canonical method to use. Signed-off-by: Eric Biggers Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Fenghua Yu Cc: Kees Cook Cc: Kevin Hao Cc: Linus Torvalds Cc: Michael Halcrow Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yu-cheng Yu Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170924105913.9157-11-mingo@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/regset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b831d5b9de99c..3ea1513723896 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -134,7 +134,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) { + if (using_compacted_format()) { if (kbuf) ret = copy_kernel_to_xstate(xsave, kbuf); else -- GitLab From a98c75fcd0ec02623f4f56d824d76e659410a52b Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 23 Aug 2017 19:13:26 +0200 Subject: [PATCH 0414/1507] drm/tegra: trace: Fix path to include The TRACE_INCLUDE_FILE macro needs to specify the path relative to the define_trace.h header rather than relative to the file defining it. Reported-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20170823171326.23620-1-thierry.reding@gmail.com --- drivers/gpu/drm/tegra/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/tegra/trace.h b/drivers/gpu/drm/tegra/trace.h index e9b7cdad5c4c1..5a1ab4046e926 100644 --- a/drivers/gpu/drm/tegra/trace.h +++ b/drivers/gpu/drm/tegra/trace.h @@ -63,6 +63,6 @@ DEFINE_EVENT(register_access, sor_readl, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra #define TRACE_INCLUDE_FILE trace #include -- GitLab From d8bd9f3f0925d22726de159531bfe3774b5cacc6 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 22 Sep 2017 13:32:21 +1000 Subject: [PATCH 0415/1507] powerpc: Handle MCE on POWER9 with only DSISR bit 30 set On POWER9 DD2.1 and below, it's possible for a paste instruction to cause a Machine Check Exception (MCE) where only DSISR bit 30 (IBM 33) is set. This will result in the MCE handler seeing an unknown event, which triggers linux to crash. We change this by detecting unknown events caused by load/stores in the MCE handler and marking them as handled so that we no longer crash. An MCE that occurs like this is spurious, so we don't need to do anything in terms of servicing it. If there is something that needs to be serviced, the CPU will raise the MCE again with the correct DSISR so that it can be serviced properly. Signed-off-by: Michael Neuling Reviewed-by: Nicholas Piggin [mpe: Expand comment with details from change log, use normal bit #s] Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/mce_power.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index b76ca198e09c1..f523125b9d343 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -624,5 +624,18 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs) long __machine_check_early_realmode_p9(struct pt_regs *regs) { + /* + * On POWER9 DD2.1 and below, it's possible to get a machine check + * caused by a paste instruction where only DSISR bit 30 is set. This + * will result in the MCE handler seeing an unknown event and the kernel + * crashing. An MCE that occurs like this is spurious, so we don't need + * to do anything in terms of servicing it. If there is something that + * needs to be serviced, the CPU will raise the MCE again with the + * correct DSISR so that it can be serviced properly. So detect this + * case and mark it as handled. + */ + if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x40000000) + return 1; + return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table); } -- GitLab From b621129f4f08c8d42ac4de2e77a07c5cf0c4b740 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Wed, 15 Feb 2017 16:33:56 +0300 Subject: [PATCH 0416/1507] netfilter: ipvs: full-functionality option for ECN encapsulation in tunnel IPVS tunnel mode works as simple tunnel (see RFC 3168) copying ECN field to outer header. That's result in packet drops on egress tunnels in case the egress tunnel operates as ECN-capable with Full-functionality option (like ip_tunnel and ip6_tunnel kernel modules), according to RFC 3168 section 9.1.1 recommendation. This patch implements ECN full-functionality option into ipvs xmit code. Cc: netdev@vger.kernel.org Cc: lvs-devel@vger.kernel.org Signed-off-by: Vadim Fedorenko Reviewed-by: Konstantin Khlebnikov Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_xmit.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 90d396814798e..4527921b1c3ac 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -921,6 +921,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, { struct sk_buff *new_skb = NULL; struct iphdr *old_iph = NULL; + __u8 old_dsfield; #ifdef CONFIG_IP_VS_IPV6 struct ipv6hdr *old_ipv6h = NULL; #endif @@ -945,7 +946,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, *payload_len = ntohs(old_ipv6h->payload_len) + sizeof(*old_ipv6h); - *dsfield = ipv6_get_dsfield(old_ipv6h); + old_dsfield = ipv6_get_dsfield(old_ipv6h); *ttl = old_ipv6h->hop_limit; if (df) *df = 0; @@ -960,12 +961,15 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, /* fix old IP header checksum */ ip_send_check(old_iph); - *dsfield = ipv4_get_dsfield(old_iph); + old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) *payload_len = ntohs(old_iph->tot_len); } + /* Implement full-functionality option for ECN encapsulation */ + *dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield); + return skb; error: kfree_skb(skb); -- GitLab From ff40adf7fbdff96860b1153332c0b1c7bab6e0c1 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 24 Aug 2017 18:19:48 -0600 Subject: [PATCH 0417/1507] Btrfs: use the new helper wbc_to_write_flags This updates btrfs to use the helper wbc_to_write_flags which has been applied in ext4/xfs/f2fs/block. Please note that, with this, btrfs's dirty pages written by a writeback job will carry the flag REQ_BACKGROUND, which is currently used by writeback-throttle to determine whether it should go to get a request or wait. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d17783d702287..4ead6da5a6451 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, unsigned int write_flags = 0; unsigned long nr_written = 0; - if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = REQ_SYNC; + write_flags = wbc_to_write_flags(wbc); trace___extent_writepage(page, inode, wbc); @@ -3718,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, unsigned long i, num_pages; unsigned long bio_flags = 0; unsigned long start, end; - unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META; + unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META; int ret = 0; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); -- GitLab From 5f14efd3d437205143dcffcf776e0122eae1755a Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 23 Aug 2017 12:15:09 -0600 Subject: [PATCH 0418/1507] Btrfs: do not reset bio->bi_ops while writing bio flush_epd_write_bio() sets bio->bi_opf by itself to honor REQ_SYNC, but it's not needed at all since bio->bi_opf has set up properly in both __extent_writepage() and write_one_eb(), and in the case of write_one_eb(), it also sets REQ_META, which we will lose in flush_epd_write_bio(). This remove this unnecessary bio->bi_opf setting. Signed-off-by: Liu Bo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4ead6da5a6451..3738d245518ca 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4062,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd) if (epd->bio) { int ret; - bio_set_op_attrs(epd->bio, REQ_OP_WRITE, - epd->sync_io ? REQ_SYNC : 0); - ret = submit_one_bio(epd->bio, 0, epd->bio_flags); BUG_ON(ret < 0); /* -ENOMEM */ epd->bio = NULL; -- GitLab From bea7eafdbda3ba1d4b2ccb9cca829eefb7989bb9 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 22 Aug 2017 23:46:00 -0700 Subject: [PATCH 0419/1507] Btrfs: fix incorrect {node,sector}size endianness from BTRFS_IOC_FS_INFO fs_info->super_copy->{node,sector}size are little-endian, but the ioctl should return the values in native endianness. Use the cached values in btrfs_fs_info instead. Found with sparse. Fixes: 80a773fbfc2d ("btrfs: retrieve more info from FS_INFO ioctl") Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ae8fbf9d3de2a..cf1c2ee030ddb 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2769,9 +2769,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } mutex_unlock(&fs_devices->device_list_mutex); - fi_args->nodesize = fs_info->super_copy->nodesize; - fi_args->sectorsize = fs_info->super_copy->sectorsize; - fi_args->clone_alignment = fs_info->super_copy->sectorsize; + fi_args->nodesize = fs_info->nodesize; + fi_args->sectorsize = fs_info->sectorsize; + fi_args->clone_alignment = fs_info->sectorsize; if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; -- GitLab From 63d71450c8d817649a79e37d685523f988b9cc98 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 1 Sep 2017 17:58:47 +0900 Subject: [PATCH 0420/1507] btrfs: clear ordered flag on cleaning up ordered extents Commit 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") introduced btrfs_cleanup_ordered_extents() to cleanup submitted ordered extents. However, it does not clear the ordered bit (Private2) of corresponding pages. Thus, the following BUG occurs from free_pages_check_bad() (on btrfs/125 with nospace_cache). BUG: Bad page state in process btrfs pfn:3fa787 page:ffffdf2acfe9e1c0 count:0 mapcount:0 mapping: (null) index:0xd flags: 0x8000000000002008(uptodate|private_2) raw: 8000000000002008 0000000000000000 000000000000000d 00000000ffffffff raw: ffffdf2acf5c1b20 ffffb443802238b0 0000000000000000 0000000000000000 page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set bad because of flags: 0x2000(private_2) This patch clears the flag same as other places calling btrfs_dec_test_ordered_pending() for every page in the specified range. Fixes: 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") Cc: # 4.12 Signed-off-by: Naohiro Aota Reviewed-by: Qu Wenruo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d184a46e46c49..455c0f22fe2da 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -135,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } -- GitLab From 67c003f90fd68062d92a7ffade36f9b2a9098bd8 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 1 Sep 2017 17:59:07 +0900 Subject: [PATCH 0421/1507] btrfs: finish ordered extent cleaning if no progress is found __endio_write_update_ordered() repeats the search until it reaches the end of the specified range. This works well with direct IO path, because before the function is called, it's ensured that there are ordered extents filling whole the range. It's not the case, however, when it's called from run_delalloc_range(): it is possible to have error in the midle of the loop in e.g. run_delalloc_nocow(), so that there exisits the range not covered by any ordered extents. By cleaning such "uncomplete" range, __endio_write_update_ordered() stucks at offset where there're no ordered extents. Since the ordered extents are created from head to tail, we can stop the search if there are no offset progress. Fixes: 524272607e88 ("btrfs: Handle delalloc error correctly to avoid ordered extent hang") Cc: # 4.12 Signed-off-by: Naohiro Aota Reviewed-by: Qu Wenruo Reviewed-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/inode.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 455c0f22fe2da..f78c5640c6dc4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8396,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8407,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8417,6 +8419,12 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL); btrfs_queue_work(wq, &ordered->work); out_test: + /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again -- GitLab From bb166d7207432d3c7d10c45dc052f12ba3a2121d Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 25 Aug 2017 14:15:14 +0900 Subject: [PATCH 0422/1507] btrfs: fix NULL pointer dereference from free_reloc_roots() __del_reloc_root should be called before freeing up reloc_root->node. If not, calling __del_reloc_root() dereference reloc_root->node, causing the system BUG. Fixes: 6bdf131fac23 ("Btrfs: don't leak reloc root nodes on error") Cc: # 4.9 Signed-off-by: Naohiro Aota Reviewed-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/relocation.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3a49a3c2fca45..9841faef08ea7 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2400,11 +2400,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } -- GitLab From ca6842bf01dc1ad41195eac1e343b4f08c496ba8 Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Fri, 22 Jan 2016 09:13:25 +0900 Subject: [PATCH 0423/1507] Btrfs: send: fix error number for unknown inode types ENOTSUPP should not be returned to the user program. (cf. include/linux/errno.h) Therefore, EOPNOTSUPP is used instead of ENOTSUPP. Signed-off-by: Tsutomu Itoh Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 8f1d3d6e7087a..43430e6c99aa1 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -2640,7 +2640,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino) } else { btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } -- GitLab From 6d6d282932d1a609e60dc4467677e0e863682f57 Mon Sep 17 00:00:00 2001 From: satoru takeuchi Date: Tue, 12 Sep 2017 22:42:52 +0900 Subject: [PATCH 0424/1507] btrfs: prevent to set invalid default subvolid `btrfs sub set-default` succeeds to set an ID which isn't corresponding to any fs/file tree. If such the bad ID is set to a filesystem, we can't mount this filesystem without specifying `subvol` or `subvolid` mount options. Fixes: 6ef5ed0d386b ("Btrfs: add ioctl and incompat flag to set the default mount subvol") Cc: Signed-off-by: Satoru Takeuchi Reviewed-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cf1c2ee030ddb..d4a77993e52f9 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4057,6 +4057,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { -- GitLab From 78ad4ce014d025f41b8dde3a81876832ead643cf Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Fri, 8 Sep 2017 17:48:55 +0900 Subject: [PATCH 0425/1507] btrfs: propagate error to btrfs_cmp_data_prepare caller btrfs_cmp_data_prepare() (almost) always returns 0 i.e. ignoring errors from gather_extent_pages(). While the pages are freed by btrfs_cmp_data_free(), cmp->num_pages still has > 0. Then, btrfs_extent_same() try to access the already freed pages causing faults (or violates PageLocked assertion). This patch just return the error as is so that the caller stop the process. Signed-off-by: Naohiro Aota Fixes: f441460202cb ("btrfs: fix deadlock with extent-same and readpage") Cc: # 4.2 Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d4a77993e52f9..802df5755cd3b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3028,7 +3028,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) -- GitLab From c2faff790ccd11ea5be8e3ca99713f116fcd6030 Mon Sep 17 00:00:00 2001 From: "Misono, Tomohiro" Date: Wed, 30 Aug 2017 16:33:16 +0900 Subject: [PATCH 0426/1507] btrfs: remove BTRFS_FS_QUOTA_DISABLING flag Currently, "btrfs quota enable" would fail after "btrfs quota disable" on the first time with syslog output "qgroup_rescan_init failed with -22", but it would succeed on the second time. When "quota disable" is called, BTRFS_FS_QUOTA_DISABLING flag bit will be set in fs_info->flags in btrfs_quota_disable(), but it will not be droppd in btrfs_run_qgroups() (which is called in btrfs_commit_transaction()) because quota_root has already been freed. If "quota enable" is called after that, both BTRFS_FS_QUOTA_DISABLING and BTRFS_FS_QUOTA_ENABLED flag would be dropped in the btrfs_run_qgroups() since quota_root is not NULL. This leads to the failure of "quota enable" on the first time. BTRFS_FS_QUOTA_DISABLING flag is not used outside of "quota disable" context and is equivalent to whether quota_root is NULL or not. btrfs_run_qgroups() checks whether quota_root is NULL or not in the first place. So, let's remove BTRFS_FS_QUOTA_DISABLING flag. Signed-off-by: Tomohiro Misono Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 1 - fs/btrfs/qgroup.c | 4 ---- 2 files changed, 5 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2add002662f4b..b7ccfcc01732b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -708,7 +708,6 @@ struct btrfs_delayed_root; #define BTRFS_FS_OPEN 5 #define BTRFS_FS_QUOTA_ENABLED 6 #define BTRFS_FS_QUOTA_ENABLING 7 -#define BTRFS_FS_QUOTA_DISABLING 8 #define BTRFS_FS_UPDATE_UUID_TREE_GEN 9 #define BTRFS_FS_CREATING_FREE_SPACE_TREE 10 #define BTRFS_FS_BTREE_ERR 11 diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5c8b61c86e61f..770f667269f57 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, } ret = 0; out: - set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags); btrfs_free_path(path); return ret; } @@ -953,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (!fs_info->quota_root) goto out; clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -2086,8 +2084,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags)) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags)) - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { -- GitLab From fed3b381145e2e7c66b0b3f640851e1633ebd07f Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 13 Sep 2017 12:25:21 -0600 Subject: [PATCH 0427/1507] Btrfs: do not backup tree roots when fsync It doesn't make sense to backup tree roots when doing fsync, since during fsync those tree roots have not been consistent on disk. Signed-off-by: Liu Bo Reviewed-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 27d4586405366..0f2271815eb63 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3641,7 +3641,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - backup_super_roots(fs_info); + + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; -- GitLab From bd7d63c2ceaf737eeb21630a2b62fc5fe34dba29 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 19 Sep 2017 17:50:09 -0600 Subject: [PATCH 0428/1507] Btrfs: use btrfs_op instead of bio_op in __btrfs_map_block This seems to be a leftover of commit cf8cddd38bab ("btrfs: don't abuse REQ_OP_* flags for btrfs_map_block"). It should use btrfs_op() helper to provide one of 'enum btrfs_map_op' types. Fixes: cf8cddd38bab ("btrfs: don't abuse REQ_OP_* flags for btrfs_map_block") Signed-off-by: Liu Bo Reviewed-by: Satoru Takeuchi Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d024f1b072823..6a72f88f77b60 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6166,7 +6166,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, map_length = length; btrfs_bio_counter_inc_blocked(fs_info); - ret = __btrfs_map_block(fs_info, bio_op(bio), logical, + ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); -- GitLab From cf1167d5c1abf3bc42b2a1562bfa7937c05337e2 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 20 Sep 2017 17:50:18 -0600 Subject: [PATCH 0429/1507] Btrfs: fix kernel oops while reading compressed data The kernel oops happens at kernel BUG at fs/btrfs/extent_io.c:2104! ... RIP: clean_io_failure+0x263/0x2a0 [btrfs] It's showing that read-repair code is using an improper mirror index. This is due to the fact that compression read's endio hasn't recorded the failed mirror index in %cb->orig_bio. With this, btrfs's read-repair can work properly on reading compressed data. Signed-off-by: Liu Bo Reported-by: Paul Jones Tested-by: Paul Jones Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/compression.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 883ecc58fd0da..c6aa53c4c1020 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -107,6 +107,7 @@ static void end_compressed_bio_read(struct bio *bio) struct inode *inode; struct page *page; unsigned long index; + unsigned int mirror = btrfs_io_bio(bio)->mirror_num; int ret; if (bio->bi_status) @@ -118,6 +119,14 @@ static void end_compressed_bio_read(struct bio *bio) if (!refcount_dec_and_test(&cb->pending_bios)) goto out; + /* + * Record the correct mirror_num in cb->orig_bio so that + * read-repair can work properly. + */ + ASSERT(btrfs_io_bio(cb->orig_bio)); + btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; + cb->mirror_num = mirror; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); -- GitLab From e6311f240c946788131ba2b97e14f37312688072 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 20 Sep 2017 17:50:19 -0600 Subject: [PATCH 0430/1507] Btrfs: skip checksum when reading compressed data if some IO have failed Currently even if the underlying disk reports failure on IO, compressed read endio still gets to verify checksum and reports it as a checksum error. In fact, if some IO have failed during reading a compressed data extent , there's no way the checksum could match, therefore, we can skip that in order to return error quickly to the upper layer. Please note that we need to do this after recording the failed mirror index so that read-repair in the upper layer's endio can work properly. Signed-off-by: Liu Bo Tested-by: Paul Jones Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/compression.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c6aa53c4c1020..fc31af98a41bc 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -108,7 +108,7 @@ static void end_compressed_bio_read(struct bio *bio) struct page *page; unsigned long index; unsigned int mirror = btrfs_io_bio(bio)->mirror_num; - int ret; + int ret = 0; if (bio->bi_status) cb->errors = 1; @@ -127,6 +127,13 @@ static void end_compressed_bio_read(struct bio *bio) btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; cb->mirror_num = mirror; + /* + * Some IO in this cb have failed, just skip checksum as there + * is no way it could be correct. + */ + if (cb->errors == 1) + goto csum_failed; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); -- GitLab From 36b96fdc6b2dc6f4a0fedc563fa7508c91b90a10 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Sun, 17 Sep 2017 09:02:29 +0000 Subject: [PATCH 0431/1507] btrfs: Report error on removing qgroup if del_qgroup_item fails Previously, we were calling del_qgroup_item, and ignoring the return code resulting in a potential to have divergent in-memory state without an error. Perhaps, it makes sense to handle this error code, and put the filesystem into a read only, or similar state. This patch only adds reporting of the error if the error is fatal, (any error other than qgroup not found). Signed-off-by: Sargun Dhillon Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 770f667269f57..e172d4843eae2 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1305,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, } } ret = del_qgroup_item(trans, quota_root, qgroupid); + if (ret && ret != -ENOENT) + goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, -- GitLab From 99c4e3b96c797f047be4e6b7c03cfca01959f146 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Fri, 15 Sep 2017 15:06:51 -0600 Subject: [PATCH 0432/1507] Btrfs: fix unexpected result when dio reading corrupted blocks commit 4246a0b63bd8 ("block: add a bi_error field to struct bio") changed the logic of how dio read endio reports errors. For single stripe dio read, %bio->bi_status reflects the error before verifying checksum, and now we're updating it when data block matches with its checksum, while in the mismatching case, %bio->bi_status is not updated to relfect that. When some blocks in a file have been corrupted on disk, reading such a file ends up with 1) checksum errors are reported in kernel log 2) read(2) returns successfully with some content being 0x01. In order to fix it, we need to report its checksum mismatch error to the upper layer (dio layer in this case) as well. Fixes: 4246a0b63bd8 ("block: add a bi_error field to struct bio") Signed-off-by: Liu Bo Reported-by: Goffredo Baroncelli Tested-by: Goffredo Baroncelli Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f78c5640c6dc4..c242d0230db90 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8366,11 +8366,8 @@ static void btrfs_endio_direct_read(struct bio *bio) struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); - if (!err) - bio->bi_status = 0; - } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@ -8378,7 +8375,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_status = bio->bi_status; + dio_bio->bi_status = err; dio_end_io(dio_bio); if (io_bio->end_io) -- GitLab From 8c6c592831a09a28428448e68fb08c6bbb8b9b8b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 29 Aug 2017 10:11:39 -0400 Subject: [PATCH 0433/1507] btrfs: log csums for all modified extents Amir reported a bug discovered by his cleaned up version of my dm-log-writes xfstests where we were missing csums at certain replay points. This is because fsx was doing an msync(), which essentially fsync()'s a specific range of a file. We will log all modified extents, but only search for the checksums in the range we are being asked to sync. We cannot simply log the extents in the range we're being asked because we are logging the inode item as it is currently, which if it has had a i_size update before the msync means we will miss extents when replaying. We could possibly get around this by marking the inode with the transaction that extended the i_size to see if we have this case, but this would be racy and we'd have to lock the whole range of the inode to make sure we didn't have an ordered extent outside of our range that was in the middle of completing. Fix this simply by keeping track of the modified extents range and logging the csums for the entire range of extents that we are logging. This makes the xfstest pass. Reported-by: Amir Goldstein Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ad7f4bab640be..c800d067fcbf0 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4181,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; + u64 logged_start, logged_end; u64 test_gen; int ret = 0; int num = 0; @@ -4190,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; + logged_start = start; + logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); - /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we @@ -4208,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + + if (em->start < logged_start) + logged_start = em->start; + if ((em->start + em->len - 1) > logged_end) + logged_end = em->start + em->len - 1; + /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); set_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -4216,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - btrfs_get_logged_extents(inode, logged_list, start, end); + btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* * Some ordered extents started by fsync might have completed * before we could collect them into the list logged_list, which -- GitLab From 0bc15d85d97d44e8979ff91d0c1fbafe6fd4172c Mon Sep 17 00:00:00 2001 From: Nickey Yang Date: Tue, 26 Sep 2017 15:55:22 +0800 Subject: [PATCH 0434/1507] arm64: dts: rockchip: add the grf clk for dw-mipi-dsi on rk3399 The clk of grf must be enabled before writing grf register for rk3399. Signed-off-by: Nickey Yang [the grf clock is already part of the binding since march 2017] Signed-off-by: Heiko Stuebner --- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 6aa43fd471480..ab7629c5b856d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1630,8 +1630,8 @@ mipi_dsi: mipi@ff960000 { reg = <0x0 0xff960000 0x0 0x8000>; interrupts = ; clocks = <&cru SCLK_DPHY_PLL>, <&cru PCLK_MIPI_DSI0>, - <&cru SCLK_DPHY_TX0_CFG>; - clock-names = "ref", "pclk", "phy_cfg"; + <&cru SCLK_DPHY_TX0_CFG>, <&cru PCLK_VIO_GRF>; + clock-names = "ref", "pclk", "phy_cfg", "grf"; power-domains = <&power RK3399_PD_VIO>; rockchip,grf = <&grf>; status = "disabled"; -- GitLab From e88d62cd4b2f0b1ae55e9008e79c2794b1fc914d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 26 Sep 2017 12:41:52 +0100 Subject: [PATCH 0435/1507] percpu: make this_cpu_generic_read() atomic w.r.t. interrupts As raw_cpu_generic_read() is a plain read from a raw_cpu_ptr() address, it's possible (albeit unlikely) that the compiler will split the access across multiple instructions. In this_cpu_generic_read() we disable preemption but not interrupts before calling raw_cpu_generic_read(). Thus, an interrupt could be taken in the middle of the split load instructions. If a this_cpu_write() or RMW this_cpu_*() op is made to the same variable in the interrupt handling path, this_cpu_read() will return a torn value. For native word types, we can avoid tearing using READ_ONCE(), but this won't work in all cases (e.g. 64-bit types on most 32-bit platforms). This patch reworks this_cpu_generic_read() to use READ_ONCE() where possible, otherwise falling back to disabling interrupts. Signed-off-by: Mark Rutland Cc: Arnd Bergmann Cc: Christoph Lameter Cc: Peter Zijlstra Cc: Pranith Kumar Cc: Tejun Heo Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Tejun Heo --- include/asm-generic/percpu.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 0504ef8f3aa31..976f8ac26665b 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -115,15 +115,35 @@ do { \ (__ret); \ }) -#define this_cpu_generic_read(pcp) \ +#define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ typeof(pcp) __ret; \ preempt_disable_notrace(); \ - __ret = raw_cpu_generic_read(pcp); \ + __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ __ret; \ }) +#define __this_cpu_generic_read_noirq(pcp) \ +({ \ + typeof(pcp) __ret; \ + unsigned long __flags; \ + raw_local_irq_save(__flags); \ + __ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(__flags); \ + __ret; \ +}) + +#define this_cpu_generic_read(pcp) \ +({ \ + typeof(pcp) __ret; \ + if (__native_word(pcp)) \ + __ret = __this_cpu_generic_read_nopreempt(pcp); \ + else \ + __ret = __this_cpu_generic_read_noirq(pcp); \ + __ret; \ +}) + #define this_cpu_generic_to_op(pcp, val, op) \ do { \ unsigned long __flags; \ -- GitLab From 2d8f63297b9f0b430c96329893667c0bfdcbd47e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 19 Sep 2017 18:38:13 +0300 Subject: [PATCH 0436/1507] drm/i915: always update ELD connector type after get modes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drm_edid_to_eld() initializes the connector ELD to zero, overwriting the ELD connector type initialized in intel_audio_codec_enable(). If userspace does getconnector and thus get_modes after modeset, a subsequent audio component i915_audio_component_get_eld() call will receive an ELD without the connector type properly set. It's fine for HDMI, but screws up audio for DP. Always set the ELD connector type at intel_connector_update_modes() based on the connector type. We can drop the connector type update from intel_audio_codec_enable(). Credits to Joseph Nuzman for figuring this out. Cc: Ville Syrjälä Cc: Joseph Nuzman Reported-by: Joseph Nuzman Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101583 Reviewed-by: Ville Syrjälä Tested-by: Joseph Nuzman Cc: stable@vger.kernel.org # v4.10+, maybe earlier Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20170919153813.29808-1-jani.nikula@intel.com (cherry picked from commit d81fb7fd9436e81fda67e5bc8ed0713aa28d3db2) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_audio.c | 5 ----- drivers/gpu/drm/i915/intel_modes.c | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index d805b6e6fe714..27743be5b768e 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -606,11 +606,6 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder, connector->encoder->base.id, connector->encoder->name); - /* ELD Conn_Type */ - connector->eld[5] &= ~(3 << 2); - if (intel_crtc_has_dp_encoder(crtc_state)) - connector->eld[5] |= (1 << 2); - connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; if (dev_priv->display.audio_codec_enable) diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 951e834dd2744..28a778b785ac9 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -30,6 +30,21 @@ #include "intel_drv.h" #include "i915_drv.h" +static void intel_connector_update_eld_conn_type(struct drm_connector *connector) +{ + u8 conn_type; + + if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + conn_type = DRM_ELD_CONN_TYPE_DP; + } else { + conn_type = DRM_ELD_CONN_TYPE_HDMI; + } + + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK; + connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type; +} + /** * intel_connector_update_modes - update connector from edid * @connector: DRM connector device to use @@ -44,6 +59,8 @@ int intel_connector_update_modes(struct drm_connector *connector, ret = drm_add_edid_modes(connector, edid); drm_edid_to_eld(connector, edid); + intel_connector_update_eld_conn_type(connector); + return ret; } -- GitLab From bf5d10dcae3549b779490672c705c6ac79cf68a3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 14 Sep 2017 17:21:54 +0100 Subject: [PATCH 0437/1507] drm/i915: remove redundant variable hw_check hw_check is being assigned and updated but is no longer being read, hence it is redundant and can be removed. Detected by clang scan-build: "warning: Value stored to 'hw_check' during its initialization is never read" Fixes: f6d1973db2d2 ("drm/i915: Move modeset state verifier calls") Signed-off-by: Colin Ian King Reviewed-by: Chris Wilson Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20170914162154.11304-1-colin.king@canonical.com (cherry picked from commit 4babc5e27cfda59e2e257d28628b8d853aea5206) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_display.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 00cd17c76fdcc..64f7b51ed97c1 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12359,7 +12359,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; struct intel_crtc_state *intel_cstate; - bool hw_check = intel_state->modeset; u64 put_domains[I915_MAX_PIPES] = {}; unsigned crtc_vblank_mask = 0; int i; @@ -12376,7 +12375,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) if (needs_modeset(new_crtc_state) || to_intel_crtc_state(new_crtc_state)->update_pipe) { - hw_check = true; put_domains[to_intel_crtc(crtc)->pipe] = modeset_get_crtc_power_domains(crtc, -- GitLab From 2ba7d7e0437127314864238f8bfcb8369d81075c Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 21 Sep 2017 17:19:20 +0300 Subject: [PATCH 0438/1507] drm/i915/bios: ignore HDMI on port A MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The hardware state readout oopses after several warnings when trying to use HDMI on port A, if such a combination is configured in VBT. Filter the combo out already at the VBT parsing phase. v2: also ignore DVI (Ville) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102889 Cc: stable@vger.kernel.org Cc: Imre Deak Reviewed-by: Ville Syrjälä Tested-by: Daniel Drake Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20170921141920.18172-1-jani.nikula@intel.com (cherry picked from commit d27ffc1d00327c29b3aa97f941b42f0949f9e99f) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_bios.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 183e87e8ea319..00c6aee0a9a19 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1163,6 +1163,13 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0; is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR); + if (port == PORT_A && is_dvi) { + DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n", + is_hdmi ? "/HDMI" : ""); + is_dvi = false; + is_hdmi = false; + } + info->supports_dvi = is_dvi; info->supports_hdmi = is_hdmi; info->supports_dp = is_dp; -- GitLab From 1f4cf93b133ba6596ae69cfd09b48aa7b47cca41 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 11:04:23 +0200 Subject: [PATCH 0439/1507] net: ena: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_com.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 52beba8c7a399..ded29af648c91 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -315,7 +315,7 @@ static struct ena_comp_ctx *ena_com_submit_admin_cmd(struct ena_com_admin_queue cmd_size_in_bytes, comp, comp_size_in_bytes); - if (unlikely(IS_ERR(comp_ctx))) + if (IS_ERR(comp_ctx)) admin_queue->running_state = false; spin_unlock_irqrestore(&admin_queue->q_lock, flags); @@ -1130,7 +1130,7 @@ int ena_com_execute_admin_command(struct ena_com_admin_queue *admin_queue, comp_ctx = ena_com_submit_admin_cmd(admin_queue, cmd, cmd_size, comp, comp_size); - if (unlikely(IS_ERR(comp_ctx))) { + if (IS_ERR(comp_ctx)) { if (comp_ctx == ERR_PTR(-ENODEV)) pr_debug("Failed to submit command [%ld]\n", PTR_ERR(comp_ctx)); -- GitLab From 98e4fcff3e755c6c3de2d4f63c080b4009a599bd Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 11:21:42 +0200 Subject: [PATCH 0440/1507] datagram: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- net/core/datagram.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index f7fb7e3f2acf3..0b7b4c22719e9 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -188,7 +188,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, } if (!skb->len) { skb = skb_set_peeked(skb); - if (unlikely(IS_ERR(skb))) { + if (IS_ERR(skb)) { *err = PTR_ERR(skb); return NULL; } -- GitLab From 63a4e80be4f523dbde6412decfa8244ff73cc4b9 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 11:22:31 +0200 Subject: [PATCH 0441/1507] ipv6: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 96861c702c069..13c3b697f8c04 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3297,7 +3297,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev, struct rt6_info *rt, *prev; rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (unlikely(IS_ERR(rt))) + if (IS_ERR(rt)) return PTR_ERR(rt); /* ifp->rt can be accessed outside of rtnl */ -- GitLab From d9db5e3680c87fdbdf86fcb1c42caea4bf98680c Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 11:22:58 +0200 Subject: [PATCH 0442/1507] kcm: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index af4e76ac88ff0..0b750a22c4b9b 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1650,7 +1650,7 @@ static int kcm_clone(struct socket *osock, struct kcm_clone *info, } newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); - if (unlikely(IS_ERR(newfile))) { + if (IS_ERR(newfile)) { err = PTR_ERR(newfile); goto out_sock_alloc_fail; } -- GitLab From 36f6ee22d2d66046e369757ec6bbe1c482957ba6 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Tue, 26 Sep 2017 15:14:29 +0300 Subject: [PATCH 0443/1507] vti: fix use after free in vti_tunnel_xmit/vti6_tnl_xmit When running LTP IPsec tests, KASan might report: BUG: KASAN: use-after-free in vti_tunnel_xmit+0xeee/0xff0 [ip_vti] Read of size 4 at addr ffff880dc6ad1980 by task swapper/0/0 ... Call Trace: dump_stack+0x63/0x89 print_address_description+0x7c/0x290 kasan_report+0x28d/0x370 ? vti_tunnel_xmit+0xeee/0xff0 [ip_vti] __asan_report_load4_noabort+0x19/0x20 vti_tunnel_xmit+0xeee/0xff0 [ip_vti] ? vti_init_net+0x190/0x190 [ip_vti] ? save_stack_trace+0x1b/0x20 ? save_stack+0x46/0xd0 dev_hard_start_xmit+0x147/0x510 ? icmp_echo.part.24+0x1f0/0x210 __dev_queue_xmit+0x1394/0x1c60 ... Freed by task 0: save_stack_trace+0x1b/0x20 save_stack+0x46/0xd0 kasan_slab_free+0x70/0xc0 kmem_cache_free+0x81/0x1e0 kfree_skbmem+0xb1/0xe0 kfree_skb+0x75/0x170 kfree_skb_list+0x3e/0x60 __dev_queue_xmit+0x1298/0x1c60 dev_queue_xmit+0x10/0x20 neigh_resolve_output+0x3a8/0x740 ip_finish_output2+0x5c0/0xe70 ip_finish_output+0x4ba/0x680 ip_output+0x1c1/0x3a0 xfrm_output_resume+0xc65/0x13d0 xfrm_output+0x1e4/0x380 xfrm4_output_finish+0x5c/0x70 Can be fixed if we get skb->len before dst_output(). Fixes: b9959fd3b0fa ("vti: switch to new ip tunnel code") Fixes: 22e1b23dafa8 ("vti6: Support inter address family tunneling.") Signed-off-by: Alexey Kodanev Signed-off-by: David S. Miller --- net/ipv4/ip_vti.c | 3 ++- net/ipv6/ip6_vti.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 5ed63d2509506..89453cf62158f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -168,6 +168,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ + int pkt_len = skb->len; int err; int mtu; @@ -229,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) - err = skb->len; + err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 79444a4bfd6d2..bcdc2d557de13 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -445,6 +445,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; + int pkt_len = skb->len; int err = -1; int mtu; @@ -502,7 +503,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += skb->len; + tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); } else { -- GitLab From 1fac4b2fdbccab69cb781aae68f540be94d5549e Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 15:12:26 +0200 Subject: [PATCH 0444/1507] bnxt_en: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c25f5b555adfa..5ba49938ba55c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1491,7 +1491,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, (struct rx_tpa_end_cmp *)rxcmp, (struct rx_tpa_end_cmp_ext *)rxcmp1, event); - if (unlikely(IS_ERR(skb))) + if (IS_ERR(skb)) return -EBUSY; rc = -ENOMEM; -- GitLab From 92978ee801844b16180f2168ffffd05647da551a Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 15:13:23 +0200 Subject: [PATCH 0445/1507] net/mlx5: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 4614ddfa91ebc..6a7c8b04447eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -256,7 +256,7 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev, goto drop; } mdata = mlx5e_ipsec_add_metadata(skb); - if (unlikely(IS_ERR(mdata))) { + if (IS_ERR(mdata)) { atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_metadata); goto drop; } -- GitLab From 2091c227fa855776aafffad7ecd25ac0734df1a0 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 26 Sep 2017 15:14:15 +0200 Subject: [PATCH 0446/1507] ldmvsw: Remove redundant unlikely() IS_ERR() already implies unlikely(), so it can be omitted. Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/ldmvsw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5b56c24b6ed2e..5feeaa9f0a9e0 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -307,7 +307,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) /* Get (or create) the vnet associated with this port */ vp = vsw_get_vnet(hp, vdev->mp, &handle); - if (unlikely(IS_ERR(vp))) { + if (IS_ERR(vp)) { err = PTR_ERR(vp); pr_err("Failed to get vnet for vsw-port\n"); mdesc_release(hp); -- GitLab From 62b982eeb4589b2e6d7c01a90590e3a4c2b2ca19 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 26 Sep 2017 16:16:43 +0200 Subject: [PATCH 0447/1507] l2tp: fix race condition in l2tp_tunnel_delete If we try to delete the same tunnel twice, the first delete operation does a lookup (l2tp_tunnel_get), finds the tunnel, calls l2tp_tunnel_delete, which queues it for deletion by l2tp_tunnel_del_work. The second delete operation also finds the tunnel and calls l2tp_tunnel_delete. If the workqueue has already fired and started running l2tp_tunnel_del_work, then l2tp_tunnel_delete will queue the same tunnel a second time, and try to free the socket again. Add a dead flag to prevent firing the workqueue twice. Then we can remove the check of queue_work's result that was meant to prevent that race but doesn't. Reproducer: ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 local 192.168.0.2 remote 192.168.0.1 encap udp udp_sport 5000 udp_dport 6000 ip l2tp add session name l2tp1 tunnel_id 3000 session_id 1000 peer_session_id 2000 ip link set l2tp1 up ip l2tp del tunnel tunnel_id 3000 ip l2tp del tunnel tunnel_id 3000 Fixes: f8ccac0e4493 ("l2tp: put tunnel socket release on a workqueue") Reported-by: Jianlin Shi Signed-off-by: Sabrina Dubroca Acked-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 10 ++++------ net/l2tp/l2tp_core.h | 5 ++++- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index d8c2a89a76e18..02d61101b108d 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1688,14 +1688,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); /* This function is used by the netlink TUNNEL_DELETE command. */ -int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { - l2tp_tunnel_inc_refcount(tunnel); - if (false == queue_work(l2tp_wq, &tunnel->del_work)) { - l2tp_tunnel_dec_refcount(tunnel); - return 1; + if (!test_and_set_bit(0, &tunnel->dead)) { + l2tp_tunnel_inc_refcount(tunnel); + queue_work(l2tp_wq, &tunnel->del_work); } - return 0; } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 70a12df40a5f0..67c79d9b5c6cb 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -161,6 +161,9 @@ struct l2tp_tunnel_cfg { struct l2tp_tunnel { int magic; /* Should be L2TP_TUNNEL_MAGIC */ + + unsigned long dead; + struct rcu_head rcu; rwlock_t hlist_lock; /* protect session_hlist */ bool acpt_newsess; /* Indicates whether this @@ -255,7 +258,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); -int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); +void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, -- GitLab From b92af5a72ca982f0aa3df22f57a178aa5b0f4357 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Thu, 10 Aug 2017 15:29:12 +0300 Subject: [PATCH 0448/1507] net/mlx5: Fix creating a new FTE when an existing but full FTE exists Currently, when a flow steering rule is added, we look for a FTE with an identical value. If we find a match, we try to merge the required destinations with the existing ones. In a case where the existing destination list is full, the code should return an error to its consumer. However, the current code just tries to create another FTE. Fixing that by returning an error in this special scenario. Fixes: f478be79a22e ("net/mlx5: Add hash table for flow groups in flow table") Signed-off-by: Matan Barak Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5a7bea688ec87..6ffe9251bf620 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1449,7 +1449,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, int dest_num) { struct mlx5_flow_group *g; - struct mlx5_flow_handle *rule = ERR_PTR(-ENOENT); + struct mlx5_flow_handle *rule; struct rhlist_head *tmp, *list; struct match_list { struct list_head list; @@ -1513,6 +1513,8 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, unlock_ref_node(&g->node); } + rule = ERR_PTR(-ENOENT); + free_list: if (!list_empty(&match_head)) { struct match_list *match_tmp; @@ -1553,7 +1555,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); - if (!IS_ERR(rule)) + if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOENT) goto unlock; g = create_autogroup(ft, spec->match_criteria_enable, -- GitLab From 800350a3f145010c353bd7425428c05ac5cfc26a Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 23 Aug 2017 17:50:03 +0300 Subject: [PATCH 0449/1507] net/mlx5: Avoid NULL pointer dereference on steering cleanup On cleanup, when the node is the last child of parent then it calls to tree_put_node on the parent, if the parent's reference count is decremented to 0 (for e.g. when deleting last destination of FTE) then we free the parent as well and vice versa. In such a case we will try to free the parent node again. Increment the parent reference count before cleaning it's children will prevent implicit release of the parent object. Fixes: 0da2d66666d3 ('net/mlx5: Properly remove all steering objects') signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 6ffe9251bf620..f390828d87287 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2068,8 +2068,10 @@ static void clean_tree(struct fs_node *node) struct fs_node *iter; struct fs_node *temp; + tree_get_node(node); list_for_each_entry_safe(iter, temp, &node->children, list) clean_tree(iter); + tree_put_node(node); tree_remove_node(node); } } -- GitLab From 75d1d187b2ac86d1af2f1fd125ec21f104ca34b0 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 16 Jul 2017 15:18:45 +0300 Subject: [PATCH 0450/1507] net/mlx5: Move the entry index allocator to flow group When new flow table entry is added, we search for free index in the flow group and not in the flow table, therefore we can move the allocator from flow table to flow group. In downstream patches it will enable us to lock smaller part of the steering tree. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 18 +++++++++--------- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f390828d87287..2a0b5560a8b5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -384,7 +384,6 @@ static void del_flow_table(struct fs_node *node) err = mlx5_cmd_destroy_flow_table(dev, ft); if (err) mlx5_core_warn(dev, "flow steering can't destroy ft\n"); - ida_destroy(&ft->fte_allocator); rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; @@ -445,7 +444,7 @@ static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg) WARN_ON(ret); fte->status = 0; fs_get_obj(ft, fg->node.parent); - ida_simple_remove(&ft->fte_allocator, fte->index); + ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); } static void del_fte(struct fs_node *node) @@ -488,6 +487,7 @@ static void del_flow_group(struct fs_node *node) ft->autogroup.num_groups--; rhashtable_destroy(&fg->ftes_hash); + ida_destroy(&fg->fte_allocator); err = rhltable_remove(&ft->fgs_hash, &fg->hash, rhash_fg); @@ -537,6 +537,7 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) kfree(fg); return ERR_PTR(ret); } + ida_init(&fg->fte_allocator); fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, sizeof(fg->mask.match_criteria)); @@ -575,7 +576,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); - ida_init(&ft->fte_allocator); return ft; } @@ -892,7 +892,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa destroy_ft: mlx5_cmd_destroy_flow_table(root->dev, ft); free_ft: - ida_destroy(&ft->fte_allocator); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -1003,6 +1002,7 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table * rhash_fg)); err_free_fg: rhashtable_destroy(&fg->ftes_hash); + ida_destroy(&fg->fte_allocator); kfree(fg); return ERR_PTR(err); @@ -1181,18 +1181,18 @@ static struct fs_fte *create_fte(struct mlx5_flow_group *fg, u32 *match_value, struct mlx5_flow_act *flow_act) { - struct mlx5_flow_table *ft; struct fs_fte *fte; int index; int ret; - fs_get_obj(ft, fg->node.parent); - index = ida_simple_get(&ft->fte_allocator, fg->start_index, - fg->start_index + fg->max_ftes, + index = ida_simple_get(&fg->fte_allocator, 0, + fg->max_ftes, GFP_KERNEL); if (index < 0) return ERR_PTR(index); + index += fg->start_index; + fte = alloc_fte(flow_act, match_value, index); if (IS_ERR(fte)) { ret = PTR_ERR(fte); @@ -1207,7 +1207,7 @@ static struct fs_fte *create_fte(struct mlx5_flow_group *fg, err_hash: kfree(fte); err_alloc: - ida_simple_remove(&ft->fte_allocator, index); + ida_simple_remove(&fg->fte_allocator, index - fg->start_index); return ERR_PTR(ret); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 5509a752f98e7..02c969c3d3333 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -119,7 +119,6 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; - struct ida fte_allocator; struct rhltable fgs_hash; }; @@ -199,6 +198,7 @@ struct mlx5_flow_group { struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; + struct ida fte_allocator; u32 id; struct rhashtable ftes_hash; struct rhlist_head hash; -- GitLab From 46719d77d5f38b8ef04aa5a5cd91263b11d741d7 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 25 Jul 2017 19:20:49 +0300 Subject: [PATCH 0451/1507] net/mlx5: Export building of matched flow groups list Refactor the code and export the build of the matched flow groups list to separate function. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 100 +++++++++++------- 1 file changed, 64 insertions(+), 36 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2a0b5560a8b5b..33bcaca70a696 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1441,47 +1441,87 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, return true; } -static struct mlx5_flow_handle * -try_add_to_existing_fg(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - struct mlx5_flow_act *flow_act, - struct mlx5_flow_destination *dest, - int dest_num) -{ +struct match_list { + struct list_head list; struct mlx5_flow_group *g; - struct mlx5_flow_handle *rule; +}; + +struct match_list_head { + struct list_head list; + struct match_list first; +}; + +static void free_match_list(struct match_list_head *head) +{ + if (!list_empty(&head->list)) { + struct match_list *iter, *match_tmp; + + list_del(&head->first.list); + list_for_each_entry_safe(iter, match_tmp, &head->list, + list) { + list_del(&iter->list); + kfree(iter); + } + } +} + +static int build_match_list(struct match_list_head *match_head, + struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) +{ struct rhlist_head *tmp, *list; - struct match_list { - struct list_head list; - struct mlx5_flow_group *g; - } match_list, *iter; - LIST_HEAD(match_head); + struct mlx5_flow_group *g; + int err = 0; rcu_read_lock(); + INIT_LIST_HEAD(&match_head->list); /* Collect all fgs which has a matching match_criteria */ list = rhltable_lookup(&ft->fgs_hash, spec, rhash_fg); + /* RCU is atomic, we can't execute FW commands here */ rhl_for_each_entry_rcu(g, tmp, list, hash) { struct match_list *curr_match; - if (likely(list_empty(&match_head))) { - match_list.g = g; - list_add_tail(&match_list.list, &match_head); + if (likely(list_empty(&match_head->list))) { + match_head->first.g = g; + list_add_tail(&match_head->first.list, + &match_head->list); continue; } - curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); + curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { - rcu_read_unlock(); - rule = ERR_PTR(-ENOMEM); - goto free_list; + free_match_list(match_head); + err = -ENOMEM; + goto out; } curr_match->g = g; - list_add_tail(&curr_match->list, &match_head); + list_add_tail(&curr_match->list, &match_head->list); } +out: rcu_read_unlock(); + return err; +} + +static struct mlx5_flow_handle * +try_add_to_existing_fg(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num) +{ + struct mlx5_flow_group *g; + struct mlx5_flow_handle *rule; + struct match_list_head match_head; + struct match_list *iter; + int err; + + /* Collect all fgs which has a matching match_criteria */ + err = build_match_list(&match_head, ft, spec); + if (err) + return ERR_PTR(err); /* Try to find a fg that already contains a matching fte */ - list_for_each_entry(iter, &match_head, list) { + list_for_each_entry(iter, &match_head.list, list) { struct fs_fte *fte; g = iter->g; @@ -1500,7 +1540,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, /* No group with matching fte found. Try to add a new fte to any * matching fg. */ - list_for_each_entry(iter, &match_head, list) { + list_for_each_entry(iter, &match_head.list, list) { g = iter->g; nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); @@ -1516,19 +1556,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, rule = ERR_PTR(-ENOENT); free_list: - if (!list_empty(&match_head)) { - struct match_list *match_tmp; - - /* The most common case is having one FG. Since we want to - * optimize this case, we save the first on the stack. - * Therefore, no need to free it. - */ - list_del(&list_first_entry(&match_head, typeof(*iter), list)->list); - list_for_each_entry_safe(iter, match_tmp, &match_head, list) { - list_del(&iter->list); - kfree(iter); - } - } + free_match_list(&match_head); return rule; } -- GitLab From 19f100fef4ad46f21cfdfb1eeeb63fc38c2e57f1 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 26 Jul 2017 16:28:26 +0300 Subject: [PATCH 0452/1507] net/mlx5: Refactor FTE and FG creation code Split the creation code to two parts: 1) Object allocation - allocate the steering node and initialize its resources. 2) The firmware command execution. Adding active flag to each node - this flag indicates if the object exists in the hardware or not, if not we don't free the hardware resource in error flow. This change will give us the ability to take write lock on the parent node (e.g. FG for FTE creationg) only on the first part. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 356 ++++++++++-------- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + 2 files changed, 190 insertions(+), 167 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 33bcaca70a696..41f26f440099a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -179,14 +179,14 @@ find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest); static void tree_init_node(struct fs_node *node, - unsigned int refcount, void (*remove_func)(struct fs_node *)) { - atomic_set(&node->refcount, refcount); + atomic_set(&node->refcount, 1); INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); mutex_init(&node->lock); node->remove_func = remove_func; + node->active = false; } static void tree_add_node(struct fs_node *node, struct fs_node *parent) @@ -381,9 +381,11 @@ static void del_flow_table(struct fs_node *node) fs_get_obj(ft, node); dev = get_dev(&ft->node); - err = mlx5_cmd_destroy_flow_table(dev, ft); - if (err) - mlx5_core_warn(dev, "flow steering can't destroy ft\n"); + if (node->active) { + err = mlx5_cmd_destroy_flow_table(dev, ft); + if (err) + mlx5_core_warn(dev, "flow steering can't destroy ft\n"); + } rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; @@ -435,18 +437,6 @@ static void del_rule(struct fs_node *node) } } -static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg) -{ - struct mlx5_flow_table *ft; - int ret; - - ret = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - WARN_ON(ret); - fte->status = 0; - fs_get_obj(ft, fg->node.parent); - ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); -} - static void del_fte(struct fs_node *node) { struct mlx5_flow_table *ft; @@ -461,14 +451,20 @@ static void del_fte(struct fs_node *node) trace_mlx5_fs_del_fte(fte); dev = get_dev(&ft->node); - err = mlx5_cmd_delete_fte(dev, ft, - fte->index); - if (err) - mlx5_core_warn(dev, - "flow steering can't delete fte in index %d of flow group id %d\n", - fte->index, fg->id); + if (node->active) { + err = mlx5_cmd_delete_fte(dev, ft, + fte->index); + if (err) + mlx5_core_warn(dev, + "flow steering can't delete fte in index %d of flow group id %d\n", + fte->index, fg->id); + } - destroy_fte(fte, fg); + err = rhashtable_remove_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + WARN_ON(err); + ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); } static void del_flow_group(struct fs_node *node) @@ -492,7 +488,7 @@ static void del_flow_group(struct fs_node *node) &fg->hash, rhash_fg); WARN_ON(err); - if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) + if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", fg->id, ft->id); } @@ -518,14 +514,57 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, return fte; } -static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) +static struct fs_fte *alloc_insert_fte(struct mlx5_flow_group *fg, + u32 *match_value, + struct mlx5_flow_act *flow_act) +{ + struct fs_fte *fte; + int index; + int ret; + + index = ida_simple_get(&fg->fte_allocator, 0, + fg->max_ftes, + GFP_KERNEL); + if (index < 0) + return ERR_PTR(index); + + fte = alloc_fte(flow_act, match_value, index + fg->start_index); + if (IS_ERR(fte)) { + ret = PTR_ERR(fte); + goto err_ida_remove; + } + + ret = rhashtable_insert_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + if (ret) + goto err_free; + + tree_init_node(&fte->node, del_fte); + tree_add_node(&fte->node, &fg->node); + list_add_tail(&fte->node.list, &fg->node.children); + + return fte; + +err_free: + kfree(fte); +err_ida_remove: + ida_simple_remove(&fg->fte_allocator, index); + return ERR_PTR(ret); +} + +static void dealloc_flow_group(struct mlx5_flow_group *fg) +{ + rhashtable_destroy(&fg->ftes_hash); + kfree(fg); +} + +static struct mlx5_flow_group *alloc_flow_group(u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index) { struct mlx5_flow_group *fg; - void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, - create_fg_in, match_criteria); - u8 match_criteria_enable = MLX5_GET(create_flow_group_in, - create_fg_in, - match_criteria_enable); int ret; fg = kzalloc(sizeof(*fg), GFP_KERNEL); @@ -536,16 +575,47 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) if (ret) { kfree(fg); return ERR_PTR(ret); - } +} ida_init(&fg->fte_allocator); fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, sizeof(fg->mask.match_criteria)); fg->node.type = FS_TYPE_FLOW_GROUP; - fg->start_index = MLX5_GET(create_flow_group_in, create_fg_in, - start_flow_index); - fg->max_ftes = MLX5_GET(create_flow_group_in, create_fg_in, - end_flow_index) - fg->start_index + 1; + fg->start_index = start_index; + fg->max_ftes = end_index - start_index + 1; + + return fg; +} + +static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + void *match_criteria, + int start_index, + int end_index, + struct list_head *prev) +{ + struct mlx5_flow_group *fg; + int ret; + + fg = alloc_flow_group(match_criteria_enable, match_criteria, + start_index, end_index); + if (IS_ERR(fg)) + return fg; + + /* initialize refcnt, add to parent list */ + ret = rhltable_insert(&ft->fgs_hash, + &fg->hash, + rhash_fg); + if (ret) { + dealloc_flow_group(fg); + return ERR_PTR(ret); + } + + tree_init_node(&fg->node, del_flow_group); + tree_add_node(&fg->node, &ft->node); + /* Add node to group list */ + list_add(&fg->node.list, prev); + return fg; } @@ -870,7 +940,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - tree_init_node(&ft->node, 1, del_flow_table); + tree_init_node(&ft->node, del_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type, @@ -882,6 +952,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa err = connect_flow_table(root->dev, ft, fs_prio); if (err) goto destroy_ft; + ft->node.active = true; lock_ref_node(&fs_prio->node); tree_add_node(&ft->node, &fs_prio->node); list_add_flow_table(ft, fs_prio); @@ -959,55 +1030,6 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, } EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table); -/* Flow table should be locked */ -static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table *ft, - u32 *fg_in, - struct list_head - *prev_fg, - bool is_auto_fg) -{ - struct mlx5_flow_group *fg; - struct mlx5_core_dev *dev = get_dev(&ft->node); - int err; - - if (!dev) - return ERR_PTR(-ENODEV); - - fg = alloc_flow_group(fg_in); - if (IS_ERR(fg)) - return fg; - - err = rhltable_insert(&ft->fgs_hash, &fg->hash, rhash_fg); - if (err) - goto err_free_fg; - - err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); - if (err) - goto err_remove_fg; - - if (ft->autogroup.active) - ft->autogroup.num_groups++; - /* Add node to tree */ - tree_init_node(&fg->node, !is_auto_fg, del_flow_group); - tree_add_node(&fg->node, &ft->node); - /* Add node to group list */ - list_add(&fg->node.list, prev_fg); - - trace_mlx5_fs_add_fg(fg); - return fg; - -err_remove_fg: - WARN_ON(rhltable_remove(&ft->fgs_hash, - &fg->hash, - rhash_fg)); -err_free_fg: - rhashtable_destroy(&fg->ftes_hash); - ida_destroy(&fg->fte_allocator); - kfree(fg); - - return ERR_PTR(err); -} - struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *fg_in) { @@ -1016,7 +1038,13 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u8 match_criteria_enable = MLX5_GET(create_flow_group_in, fg_in, match_criteria_enable); + int start_index = MLX5_GET(create_flow_group_in, fg_in, + start_flow_index); + int end_index = MLX5_GET(create_flow_group_in, fg_in, + end_flow_index); + struct mlx5_core_dev *dev = get_dev(&ft->node); struct mlx5_flow_group *fg; + int err; if (!check_valid_mask(match_criteria_enable, match_criteria)) return ERR_PTR(-EINVAL); @@ -1025,8 +1053,20 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, return ERR_PTR(-EPERM); lock_ref_node(&ft->node); - fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false); + fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria, + start_index, end_index, + ft->node.children.prev); unlock_ref_node(&ft->node); + if (IS_ERR(fg)) + return fg; + + err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); + if (err) { + tree_put_node(&fg->node); + return ERR_PTR(err); + } + trace_mlx5_fs_add_fg(fg); + fg->node.active = true; return fg; } @@ -1111,7 +1151,7 @@ create_flow_handle(struct fs_fte *fte, /* Add dest to dests list- we need flow tables to be in the * end of the list for forward to next prio rules. */ - tree_init_node(&rule->node, 1, del_rule); + tree_init_node(&rule->node, del_rule); if (dest && dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) list_add(&rule->node.list, &fte->node.children); @@ -1167,6 +1207,7 @@ add_rule_fte(struct fs_fte *fte, if (err) goto free_handle; + fte->node.active = true; fte->status |= FS_FTE_STATUS_EXISTING; out: @@ -1177,59 +1218,17 @@ add_rule_fte(struct fs_fte *fte, return ERR_PTR(err); } -static struct fs_fte *create_fte(struct mlx5_flow_group *fg, - u32 *match_value, - struct mlx5_flow_act *flow_act) +static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec) { - struct fs_fte *fte; - int index; - int ret; - - index = ida_simple_get(&fg->fte_allocator, 0, - fg->max_ftes, - GFP_KERNEL); - if (index < 0) - return ERR_PTR(index); - - index += fg->start_index; - - fte = alloc_fte(flow_act, match_value, index); - if (IS_ERR(fte)) { - ret = PTR_ERR(fte); - goto err_alloc; - } - ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte); - if (ret) - goto err_hash; - - return fte; - -err_hash: - kfree(fte); -err_alloc: - ida_simple_remove(&fg->fte_allocator, index - fg->start_index); - return ERR_PTR(ret); -} - -static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct list_head *prev = &ft->node.children; - unsigned int candidate_index = 0; struct mlx5_flow_group *fg; - void *match_criteria_addr; + unsigned int candidate_index = 0; unsigned int group_size = 0; - u32 *in; if (!ft->autogroup.active) return ERR_PTR(-ENOENT); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return ERR_PTR(-ENOMEM); - if (ft->autogroup.num_groups < ft->autogroup.required_groups) /* We save place for flow groups in addition to max types */ group_size = ft->max_fte / (ft->autogroup.required_groups + 1); @@ -1247,25 +1246,55 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, prev = &fg->node.list; } - if (candidate_index + group_size > ft->max_fte) { - fg = ERR_PTR(-ENOSPC); + if (candidate_index + group_size > ft->max_fte) + return ERR_PTR(-ENOSPC); + + fg = alloc_insert_flow_group(ft, + spec->match_criteria_enable, + spec->match_criteria, + candidate_index, + candidate_index + group_size - 1, + prev); + if (IS_ERR(fg)) goto out; - } + + ft->autogroup.num_groups++; + +out: + return fg; +} + +static int create_auto_flow_group(struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + struct mlx5_core_dev *dev = get_dev(&ft->node); + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + void *match_criteria_addr; + int err; + u32 *in; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; MLX5_SET(create_flow_group_in, in, match_criteria_enable, - match_criteria_enable); - MLX5_SET(create_flow_group_in, in, start_flow_index, candidate_index); - MLX5_SET(create_flow_group_in, in, end_flow_index, candidate_index + - group_size - 1); + fg->mask.match_criteria_enable); + MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index); + MLX5_SET(create_flow_group_in, in, end_flow_index, fg->start_index + + fg->max_ftes - 1); match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); - memcpy(match_criteria_addr, match_criteria, - MLX5_ST_SZ_BYTES(fte_match_param)); + memcpy(match_criteria_addr, fg->mask.match_criteria, + sizeof(fg->mask.match_criteria)); + + err = mlx5_cmd_create_flow_group(dev, ft, in, &fg->id); + if (!err) { + fg->node.active = true; + trace_mlx5_fs_add_fg(fg); + } - fg = create_flow_group_common(ft, in, prev, true); -out: kvfree(in); - return fg; + return err; } static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, @@ -1368,23 +1397,17 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, } fs_get_obj(ft, fg->node.parent); - fte = create_fte(fg, match_value, flow_act); + fte = alloc_insert_fte(fg, match_value, flow_act); if (IS_ERR(fte)) return (void *)fte; - tree_init_node(&fte->node, 0, del_fte); nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); handle = add_rule_fte(fte, fg, dest, dest_num, false); if (IS_ERR(handle)) { unlock_ref_node(&fte->node); - destroy_fte(fte, fg); - kfree(fte); + tree_put_node(&fte->node); return handle; } - tree_add_node(&fte->node, &fg->node); - /* fte list isn't sorted */ - list_add_tail(&fte->node.list, &fg->node.children); - trace_mlx5_fs_set_fte(fte, true); add_rules: for (i = 0; i < handle->num_rules; i++) { if (atomic_read(&handle->rule[i]->node.refcount) == 1) { @@ -1571,6 +1594,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, { struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; + int err; int i; if (!check_valid_spec(spec)) @@ -1586,24 +1610,22 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOENT) goto unlock; - g = create_autogroup(ft, spec->match_criteria_enable, - spec->match_criteria); + g = alloc_auto_flow_group(ft, spec); if (IS_ERR(g)) { rule = (void *)g; goto unlock; } + err = create_auto_flow_group(ft, g); + if (err) { + rule = ERR_PTR(err); + goto put_fg; + } + rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, NULL); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - unlock_ref_node(&ft->node); - tree_get_node(&g->node); - tree_remove_node(&g->node); - return rule; - } +put_fg: + tree_put_node(&g->node); unlock: unlock_ref_node(&ft->node); return rule; @@ -1847,7 +1869,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, 1, NULL); + tree_init_node(&fs_prio->node, NULL); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -1873,7 +1895,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -1998,7 +2020,7 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering ns = &root_ns->ns; fs_init_namespace(ns); mutex_init(&root_ns->chain_lock); - tree_init_node(&ns->node, 1, NULL); + tree_init_node(&ns->node, NULL); tree_add_node(&ns->node, NULL); return root_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 02c969c3d3333..6e5d25b4f8de4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -82,6 +82,7 @@ struct fs_node { /* lock the node for writing and traversing */ struct mutex lock; atomic_t refcount; + bool active; void (*remove_func)(struct fs_node *); }; -- GitLab From c7784b1c8ab3f44dc2e643a8feb77584792c9108 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 27 Aug 2017 09:07:44 +0300 Subject: [PATCH 0453/1507] net/mlx5: Replace fs_node mutex with reader/writer semaphore Currently, steering object is protected by mutex lock, replace the mutex lock with reader/writer semaphore . In this patch we still use only write semaphore. In downstream patches we will switch part of the write locks to read locks. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 28 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 41f26f440099a..9406e72728073 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -145,10 +145,10 @@ static struct init_tree_node { } }; -enum fs_i_mutex_lock_class { - FS_MUTEX_GRANDPARENT, - FS_MUTEX_PARENT, - FS_MUTEX_CHILD +enum fs_i_lock_class { + FS_LOCK_GRANDPARENT, + FS_LOCK_PARENT, + FS_LOCK_CHILD }; static const struct rhashtable_params rhash_fte = { @@ -184,7 +184,7 @@ static void tree_init_node(struct fs_node *node, atomic_set(&node->refcount, 1); INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); - mutex_init(&node->lock); + init_rwsem(&node->lock); node->remove_func = remove_func; node->active = false; } @@ -208,10 +208,10 @@ static void tree_get_node(struct fs_node *node) } static void nested_lock_ref_node(struct fs_node *node, - enum fs_i_mutex_lock_class class) + enum fs_i_lock_class class) { if (node) { - mutex_lock_nested(&node->lock, class); + down_write_nested(&node->lock, class); atomic_inc(&node->refcount); } } @@ -219,7 +219,7 @@ static void nested_lock_ref_node(struct fs_node *node, static void lock_ref_node(struct fs_node *node) { if (node) { - mutex_lock(&node->lock); + down_write(&node->lock); atomic_inc(&node->refcount); } } @@ -228,7 +228,7 @@ static void unlock_ref_node(struct fs_node *node) { if (node) { atomic_dec(&node->refcount); - mutex_unlock(&node->lock); + up_write(&node->lock); } } @@ -1376,7 +1376,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, int old_action; int ret; - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); + nested_lock_ref_node(&fte->node, FS_LOCK_CHILD); ret = check_conflicting_ftes(fte, flow_act); if (ret) { handle = ERR_PTR(ret); @@ -1400,7 +1400,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, fte = alloc_insert_fte(fg, match_value, flow_act); if (IS_ERR(fte)) return (void *)fte; - nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); + nested_lock_ref_node(&fte->node, FS_LOCK_CHILD); handle = add_rule_fte(fte, fg, dest, dest_num, false); if (IS_ERR(handle)) { unlock_ref_node(&fte->node); @@ -1548,7 +1548,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, struct fs_fte *fte; g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); + nested_lock_ref_node(&g->node, FS_LOCK_PARENT); fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, rhash_fte); if (fte) { @@ -1566,7 +1566,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, list_for_each_entry(iter, &match_head.list, list) { g = iter->g; - nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); + nested_lock_ref_node(&g->node, FS_LOCK_PARENT); rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, NULL); if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) { @@ -1605,7 +1605,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, return ERR_PTR(-EINVAL); } - nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); + nested_lock_ref_node(&ft->node, FS_LOCK_GRANDPARENT); rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOENT) goto unlock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 6e5d25b4f8de4..b5c079f35051d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -80,7 +80,7 @@ struct fs_node { struct fs_node *parent; struct fs_node *root; /* lock the node for writing and traversing */ - struct mutex lock; + struct rw_semaphore lock; atomic_t refcount; bool active; void (*remove_func)(struct fs_node *); -- GitLab From bd71b08ec2ee4504bcc3b37a9283ce15e93dfacd Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 27 Aug 2017 09:19:11 +0300 Subject: [PATCH 0454/1507] net/mlx5: Support multiple updates of steering rules in parallel Most of the time spent on adding new flow steering rule is executing the firmware command. The most common action is adding a new flow steering entry. In order to enhance the update rate we parallelize the commands by doing the following: 1) Replace the mutex lock with readers-writers semaphore and take the write lock only when necessary (e.g. allocating a new flow table entry index or adding a node to the parent's children list). When we try to find a suitable child in the parent's children list (e.g. search for flow group with the same match_criteria of the rule) then we only take the read lock. 2) Add versioning mechanism - each steering entity (FT, FG, FTE, DST) will have an incremental version. The version is increased when the entity is changed (e.g. when a new FTE was added to FG - the FG's version is increased). Versioning is used in order to determine if the last traverse of an entity's children is valid or a rescan under write lock is required. This support improves the insertion rate of steering rules from ~5k/sec to ~40k/sec. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 386 ++++++++++++------ .../net/ethernet/mellanox/mlx5/core/fs_core.h | 4 +- 2 files changed, 264 insertions(+), 126 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9406e72728073..e7301cf747c54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -168,10 +168,16 @@ static const struct rhashtable_params rhash_fg = { }; -static void del_rule(struct fs_node *node); -static void del_flow_table(struct fs_node *node); -static void del_flow_group(struct fs_node *node); -static void del_fte(struct fs_node *node); +static void del_hw_flow_table(struct fs_node *node); +static void del_hw_flow_group(struct fs_node *node); +static void del_hw_fte(struct fs_node *node); +static void del_sw_flow_table(struct fs_node *node); +static void del_sw_flow_group(struct fs_node *node); +static void del_sw_fte(struct fs_node *node); +/* Delete rule (destination) is special case that + * requires to lock the FTE for all the deletion process. + */ +static void del_sw_hw_rule(struct fs_node *node); static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2); static struct mlx5_flow_rule * @@ -179,13 +185,15 @@ find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest); static void tree_init_node(struct fs_node *node, - void (*remove_func)(struct fs_node *)) + void (*del_hw_func)(struct fs_node *), + void (*del_sw_func)(struct fs_node *)) { atomic_set(&node->refcount, 1); INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->children); init_rwsem(&node->lock); - node->remove_func = remove_func; + node->del_hw_func = del_hw_func; + node->del_sw_func = del_sw_func; node->active = false; } @@ -202,50 +210,69 @@ static void tree_add_node(struct fs_node *node, struct fs_node *parent) node->root = parent->root; } -static void tree_get_node(struct fs_node *node) +static int tree_get_node(struct fs_node *node) { - atomic_inc(&node->refcount); + return atomic_add_unless(&node->refcount, 1, 0); } -static void nested_lock_ref_node(struct fs_node *node, - enum fs_i_lock_class class) +static void nested_down_read_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - down_write_nested(&node->lock, class); + down_read_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void lock_ref_node(struct fs_node *node) +static void nested_down_write_ref_node(struct fs_node *node, + enum fs_i_lock_class class) { if (node) { - down_write(&node->lock); + down_write_nested(&node->lock, class); atomic_inc(&node->refcount); } } -static void unlock_ref_node(struct fs_node *node) +static void down_write_ref_node(struct fs_node *node) { if (node) { - atomic_dec(&node->refcount); - up_write(&node->lock); + down_write(&node->lock); + atomic_inc(&node->refcount); } } +static void up_read_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_read(&node->lock); +} + +static void up_write_ref_node(struct fs_node *node) +{ + atomic_dec(&node->refcount); + up_write(&node->lock); +} + static void tree_put_node(struct fs_node *node) { struct fs_node *parent_node = node->parent; - lock_ref_node(parent_node); if (atomic_dec_and_test(&node->refcount)) { - if (parent_node) + if (node->del_hw_func) + node->del_hw_func(node); + if (parent_node) { + /* Only root namespace doesn't have parent and we just + * need to free its node. + */ + down_write_ref_node(parent_node); list_del_init(&node->list); - if (node->remove_func) - node->remove_func(node); + if (node->del_sw_func) + node->del_sw_func(node); + up_write_ref_node(parent_node); + } kfree(node); node = NULL; } - unlock_ref_node(parent_node); if (!node && parent_node) tree_put_node(parent_node); } @@ -371,11 +398,10 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } -static void del_flow_table(struct fs_node *node) +static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - struct fs_prio *prio; int err; fs_get_obj(ft, node); @@ -386,12 +412,21 @@ static void del_flow_table(struct fs_node *node) if (err) mlx5_core_warn(dev, "flow steering can't destroy ft\n"); } +} + +static void del_sw_flow_table(struct fs_node *node) +{ + struct mlx5_flow_table *ft; + struct fs_prio *prio; + + fs_get_obj(ft, node); + rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; } -static void del_rule(struct fs_node *node) +static void del_sw_hw_rule(struct fs_node *node) { struct mlx5_flow_rule *rule; struct mlx5_flow_table *ft; @@ -407,7 +442,6 @@ static void del_rule(struct fs_node *node) fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); trace_mlx5_fs_del_rule(rule); - list_del(&rule->node.list); if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { mutex_lock(&rule->dest_attr.ft->lock); list_del(&rule->next_ft); @@ -437,7 +471,7 @@ static void del_rule(struct fs_node *node) } } -static void del_fte(struct fs_node *node) +static void del_hw_fte(struct fs_node *node) { struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; @@ -448,8 +482,8 @@ static void del_fte(struct fs_node *node) fs_get_obj(fte, node); fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); - trace_mlx5_fs_del_fte(fte); + trace_mlx5_fs_del_fte(fte); dev = get_dev(&ft->node); if (node->active) { err = mlx5_cmd_delete_fte(dev, ft, @@ -459,6 +493,16 @@ static void del_fte(struct fs_node *node) "flow steering can't delete fte in index %d of flow group id %d\n", fte->index, fg->id); } +} + +static void del_sw_fte(struct fs_node *node) +{ + struct mlx5_flow_group *fg; + struct fs_fte *fte; + int err; + + fs_get_obj(fte, node); + fs_get_obj(fg, fte->node.parent); err = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, @@ -467,30 +511,39 @@ static void del_fte(struct fs_node *node) ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); } -static void del_flow_group(struct fs_node *node) +static void del_hw_flow_group(struct fs_node *node) { struct mlx5_flow_group *fg; struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; - int err; fs_get_obj(fg, node); fs_get_obj(ft, fg->node.parent); dev = get_dev(&ft->node); trace_mlx5_fs_del_fg(fg); - if (ft->autogroup.active) - ft->autogroup.num_groups--; + if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) + mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", + fg->id, ft->id); +} + +static void del_sw_flow_group(struct fs_node *node) +{ + struct mlx5_flow_group *fg; + struct mlx5_flow_table *ft; + int err; + + fs_get_obj(fg, node); + fs_get_obj(ft, fg->node.parent); rhashtable_destroy(&fg->ftes_hash); ida_destroy(&fg->fte_allocator); + if (ft->autogroup.active) + ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, rhash_fg); WARN_ON(err); - if (fg->node.active && mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) - mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", - fg->id, ft->id); } static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, @@ -540,7 +593,7 @@ static struct fs_fte *alloc_insert_fte(struct mlx5_flow_group *fg, if (ret) goto err_free; - tree_init_node(&fte->node, del_fte); + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); tree_add_node(&fte->node, &fg->node); list_add_tail(&fte->node.list, &fg->node.children); @@ -611,10 +664,11 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f return ERR_PTR(ret); } - tree_init_node(&fg->node, del_flow_group); + tree_init_node(&fg->node, del_hw_flow_group, del_sw_flow_group); tree_add_node(&fg->node, &ft->node); /* Add node to group list */ list_add(&fg->node.list, prev); + atomic_inc(&ft->node.version); return fg; } @@ -794,7 +848,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, fs_get_obj(fte, rule->node.parent); if (!(fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) return -EINVAL; - lock_ref_node(&fte->node); + down_write_ref_node(&fte->node); fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); @@ -803,7 +857,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, ft, fg->id, modify_mask, fte); - unlock_ref_node(&fte->node); + up_write_ref_node(&fte->node); return err; } @@ -940,7 +994,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa goto unlock_root; } - tree_init_node(&ft->node, del_flow_table); + tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type, @@ -953,11 +1007,11 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa if (err) goto destroy_ft; ft->node.active = true; - lock_ref_node(&fs_prio->node); + down_write_ref_node(&fs_prio->node); tree_add_node(&ft->node, &fs_prio->node); list_add_flow_table(ft, fs_prio); fs_prio->num_ft++; - unlock_ref_node(&fs_prio->node); + up_write_ref_node(&fs_prio->node); mutex_unlock(&root->chain_lock); return ft; destroy_ft: @@ -1052,11 +1106,11 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, if (ft->autogroup.active) return ERR_PTR(-EPERM); - lock_ref_node(&ft->node); + down_write_ref_node(&ft->node); fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria, start_index, end_index, ft->node.children.prev); - unlock_ref_node(&ft->node); + up_write_ref_node(&ft->node); if (IS_ERR(fg)) return fg; @@ -1151,7 +1205,7 @@ create_flow_handle(struct fs_fte *fte, /* Add dest to dests list- we need flow tables to be in the * end of the list for forward to next prio rules. */ - tree_init_node(&rule->node, del_rule); + tree_init_node(&rule->node, NULL, del_sw_hw_rule); if (dest && dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) list_add(&rule->node.list, &fte->node.children); @@ -1209,6 +1263,7 @@ add_rule_fte(struct fs_fte *fte, fte->node.active = true; fte->status |= FS_FTE_STATUS_EXISTING; + atomic_inc(&fte->node.version); out: return handle; @@ -1369,54 +1424,30 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, struct fs_fte *fte) { struct mlx5_flow_handle *handle; - struct mlx5_flow_table *ft; + int old_action; int i; + int ret; - if (fte) { - int old_action; - int ret; - - nested_lock_ref_node(&fte->node, FS_LOCK_CHILD); - ret = check_conflicting_ftes(fte, flow_act); - if (ret) { - handle = ERR_PTR(ret); - goto unlock_fte; - } - - old_action = fte->action; - fte->action |= flow_act->action; - handle = add_rule_fte(fte, fg, dest, dest_num, - old_action != flow_act->action); - if (IS_ERR(handle)) { - fte->action = old_action; - goto unlock_fte; - } else { - trace_mlx5_fs_set_fte(fte, false); - goto add_rules; - } - } - fs_get_obj(ft, fg->node.parent); + ret = check_conflicting_ftes(fte, flow_act); + if (ret) + return ERR_PTR(ret); - fte = alloc_insert_fte(fg, match_value, flow_act); - if (IS_ERR(fte)) - return (void *)fte; - nested_lock_ref_node(&fte->node, FS_LOCK_CHILD); - handle = add_rule_fte(fte, fg, dest, dest_num, false); + old_action = fte->action; + fte->action |= flow_act->action; + handle = add_rule_fte(fte, fg, dest, dest_num, + old_action != flow_act->action); if (IS_ERR(handle)) { - unlock_ref_node(&fte->node); - tree_put_node(&fte->node); + fte->action = old_action; return handle; } + trace_mlx5_fs_set_fte(fte, false); -add_rules: for (i = 0; i < handle->num_rules; i++) { if (atomic_read(&handle->rule[i]->node.refcount) == 1) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } } -unlock_fte: - unlock_ref_node(&fte->node); return handle; } @@ -1480,8 +1511,10 @@ static void free_match_list(struct match_list_head *head) struct match_list *iter, *match_tmp; list_del(&head->first.list); + tree_put_node(&head->first.g->node); list_for_each_entry_safe(iter, match_tmp, &head->list, list) { + tree_put_node(&iter->g->node); list_del(&iter->list); kfree(iter); } @@ -1505,6 +1538,8 @@ static int build_match_list(struct match_list_head *match_head, struct match_list *curr_match; if (likely(list_empty(&match_head->list))) { + if (!tree_get_node(&g->node)) + continue; match_head->first.g = g; list_add_tail(&match_head->first.list, &match_head->list); @@ -1517,6 +1552,10 @@ static int build_match_list(struct match_list_head *match_head, err = -ENOMEM; goto out; } + if (!tree_get_node(&g->node)) { + kfree(curr_match); + continue; + } curr_match->g = g; list_add_tail(&curr_match->list, &match_head->list); } @@ -1525,62 +1564,119 @@ static int build_match_list(struct match_list_head *match_head, return err; } +static u64 matched_fgs_get_version(struct list_head *match_head) +{ + struct match_list *iter; + u64 version = 0; + + list_for_each_entry(iter, match_head, list) + version += (u64)atomic_read(&iter->g->node.version); + return version; +} + static struct mlx5_flow_handle * try_add_to_existing_fg(struct mlx5_flow_table *ft, + struct list_head *match_head, struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, - int dest_num) + int dest_num, + int ft_version) { struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; - struct match_list_head match_head; struct match_list *iter; - int err; + bool take_write = false; + struct fs_fte *fte; + u64 version; - /* Collect all fgs which has a matching match_criteria */ - err = build_match_list(&match_head, ft, spec); - if (err) - return ERR_PTR(err); + list_for_each_entry(iter, match_head, list) { + nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); + ida_pre_get(&iter->g->fte_allocator, GFP_KERNEL); + } +search_again_locked: + version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ - list_for_each_entry(iter, &match_head.list, list) { - struct fs_fte *fte; + list_for_each_entry(iter, match_head, list) { + struct fs_fte *fte_tmp; g = iter->g; - nested_lock_ref_node(&g->node, FS_LOCK_PARENT); - fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (fte) { - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, fte); - unlock_ref_node(&g->node); - goto free_list; + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + continue; + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + } else { + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); } - unlock_ref_node(&g->node); + + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte_tmp); + up_write_ref_node(&fte_tmp->node); + tree_put_node(&fte_tmp->node); + return rule; } /* No group with matching fte found. Try to add a new fte to any * matching fg. */ - list_for_each_entry(iter, &match_head.list, list) { - g = iter->g; - nested_lock_ref_node(&g->node, FS_LOCK_PARENT); - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num, NULL); - if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) { - unlock_ref_node(&g->node); - goto free_list; - } - unlock_ref_node(&g->node); + if (!take_write) { + list_for_each_entry(iter, match_head, list) + up_read_ref_node(&iter->g->node); + list_for_each_entry(iter, match_head, list) + nested_down_write_ref_node(&iter->g->node, + FS_LOCK_PARENT); + take_write = true; } - rule = ERR_PTR(-ENOENT); + /* Check the ft version, for case that new flow group + * was added while the fgs weren't locked + */ + if (atomic_read(&ft->node.version) != ft_version) { + rule = ERR_PTR(-EAGAIN); + goto out; + } -free_list: - free_match_list(&match_head); + /* Check the fgs version, for case the new FTE with the + * same values was added while the fgs weren't locked + */ + if (version != matched_fgs_get_version(match_head)) + goto search_again_locked; + + list_for_each_entry(iter, match_head, list) { + g = iter->g; + + if (!g->node.active) + continue; + fte = alloc_insert_fte(g, spec->match_value, flow_act); + if (IS_ERR(fte)) { + if (PTR_ERR(fte) == -ENOSPC) + continue; + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + return (void *)fte; + } + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); + return rule; + } + rule = ERR_PTR(-ENOENT); +out: + list_for_each_entry(iter, match_head, list) + up_write_ref_node(&iter->g->node); return rule; } @@ -1594,6 +1690,10 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, { struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; + struct match_list_head match_head; + bool take_write = false; + struct fs_fte *fte; + int version; int err; int i; @@ -1604,31 +1704,67 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (!dest_is_valid(&dest[i], flow_act->action, ft)) return ERR_PTR(-EINVAL); } + nested_down_read_ref_node(&ft->node, FS_LOCK_GRANDPARENT); +search_again_locked: + version = atomic_read(&ft->node.version); - nested_lock_ref_node(&ft->node, FS_LOCK_GRANDPARENT); - rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); - if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOENT) - goto unlock; + /* Collect all fgs which has a matching match_criteria */ + err = build_match_list(&match_head, ft, spec); + if (err) + return ERR_PTR(err); + + if (!take_write) + up_read_ref_node(&ft->node); + + rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest, + dest_num, version); + free_match_list(&match_head); + if (!IS_ERR(rule) || + (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) + return rule; + + if (!take_write) { + nested_down_write_ref_node(&ft->node, FS_LOCK_GRANDPARENT); + take_write = true; + } + + if (PTR_ERR(rule) == -EAGAIN || + version != atomic_read(&ft->node.version)) + goto search_again_locked; g = alloc_auto_flow_group(ft, spec); if (IS_ERR(g)) { rule = (void *)g; - goto unlock; + up_write_ref_node(&ft->node); + return rule; } + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + up_write_ref_node(&ft->node); + err = create_auto_flow_group(ft, g); - if (err) { - rule = ERR_PTR(err); - goto put_fg; + if (err) + goto err_release_fg; + + fte = alloc_insert_fte(g, spec->match_value, flow_act); + if (IS_ERR(fte)) { + err = PTR_ERR(fte); + goto err_release_fg; } + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); + up_write_ref_node(&g->node); rule = add_rule_fg(g, spec->match_value, flow_act, dest, - dest_num, NULL); -put_fg: + dest_num, fte); + up_write_ref_node(&fte->node); + tree_put_node(&fte->node); tree_put_node(&g->node); -unlock: - unlock_ref_node(&ft->node); return rule; + +err_release_fg: + up_write_ref_node(&g->node); + tree_put_node(&g->node); + return ERR_PTR(err); } static bool fwd_next_prio_supported(struct mlx5_flow_table *ft) @@ -1869,7 +2005,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, NULL); + tree_init_node(&fs_prio->node, NULL, NULL); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -1895,7 +2031,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -2020,7 +2156,7 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering ns = &root_ns->ns; fs_init_namespace(ns); mutex_init(&root_ns->chain_lock); - tree_init_node(&ns->node, NULL); + tree_init_node(&ns->node, NULL, NULL); tree_add_node(&ns->node, NULL); return root_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index b5c079f35051d..875b753862b0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -83,7 +83,9 @@ struct fs_node { struct rw_semaphore lock; atomic_t refcount; bool active; - void (*remove_func)(struct fs_node *); + void (*del_hw_func)(struct fs_node *); + void (*del_sw_func)(struct fs_node *); + atomic_t version; }; struct mlx5_flow_rule { -- GitLab From f5c2ff179f51101893e42e78683b23a487929d6c Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 29 Aug 2017 19:17:12 +0300 Subject: [PATCH 0455/1507] net/mlx5: Allocate FTE object without lock Allocation of new FTE is a massive operation, part of it could be done without taking the flow group write lock. Split the FTE allocation to two functions of actions which need to be under lock and action which don't have. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 92 +++++++++---------- 1 file changed, 46 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e7301cf747c54..bc4bbb72fa866 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -546,9 +546,33 @@ static void del_sw_flow_group(struct fs_node *node) WARN_ON(err); } -static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, - u32 *match_value, - unsigned int index) +static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) +{ + int index; + int ret; + + index = ida_simple_get(&fg->fte_allocator, 0, fg->max_ftes, GFP_KERNEL); + if (index < 0) + return index; + + fte->index = index + fg->start_index; + ret = rhashtable_insert_fast(&fg->ftes_hash, + &fte->hash, + rhash_fte); + if (ret) + goto err_ida_remove; + + tree_add_node(&fte->node, &fg->node); + list_add_tail(&fte->node.list, &fg->node.children); + return 0; + +err_ida_remove: + ida_simple_remove(&fg->fte_allocator, index); + return ret; +} + +static struct fs_fte *alloc_fte(u32 *match_value, + struct mlx5_flow_act *flow_act) { struct fs_fte *fte; @@ -559,51 +583,13 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, memcpy(fte->val, match_value, sizeof(fte->val)); fte->node.type = FS_TYPE_FLOW_ENTRY; fte->flow_tag = flow_act->flow_tag; - fte->index = index; fte->action = flow_act->action; fte->encap_id = flow_act->encap_id; fte->modify_id = flow_act->modify_id; - return fte; -} - -static struct fs_fte *alloc_insert_fte(struct mlx5_flow_group *fg, - u32 *match_value, - struct mlx5_flow_act *flow_act) -{ - struct fs_fte *fte; - int index; - int ret; - - index = ida_simple_get(&fg->fte_allocator, 0, - fg->max_ftes, - GFP_KERNEL); - if (index < 0) - return ERR_PTR(index); - - fte = alloc_fte(flow_act, match_value, index + fg->start_index); - if (IS_ERR(fte)) { - ret = PTR_ERR(fte); - goto err_ida_remove; - } - - ret = rhashtable_insert_fast(&fg->ftes_hash, - &fte->hash, - rhash_fte); - if (ret) - goto err_free; - tree_init_node(&fte->node, del_hw_fte, del_sw_fte); - tree_add_node(&fte->node, &fg->node); - list_add_tail(&fte->node.list, &fg->node.children); return fte; - -err_free: - kfree(fte); -err_ida_remove: - ida_simple_remove(&fg->fte_allocator, index); - return ERR_PTR(ret); } static void dealloc_flow_group(struct mlx5_flow_group *fg) @@ -1589,6 +1575,11 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, bool take_write = false; struct fs_fte *fte; u64 version; + int err; + + fte = alloc_fte(spec->match_value, flow_act); + if (IS_ERR(fte)) + return ERR_PTR(-ENOMEM); list_for_each_entry(iter, match_head, list) { nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); @@ -1620,6 +1611,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, flow_act, dest, dest_num, fte_tmp); up_write_ref_node(&fte_tmp->node); tree_put_node(&fte_tmp->node); + kfree(fte); return rule; } @@ -1655,13 +1647,14 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, if (!g->node.active) continue; - fte = alloc_insert_fte(g, spec->match_value, flow_act); - if (IS_ERR(fte)) { - if (PTR_ERR(fte) == -ENOSPC) + err = insert_fte(g, fte); + if (err) { + if (err == -ENOSPC) continue; list_for_each_entry(iter, match_head, list) up_write_ref_node(&iter->g->node); - return (void *)fte; + kfree(fte); + return ERR_PTR(err); } nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); @@ -1677,6 +1670,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, out: list_for_each_entry(iter, match_head, list) up_write_ref_node(&iter->g->node); + kfree(fte); return rule; } @@ -1746,12 +1740,18 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (err) goto err_release_fg; - fte = alloc_insert_fte(g, spec->match_value, flow_act); + fte = alloc_fte(spec->match_value, flow_act); if (IS_ERR(fte)) { err = PTR_ERR(fte); goto err_release_fg; } + err = insert_fte(g, fte); + if (err) { + kfree(fte); + goto err_release_fg; + } + nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); up_write_ref_node(&g->node); rule = add_rule_fg(g, spec->match_value, flow_act, dest, -- GitLab From a369d4ac4dff92129ea0dfa3d66f45a830e29098 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 27 Aug 2017 13:18:40 +0300 Subject: [PATCH 0456/1507] net/mlx5: Add FGs and FTEs memory pool Add memory pool allocation for flow groups and flow table entry. It is useful because these objects are not small and could be allocated/deallocated many times. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 67 ++++++++++++++----- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 2 + 2 files changed, 53 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index bc4bbb72fa866..7a136ae2547a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -269,8 +269,9 @@ static void tree_put_node(struct fs_node *node) if (node->del_sw_func) node->del_sw_func(node); up_write_ref_node(parent_node); + } else { + kfree(node); } - kfree(node); node = NULL; } if (!node && parent_node) @@ -389,6 +390,15 @@ static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) return container_of(ns, struct mlx5_flow_root_namespace, ns); } +static inline struct mlx5_flow_steering *get_steering(struct fs_node *node) +{ + struct mlx5_flow_root_namespace *root = find_root(node); + + if (root) + return root->dev->priv.steering; + return NULL; +} + static inline struct mlx5_core_dev *get_dev(struct fs_node *node) { struct mlx5_flow_root_namespace *root = find_root(node); @@ -424,6 +434,7 @@ static void del_sw_flow_table(struct fs_node *node) rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; + kfree(ft); } static void del_sw_hw_rule(struct fs_node *node) @@ -469,6 +480,7 @@ static void del_sw_hw_rule(struct fs_node *node) "%s can't del rule fg id=%d fte_index=%d\n", __func__, fg->id, fte->index); } + kfree(rule); } static void del_hw_fte(struct fs_node *node) @@ -497,6 +509,7 @@ static void del_hw_fte(struct fs_node *node) static void del_sw_fte(struct fs_node *node) { + struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; struct fs_fte *fte; int err; @@ -509,6 +522,7 @@ static void del_sw_fte(struct fs_node *node) rhash_fte); WARN_ON(err); ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); + kmem_cache_free(steering->ftes_cache, fte); } static void del_hw_flow_group(struct fs_node *node) @@ -529,6 +543,7 @@ static void del_hw_flow_group(struct fs_node *node) static void del_sw_flow_group(struct fs_node *node) { + struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; struct mlx5_flow_table *ft; int err; @@ -544,6 +559,7 @@ static void del_sw_flow_group(struct fs_node *node) &fg->hash, rhash_fg); WARN_ON(err); + kmem_cache_free(steering->fgs_cache, fg); } static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) @@ -571,12 +587,14 @@ static int insert_fte(struct mlx5_flow_group *fg, struct fs_fte *fte) return ret; } -static struct fs_fte *alloc_fte(u32 *match_value, +static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, + u32 *match_value, struct mlx5_flow_act *flow_act) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct fs_fte *fte; - fte = kzalloc(sizeof(*fte), GFP_KERNEL); + fte = kmem_cache_zalloc(steering->ftes_cache, GFP_KERNEL); if (!fte) return ERR_PTR(-ENOMEM); @@ -592,13 +610,15 @@ static struct fs_fte *alloc_fte(u32 *match_value, return fte; } -static void dealloc_flow_group(struct mlx5_flow_group *fg) +static void dealloc_flow_group(struct mlx5_flow_steering *steering, + struct mlx5_flow_group *fg) { rhashtable_destroy(&fg->ftes_hash); - kfree(fg); + kmem_cache_free(steering->fgs_cache, fg); } -static struct mlx5_flow_group *alloc_flow_group(u8 match_criteria_enable, +static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steering, + u8 match_criteria_enable, void *match_criteria, int start_index, int end_index) @@ -606,13 +626,13 @@ static struct mlx5_flow_group *alloc_flow_group(u8 match_criteria_enable, struct mlx5_flow_group *fg; int ret; - fg = kzalloc(sizeof(*fg), GFP_KERNEL); + fg = kmem_cache_zalloc(steering->fgs_cache, GFP_KERNEL); if (!fg) return ERR_PTR(-ENOMEM); ret = rhashtable_init(&fg->ftes_hash, &rhash_fte); if (ret) { - kfree(fg); + kmem_cache_free(steering->fgs_cache, fg); return ERR_PTR(ret); } ida_init(&fg->fte_allocator); @@ -633,10 +653,11 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f int end_index, struct list_head *prev) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct mlx5_flow_group *fg; int ret; - fg = alloc_flow_group(match_criteria_enable, match_criteria, + fg = alloc_flow_group(steering, match_criteria_enable, match_criteria, start_index, end_index); if (IS_ERR(fg)) return fg; @@ -646,7 +667,7 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f &fg->hash, rhash_fg); if (ret) { - dealloc_flow_group(fg); + dealloc_flow_group(steering, fg); return ERR_PTR(ret); } @@ -1569,6 +1590,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, int dest_num, int ft_version) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; struct match_list *iter; @@ -1577,7 +1599,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, u64 version; int err; - fte = alloc_fte(spec->match_value, flow_act); + fte = alloc_fte(ft, spec->match_value, flow_act); if (IS_ERR(fte)) return ERR_PTR(-ENOMEM); @@ -1611,7 +1633,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, flow_act, dest, dest_num, fte_tmp); up_write_ref_node(&fte_tmp->node); tree_put_node(&fte_tmp->node); - kfree(fte); + kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1653,7 +1675,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, continue; list_for_each_entry(iter, match_head, list) up_write_ref_node(&iter->g->node); - kfree(fte); + kmem_cache_free(steering->ftes_cache, fte); return ERR_PTR(err); } @@ -1670,7 +1692,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, out: list_for_each_entry(iter, match_head, list) up_write_ref_node(&iter->g->node); - kfree(fte); + kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1682,6 +1704,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, int dest_num) { + struct mlx5_flow_steering *steering = get_steering(&ft->node); struct mlx5_flow_group *g; struct mlx5_flow_handle *rule; struct match_list_head match_head; @@ -1740,7 +1763,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (err) goto err_release_fg; - fte = alloc_fte(spec->match_value, flow_act); + fte = alloc_fte(ft, spec->match_value, flow_act); if (IS_ERR(fte)) { err = PTR_ERR(fte); goto err_release_fg; @@ -1748,7 +1771,7 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, err = insert_fte(g, fte); if (err) { - kfree(fte); + kmem_cache_free(steering->ftes_cache, fte); goto err_release_fg; } @@ -2281,6 +2304,8 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); mlx5_cleanup_fc_stats(dev); + kmem_cache_destroy(steering->ftes_cache); + kmem_cache_destroy(steering->fgs_cache); kfree(steering); } @@ -2386,6 +2411,16 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) steering->dev = dev; dev->priv.steering = steering; + steering->fgs_cache = kmem_cache_create("mlx5_fs_fgs", + sizeof(struct mlx5_flow_group), 0, + 0, NULL); + steering->ftes_cache = kmem_cache_create("mlx5_fs_ftes", sizeof(struct fs_fte), 0, + 0, NULL); + if (!steering->ftes_cache || !steering->fgs_cache) { + err = -ENOMEM; + goto err; + } + if ((((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && (MLX5_CAP_GEN(dev, nic_flow_table))) || ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 875b753862b0f..ebe184515433f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -65,6 +65,8 @@ enum fs_fte_status { struct mlx5_flow_steering { struct mlx5_core_dev *dev; + struct kmem_cache *fgs_cache; + struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; struct mlx5_flow_root_namespace *esw_egress_root_ns; -- GitLab From 6851a3db7e224bbb85e23b3c64a506c9e0904382 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Mon, 18 Sep 2017 14:46:03 -0700 Subject: [PATCH 0457/1507] xfs: validate bdev support for DAX inode flag Currently only the blocksize is checked, but we should really be calling bdev_dax_supported() which also tests to make sure we can get a struct dax_device and that the dax_direct_access() path is working. This is the same check that we do for the "-o dax" mount option in xfs_fs_fill_super(). This does not fix the race issues that caused the XFS DAX inode option to be disabled, so that option will still be disabled. If/when we re-enable it, though, I think we will want this issue to have been fixed. I also do think that we want to fix this in stable kernels. Signed-off-by: Ross Zwisler CC: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5049e8ab6e302..aa75389be8cfa 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1088,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1100,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } -- GitLab From 546e7be8244dc050effef0555df5b8d94d10dafc Mon Sep 17 00:00:00 2001 From: Chandan Rajendra Date: Fri, 22 Sep 2017 11:47:33 -0700 Subject: [PATCH 0458/1507] iomap_dio_rw: Allocate AIO completion queue before submitting dio Executing xfs/104 test in a loop on Linux-v4.13 kernel on a ppc64 machine can cause the following NULL pointer dereference, .queue_work_on+0x4c/0x80 .iomap_dio_bio_end_io+0xbc/0x1f0 .bio_endio+0x118/0x1f0 .blk_update_request+0xd0/0x470 .blk_mq_end_request+0x24/0xc0 .lo_complete_rq+0x40/0xe0 .__blk_mq_complete_request_remote+0x28/0x40 .flush_smp_call_function_queue+0xc4/0x1e0 .smp_ipi_demux_relaxed+0x8c/0x100 .icp_hv_ipi_action+0x54/0xa0 .__handle_irq_event_percpu+0x84/0x2c0 .handle_irq_event_percpu+0x28/0x80 .handle_percpu_irq+0x78/0xc0 .generic_handle_irq+0x40/0x70 .__do_irq+0x88/0x200 .call_do_irq+0x14/0x24 .do_IRQ+0x84/0x130 This occurs due to the following sequence of events, 1. Allocate dio for Direct I/O write. 2. Invoke iomap_apply() until iov_iter_count() bytes have been submitted. - Assume that we have submitted atleast one bio. Hence iomap_dio->ref value will be >= 2. - If during the second iteration, iomap_apply() ends up returning -ENOSPC, we would break out of the loop and since the 'ret' value is a negative number we end up not allocating memory for super_block->s_dio_done_wq. 3. Meanwhile, iomap_dio_bio_end_io() is invoked for bios that have been submitted and here the code ends up dereferencing the NULL pointer stored at super_block->s_dio_done_wq. This commit fixes the bug by allocating memory for super_block->s_dio_done_wq before iomap_apply() is invoked. Reported-by: Eryu Guan Reviewed-by: Christoph Hellwig Tested-by: Eryu Guan Signed-off-by: Chandan Rajendra Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/iomap.c b/fs/iomap.c index 269b24a01f321..d4f526a3f5b2f 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -993,6 +993,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, WARN_ON_ONCE(ret); ret = 0; + if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + inode_dio_begin(inode); blk_start_plug(&plug); @@ -1015,13 +1022,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret < 0) iomap_dio_set_error(dio, ret); - if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && - !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - iomap_dio_set_error(dio, ret); - } - if (!atomic_dec_and_test(&dio->ref)) { if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; -- GitLab From ee70daaba82d70766d0723b743d9fdeb3b06102a Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Thu, 21 Sep 2017 11:26:18 -0700 Subject: [PATCH 0459/1507] xfs: update i_size after unwritten conversion in dio completion Since commit d531d91d6990 ("xfs: always use unwritten extents for direct I/O writes"), we start allocating unwritten extents for all direct writes to allow appending aio in XFS. But for dio writes that could extend file size we update the in-core inode size first, then convert the unwritten extents to real allocations at dio completion time in xfs_dio_write_end_io(). Thus a racing direct read could see the new i_size and find the unwritten extents first and read zeros instead of actual data, if the direct writer also takes a shared iolock. Fix it by updating the in-core inode size after the unwritten extent conversion. To do this, introduce a new boolean argument to xfs_iomap_write_unwritten() to tell if we want to update in-core i_size or not. Suggested-by: Brian Foster Reviewed-by: Brian Foster Signed-off-by: Eryu Guan Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_aops.c | 3 ++- fs/xfs/xfs_file.c | 33 +++++++++++++++++++-------------- fs/xfs/xfs_iomap.c | 7 +++++-- fs/xfs/xfs_iomap.h | 2 +- fs/xfs/xfs_pnfs.c | 2 +- 5 files changed, 28 insertions(+), 19 deletions(-) diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 29172609f2a31..f18e5932aec4b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -343,7 +343,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 350b6d43ba23b..309e26c9dddb4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -434,7 +434,6 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; - bool update_size = false; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -445,6 +444,21 @@ xfs_dio_write_end_io( if (size <= 0) return size; + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & IOMAP_DIO_UNWRITTEN) + return xfs_iomap_write_unwritten(ip, offset, size, true); + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -459,20 +473,11 @@ xfs_dio_write_end_io( spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); - update_size = true; - } - spin_unlock(&ip->i_flags_lock); - - if (flags & IOMAP_DIO_COW) { - error = xfs_reflink_end_cow(ip, offset, size); - if (error) - return error; - } - - if (flags & IOMAP_DIO_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size); - else if (update_size) + spin_unlock(&ip->i_flags_lock); error = xfs_setfilesize(ip, offset, size); + } else { + spin_unlock(&ip->i_flags_lock); + } return error; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a1909bc064e9e..f179bdf1644dc 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -829,7 +829,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -840,6 +841,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -899,7 +901,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 00db3ecea0840..ee535065c5d0e 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 2f2dc3c09ad00..4246876df7b75 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -274,7 +274,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } -- GitLab From 9789dd9e1d939232e8ff4c50ef8e75aa6781b3fb Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 18 Sep 2017 09:42:09 -0700 Subject: [PATCH 0460/1507] xfs: perag initialization should only touch m_ag_max_usable for AG 0 We call __xfs_ag_resv_init to make a per-AG reservation for each AG. This makes the reservation per-AG, not per-filesystem. Therefore, it is incorrect to adjust m_ag_max_usable for each AG. Adjust it only when we're reserving AG 0's blocks so that we only do it once per fs. Signed-off-by: Darrick J. Wong Reviewed-by: Brian Foster --- fs/xfs/libxfs/xfs_ag_resv.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index b008ff3250eba..df3e600835e8d 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -156,7 +156,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -216,7 +217,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; -- GitLab From 842f6e9f786226c58fcbd5ef80eadca72fdfe652 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Fri, 22 Sep 2017 11:47:46 -0700 Subject: [PATCH 0461/1507] xfs: Capture state of the right inode in xfs_iflush_done My previous patch: d3a304b6292168b83b45d624784f973fdc1ca674 check for XFS_LI_FAILED flag xfs_iflush done, so the failed item can be properly resubmitted. In the loop scanning other inodes being completed, it should check the current item for the XFS_LI_FAILED, and not the initial one. The state of the initial inode is checked after the loop ends Kudos to Eric for catching this. Signed-off-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_inode_item.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 6d0f74ec31e89..a705f34b58fad 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -745,7 +745,7 @@ xfs_iflush_done( */ iip = INODE_ITEM(blip); if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || - lip->li_flags & XFS_LI_FAILED) + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; -- GitLab From 5e5c943c1f257c2b3424fc3f8a7b18570152dab3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 18 Sep 2017 09:41:17 -0700 Subject: [PATCH 0462/1507] xfs: revert "xfs: factor rmap btree size into the indlen calculations" In commit fd26a88093ba we added a worst case estimate for rmapbt blocks needed to satisfy the block mapping request. Since then, we added the ability to reserve enough space in each AG such that we should never run out of blocks to grow the rmapbt, which makes this calculation unnecessary. Revert the commit because it makes the extra delalloc indlen accounting unnecessary and incorrect. Reported-by: Eryu Guan Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_bmap.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 459f4b4f08fe5..044a363119bea 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,7 +49,6 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" #include "xfs_icache.h" @@ -192,12 +191,8 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; mp = ip->i_mount; - - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -205,20 +200,12 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } -- GitLab From 89fcbb564f4a64c439d597c2702f990eed49c8a1 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 21 Sep 2017 19:01:36 -0600 Subject: [PATCH 0463/1507] netfilter: xt_socket: Restore mark from full sockets only An out of bounds error was detected on an ARM64 target with Android based kernel 4.9. This occurs while trying to restore mark on a skb from an inet request socket. BUG: KASAN: slab-out-of-bounds in socket_match.isra.2+0xc8/0x1f0 net/netfilter/xt_socket.c:248 Read of size 4 at addr ffffffc06a8d824c by task syz-fuzzer/1532 CPU: 7 PID: 1532 Comm: syz-fuzzer Tainted: G W O 4.9.41+ #1 Call trace: [] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:76 [] show_stack+0x28/0x38 arch/arm64/kernel/traps.c:226 [] __dump_stack lib/dump_stack.c:15 [inline] [] dump_stack+0xe4/0x134 lib/dump_stack.c:51 [] print_address_description+0x68/0x258 mm/kasan/report.c:248 [] kasan_report_error mm/kasan/report.c:347 [inline] [] kasan_report.part.2+0x228/0x2f0 mm/kasan/report.c:371 [] kasan_report+0x5c/0x70 mm/kasan/report.c:372 [] check_memory_region_inline mm/kasan/kasan.c:308 [inline] [] __asan_load4+0x88/0xa0 mm/kasan/kasan.c:740 [] socket_match.isra.2+0xc8/0x1f0 net/netfilter/xt_socket.c:248 [] socket_mt4_v1_v2_v3+0x3c/0x48 net/netfilter/xt_socket.c:272 [] ipt_do_table+0x54c/0xad8 net/ipv4/netfilter/ip_tables.c:311 [] iptable_mangle_hook+0x6c/0x220 net/ipv4/netfilter/iptable_mangle.c:90 ... Allocated by task 1532: save_stack_trace_tsk+0x0/0x2a0 arch/arm64/kernel/stacktrace.c:131 save_stack_trace+0x28/0x38 arch/arm64/kernel/stacktrace.c:215 save_stack mm/kasan/kasan.c:495 [inline] set_track mm/kasan/kasan.c:507 [inline] kasan_kmalloc+0xd8/0x188 mm/kasan/kasan.c:599 kasan_slab_alloc+0x14/0x20 mm/kasan/kasan.c:537 slab_post_alloc_hook mm/slab.h:417 [inline] slab_alloc_node mm/slub.c:2728 [inline] slab_alloc mm/slub.c:2736 [inline] kmem_cache_alloc+0x14c/0x2e8 mm/slub.c:2741 reqsk_alloc include/net/request_sock.h:87 [inline] inet_reqsk_alloc+0x4c/0x238 net/ipv4/tcp_input.c:6236 tcp_conn_request+0x2b0/0xea8 net/ipv4/tcp_input.c:6341 tcp_v4_conn_request+0xe0/0x100 net/ipv4/tcp_ipv4.c:1256 tcp_rcv_state_process+0x384/0x18a8 net/ipv4/tcp_input.c:5926 tcp_v4_do_rcv+0x2f0/0x3e0 net/ipv4/tcp_ipv4.c:1430 tcp_v4_rcv+0x1278/0x1350 net/ipv4/tcp_ipv4.c:1709 ip_local_deliver_finish+0x174/0x3e0 net/ipv4/ip_input.c:216 v1->v2: Change socket_mt6_v1_v2_v3() as well as mentioned by Eric v2->v3: Put the correct fixes tag Fixes: 01555e74bde5 ("netfilter: xt_socket: add XT_SOCKET_RESTORESKMARK flag") Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index e75ef39669c5a..575d2153e3b81 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -76,7 +76,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) @@ -133,7 +133,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) transparent = nf_sk_is_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && - transparent) + transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; if (sk != skb->sk) -- GitLab From 48596a8ddc46f96afb6a2cd72787cb15d6bb01fc Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 23 Sep 2017 23:37:40 +0200 Subject: [PATCH 0464/1507] netfilter: ipset: Fix adding an IPv4 range containing more than 2^31 addresses Wrong comparison prevented the hash types to add a range with more than 2^31 addresses but reported as a success. Fixes Netfilter's bugzilla id #1005, reported by Oleg Serditov and Oliver Ford. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_hash_ip.c | 22 +++++++++++--------- net/netfilter/ipset/ip_set_hash_ipmark.c | 2 +- net/netfilter/ipset/ip_set_hash_ipport.c | 2 +- net/netfilter/ipset/ip_set_hash_ipportip.c | 2 +- net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 ++-- net/netfilter/ipset/ip_set_hash_net.c | 2 +- net/netfilter/ipset/ip_set_hash_netiface.c | 2 +- net/netfilter/ipset/ip_set_hash_netnet.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netport.c | 2 +- net/netfilter/ipset/ip_set_hash_netportnet.c | 4 ++-- 10 files changed, 24 insertions(+), 22 deletions(-) diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 20bfbd315f618..613eb212cb488 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -123,13 +123,12 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; ip &= ip_set_hostmask(h->netmask); + e.ip = htonl(ip); + if (e.ip == 0) + return -IPSET_ERR_HASH_ELEM; - if (adt == IPSET_TEST) { - e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + if (adt == IPSET_TEST) return adtfn(set, &e, &ext, &ext, flags); - } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { @@ -148,17 +147,20 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); - if (retried) + if (retried) { ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip += hosts) { e.ip = htonl(ip); - if (e.ip == 0) - return -IPSET_ERR_HASH_ELEM; + } + for (; ip <= ip_to;) { ret = adtfn(set, &e, &ext, &ext, flags); - if (ret && !ip_set_eexist(ret, flags)) return ret; + ip += hosts; + e.ip = htonl(ip); + if (e.ip == 0) + return 0; + ret = 0; } return ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index b64cf14e8352f..f3ba8348cf9df 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -149,7 +149,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index f438740e6c6a4..ddb8039ec1d27 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -178,7 +178,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 6215fb898c509..a7f4d7a854209 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -185,7 +185,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5ab1b99a53c2b..a2f19b9906e90 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -271,7 +271,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; !before(ip_to, ip); ip++) { + for (; ip <= ip_to; ip++) { e.ip = htonl(ip); p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; @@ -281,7 +281,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip == ntohl(h->next.ip) && p == ntohs(h->next.port) ? ntohl(h->next.ip2) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip2 = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &cidr); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 5d9e895452e74..1c67a1761e458 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -193,7 +193,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], } if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 44cf11939c916..d417074f1c1a2 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -255,7 +255,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index db614e13b193d..7f9ae2e9645be 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -250,13 +250,13 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); ip2 = (retried && ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 54b64b6cd0cdb..e6ef382febe46 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -241,7 +241,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip = htonl(ip); last = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index aff846960ac44..8602f2595a1a1 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -291,7 +291,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip[0]); - while (!after(ip, ip_to)) { + while (ip <= ip_to) { e.ip[0] = htonl(ip); ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port) @@ -301,7 +301,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip2 = (retried && ip == ntohl(h->next.ip[0]) && p == ntohs(h->next.port)) ? ntohl(h->next.ip[1]) : ip2_from; - while (!after(ip2, ip2_to)) { + while (ip2 <= ip2_to) { e.ip[1] = htonl(ip2); ip2_last = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); -- GitLab From e23ed762db7ed1950a6408c3be80bc56909ab3d4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 11:57:54 +0200 Subject: [PATCH 0465/1507] netfilter: ipset: pernet ops must be unregistered last Removing the ipset module leaves a small window where one cpu performs module removal while another runs a command like 'ipset flush'. ipset uses net_generic(), unregistering the pernet ops frees this storage area. Fix it by first removing the user-visible api handlers and the pernet ops last. Fixes: 1785e8f473082 ("netfiler: ipset: Add net namespace for ipset") Reported-by: Li Shuang Signed-off-by: Florian Westphal Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e495b5e484b11..a7f049ff3049a 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -2072,25 +2072,28 @@ static struct pernet_operations ip_set_net_ops = { static int __init ip_set_init(void) { - int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); + int ret = register_pernet_subsys(&ip_set_net_ops); + if (ret) { + pr_err("ip_set: cannot register pernet_subsys.\n"); + return ret; + } + + ret = nfnetlink_subsys_register(&ip_set_netlink_subsys); if (ret != 0) { pr_err("ip_set: cannot register with nfnetlink.\n"); + unregister_pernet_subsys(&ip_set_net_ops); return ret; } + ret = nf_register_sockopt(&so_set); if (ret != 0) { pr_err("SO_SET registry failed: %d\n", ret); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + unregister_pernet_subsys(&ip_set_net_ops); return ret; } - ret = register_pernet_subsys(&ip_set_net_ops); - if (ret) { - pr_err("ip_set: cannot register pernet_subsys.\n"); - nf_unregister_sockopt(&so_set); - nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - return ret; - } + pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } @@ -2098,9 +2101,10 @@ ip_set_init(void) static void __exit ip_set_fini(void) { - unregister_pernet_subsys(&ip_set_net_ops); nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); + + unregister_pernet_subsys(&ip_set_net_ops); pr_debug("these are the famous last words\n"); } -- GitLab From e0a8f9de16fce34fc2957eca4c71d3ff2ac286d5 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 24 Sep 2017 12:09:42 +0300 Subject: [PATCH 0466/1507] qed: Add iWARP enablement support This patch is the last of the initial iWARP patch series. It adds the possiblity to actually detect iWARP from the device and enable it in the critical locations which basically make iWARP available. It wasn't submitted until now as iWARP hadn't been accepted into the rdma tree. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 6 ++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.c | 8 ++++---- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 5 ++++- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 1 + 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index af106be8cc080..afd07ad916314 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2069,6 +2069,12 @@ static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn, num_srqs = min_t(u32, 32 * 1024, p_params->num_srqs); + if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) { + DP_NOTICE(p_hwfn, + "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n"); + p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE; + } + switch (p_hwfn->hw_info.personality) { case QED_PCI_ETH_IWARP: /* Each QP requires one connection */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 376485d99357d..8b99c7d26f341 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1691,12 +1691,12 @@ qed_mcp_get_shmem_proto_mfw(struct qed_hwfn *p_hwfn, case FW_MB_PARAM_GET_PF_RDMA_ROCE: *p_proto = QED_PCI_ETH_ROCE; break; + case FW_MB_PARAM_GET_PF_RDMA_IWARP: + *p_proto = QED_PCI_ETH_IWARP; + break; case FW_MB_PARAM_GET_PF_RDMA_BOTH: - DP_NOTICE(p_hwfn, - "Current day drivers don't support RoCE & iWARP. Default to RoCE-only\n"); - *p_proto = QED_PCI_ETH_ROCE; + *p_proto = QED_PCI_ETH_RDMA; break; - case FW_MB_PARAM_GET_PF_RDMA_IWARP: default: DP_NOTICE(p_hwfn, "MFW answers GET_PF_RDMA_PROTOCOL but param is %08x\n", diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 6fb99518a61fd..06715f7403efa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -156,7 +156,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, return rc; p_hwfn->p_rdma_info = p_rdma_info; - p_rdma_info->proto = PROTOCOLID_ROCE; + if (QED_IS_IWARP_PERSONALITY(p_hwfn)) + p_rdma_info->proto = PROTOCOLID_IWARP; + else + p_rdma_info->proto = PROTOCOLID_ROCE; num_cons = qed_cxt_get_proto_cid_count(p_hwfn, p_rdma_info->proto, NULL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 46d0c3cb83a56..a1d33f35aad3a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -377,6 +377,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->personality = PERSONALITY_ISCSI; break; case QED_PCI_ETH_ROCE: + case QED_PCI_ETH_IWARP: p_ramrod->personality = PERSONALITY_RDMA_AND_ETH; break; default: -- GitLab From d1abfd0b4ee2b83af88098a0c7105622c3d66e73 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 24 Sep 2017 12:09:43 +0300 Subject: [PATCH 0467/1507] qed: Add iWARP out of order support iWARP requires OOO support which is already provided by the ll2 interface (until now was used only for iSCSI offload). The changes mostly include opening a ll2 dedicated connection for OOO and notifiying the FW about the handle id. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 44 +++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 11 +++++- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 7 +++- 3 files changed, 59 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 9d989c96278c0..568e9853cc8d7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -41,6 +41,7 @@ #include "qed_rdma.h" #include "qed_reg_addr.h" #include "qed_sp.h" +#include "qed_ooo.h" #define QED_IWARP_ORD_DEFAULT 32 #define QED_IWARP_IRD_DEFAULT 32 @@ -119,6 +120,13 @@ static void qed_iwarp_cid_cleaned(struct qed_hwfn *p_hwfn, u32 cid) spin_unlock_bh(&p_hwfn->p_rdma_info->lock); } +void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn, + struct iwarp_init_func_params *p_ramrod) +{ + p_ramrod->ll2_ooo_q_index = RESC_START(p_hwfn, QED_LL2_QUEUE) + + p_hwfn->p_rdma_info->iwarp.ll2_ooo_handle; +} + static int qed_iwarp_alloc_cid(struct qed_hwfn *p_hwfn, u32 *cid) { int rc; @@ -1876,6 +1884,16 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL; } + if (iwarp_info->ll2_ooo_handle != QED_IWARP_HANDLE_INVAL) { + rc = qed_ll2_terminate_connection(p_hwfn, + iwarp_info->ll2_ooo_handle); + if (rc) + DP_INFO(p_hwfn, "Failed to terminate ooo connection\n"); + + qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_ooo_handle); + iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; + } + qed_llh_remove_mac_filter(p_hwfn, p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr); return rc; @@ -1927,10 +1945,12 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; + u16 n_ooo_bufs; int rc = 0; iwarp_info = &p_hwfn->p_rdma_info->iwarp; iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL; + iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; iwarp_info->max_mtu = params->max_mtu; @@ -1978,6 +1998,29 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; + /* Start OOO connection */ + data.input.conn_type = QED_LL2_TYPE_OOO; + data.input.mtu = params->max_mtu; + + n_ooo_bufs = (QED_IWARP_MAX_OOO * QED_IWARP_RCV_WND_SIZE_DEF) / + iwarp_info->max_mtu; + n_ooo_bufs = min_t(u32, n_ooo_bufs, QED_IWARP_LL2_OOO_MAX_RX_SIZE); + + data.input.rx_num_desc = n_ooo_bufs; + data.input.rx_num_ooo_buffers = n_ooo_bufs; + + data.input.tx_max_bds_per_packet = 1; /* will never be fragmented */ + data.input.tx_num_desc = QED_IWARP_LL2_OOO_DEF_TX_SIZE; + data.p_connection_handle = &iwarp_info->ll2_ooo_handle; + + rc = qed_ll2_acquire_connection(p_hwfn, &data); + if (rc) + goto err; + + rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_ooo_handle); + if (rc) + goto err; + return rc; err: qed_iwarp_ll2_stop(p_hwfn, p_ptt); @@ -2014,6 +2057,7 @@ int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, qed_spq_register_async_cb(p_hwfn, PROTOCOLID_IWARP, qed_iwarp_async_event); + qed_ooo_setup(p_hwfn); return qed_iwarp_ll2_start(p_hwfn, params, p_ptt); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 148ef3c33a5dc..9e2bfde894df1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -47,7 +47,12 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_LL2_SYN_TX_SIZE (128) #define QED_IWARP_LL2_SYN_RX_SIZE (256) #define QED_IWARP_MAX_SYN_PKT_SIZE (128) -#define QED_IWARP_HANDLE_INVAL (0xff) + +#define QED_IWARP_LL2_OOO_DEF_TX_SIZE (256) +#define QED_IWARP_MAX_OOO (16) +#define QED_IWARP_LL2_OOO_MAX_RX_SIZE (16384) + +#define QED_IWARP_HANDLE_INVAL (0xff) struct qed_iwarp_ll2_buff { void *data; @@ -67,6 +72,7 @@ struct qed_iwarp_info { u8 crc_needed; u8 tcp_flags; u8 ll2_syn_handle; + u8 ll2_ooo_handle; u8 peer2peer; enum mpa_negotiation_mode mpa_rev; enum mpa_rtr_type rtr_type; @@ -147,6 +153,9 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn); int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_rdma_start_in_params *params); +void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn, + struct iwarp_init_func_params *p_ramrod); + int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 06715f7403efa..4f46f28517804 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -551,10 +551,13 @@ static int qed_rdma_start_fw(struct qed_hwfn *p_hwfn, if (rc) return rc; - if (QED_IS_IWARP_PERSONALITY(p_hwfn)) + if (QED_IS_IWARP_PERSONALITY(p_hwfn)) { + qed_iwarp_init_fw_ramrod(p_hwfn, + &p_ent->ramrod.iwarp_init_func.iwarp); p_ramrod = &p_ent->ramrod.iwarp_init_func.rdma; - else + } else { p_ramrod = &p_ent->ramrod.roce_init_func.rdma; + } p_params_header = &p_ramrod->params_header; p_params_header->cnq_start_offset = (u8)RESC_START(p_hwfn, -- GitLab From 471115ab9804f45cb8e091e426c9c67fe75e41b0 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 24 Sep 2017 12:09:44 +0300 Subject: [PATCH 0468/1507] qed: Fix maximum number of CQs for iWARP The maximum number of CQs supported is bound to the number of connections supported, which differs between RoCE and iWARP. This fixes a crash that occurred in iWARP when running 1000 sessions using perftest. Fixes: 67b40dccc45 ("qed: Implement iWARP initialization, teardown and qp operations") Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 4f46f28517804..c8c4b3940564d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -209,11 +209,11 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, goto free_pd_map; } - /* Allocate bitmap for cq's. The maximum number of CQs is bounded to - * twice the number of QPs. + /* Allocate bitmap for cq's. The maximum number of CQs is bound to + * the number of connections we support. (num_qps in iWARP or + * num_qps/2 in RoCE). */ - rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map, - p_rdma_info->num_qps * 2, "CQ"); + rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->cq_map, num_cons, "CQ"); if (rc) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Failed to allocate cq bitmap, rc = %d\n", rc); @@ -222,10 +222,10 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn, /* Allocate bitmap for toggle bit for cq icids * We toggle the bit every time we create or resize cq for a given icid. - * The maximum number of CQs is bounded to twice the number of QPs. + * Size needs to equal the size of the cq bmap. */ rc = qed_rdma_bmap_alloc(p_hwfn, &p_rdma_info->toggle_bits, - p_rdma_info->num_qps * 2, "Toggle"); + num_cons, "Toggle"); if (rc) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Failed to allocate toogle bits, rc = %d\n", rc); -- GitLab From 1e99c497012cd8647972876f1bd18545bc907aea Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Sun, 24 Sep 2017 12:09:45 +0300 Subject: [PATCH 0469/1507] qed: iWARP - Add check for errors on a SYN packet A SYN packet which arrives with errors from FW should be dropped. This required adding an additional field to the ll2 rx completion data. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 8 ++++++++ drivers/net/ethernet/qlogic/qed/qed_ll2.c | 1 + include/linux/qed/qed_ll2_if.h | 1 + 3 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 568e9853cc8d7..8fc9c811f6e32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1733,6 +1733,14 @@ qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) memset(&cm_info, 0, sizeof(cm_info)); ll2_syn_handle = p_hwfn->p_rdma_info->iwarp.ll2_syn_handle; + + /* Check if packet was received with errors... */ + if (data->err_flags) { + DP_NOTICE(p_hwfn, "Error received on SYN packet: 0x%x\n", + data->err_flags); + goto err; + } + if (GET_FIELD(data->parse_flags, PARSING_AND_ERR_FLAGS_L4CHKSMWASCALCULATED) && GET_FIELD(data->parse_flags, PARSING_AND_ERR_FLAGS_L4CHKSMERROR)) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index c06ad4f0758eb..250afa5486cfa 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -413,6 +413,7 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn, struct qed_ll2_comp_rx_data *data) { data->parse_flags = le16_to_cpu(p_cqe->rx_cqe_fp.parse_flags.flags); + data->err_flags = le16_to_cpu(p_cqe->rx_cqe_fp.err_flags.flags); data->length.packet_length = le16_to_cpu(p_cqe->rx_cqe_fp.packet_length); data->vlan = le16_to_cpu(p_cqe->rx_cqe_fp.vlan); diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index dd7a3b86bb9e5..89fa0bbd54f32 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -101,6 +101,7 @@ struct qed_ll2_comp_rx_data { void *cookie; dma_addr_t rx_buf_addr; u16 parse_flags; + u16 err_flags; u16 vlan; bool b_last_packet; u8 connection_handle; -- GitLab From 3bd3b9ed1b602c065aa0b1ba109b9622afa6ff98 Mon Sep 17 00:00:00 2001 From: Himanshu Jha Date: Sun, 24 Sep 2017 17:41:24 +0530 Subject: [PATCH 0470/1507] net: bcm63xx_enet: Use setup_timer and mod_timer Use setup_timer and mod_timer API instead of structure assignments. This is done using Coccinelle and semantic patch used for this as follows: @@ expression x,y,z,a,b; @@ -init_timer (&x); +setup_timer (&x, y, z); +mod_timer (&a, b); -x.function = y; -x.data = z; -x.expires = b; -add_timer(&a); Signed-off-by: Himanshu Jha Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index f8bbbbfca06e0..c6221f04a7486 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -2331,11 +2331,8 @@ static int bcm_enetsw_open(struct net_device *dev) } /* start phy polling timer */ - init_timer(&priv->swphy_poll); - priv->swphy_poll.function = swphy_poll_timer; - priv->swphy_poll.data = (unsigned long)priv; - priv->swphy_poll.expires = jiffies; - add_timer(&priv->swphy_poll); + setup_timer(&priv->swphy_poll, swphy_poll_timer, (unsigned long)priv); + mod_timer(&priv->swphy_poll, jiffies); return 0; out: -- GitLab From 6aaae2b6c4330a46204bca042f1d2f41e8e18dea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:50 +0200 Subject: [PATCH 0471/1507] bpf: rename bpf_compute_data_end into bpf_compute_data_pointers Just do the rename into bpf_compute_data_pointers() as we'll add one more pointer here to recompute. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/filter.h | 9 ++++++--- kernel/bpf/sockmap.c | 4 ++-- net/bpf/test_run.c | 2 +- net/core/filter.c | 14 +++++++------- net/core/lwt_bpf.c | 2 +- net/sched/act_bpf.c | 4 ++-- net/sched/cls_bpf.c | 4 ++-- 7 files changed, 21 insertions(+), 18 deletions(-) diff --git a/include/linux/filter.h b/include/linux/filter.h index d29e58fde364f..052bab3d62e72 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -496,10 +496,13 @@ struct xdp_buff { void *data_hard_start; }; -/* compute the linear packet data range [data, data_end) which - * will be accessed by cls_bpf, act_bpf and lwt programs +/* Compute the linear packet data range [data, data_end) which + * will be accessed by various program types (cls_bpf, act_bpf, + * lwt, ...). Subsystems allowing direct data access must (!) + * ensure that cb[] area can be written to when BPF program is + * invoked (otherwise cb[] save/restore is necessary). */ -static inline void bpf_compute_data_end(struct sk_buff *skb) +static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e49698..a298d66666981 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -102,7 +102,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) skb_orphan(skb); skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; @@ -369,7 +369,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6be41a44d688a..df672517b4fdb 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -133,7 +133,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, if (is_l2) __skb_push(skb, ETH_HLEN); if (is_direct_pkt_access) - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); retval = bpf_test_run(prog, skb, repeat, &duration); if (!is_l2) __skb_push(skb, ETH_HLEN); diff --git a/net/core/filter.c b/net/core/filter.c index 82edad58d0668..c468e7cfad195 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1402,7 +1402,7 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, { int err = __bpf_try_make_writable(skb, write_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return err; } @@ -1962,7 +1962,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -1984,7 +1984,7 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2178,7 +2178,7 @@ BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2303,7 +2303,7 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) : bpf_skb_net_grow(skb, len_diff_abs); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2394,7 +2394,7 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, skb_gso_reset(skb); } - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return ret; } @@ -2434,7 +2434,7 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 1307731ddfe4a..e7e626fb87bb3 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -51,7 +51,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, */ preempt_disable(); rcu_read_lock(); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); rcu_read_unlock(); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index c0c707eb2c962..5ef8ce8c83d4e 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -49,11 +49,11 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); } rcu_read_unlock(); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 520c5027646ae..36671b0fb1253 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -99,11 +99,11 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(prog->filter, skb); } -- GitLab From de8f3a83b0a0fddb2cf56e7a718127e9619ea3da Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:51 +0200 Subject: [PATCH 0472/1507] bpf: add meta pointer for direct access This work enables generic transfer of metadata from XDP into skb. The basic idea is that we can make use of the fact that the resulting skb must be linear and already comes with a larger headroom for supporting bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work on a similar principle and introduce a small helper bpf_xdp_adjust_meta() for adjusting a new pointer called xdp->data_meta. Thus, the packet has a flexible and programmable room for meta data, followed by the actual packet data. struct xdp_buff is therefore laid out that we first point to data_hard_start, then data_meta directly prepended to data followed by data_end marking the end of packet. bpf_xdp_adjust_head() takes into account whether we have meta data already prepended and if so, memmove()s this along with the given offset provided there's enough room. xdp->data_meta is optional and programs are not required to use it. The rationale is that when we process the packet in XDP (e.g. as DoS filter), we can push further meta data along with it for the XDP_PASS case, and give the guarantee that a clsact ingress BPF program on the same device can pick this up for further post-processing. Since we work with skb there, we can also set skb->mark, skb->priority or other skb meta data out of BPF, thus having this scratch space generic and programmable allows for more flexibility than defining a direct 1:1 transfer of potentially new XDP members into skb (it's also more efficient as we don't need to initialize/handle each of such new members). The facility also works together with GRO aggregation. The scratch space at the head of the packet can be multiple of 4 byte up to 32 byte large. Drivers not yet supporting xdp->data_meta can simply be set up with xdp->data_meta as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out, such that the subsequent match against xdp->data for later access is guaranteed to fail. The verifier treats xdp->data_meta/xdp->data the same way as we treat xdp->data/xdp->data_end pointer comparisons. The requirement for doing the compare against xdp->data is that it hasn't been modified from it's original address we got from ctx access. It may have a range marking already from prior successful xdp->data/xdp->data_end pointer comparisons though. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 + .../net/ethernet/cavium/thunder/nicvf_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 + .../net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + .../ethernet/netronome/nfp/nfp_net_common.c | 1 + drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 + drivers/net/tun.c | 1 + drivers/net/virtio_net.c | 2 + include/linux/bpf.h | 1 + include/linux/filter.h | 21 +++- include/linux/skbuff.h | 68 ++++++++++- include/uapi/linux/bpf.h | 13 +- kernel/bpf/verifier.c | 114 +++++++++++++----- net/bpf/test_run.c | 1 + net/core/dev.c | 31 ++++- net/core/filter.c | 77 +++++++++++- net/core/skbuff.c | 2 + 19 files changed, 297 insertions(+), 42 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index d8f0c837b72cf..06ce63c00821b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp.data_hard_start = *data_ptr - offset; xdp.data = *data_ptr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = *data_ptr + *len; orig_data = xdp.data; mapping = rx_buf->mapping - bp->rx_dma_offset; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da51ba73..d68478afccbf5 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp.data_hard_start = page_address(page); xdp.data = (void *)cpu_addr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1519dfb851d01..f426762bd83a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2107,6 +2107,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - i40e_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368d08d0f..04bb03bda1cd7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2326,6 +2326,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b97a55c827ebc..8f9cb8abc4970 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -762,6 +762,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp.data_hard_start = va - frags[0].page_offset; xdp.data = va; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + length; orig_data = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638384d38..30b3f3fbd7199 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -794,6 +794,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, return false; xdp.data = va + *rx_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 1c0187f0af51f..e3a38be3600af 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1583,6 +1583,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, xdp.data_hard_start = hard_start; xdp.data = data + *off; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = data + *off + *len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 6fc854b120b03..48ec4c56cddf0 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp.data_hard_start = page_address(bd->data); xdp.data = xdp.data_hard_start + *data_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; /* Queues always have a full reset currently, so for the time diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2c36f6ebad792..a6e0bffe3d293 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1468,6 +1468,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp.data_hard_start = buf; xdp.data = buf + pad; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index dd14a45479321..fc059f193e7dc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -554,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len; xdp.data = xdp.data_hard_start + xdp_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); @@ -686,6 +687,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, data = page_address(xdp_page) + offset; xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len; xdp.data = data + vi->hdr_len; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + (len - vi->hdr_len); act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e70..2b672c50f160e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -137,6 +137,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 052bab3d62e72..911d454af1078 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -487,12 +487,14 @@ struct sk_filter { struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; @@ -507,7 +509,8 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -728,8 +731,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9db5539a6fb2..19e64bfb1a669 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -3400,6 +3401,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98f..e43491ac48237 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -582,6 +582,12 @@ union bpf_attr { * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -638,6 +644,7 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ + FN(xdp_adjust_meta), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -715,7 +722,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ __u32 family; __u32 remote_ip4; /* Stored in network byte order */ __u32 local_ip4; /* Stored in network byte order */ @@ -723,6 +730,9 @@ struct __sk_buff { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; }; struct bpf_tunnel_key { @@ -783,6 +793,7 @@ enum xdp_action { struct xdp_md { __u32 data; __u32 data_end; + __u32 data_meta; }; enum sk_action { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e8..f849eca36052c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -519,6 +526,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +734,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1080,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1160,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1206,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1346,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1379,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1388,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1440,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1456,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1629,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1639,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1967,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2457,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2520,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2528,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2893,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -3298,8 +3355,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != PTR_TO_PACKET) + if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index df672517b4fdb..a86e6687026ee 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; retval = bpf_test_run(prog, &xdp, repeat, &duration); diff --git a/net/core/dev.c b/net/core/dev.c index 97abddd9039a1..e350c768d4b5a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3864,8 +3864,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + u32 metalen, act = XDP_DROP; struct xdp_buff xdp; - u32 act = XDP_DROP; void *orig_data; int hlen, off; u32 mac_len; @@ -3876,8 +3876,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_cloned(skb)) return XDP_PASS; - if (skb_linearize(skb)) - goto do_drop; + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (troom > 0 && __skb_linearize(skb)) + goto do_drop; + } /* The XDP program wants to see the packet starting at the MAC * header. @@ -3885,6 +3902,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; xdp.data = skb->data - mac_len; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + hlen; xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data; @@ -3902,10 +3920,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); - /* fall through */ + break; case XDP_PASS: + metalen = xdp.data - xdp.data_meta; + if (metalen) + skb_metadata_set(skb, metalen); break; - default: bpf_warn_invalid_xdp_action(act); /* fall through */ @@ -4695,6 +4715,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); diff --git a/net/core/filter.c b/net/core/filter.c index c468e7cfad195..9b6e7e84aafda 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2447,14 +2447,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) +{ + return xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; +} + BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + unsigned long metalen = xdp_get_metalen(xdp); + void *data_start = xdp->data_hard_start + metalen; void *data = xdp->data + offset; - if (unlikely(data < xdp->data_hard_start || + if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; + if (metalen) + memmove(xdp->data_meta + offset, + xdp->data_meta, metalen); + xdp->data_meta += offset; xdp->data = data; return 0; @@ -2468,6 +2480,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) +{ + void *meta = xdp->data_meta + offset; + unsigned long metalen = xdp->data - meta; + + if (xdp_data_meta_unsupported(xdp)) + return -ENOTSUPP; + if (unlikely(meta < xdp->data_hard_start || + meta > xdp->data)) + return -EINVAL; + if (unlikely((metalen & (sizeof(__u32) - 1)) || + (metalen > 32))) + return -EACCES; + + xdp->data_meta = meta; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { + .func = bpf_xdp_adjust_meta, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static int __bpf_tx_xdp(struct net_device *dev, struct bpf_map *map, struct xdp_buff *xdp, @@ -2692,7 +2731,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head) + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta) return true; return false; @@ -3288,6 +3328,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; + case BPF_FUNC_xdp_adjust_meta: + return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: @@ -3418,6 +3460,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; @@ -3444,6 +3487,7 @@ static bool sk_filter_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; @@ -3468,6 +3512,7 @@ static bool lwt_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, data_meta): return false; } @@ -3586,6 +3631,9 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; + case bpf_ctx_range(struct __sk_buff, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3619,6 +3667,9 @@ static bool xdp_is_valid_access(int off, int size, case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; + case offsetof(struct xdp_md, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3677,6 +3728,12 @@ static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + return false; + } + if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): @@ -3689,8 +3746,6 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { - case bpf_ctx_range(struct __sk_buff, tc_classid): - return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; @@ -3847,6 +3902,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_buff, data)); break; + case offsetof(struct __sk_buff, data_meta): + off = si->off; + off -= offsetof(struct __sk_buff, data_meta); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_meta); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); @@ -4095,6 +4159,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; + case offsetof(struct xdp_md, data_meta): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, data_meta)); + break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 000ce735fa8d6..d98c2e3ce2bfd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + skb_metadata_clear(skb); + /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). -- GitLab From ac29991ba137cc0e3b0f647fb41e79300230f15c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:52 +0200 Subject: [PATCH 0473/1507] bpf: update bpf.h uapi header for tools Looks like a couple of updates missed to get carried into tools/include/uapi/, so copy the bpf.h header as usual to pull in latest updates. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- tools/include/uapi/linux/bpf.h | 45 ++++++++++++++++++++++++---------- 1 file changed, 32 insertions(+), 13 deletions(-) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 461811e571409..e43491ac48237 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -143,12 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -enum bpf_sockmap_flags { - BPF_SOCKMAP_UNSPEC, - BPF_SOCKMAP_STRPARSER, - __MAX_BPF_SOCKMAP_FLAG -}; - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -368,9 +362,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -577,6 +582,12 @@ union bpf_attr { * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -632,7 +643,8 @@ union bpf_attr { FN(skb_adjust_room), \ FN(redirect_map), \ FN(sk_redirect_map), \ - FN(sock_map_update), + FN(sock_map_update), \ + FN(xdp_adjust_meta), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -710,7 +722,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ __u32 family; __u32 remote_ip4; /* Stored in network byte order */ __u32 local_ip4; /* Stored in network byte order */ @@ -718,6 +730,9 @@ struct __sk_buff { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; }; struct bpf_tunnel_key { @@ -753,20 +768,23 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook @@ -775,6 +793,7 @@ enum xdp_action { struct xdp_md { __u32 data; __u32 data_end; + __u32 data_meta; }; enum sk_action { -- GitLab From 22c8852624fc90a90709d1237625ca57999c5092 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:53 +0200 Subject: [PATCH 0474/1507] bpf: improve selftests and add tests for meta pointer Add various test_verifier selftests, and a simple xdp/tc functional test that is being attached to veths. Also let new versions of clang use the recently added -mcpu=probe support [1] for the BPF target, so that it can probe the underlying kernel for BPF insn set extensions. We could also just set this options always, where older versions just ignore it and give a note to the user that the -mcpu value is not supported, but given emitting the note cannot be turned off from clang side lets not confuse users running selftests with it, thus fallback to the default generic one when we see that clang doesn't support it. Also allow CPU option to be overridden in the Makefile from command line. [1] https://github.com/llvm-mirror/llvm/commit/d7276a40d87b89aed89978dec6457a5b8b3a0db5 Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/Makefile | 21 +- tools/testing/selftests/bpf/bpf_helpers.h | 2 + tools/testing/selftests/bpf/test_verifier.c | 247 +++++++++++++++++++ tools/testing/selftests/bpf/test_xdp_meta.c | 53 ++++ tools/testing/selftests/bpf/test_xdp_meta.sh | 51 ++++ 5 files changed, 370 insertions(+), 4 deletions(-) create mode 100644 tools/testing/selftests/bpf/test_xdp_meta.c create mode 100755 tools/testing/selftests/bpf/test_xdp_meta.sh diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f4b23d6974486..924af8d79bded 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -15,9 +15,10 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ - test_pkt_md_access.o test_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.o + test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ + sockmap_verdict_prog.o -TEST_PROGS := test_kmod.sh test_xdp_redirect.sh +TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh include ../lib.mk @@ -34,8 +35,20 @@ $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ CLANG ?= clang +LLC ?= llc + +PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) + +# Let newer LLVM versions transparently probe the kernel for availability +# of full BPF instruction set. +ifeq ($(PROBE),) + CPU ?= probe +else + CPU ?= generic +endif %.o: %.c $(CLANG) -I. -I./include/uapi -I../../../include/uapi \ - -Wno-compare-distinct-pointer-types \ - -O2 -target bpf -c $< -o $@ + -Wno-compare-distinct-pointer-types \ + -O2 -target bpf -emit-llvm -c $< -o - | \ + $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 4875395b0b52e..a56053db26f54 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -62,6 +62,8 @@ static unsigned long long (*bpf_get_prandom_u32)(void) = (void *) BPF_FUNC_get_prandom_u32; static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = (void *) BPF_FUNC_xdp_adjust_head; +static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_meta; static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 26f3250bdcd25..a0426147523d9 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6645,6 +6645,253 @@ static struct bpf_test tests[] = { .errstr = "BPF_END uses reserved fields", .result = REJECT, }, + { + "meta access, test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet, off=-8", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test5", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3), + BPF_MOV64_IMM(BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_xdp_adjust_meta), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R3 !read_ok", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test7", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test8", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test9", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test10", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_IMM(BPF_REG_5, 42), + BPF_MOV64_IMM(BPF_REG_6, 24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test11", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_MOV64_IMM(BPF_REG_5, 42), + BPF_MOV64_IMM(BPF_REG_6, 24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8), + BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "meta access, test12", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c new file mode 100644 index 0000000000000..8d01826506530 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_meta.c @@ -0,0 +1,53 @@ +#include +#include +#include + +#include "bpf_helpers.h" + +#define __round_mask(x, y) ((__typeof__(x))((y) - 1)) +#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) +#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem + +SEC("t") +int ing_cls(struct __sk_buff *ctx) +{ + __u8 *data, *data_meta, *data_end; + __u32 diff = 0; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return TC_ACT_SHOT; + + diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0]; + diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2]; + + return diff ? TC_ACT_SHOT : TC_ACT_OK; +} + +SEC("x") +int ing_xdp(struct xdp_md *ctx) +{ + __u8 *data, *data_meta, *data_end; + int ret; + + ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4)); + if (ret < 0) + return XDP_DROP; + + data_meta = ctx_ptr(ctx, data_meta); + data_end = ctx_ptr(ctx, data_end); + data = ctx_ptr(ctx, data); + + if (data + ETH_ALEN > data_end || + data_meta + round_up(ETH_ALEN, 4) > data) + return XDP_DROP; + + __builtin_memcpy(data_meta, data, ETH_ALEN); + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh new file mode 100755 index 0000000000000..307aa856cee3e --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -0,0 +1,51 @@ +#!/bin/sh + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_xdp_meta [PASS]"; + else + echo "selftests: test_xdp_meta [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null +} + +ip link set dev lo xdp off 2>/dev/null > /dev/null +if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without the ip xdp support" + exit 0 +fi +set -e + +ip netns add ns1 +ip netns add ns2 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 type veth peer name veth2 + +ip link set veth1 netns ns1 +ip link set veth2 netns ns2 + +ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1 +ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2 + +ip netns exec ns1 tc qdisc add dev veth1 clsact +ip netns exec ns2 tc qdisc add dev veth2 clsact + +ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t + +ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x +ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x + +ip netns exec ns1 ip link set dev veth1 up +ip netns exec ns2 ip link set dev veth2 up + +ip netns exec ns1 ping -c 1 10.1.1.22 +ip netns exec ns2 ping -c 1 10.1.1.11 + +exit 0 -- GitLab From 65d88fd0baaa5c9def9383ac696097911d4ceb73 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:54 +0200 Subject: [PATCH 0475/1507] bpf, nfp: add meta data support Implement support for transferring XDP meta data into skb for nfp driver; before calling into the program, xdp.data_meta points to xdp.data, where on program return with pass verdict, we call into skb_metadata_set(). Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/nfp_net_common.c | 40 +++++++------------ 1 file changed, 15 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index e3a38be3600af..d2f73feb84979 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1574,27 +1574,6 @@ nfp_net_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, return true; } -static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, - unsigned int *off, unsigned int *len) -{ - struct xdp_buff xdp; - void *orig_data; - int ret; - - xdp.data_hard_start = hard_start; - xdp.data = data + *off; - xdp_set_data_meta_invalid(&xdp); - xdp.data_end = data + *off + *len; - - orig_data = xdp.data; - ret = bpf_prog_run_xdp(prog, &xdp); - - *len -= xdp.data - orig_data; - *off += xdp.data - orig_data; - - return ret; -} - /** * nfp_net_rx() - receive up to @budget packets on @rx_ring * @rx_ring: RX ring to receive from @@ -1630,6 +1609,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) struct nfp_meta_parsed meta; struct net_device *netdev; dma_addr_t new_dma_addr; + u32 meta_len_xdp = 0; void *new_frag; idx = D_IDX(rx_ring, rx_ring->rd_p); @@ -1708,16 +1688,24 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF && dp->bpf_offload_xdp) && !meta.portid) { + void *orig_data = rxbuf->frag + pkt_off; unsigned int dma_off; - void *hard_start; + struct xdp_buff xdp; int act; - hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM; + xdp.data_hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM; + xdp.data = orig_data; + xdp.data_meta = orig_data; + xdp.data_end = orig_data + pkt_len; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + + pkt_len -= xdp.data - orig_data; + pkt_off += xdp.data - orig_data; - act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start, - &pkt_off, &pkt_len); switch (act) { case XDP_PASS: + meta_len_xdp = xdp.data - xdp.data_meta; break; case XDP_TX: dma_off = pkt_off - NFP_NET_RX_BUF_HEADROOM; @@ -1785,6 +1773,8 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) if (rxd->rxd.flags & PCIE_DESC_RX_VLAN) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), le16_to_cpu(rxd->rxd.vlan)); + if (meta_len_xdp) + skb_metadata_set(skb, meta_len_xdp); napi_gro_receive(&rx_ring->r_vec->napi, skb); } -- GitLab From 366a88fe2f40d6772985ec78cdd34df7f109bb88 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:55 +0200 Subject: [PATCH 0476/1507] bpf, ixgbe: add meta data support Implement support for transferring XDP meta data into skb for ixgbe driver; before calling into the program, xdp.data_meta points to xdp.data, where on program return with pass verdict, we call into skb_metadata_set(). We implement this for the default ixgbe_build_skb() variant. For the ixgbe_construct_skb() that is used when legacy-rx buffer mananagement mode is turned on via ethtool, I found that XDP gets 0 headroom, so neither xdp_adjust_head() nor xdp_adjust_meta() can be used with this. Just add a comment with explanation for this operating mode. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 30 ++++++++++++++++--- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 04bb03bda1cd7..3942c6208745c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2133,6 +2133,21 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, #if L1_CACHE_BYTES < 128 prefetch(xdp->data + L1_CACHE_BYTES); #endif + /* Note, we get here by enabling legacy-rx via: + * + * ethtool --set-priv-flags legacy-rx on + * + * In this mode, we currently get 0 extra XDP headroom as + * opposed to having legacy-rx off, where we process XDP + * packets going to stack via ixgbe_build_skb(). The latter + * provides us currently with 192 bytes of headroom. + * + * For ixgbe_construct_skb() mode it means that the + * xdp->data_meta will always point to xdp->data, since + * the helper cannot expand the head. Should this ever + * change in future for legacy-rx mode on, then lets also + * add xdp->data_meta handling here. + */ /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE); @@ -2165,6 +2180,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, struct xdp_buff *xdp, union ixgbe_adv_rx_desc *rx_desc) { + unsigned int metasize = xdp->data - xdp->data_meta; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else @@ -2174,10 +2190,14 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, #endif struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(xdp->data); + /* Prefetch first cache line of first page. If xdp->data_meta + * is unused, this points extactly as xdp->data, otherwise we + * likely have a consumer accessing first few bytes of meta + * data, and then actual data. + */ + prefetch(xdp->data_meta); #if L1_CACHE_BYTES < 128 - prefetch(xdp->data + L1_CACHE_BYTES); + prefetch(xdp->data_meta + L1_CACHE_BYTES); #endif /* build an skb to around the page buffer */ @@ -2188,6 +2208,8 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, /* update pointers within the skb to store the data */ skb_reserve(skb, xdp->data - xdp->data_hard_start); __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); /* record DMA address if this is the start of a chain of buffers */ if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) @@ -2326,7 +2348,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; - xdp_set_data_meta_invalid(&xdp); + xdp.data_meta = xdp.data; xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; -- GitLab From d85fc17beeb06f9979d63fe4d9fbffbb1a00bba4 Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Mon, 25 Sep 2017 10:48:47 +0300 Subject: [PATCH 0477/1507] aquantia: Setup max_mtu in ndev to enable jumbo frames Although hardware is capable for almost 16K MTU, without max_mtu field correctly set it only allows standard MTU to be used. This patch enables max MTU, calculating it from hardware maximum frame size of 16352 octets (including FCS). Fixes: 5513e16421cb ("net: ethernet: aquantia: Fixes for aq_ndev_change_mtu") Signed-off-by: Pavel Belous Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 11 ++--------- .../aquantia/atlantic/hw_atl/hw_atl_b0_internal.h | 2 +- 2 files changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 6ac9e2602d6d8..bf26a59a9d8e2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -214,7 +214,6 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, SET_NETDEV_DEV(ndev, dev); ndev->if_port = port; - ndev->min_mtu = ETH_MIN_MTU; self->ndev = ndev; self->aq_pci_func = aq_pci_func; @@ -283,6 +282,7 @@ int aq_nic_ndev_init(struct aq_nic_s *self) self->ndev->features = aq_hw_caps->hw_features; self->ndev->priv_flags = aq_hw_caps->hw_priv_flags; self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN; + self->ndev->max_mtu = self->aq_hw_caps.mtu - ETH_FCS_LEN - ETH_HLEN; return 0; } @@ -693,16 +693,9 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu) { - int err = 0; - - if (new_mtu > self->aq_hw_caps.mtu) { - err = -EINVAL; - goto err_exit; - } self->aq_nic_cfg.mtu = new_mtu; -err_exit: - return err; + return 0; } int aq_nic_set_mac(struct aq_nic_s *self, struct net_device *ndev) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h index f3957e9303405..fcf89e25a773e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h @@ -16,7 +16,7 @@ #include "../aq_common.h" -#define HW_ATL_B0_MTU_JUMBO (16000U) +#define HW_ATL_B0_MTU_JUMBO 16352U #define HW_ATL_B0_MTU 1514U #define HW_ATL_B0_TX_RINGS 4U -- GitLab From 3aec6412e007b294d4c135f5c7ed5e5ecf37dd2e Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Mon, 25 Sep 2017 10:48:48 +0300 Subject: [PATCH 0478/1507] aquantia: Fix Tx queue hangups Driver did a poor job in managing its Tx queues: Sometimes it could stop tx queues due to link down condition in aq_nic_xmit - but never waked up them. That led to Tx path total suspend. This patch fixes this and improves generic queue management: - introduces queue restart counter - uses generic netif_ interface to disable and enable tx path - refactors link up/down condition and introduces dmesg log event when link changes. - introduces new constant for minimum descriptors count required for queue wakeup Signed-off-by: Pavel Belous Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- .../net/ethernet/aquantia/atlantic/aq_cfg.h | 4 + .../net/ethernet/aquantia/atlantic/aq_nic.c | 91 ++++++++----------- .../net/ethernet/aquantia/atlantic/aq_nic.h | 2 - .../net/ethernet/aquantia/atlantic/aq_ring.c | 26 ++++++ .../net/ethernet/aquantia/atlantic/aq_ring.h | 4 + .../net/ethernet/aquantia/atlantic/aq_vec.c | 8 +- 6 files changed, 76 insertions(+), 59 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index 214986436ece5..0fdaaa643073a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -51,6 +51,10 @@ #define AQ_CFG_SKB_FRAGS_MAX 32U +/* Number of descriptors available in one ring to resume this ring queue + */ +#define AQ_CFG_RESTART_DESC_THRES (AQ_CFG_SKB_FRAGS_MAX * 2) + #define AQ_CFG_NAPI_WEIGHT 64U #define AQ_CFG_MULTICAST_ADDRESS_MAX 32U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index bf26a59a9d8e2..072a55029f047 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -119,6 +119,35 @@ int aq_nic_cfg_start(struct aq_nic_s *self) return 0; } +static int aq_nic_update_link_status(struct aq_nic_s *self) +{ + int err = self->aq_hw_ops.hw_get_link_status(self->aq_hw); + + if (err) + return err; + + if (self->link_status.mbps != self->aq_hw->aq_link_status.mbps) + pr_info("%s: link change old %d new %d\n", + AQ_CFG_DRV_NAME, self->link_status.mbps, + self->aq_hw->aq_link_status.mbps); + + self->link_status = self->aq_hw->aq_link_status; + if (!netif_carrier_ok(self->ndev) && self->link_status.mbps) { + aq_utils_obj_set(&self->header.flags, + AQ_NIC_FLAG_STARTED); + aq_utils_obj_clear(&self->header.flags, + AQ_NIC_LINK_DOWN); + netif_carrier_on(self->ndev); + netif_tx_wake_all_queues(self->ndev); + } + if (netif_carrier_ok(self->ndev) && !self->link_status.mbps) { + netif_carrier_off(self->ndev); + netif_tx_disable(self->ndev); + aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); + } + return 0; +} + static void aq_nic_service_timer_cb(unsigned long param) { struct aq_nic_s *self = (struct aq_nic_s *)param; @@ -131,26 +160,13 @@ static void aq_nic_service_timer_cb(unsigned long param) if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY)) goto err_exit; - err = self->aq_hw_ops.hw_get_link_status(self->aq_hw); - if (err < 0) + err = aq_nic_update_link_status(self); + if (err) goto err_exit; - self->link_status = self->aq_hw->aq_link_status; - self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, self->aq_nic_cfg.is_interrupt_moderation); - if (self->link_status.mbps) { - aq_utils_obj_set(&self->header.flags, - AQ_NIC_FLAG_STARTED); - aq_utils_obj_clear(&self->header.flags, - AQ_NIC_LINK_DOWN); - netif_carrier_on(self->ndev); - } else { - netif_carrier_off(self->ndev); - aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); - } - memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s)); memset(&stats_tx, 0U, sizeof(struct aq_ring_stats_tx_s)); for (i = AQ_DIMOF(self->aq_vec); i--;) { @@ -240,7 +256,6 @@ struct aq_nic_s *aq_nic_alloc_cold(const struct net_device_ops *ndev_ops, int aq_nic_ndev_register(struct aq_nic_s *self) { int err = 0; - unsigned int i = 0U; if (!self->ndev) { err = -EINVAL; @@ -262,8 +277,7 @@ int aq_nic_ndev_register(struct aq_nic_s *self) netif_carrier_off(self->ndev); - for (i = AQ_CFG_VECS_MAX; i--;) - aq_nic_ndev_queue_stop(self, i); + netif_tx_disable(self->ndev); err = register_netdev(self->ndev); if (err < 0) @@ -318,12 +332,8 @@ struct aq_nic_s *aq_nic_alloc_hot(struct net_device *ndev) err = -EINVAL; goto err_exit; } - if (netif_running(ndev)) { - unsigned int i; - - for (i = AQ_CFG_VECS_MAX; i--;) - netif_stop_subqueue(ndev, i); - } + if (netif_running(ndev)) + netif_tx_disable(ndev); for (self->aq_vecs = 0; self->aq_vecs < self->aq_nic_cfg.vecs; self->aq_vecs++) { @@ -383,16 +393,6 @@ int aq_nic_init(struct aq_nic_s *self) return err; } -void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx) -{ - netif_start_subqueue(self->ndev, idx); -} - -void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx) -{ - netif_stop_subqueue(self->ndev, idx); -} - int aq_nic_start(struct aq_nic_s *self) { struct aq_vec_s *aq_vec = NULL; @@ -451,10 +451,6 @@ int aq_nic_start(struct aq_nic_s *self) goto err_exit; } - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_nic_ndev_queue_start(self, i); - err = netif_set_real_num_tx_queues(self->ndev, self->aq_vecs); if (err < 0) goto err_exit; @@ -463,6 +459,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; + netif_tx_start_all_queues(self->ndev); + err_exit: return err; } @@ -602,7 +600,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs; unsigned int tc = 0U; int err = NETDEV_TX_OK; - bool is_nic_in_bad_state; frags = skb_shinfo(skb)->nr_frags + 1; @@ -613,13 +610,10 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) goto err_exit; } - is_nic_in_bad_state = aq_utils_obj_test(&self->header.flags, - AQ_NIC_FLAGS_IS_NOT_TX_READY) || - (aq_ring_avail_dx(ring) < - AQ_CFG_SKB_FRAGS_MAX); + aq_ring_update_queue_state(ring); - if (is_nic_in_bad_state) { - aq_nic_ndev_queue_stop(self, ring->idx); + /* Above status update may stop the queue. Check this. */ + if (__netif_subqueue_stopped(self->ndev, ring->idx)) { err = NETDEV_TX_BUSY; goto err_exit; } @@ -631,9 +625,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) ring, frags); if (err >= 0) { - if (aq_ring_avail_dx(ring) < AQ_CFG_SKB_FRAGS_MAX + 1) - aq_nic_ndev_queue_stop(self, ring->idx); - ++ring->stats.tx.packets; ring->stats.tx.bytes += skb->len; } @@ -898,9 +889,7 @@ int aq_nic_stop(struct aq_nic_s *self) struct aq_vec_s *aq_vec = NULL; unsigned int i = 0U; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_nic_ndev_queue_stop(self, i); + netif_tx_disable(self->ndev); del_timer_sync(&self->service_timer); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 7fc2a5ecb2b7a..0ddd556ff901c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -83,8 +83,6 @@ struct net_device *aq_nic_get_ndev(struct aq_nic_s *self); int aq_nic_init(struct aq_nic_s *self); int aq_nic_cfg_start(struct aq_nic_s *self); int aq_nic_ndev_register(struct aq_nic_s *self); -void aq_nic_ndev_queue_start(struct aq_nic_s *self, unsigned int idx); -void aq_nic_ndev_queue_stop(struct aq_nic_s *self, unsigned int idx); void aq_nic_ndev_free(struct aq_nic_s *self); int aq_nic_start(struct aq_nic_s *self); int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4eee1996a8259..02f79b0640bae 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -104,6 +104,32 @@ int aq_ring_init(struct aq_ring_s *self) return 0; } +void aq_ring_update_queue_state(struct aq_ring_s *ring) +{ + if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX) + aq_ring_queue_stop(ring); + else if (aq_ring_avail_dx(ring) > AQ_CFG_RESTART_DESC_THRES) + aq_ring_queue_wake(ring); +} + +void aq_ring_queue_wake(struct aq_ring_s *ring) +{ + struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic); + + if (__netif_subqueue_stopped(ndev, ring->idx)) { + netif_wake_subqueue(ndev, ring->idx); + ring->stats.tx.queue_restarts++; + } +} + +void aq_ring_queue_stop(struct aq_ring_s *ring) +{ + struct net_device *ndev = aq_nic_get_ndev(ring->aq_nic); + + if (!__netif_subqueue_stopped(ndev, ring->idx)) + netif_stop_subqueue(ndev, ring->idx); +} + void aq_ring_tx_clean(struct aq_ring_s *self) { struct device *dev = aq_nic_get_dev(self->aq_nic); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 782176c5f4f80..24523b5ac68c1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -94,6 +94,7 @@ struct aq_ring_stats_tx_s { u64 errors; u64 packets; u64 bytes; + u64 queue_restarts; }; union aq_ring_stats_s { @@ -147,6 +148,9 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self, int aq_ring_init(struct aq_ring_s *self); void aq_ring_rx_deinit(struct aq_ring_s *self); void aq_ring_free(struct aq_ring_s *self); +void aq_ring_update_queue_state(struct aq_ring_s *ring); +void aq_ring_queue_wake(struct aq_ring_s *ring); +void aq_ring_queue_stop(struct aq_ring_s *ring); void aq_ring_tx_clean(struct aq_ring_s *self); int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index ebf588004c467..305ff8ffac2c9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -59,12 +59,7 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (ring[AQ_VEC_TX_ID].sw_head != ring[AQ_VEC_TX_ID].hw_head) { aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); - - if (aq_ring_avail_dx(&ring[AQ_VEC_TX_ID]) > - AQ_CFG_SKB_FRAGS_MAX) { - aq_nic_ndev_queue_start(self->aq_nic, - ring[AQ_VEC_TX_ID].idx); - } + aq_ring_update_queue_state(&ring[AQ_VEC_TX_ID]); was_tx_cleaned = true; } @@ -364,6 +359,7 @@ void aq_vec_add_stats(struct aq_vec_s *self, stats_tx->packets += tx->packets; stats_tx->bytes += tx->bytes; stats_tx->errors += tx->errors; + stats_tx->queue_restarts += tx->queue_restarts; } } -- GitLab From a7bb1bea3a296549ebfc28afa76276ef392f9afa Mon Sep 17 00:00:00 2001 From: Igor Russkikh Date: Mon, 25 Sep 2017 10:48:49 +0300 Subject: [PATCH 0479/1507] aquantia: Fix transient invalid link down/up indications Due to a bug in aquantia atlantic card firmware, it sometimes reports invalid link speed bits. That caused driver to report link down events, although link itself is totally fine. This patch ignores such out of blue readings. Signed-off-by: Pavel Belous Signed-off-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 4f5ec9a0fbfb8..bf734b32e44b6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -351,8 +351,7 @@ int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self) break; default: - link_status->mbps = 0U; - break; + return -EBUSY; } } -- GitLab From c7545689244b50c562b1fbbc71905fba224c8a05 Mon Sep 17 00:00:00 2001 From: Pavel Belous Date: Mon, 25 Sep 2017 10:48:50 +0300 Subject: [PATCH 0480/1507] atlantic: fix iommu errors Call skb_frag_dma_map multiple times if tx length is greater than device max and avoid processing tx ring until entire packet has been sent. Signed-off-by: Igor Russkikh Signed-off-by: Pavel Belous Signed-off-by: David S. Miller --- .../net/ethernet/aquantia/atlantic/aq_nic.c | 43 +++++++++++-------- .../net/ethernet/aquantia/atlantic/aq_ring.c | 27 ++++++++---- .../net/ethernet/aquantia/atlantic/aq_ring.h | 6 ++- 3 files changed, 49 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 072a55029f047..0a5bb4114eb4c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -473,6 +473,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int frag_count = 0U; unsigned int dx = ring->sw_tail; + struct aq_ring_buff_s *first = NULL; struct aq_ring_buff_s *dx_buff = &ring->buff_ring[dx]; if (unlikely(skb_is_gso(skb))) { @@ -483,6 +484,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, dx_buff->len_l4 = tcp_hdrlen(skb); dx_buff->mss = skb_shinfo(skb)->gso_size; dx_buff->is_txc = 1U; + dx_buff->eop_index = 0xffffU; dx_buff->is_ipv6 = (ip_hdr(skb)->version == 6) ? 1U : 0U; @@ -502,6 +504,7 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) goto exit; + first = dx_buff; dx_buff->len_pkt = skb->len; dx_buff->is_sop = 1U; dx_buff->is_mapped = 1U; @@ -530,40 +533,46 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self, for (; nr_frags--; ++frag_count) { unsigned int frag_len = 0U; + unsigned int buff_offset = 0U; + unsigned int buff_size = 0U; dma_addr_t frag_pa; skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_count]; frag_len = skb_frag_size(frag); - frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), frag, 0, - frag_len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), frag_pa))) - goto mapping_error; + while (frag_len) { + if (frag_len > AQ_CFG_TX_FRAME_MAX) + buff_size = AQ_CFG_TX_FRAME_MAX; + else + buff_size = frag_len; + + frag_pa = skb_frag_dma_map(aq_nic_get_dev(self), + frag, + buff_offset, + buff_size, + DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), + frag_pa))) + goto mapping_error; - while (frag_len > AQ_CFG_TX_FRAME_MAX) { dx = aq_ring_next_dx(ring, dx); dx_buff = &ring->buff_ring[dx]; dx_buff->flags = 0U; - dx_buff->len = AQ_CFG_TX_FRAME_MAX; + dx_buff->len = buff_size; dx_buff->pa = frag_pa; dx_buff->is_mapped = 1U; + dx_buff->eop_index = 0xffffU; + + frag_len -= buff_size; + buff_offset += buff_size; - frag_len -= AQ_CFG_TX_FRAME_MAX; - frag_pa += AQ_CFG_TX_FRAME_MAX; ++ret; } - - dx = aq_ring_next_dx(ring, dx); - dx_buff = &ring->buff_ring[dx]; - - dx_buff->flags = 0U; - dx_buff->len = frag_len; - dx_buff->pa = frag_pa; - dx_buff->is_mapped = 1U; - ++ret; } + first->eop_index = dx; dx_buff->is_eop = 1U; dx_buff->skb = skb; goto exit; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 02f79b0640bae..0654e0c76bc27 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -104,6 +104,12 @@ int aq_ring_init(struct aq_ring_s *self) return 0; } +static inline bool aq_ring_dx_in_range(unsigned int h, unsigned int i, + unsigned int t) +{ + return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t)); +} + void aq_ring_update_queue_state(struct aq_ring_s *ring) { if (aq_ring_avail_dx(ring) <= AQ_CFG_SKB_FRAGS_MAX) @@ -139,23 +145,28 @@ void aq_ring_tx_clean(struct aq_ring_s *self) struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; if (likely(buff->is_mapped)) { - if (unlikely(buff->is_sop)) + if (unlikely(buff->is_sop)) { + if (!buff->is_eop && + buff->eop_index != 0xffffU && + (!aq_ring_dx_in_range(self->sw_head, + buff->eop_index, + self->hw_head))) + break; + dma_unmap_single(dev, buff->pa, buff->len, DMA_TO_DEVICE); - else + } else { dma_unmap_page(dev, buff->pa, buff->len, DMA_TO_DEVICE); + } } if (unlikely(buff->is_eop)) dev_kfree_skb_any(buff->skb); - } -} -static inline unsigned int aq_ring_dx_in_range(unsigned int h, unsigned int i, - unsigned int t) -{ - return (h < t) ? ((h < i) && (i < t)) : ((h < i) || (i < t)); + buff->pa = 0U; + buff->eop_index = 0xffffU; + } } #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 24523b5ac68c1..5844078764bd9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -65,7 +65,7 @@ struct __packed aq_ring_buff_s { }; union { struct { - u32 len:16; + u16 len; u32 is_ip_cso:1; u32 is_udp_cso:1; u32 is_tcp_cso:1; @@ -77,8 +77,10 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 rsvd3:6; + u16 eop_index; + u16 rsvd4; }; - u32 flags; + u64 flags; }; }; -- GitLab From fc46820b27a2d9a46f7e90c9ceb4a64a1bc5fab8 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 25 Sep 2017 12:23:03 +0200 Subject: [PATCH 0481/1507] vfs: Return -ENXIO for negative SEEK_HOLE / SEEK_DATA offsets In generic_file_llseek_size, return -ENXIO for negative offsets as well as offsets beyond EOF. This affects filesystems which don't implement SEEK_HOLE / SEEK_DATA internally, possibly because they don't support holes. Fixes xfstest generic/448. Signed-off-by: Andreas Gruenbacher Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- fs/read_write.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index a2b9a47235c5b..f0d4b16873e89 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -112,7 +112,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -120,7 +120,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; -- GitLab From be2336ebfd7a1aec597a26f086fc4235ab87dd2c Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:21 +0200 Subject: [PATCH 0482/1507] mlxsw: spectrum_dpipe: Fix indentation in header description Fix indentation in mlxsw_meta header's description. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_dpipe.c | 23 +++++++++++-------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 51e6846da72bc..91648094ab4c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -46,18 +46,21 @@ enum mlxsw_sp_field_metadata_id { }; static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = { - { .name = "erif_port", - .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT, - .bitwidth = 32, - .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX, + { + .name = "erif_port", + .id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT, + .bitwidth = 32, + .mapping_type = DEVLINK_DPIPE_FIELD_MAPPING_TYPE_IFINDEX, }, - { .name = "l3_forward", - .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD, - .bitwidth = 1, + { + .name = "l3_forward", + .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD, + .bitwidth = 1, }, - { .name = "l3_drop", - .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP, - .bitwidth = 1, + { + .name = "l3_drop", + .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP, + .bitwidth = 1, }, }; -- GitLab From c0859d697c258f7c864e81bc1f83d1c274e7cf4c Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:22 +0200 Subject: [PATCH 0483/1507] mlxsw: Add fields for mlxsw's meta header for adjacency table This patch adds field for mlxsw's meta header which will be used to describe the match/action behavior of the adjacency table. The fields are: 1. Adj_index - The global index of the nexthop group in the adjacency table. 2. Adj_hash_index - Local index offset which is based on packets hash mod the nexthop group size. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 91648094ab4c1..9253273a5c035 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -43,6 +43,8 @@ enum mlxsw_sp_field_metadata_id { MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT, MLXSW_SP_DPIPE_FIELD_METADATA_L3_FORWARD, MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP, + MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX, + MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX, }; static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = { @@ -62,6 +64,16 @@ static struct devlink_dpipe_field mlxsw_sp_dpipe_fields_metadata[] = { .id = MLXSW_SP_DPIPE_FIELD_METADATA_L3_DROP, .bitwidth = 1, }, + { + .name = "adj_index", + .id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX, + .bitwidth = 32, + }, + { + .name = "adj_hash_index", + .id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX, + .bitwidth = 32, + }, }; enum mlxsw_sp_dpipe_header_id { -- GitLab From dbe4598c1e929a24dc352a7dc523a3cc22a093f2 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:23 +0200 Subject: [PATCH 0484/1507] mlxsw: spectrum_router: Keep nexthops in a linked list Keep nexthops in a linked list for easy access. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0bd93dc88ffa8..0cd4b2a7d9d0e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -78,6 +78,7 @@ struct mlxsw_sp_router { struct rhashtable neigh_ht; struct rhashtable nexthop_group_ht; struct rhashtable nexthop_ht; + struct list_head nexthop_list; struct { struct mlxsw_sp_lpm_tree *trees; unsigned int tree_count; @@ -2028,6 +2029,7 @@ struct mlxsw_sp_nexthop_key { struct mlxsw_sp_nexthop { struct list_head neigh_list_node; /* member of neigh entry list */ struct list_head rif_list_node; + struct list_head router_list_node; struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group * this belongs to */ @@ -2784,6 +2786,8 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); + if (!dev) return 0; @@ -2807,6 +2811,7 @@ static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); + list_del(&nh->router_list_node); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); } @@ -4045,6 +4050,8 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, nh->nh_grp = nh_grp; memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr)); + list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); + if (!dev) return 0; nh->ifindex = dev->ifindex; @@ -4056,6 +4063,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh); + list_del(&nh->router_list_node); } static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, @@ -5990,6 +5998,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_nexthop_group_ht_init; + INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_list); err = mlxsw_sp_lpm_init(mlxsw_sp); if (err) goto err_lpm_init; -- GitLab From ec2437f42b44edc84054feb943d49e8030154c38 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:24 +0200 Subject: [PATCH 0485/1507] mlxsw: spectrum_router: Use helper to check for last neighbor Use list_is_last helper to check for last neighbor. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0cd4b2a7d9d0e..65e59a989084d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1317,7 +1317,7 @@ mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif, typeof(*neigh_entry), rif_list_node); } - if (neigh_entry->rif_list_node.next == &rif->neigh_list) + if (list_is_last(&neigh_entry->rif_list_node, &rif->neigh_list)) return NULL; return list_next_entry(neigh_entry, rif_list_node); } -- GitLab From c556cd28930661f337d7989fe74ac31871fd3888 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:25 +0200 Subject: [PATCH 0486/1507] mlxsw: spectrum_router: Add helpers for nexthop access This is done as a preparation before introducing the ability to dump the adjacency table via dpipe, and to count the table size. The current table implementation avoids tunnel entries, thus a helper for checking if the nexthop group contains tunnel entries is also provided. The mlxsw's nexthop representative struct stays private to the router module. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 71 +++++++++++++++++++ .../ethernet/mellanox/mlxsw/spectrum_router.h | 12 ++++ 2 files changed, 83 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 65e59a989084d..c062b4f666e3d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2068,6 +2068,77 @@ struct mlxsw_sp_nexthop_group { #define nh_rif nexthops[0].rif }; +struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router, + struct mlxsw_sp_nexthop *nh) +{ + if (!nh) { + if (list_empty(&router->nexthop_list)) + return NULL; + else + return list_first_entry(&router->nexthop_list, + typeof(*nh), router_list_node); + } + if (list_is_last(&nh->router_list_node, &router->nexthop_list)) + return NULL; + return list_next_entry(nh, router_list_node); +} + +bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh) +{ + return nh->offloaded; +} + +unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh) +{ + if (!nh->offloaded) + return NULL; + return nh->neigh_entry->ha; +} + +int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index, + u32 *p_adj_hash_index) +{ + struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp; + u32 adj_hash_index = 0; + int i; + + if (!nh->offloaded || !nh_grp->adj_index_valid) + return -EINVAL; + + *p_adj_index = nh_grp->adj_index; + + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i]; + + if (nh_iter == nh) + break; + if (nh_iter->offloaded) + adj_hash_index++; + } + + *p_adj_hash_index = adj_hash_index; + return 0; +} + +struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh) +{ + return nh->rif; +} + +bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_nexthop_group *nh_grp = nh->nh_grp; + int i; + + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh_iter = &nh_grp->nexthops[i]; + + if (nh_iter->type == MLXSW_SP_NEXTHOP_TYPE_IPIP) + return true; + } + return false; +} + static struct fib_info * mlxsw_sp_nexthop4_group_fi(const struct mlxsw_sp_nexthop_group *nh_grp) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index ae4c99b3f2fcb..d6951d516cf46 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -62,6 +62,7 @@ enum mlxsw_sp_rif_counter_dir { }; struct mlxsw_sp_neigh_entry; +struct mlxsw_sp_nexthop; struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp, u16 rif_index); @@ -108,5 +109,16 @@ union mlxsw_sp_l3addr mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, const struct net_device *ol_dev); __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev); +struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router, + struct mlxsw_sp_nexthop *nh); +bool mlxsw_sp_nexthop_offload(struct mlxsw_sp_nexthop *nh); +unsigned char *mlxsw_sp_nexthop_ha(struct mlxsw_sp_nexthop *nh); +int mlxsw_sp_nexthop_indexes(struct mlxsw_sp_nexthop *nh, u32 *p_adj_index, + u32 *p_adj_hash_index); +struct mlxsw_sp_rif *mlxsw_sp_nexthop_rif(struct mlxsw_sp_nexthop *nh); +bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh); +#define mlxsw_sp_nexthop_for_each(nh, router) \ + for (nh = mlxsw_sp_nexthop_next(router, NULL); nh; \ + nh = mlxsw_sp_nexthop_next(router, nh)) #endif /* _MLXSW_ROUTER_H_*/ -- GitLab From c538adb3c6e77e0f6563b71923a81de182b5132c Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:26 +0200 Subject: [PATCH 0487/1507] mlxsw: spectrum_dpipe: Add initial support for the router adjacency table Add initial support for router adjacency table. The table does lookup based on the nexthop-group index and the local nexthop offset. After locating the nexthop entry it sets the destination MAC address and the egress RIF. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_dpipe.c | 100 +++++++++++++++++- .../ethernet/mellanox/mlxsw/spectrum_dpipe.h | 1 + 2 files changed, 100 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 9253273a5c035..ca16f8924c0a3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -841,6 +841,97 @@ static void mlxsw_sp_dpipe_host6_table_fini(struct mlxsw_sp *mlxsw_sp) MLXSW_SP_DPIPE_TABLE_NAME_HOST6); } +static int mlxsw_sp_dpipe_table_adj_matches_dump(void *priv, + struct sk_buff *skb) +{ + struct devlink_dpipe_match match = {0}; + int err; + + match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match.header = &mlxsw_sp_dpipe_header_metadata; + match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX; + + err = devlink_dpipe_match_put(skb, &match); + if (err) + return err; + + match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match.header = &mlxsw_sp_dpipe_header_metadata; + match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX; + + return devlink_dpipe_match_put(skb, &match); +} + +static int mlxsw_sp_dpipe_table_adj_actions_dump(void *priv, + struct sk_buff *skb) +{ + struct devlink_dpipe_action action = {0}; + int err; + + action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action.header = &devlink_dpipe_header_ethernet; + action.field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC; + + err = devlink_dpipe_action_put(skb, &action); + if (err) + return err; + + action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action.header = &mlxsw_sp_dpipe_header_metadata; + action.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT; + + return devlink_dpipe_action_put(skb, &action); +} + +static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_nexthop *nh; + u64 size = 0; + + mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) + if (mlxsw_sp_nexthop_offload(nh) && + !mlxsw_sp_nexthop_group_has_ipip(nh)) + size++; + return size; +} + +static u64 +mlxsw_sp_dpipe_table_adj_size_get(void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + u64 size; + + rtnl_lock(); + size = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); + rtnl_unlock(); + + return size; +} + +static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = { + .matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump, + .actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump, + .size_get = mlxsw_sp_dpipe_table_adj_size_get, +}; + +static int mlxsw_sp_dpipe_adj_table_init(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + return devlink_dpipe_table_register(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_ADJ, + &mlxsw_sp_dpipe_table_adj_ops, + mlxsw_sp, false); +} + +static void mlxsw_sp_dpipe_adj_table_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + devlink_dpipe_table_unregister(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_ADJ); +} + int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); @@ -861,8 +952,14 @@ int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp) err = mlxsw_sp_dpipe_host6_table_init(mlxsw_sp); if (err) goto err_host6_table_init; - return 0; + err = mlxsw_sp_dpipe_adj_table_init(mlxsw_sp); + if (err) + goto err_adj_table_init; + + return 0; +err_adj_table_init: + mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp); err_host6_table_init: mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp); err_host4_table_init: @@ -876,6 +973,7 @@ void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + mlxsw_sp_dpipe_adj_table_fini(mlxsw_sp); mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp); mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp); mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h index 283fde4e67839..815d543cf114a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h @@ -56,5 +56,6 @@ static inline void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp) #define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif" #define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4" #define MLXSW_SP_DPIPE_TABLE_NAME_HOST6 "mlxsw_host6" +#define MLXSW_SP_DPIPE_TABLE_NAME_ADJ "mlxsw_adj" #endif /* _MLXSW_PIPELINE_H_*/ -- GitLab From f4de25fb530c936af7c3d9a158a7dde86adb2848 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:27 +0200 Subject: [PATCH 0488/1507] mlxsw: reg: Add support for counters on RATR In order to add the ability for setting counters on nexthops the RATR register should be extended. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 44 ++++++++++++++++++----- 1 file changed, 35 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 17eba19100de5..d44e673a4c4e1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4549,6 +4549,27 @@ MLXSW_ITEM32(reg, ratr, ipip_ipv4_udip, 0x18, 0, 32); */ MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24); +enum mlxsw_reg_flow_counter_set_type { + /* No count */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00, + /* Count packets and bytes */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + +/* reg_ratr_counter_set_type + * Counter set type for flow counters + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, counter_set_type, 0x28, 24, 8); + +/* reg_ratr_counter_index + * Counter index for flow counters + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, counter_index, 0x28, 0, 24); + static inline void mlxsw_reg_ratr_pack(char *payload, enum mlxsw_reg_ratr_op op, bool valid, @@ -4576,6 +4597,20 @@ static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip) mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip); } +static inline void mlxsw_reg_ratr_counter_pack(char *payload, u64 counter_index, + bool counter_enable) +{ + enum mlxsw_reg_flow_counter_set_type set_type; + + if (counter_enable) + set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES; + else + set_type = MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT; + + mlxsw_reg_ratr_counter_index_set(payload, counter_index); + mlxsw_reg_ratr_counter_set_type_set(payload, set_type); +} + /* RICNT - Router Interface Counter Register * ----------------------------------------- * The RICNT register retrieves per port performance counters @@ -5297,15 +5332,6 @@ enum mlxsw_reg_rauht_trap_id { */ MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9); -enum mlxsw_reg_flow_counter_set_type { - /* No count */ - MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00, - /* Count packets and bytes */ - MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, - /* Count only packets */ - MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05, -}; - /* reg_rauht_counter_set_type * Counter set type for flow counters * Access: RW -- GitLab From a5390278a5eb573b76d2d28ce576b6b62c2200be Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:28 +0200 Subject: [PATCH 0489/1507] mlxsw: spectrum: Add support for setting counters on nexthops Add support for setting counters on nexthops based on dpipe's adjacency table counter status. This patch also adds the ability for getting the counter value, which will be used by the dpipe adjacency table dump implementation in the next patches. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 52 +++++++++++++++++-- .../ethernet/mellanox/mlxsw/spectrum_router.h | 2 + 2 files changed, 51 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c062b4f666e3d..a75064a8ba80d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2052,6 +2052,8 @@ struct mlxsw_sp_nexthop { struct mlxsw_sp_neigh_entry *neigh_entry; struct mlxsw_sp_ipip_entry *ipip_entry; }; + unsigned int counter_index; + bool counter_valid; }; struct mlxsw_sp_nexthop_group { @@ -2068,6 +2070,41 @@ struct mlxsw_sp_nexthop_group { #define nh_rif nexthops[0].rif }; +static void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + struct devlink *devlink; + + devlink = priv_to_devlink(mlxsw_sp->core); + if (!devlink_dpipe_table_counter_enabled(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_ADJ)) + return; + + if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &nh->counter_index)) + return; + + nh->counter_valid = true; +} + +static void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + if (!nh->counter_valid) + return; + mlxsw_sp_flow_counter_free(mlxsw_sp, nh->counter_index); + nh->counter_valid = false; +} + +int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh, u64 *p_counter) +{ + if (!nh->counter_valid) + return -EINVAL; + + return mlxsw_sp_flow_counter_get(mlxsw_sp, nh->counter_index, + p_counter, NULL); +} + struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router, struct mlxsw_sp_nexthop *nh) { @@ -2396,8 +2433,8 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, - struct mlxsw_sp_nexthop *nh) +static int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; char ratr_pl[MLXSW_REG_RATR_LEN]; @@ -2406,6 +2443,11 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, true, MLXSW_REG_RATR_TYPE_ETHERNET, adj_index, neigh_entry->rif); mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha); + if (nh->counter_valid) + mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter_index, true); + else + mlxsw_reg_ratr_counter_pack(ratr_pl, 0, false); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); } @@ -2440,7 +2482,7 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp, if (nh->update || reallocate) { switch (nh->type) { case MLXSW_SP_NEXTHOP_TYPE_ETH: - err = mlxsw_sp_nexthop_mac_update + err = mlxsw_sp_nexthop_update (mlxsw_sp, adj_index, nh); break; case MLXSW_SP_NEXTHOP_TYPE_IPIP: @@ -2857,6 +2899,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); if (!dev) @@ -2883,6 +2926,7 @@ static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); } @@ -4120,6 +4164,7 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, nh->nh_grp = nh_grp; memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr)); + mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -4135,6 +4180,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); } static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index d6951d516cf46..a6e86590939fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -120,5 +120,7 @@ bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh); #define mlxsw_sp_nexthop_for_each(nh, router) \ for (nh = mlxsw_sp_nexthop_next(router, NULL); nh; \ nh = mlxsw_sp_nexthop_next(router, nh)) +int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh, u64 *p_counter); #endif /* _MLXSW_ROUTER_H_*/ -- GitLab From 190d38a52a73ef8ac05c1931dda730e0f9b79095 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:29 +0200 Subject: [PATCH 0490/1507] mlxsw: spectrum_dpipe: Add support for adjacency table dump Add support for adjacency table dump. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_dpipe.c | 238 ++++++++++++++++++ 1 file changed, 238 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index ca16f8924c0a3..e6755a96b2697 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -895,6 +895,243 @@ static u64 mlxsw_sp_dpipe_table_adj_size(struct mlxsw_sp *mlxsw_sp) return size; } +enum mlxsw_sp_dpipe_table_adj_match { + MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX, + MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX, + MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT, +}; + +enum mlxsw_sp_dpipe_table_adj_action { + MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC, + MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT, + MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT, +}; + +static void +mlxsw_sp_dpipe_table_adj_match_action_prepare(struct devlink_dpipe_match *matches, + struct devlink_dpipe_action *actions) +{ + struct devlink_dpipe_action *action; + struct devlink_dpipe_match *match; + + match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX]; + match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match->header = &mlxsw_sp_dpipe_header_metadata; + match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_INDEX; + + match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX]; + match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match->header = &mlxsw_sp_dpipe_header_metadata; + match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ADJ_HASH_INDEX; + + action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC]; + action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action->header = &devlink_dpipe_header_ethernet; + action->field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC; + + action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT]; + action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action->header = &mlxsw_sp_dpipe_header_metadata; + action->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT; +} + +static int +mlxsw_sp_dpipe_table_adj_entry_prepare(struct devlink_dpipe_entry *entry, + struct devlink_dpipe_value *match_values, + struct devlink_dpipe_match *matches, + struct devlink_dpipe_value *action_values, + struct devlink_dpipe_action *actions) +{ struct devlink_dpipe_value *action_value; + struct devlink_dpipe_value *match_value; + struct devlink_dpipe_action *action; + struct devlink_dpipe_match *match; + + entry->match_values = match_values; + entry->match_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT; + + entry->action_values = action_values; + entry->action_values_count = MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT; + + match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX]; + match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX]; + + match_value->match = match; + match_value->value_size = sizeof(u32); + match_value->value = kmalloc(match_value->value_size, GFP_KERNEL); + if (!match_value->value) + return -ENOMEM; + + match = &matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX]; + match_value = &match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX]; + + match_value->match = match; + match_value->value_size = sizeof(u32); + match_value->value = kmalloc(match_value->value_size, GFP_KERNEL); + if (!match_value->value) + return -ENOMEM; + + action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC]; + action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC]; + + action_value->action = action; + action_value->value_size = sizeof(u64); + action_value->value = kmalloc(action_value->value_size, GFP_KERNEL); + if (!action_value->value) + return -ENOMEM; + + action = &actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT]; + action_value = &action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT]; + + action_value->action = action; + action_value->value_size = sizeof(u32); + action_value->value = kmalloc(action_value->value_size, GFP_KERNEL); + if (!action_value->value) + return -ENOMEM; + + return 0; +} + +static void +__mlxsw_sp_dpipe_table_adj_entry_fill(struct devlink_dpipe_entry *entry, + u32 adj_index, u32 adj_hash_index, + unsigned char *ha, + struct mlxsw_sp_rif *rif) +{ + struct devlink_dpipe_value *value; + u32 *p_rif_value; + u32 *p_index; + + value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_INDEX]; + p_index = value->value; + *p_index = adj_index; + + value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_HASH_INDEX]; + p_index = value->value; + *p_index = adj_hash_index; + + value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_DST_MAC]; + ether_addr_copy(value->value, ha); + + value = &entry->action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_ERIF_PORT]; + p_rif_value = value->value; + *p_rif_value = mlxsw_sp_rif_index(rif); + value->mapping_value = mlxsw_sp_rif_dev_ifindex(rif); + value->mapping_valid = true; +} + +static void mlxsw_sp_dpipe_table_adj_entry_fill(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh, + struct devlink_dpipe_entry *entry) +{ + struct mlxsw_sp_rif *rif = mlxsw_sp_nexthop_rif(nh); + unsigned char *ha = mlxsw_sp_nexthop_ha(nh); + u32 adj_hash_index = 0; + u32 adj_index = 0; + int err; + + mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index); + __mlxsw_sp_dpipe_table_adj_entry_fill(entry, adj_index, + adj_hash_index, ha, rif); + err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &entry->counter); + if (!err) + entry->counter_valid = true; +} + +static int +mlxsw_sp_dpipe_table_adj_entries_get(struct mlxsw_sp *mlxsw_sp, + struct devlink_dpipe_entry *entry, + bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct mlxsw_sp_nexthop *nh; + int entry_index = 0; + int nh_count_max; + int nh_count = 0; + int nh_skip; + int j; + int err; + + rtnl_lock(); + nh_count_max = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); +start_again: + err = devlink_dpipe_entry_ctx_prepare(dump_ctx); + if (err) + goto err_ctx_prepare; + j = 0; + nh_skip = nh_count; + mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { + if (!mlxsw_sp_nexthop_offload(nh) || + mlxsw_sp_nexthop_group_has_ipip(nh)) + continue; + + if (nh_count < nh_skip) + goto skip; + + mlxsw_sp_dpipe_table_adj_entry_fill(mlxsw_sp, nh, entry); + entry->index = entry_index; + err = devlink_dpipe_entry_ctx_append(dump_ctx, entry); + if (err) { + if (err == -EMSGSIZE) { + if (!j) + goto err_entry_append; + break; + } + goto err_entry_append; + } + entry_index++; + j++; +skip: + nh_count++; + } + + devlink_dpipe_entry_ctx_close(dump_ctx); + if (nh_count != nh_count_max) + goto start_again; + rtnl_unlock(); + + return 0; + +err_ctx_prepare: +err_entry_append: + rtnl_unlock(); + return err; +} + +static int +mlxsw_sp_dpipe_table_adj_entries_dump(void *priv, bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct devlink_dpipe_value action_values[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT]; + struct devlink_dpipe_value match_values[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT]; + struct devlink_dpipe_action actions[MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT]; + struct devlink_dpipe_match matches[MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT]; + struct devlink_dpipe_entry entry = {0}; + struct mlxsw_sp *mlxsw_sp = priv; + int err; + + memset(matches, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT * + sizeof(matches[0])); + memset(match_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_MATCH_COUNT * + sizeof(match_values[0])); + memset(actions, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT * + sizeof(actions[0])); + memset(action_values, 0, MLXSW_SP_DPIPE_TABLE_ADJ_ACTION_COUNT * + sizeof(action_values[0])); + + mlxsw_sp_dpipe_table_adj_match_action_prepare(matches, actions); + err = mlxsw_sp_dpipe_table_adj_entry_prepare(&entry, + match_values, matches, + action_values, actions); + if (err) + goto out; + + err = mlxsw_sp_dpipe_table_adj_entries_get(mlxsw_sp, &entry, + counters_enabled, dump_ctx); +out: + devlink_dpipe_entry_clear(&entry); + return err; +} + static u64 mlxsw_sp_dpipe_table_adj_size_get(void *priv) { @@ -911,6 +1148,7 @@ mlxsw_sp_dpipe_table_adj_size_get(void *priv) static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = { .matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump, .actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump, + .entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump, .size_get = mlxsw_sp_dpipe_table_adj_size_get, }; -- GitLab From 427e652aa34d90960f729c0b902c3c4a8a821b2e Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Mon, 25 Sep 2017 10:32:30 +0200 Subject: [PATCH 0491/1507] mlxsw: spectrum_dpipe: Add support for controlling nexthop counters Add support for controlling nexthop counters via dpipe. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_dpipe.c | 24 +++++++++++++++++++ .../ethernet/mellanox/mlxsw/spectrum_router.c | 12 +++++----- .../ethernet/mellanox/mlxsw/spectrum_router.h | 6 +++++ 3 files changed, 36 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index e6755a96b2697..a056f23d3a0e2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -1132,6 +1132,29 @@ mlxsw_sp_dpipe_table_adj_entries_dump(void *priv, bool counters_enabled, return err; } +static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_nexthop *nh; + u32 adj_hash_index = 0; + u32 adj_index = 0; + + mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { + if (!mlxsw_sp_nexthop_offload(nh) || + mlxsw_sp_nexthop_group_has_ipip(nh)) + continue; + + mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_hash_index); + if (enable) + mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); + else + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_update(mlxsw_sp, + adj_index + adj_hash_index, nh); + } + return 0; +} + static u64 mlxsw_sp_dpipe_table_adj_size_get(void *priv) { @@ -1149,6 +1172,7 @@ static struct devlink_dpipe_table_ops mlxsw_sp_dpipe_table_adj_ops = { .matches_dump = mlxsw_sp_dpipe_table_adj_matches_dump, .actions_dump = mlxsw_sp_dpipe_table_adj_actions_dump, .entries_dump = mlxsw_sp_dpipe_table_adj_entries_dump, + .counters_set_update = mlxsw_sp_dpipe_table_adj_counters_update, .size_get = mlxsw_sp_dpipe_table_adj_size_get, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a75064a8ba80d..321f7356073ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2070,8 +2070,8 @@ struct mlxsw_sp_nexthop_group { #define nh_rif nexthops[0].rif }; -static void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { struct devlink *devlink; @@ -2086,8 +2086,8 @@ static void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, nh->counter_valid = true; } -static void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { if (!nh->counter_valid) return; @@ -2433,8 +2433,8 @@ static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, - struct mlxsw_sp_nexthop *nh) +int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry; char ratr_pl[MLXSW_REG_RATR_LEN]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index a6e86590939fb..3d449180b035f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -122,5 +122,11 @@ bool mlxsw_sp_nexthop_group_has_ipip(struct mlxsw_sp_nexthop *nh); nh = mlxsw_sp_nexthop_next(router, nh)) int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, u64 *p_counter); +int mlxsw_sp_nexthop_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_nexthop *nh); +void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh); +void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh); #endif /* _MLXSW_ROUTER_H_*/ -- GitLab From f4344e0a48121d07cf8f69415278e84c39dbe9bf Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 17:15:31 -0400 Subject: [PATCH 0492/1507] net: dsa: return -ENODEV is there is no slave PHY Instead of returning -EOPNOTSUPP when a slave device has no PHY, directly return -ENODEV as ethtool and phylib do. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index bd51ef56ec5b8..79c5a0cd99238 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -266,10 +266,10 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_slave_priv *p = netdev_priv(dev); - if (p->phy != NULL) - return phy_mii_ioctl(p->phy, ifr, cmd); + if (!p->phy) + return -ENODEV; - return -EOPNOTSUPP; + return phy_mii_ioctl(p->phy, ifr, cmd); } static int dsa_slave_port_attr_set(struct net_device *dev, @@ -429,7 +429,7 @@ dsa_slave_get_link_ksettings(struct net_device *dev, struct dsa_slave_priv *p = netdev_priv(dev); if (!p->phy) - return -EOPNOTSUPP; + return -ENODEV; phy_ethtool_ksettings_get(p->phy, cmd); @@ -442,10 +442,10 @@ dsa_slave_set_link_ksettings(struct net_device *dev, { struct dsa_slave_priv *p = netdev_priv(dev); - if (p->phy != NULL) - return phy_ethtool_ksettings_set(p->phy, cmd); + if (!p->phy) + return -ENODEV; - return -EOPNOTSUPP; + return phy_ethtool_ksettings_set(p->phy, cmd); } static void dsa_slave_get_drvinfo(struct net_device *dev, @@ -481,22 +481,22 @@ static int dsa_slave_nway_reset(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - if (p->phy != NULL) - return genphy_restart_aneg(p->phy); + if (!p->phy) + return -ENODEV; - return -EOPNOTSUPP; + return genphy_restart_aneg(p->phy); } static u32 dsa_slave_get_link(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - if (p->phy != NULL) { - genphy_update_link(p->phy); - return p->phy->link; - } + if (!p->phy) + return -ENODEV; - return -EOPNOTSUPP; + genphy_update_link(p->phy); + + return p->phy->link; } static int dsa_slave_get_eeprom_len(struct net_device *dev) -- GitLab From 0115dcd1787d2d1c50719fab98d6bcb0c17931a1 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 17:15:32 -0400 Subject: [PATCH 0493/1507] net: dsa: use slave device phydev There is no need to store a phy_device in dsa_slave_priv since net_device already provides one. Simply s/p->phy/dev->phydev/. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 1 - net/dsa/slave.c | 116 +++++++++++++++++++++------------------------ 2 files changed, 53 insertions(+), 64 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 0298a0f6a349c..eccc627762837 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -79,7 +79,6 @@ struct dsa_slave_priv { * The phylib phy_device pointer for the PHY connected * to this port. */ - struct phy_device *phy; phy_interface_t phy_interface; int old_link; int old_pause; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 79c5a0cd99238..4ea1c6eb0da8a 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -96,12 +96,12 @@ static int dsa_slave_open(struct net_device *dev) goto clear_allmulti; } - err = dsa_port_enable(dp, p->phy); + err = dsa_port_enable(dp, dev->phydev); if (err) goto clear_promisc; - if (p->phy) - phy_start(p->phy); + if (dev->phydev) + phy_start(dev->phydev); return 0; @@ -124,10 +124,10 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_master_netdev(p); struct dsa_port *dp = p->dp; - if (p->phy) - phy_stop(p->phy); + if (dev->phydev) + phy_stop(dev->phydev); - dsa_port_disable(dp, p->phy); + dsa_port_disable(dp, dev->phydev); dev_mc_unsync(master, dev); dev_uc_unsync(master, dev); @@ -264,12 +264,10 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) + if (!dev->phydev) return -ENODEV; - return phy_mii_ioctl(p->phy, ifr, cmd); + return phy_mii_ioctl(dev->phydev, ifr, cmd); } static int dsa_slave_port_attr_set(struct net_device *dev, @@ -426,12 +424,10 @@ static int dsa_slave_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) + if (!dev->phydev) return -ENODEV; - phy_ethtool_ksettings_get(p->phy, cmd); + phy_ethtool_ksettings_get(dev->phydev, cmd); return 0; } @@ -440,12 +436,10 @@ static int dsa_slave_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) + if (!dev->phydev) return -ENODEV; - return phy_ethtool_ksettings_set(p->phy, cmd); + return phy_ethtool_ksettings_set(dev->phydev, cmd); } static void dsa_slave_get_drvinfo(struct net_device *dev, @@ -479,24 +473,20 @@ dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) static int dsa_slave_nway_reset(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) + if (!dev->phydev) return -ENODEV; - return genphy_restart_aneg(p->phy); + return genphy_restart_aneg(dev->phydev); } static u32 dsa_slave_get_link(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - - if (!p->phy) + if (!dev->phydev) return -ENODEV; - genphy_update_link(p->phy); + genphy_update_link(dev->phydev); - return p->phy->link; + return dev->phydev->link; } static int dsa_slave_get_eeprom_len(struct net_device *dev) @@ -631,7 +621,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!p->phy) + if (!dev->phydev) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -642,12 +632,12 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) return ret; if (e->eee_enabled) { - ret = phy_init_eee(p->phy, 0); + ret = phy_init_eee(dev->phydev, 0); if (ret) return ret; } - return phy_ethtool_set_eee(p->phy, e); + return phy_ethtool_set_eee(dev->phydev, e); } static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -657,7 +647,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!p->phy) + if (!dev->phydev) return -ENODEV; if (!ds->ops->get_mac_eee) @@ -667,7 +657,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) if (ret) return ret; - return phy_ethtool_get_eee(p->phy, e); + return phy_ethtool_get_eee(dev->phydev, e); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -976,26 +966,26 @@ static void dsa_slave_adjust_link(struct net_device *dev) struct dsa_switch *ds = p->dp->ds; unsigned int status_changed = 0; - if (p->old_link != p->phy->link) { + if (p->old_link != dev->phydev->link) { status_changed = 1; - p->old_link = p->phy->link; + p->old_link = dev->phydev->link; } - if (p->old_duplex != p->phy->duplex) { + if (p->old_duplex != dev->phydev->duplex) { status_changed = 1; - p->old_duplex = p->phy->duplex; + p->old_duplex = dev->phydev->duplex; } - if (p->old_pause != p->phy->pause) { + if (p->old_pause != dev->phydev->pause) { status_changed = 1; - p->old_pause = p->phy->pause; + p->old_pause = dev->phydev->pause; } if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, p->dp->index, p->phy); + ds->ops->adjust_link(ds, p->dp->index, dev->phydev); if (status_changed) - phy_print_status(p->phy); + phy_print_status(dev->phydev); } static int dsa_slave_fixed_link_update(struct net_device *dev, @@ -1020,17 +1010,18 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) struct dsa_slave_priv *p = netdev_priv(slave_dev); struct dsa_switch *ds = p->dp->ds; - p->phy = mdiobus_get_phy(ds->slave_mii_bus, addr); - if (!p->phy) { + slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); + if (!slave_dev->phydev) { netdev_err(slave_dev, "no phy at %d\n", addr); return -ENODEV; } /* Use already configured phy mode */ if (p->phy_interface == PHY_INTERFACE_MODE_NA) - p->phy_interface = p->phy->interface; - return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, - p->phy_interface); + p->phy_interface = slave_dev->phydev->interface; + + return phy_connect_direct(slave_dev, slave_dev->phydev, + dsa_slave_adjust_link, p->phy_interface); } static int dsa_slave_phy_setup(struct net_device *slave_dev) @@ -1082,22 +1073,23 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } } else { - p->phy = of_phy_connect(slave_dev, phy_dn, - dsa_slave_adjust_link, - phy_flags, - p->phy_interface); + slave_dev->phydev = of_phy_connect(slave_dev, phy_dn, + dsa_slave_adjust_link, + phy_flags, + p->phy_interface); } of_node_put(phy_dn); } - if (p->phy && phy_is_fixed) - fixed_phy_set_link_update(p->phy, dsa_slave_fixed_link_update); + if (slave_dev->phydev && phy_is_fixed) + fixed_phy_set_link_update(slave_dev->phydev, + dsa_slave_fixed_link_update); /* We could not connect to a designated PHY, so use the switch internal * MDIO bus instead */ - if (!p->phy) { + if (!slave_dev->phydev) { ret = dsa_slave_phy_connect(slave_dev, p->dp->index); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", @@ -1108,7 +1100,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) } } - phy_attached_info(p->phy); + phy_attached_info(slave_dev->phydev); return 0; } @@ -1128,12 +1120,12 @@ int dsa_slave_suspend(struct net_device *slave_dev) netif_device_detach(slave_dev); - if (p->phy) { - phy_stop(p->phy); + if (slave_dev->phydev) { + phy_stop(slave_dev->phydev); p->old_pause = -1; p->old_link = -1; p->old_duplex = -1; - phy_suspend(p->phy); + phy_suspend(slave_dev->phydev); } return 0; @@ -1141,13 +1133,11 @@ int dsa_slave_suspend(struct net_device *slave_dev) int dsa_slave_resume(struct net_device *slave_dev) { - struct dsa_slave_priv *p = netdev_priv(slave_dev); - netif_device_attach(slave_dev); - if (p->phy) { - phy_resume(p->phy); - phy_start(p->phy); + if (slave_dev->phydev) { + phy_resume(slave_dev->phydev); + phy_start(slave_dev->phydev); } return 0; @@ -1240,8 +1230,8 @@ void dsa_slave_destroy(struct net_device *slave_dev) port_dn = p->dp->dn; netif_carrier_off(slave_dev); - if (p->phy) { - phy_disconnect(p->phy); + if (slave_dev->phydev) { + phy_disconnect(slave_dev->phydev); if (of_phy_is_fixed_link(port_dn)) of_phy_deregister_fixed_link(port_dn); -- GitLab From 771df31ace8a0264bcc3576d3f02660e3366cd6d Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 17:15:33 -0400 Subject: [PATCH 0494/1507] net: dsa: use phy_ethtool_get_link_ksettings Use phy_ethtool_get_link_ksettings now that dsa_slave_get_link_ksettings does exactly the same. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 4ea1c6eb0da8a..bb0f64f47ae71 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -420,17 +420,6 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) } /* ethtool operations *******************************************************/ -static int -dsa_slave_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - if (!dev->phydev) - return -ENODEV; - - phy_ethtool_ksettings_get(dev->phydev, cmd); - - return 0; -} static int dsa_slave_set_link_ksettings(struct net_device *dev, @@ -921,8 +910,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, .get_eee = dsa_slave_get_eee, - .get_link_ksettings = dsa_slave_get_link_ksettings, .set_link_ksettings = dsa_slave_set_link_ksettings, + .get_link_ksettings = phy_ethtool_get_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, }; -- GitLab From aa62a8ca85cd05b4af4d7be70ecb735f65b0449a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 17:15:34 -0400 Subject: [PATCH 0495/1507] net: dsa: use phy_ethtool_set_link_ksettings Use phy_ethtool_set_link_ksettings now that dsa_slave_set_link_ksettings does exactly the same. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index bb0f64f47ae71..d2b632cae468e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -421,16 +421,6 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* ethtool operations *******************************************************/ -static int -dsa_slave_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - if (!dev->phydev) - return -ENODEV; - - return phy_ethtool_ksettings_set(dev->phydev, cmd); -} - static void dsa_slave_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { @@ -910,8 +900,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, .get_eee = dsa_slave_get_eee, - .set_link_ksettings = dsa_slave_set_link_ksettings, .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, }; -- GitLab From 69b2c1629649b1e765516c7b452797b9697de9ac Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 17:15:35 -0400 Subject: [PATCH 0496/1507] net: dsa: use phy_ethtool_nway_reset Use phy_ethtool_nway_reset now that dsa_slave_nway_reset does exactly the same. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d2b632cae468e..bf8800de13c17 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -450,14 +450,6 @@ dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) ds->ops->get_regs(ds, p->dp->index, regs, _p); } -static int dsa_slave_nway_reset(struct net_device *dev) -{ - if (!dev->phydev) - return -ENODEV; - - return genphy_restart_aneg(dev->phydev); -} - static u32 dsa_slave_get_link(struct net_device *dev) { if (!dev->phydev) @@ -888,7 +880,7 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, .get_regs = dsa_slave_get_regs, - .nway_reset = dsa_slave_nway_reset, + .nway_reset = phy_ethtool_nway_reset, .get_link = dsa_slave_get_link, .get_eeprom_len = dsa_slave_get_eeprom_len, .get_eeprom = dsa_slave_get_eeprom, -- GitLab From 2a52a8c6e594cdc562f503492ba89ac7bc0c4074 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Sep 2017 10:58:20 +0200 Subject: [PATCH 0497/1507] mlxsw: spectrum_acl: Propagate errors from mlxsw_afa_block_jump/continue Propagate error instead of doing WARN_ON right away. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/core_acl_flex_actions.c | 14 ++++++++------ .../mellanox/mlxsw/core_acl_flex_actions.h | 4 ++-- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 6 +++--- drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 10 +++++----- .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 6 +++++- .../net/ethernet/mellanox/mlxsw/spectrum_flower.c | 4 +++- 6 files changed, 26 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index ab3ffe7a8eda7..bc55d0e76705f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -399,23 +399,25 @@ u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block) } EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index); -void mlxsw_afa_block_continue(struct mlxsw_afa_block *block) +int mlxsw_afa_block_continue(struct mlxsw_afa_block *block) { - if (WARN_ON(block->finished)) - return; + if (block->finished) + return -EINVAL; mlxsw_afa_set_goto_set(block->cur_set, MLXSW_AFA_SET_GOTO_BINDING_CMD_NONE, 0); block->finished = true; + return 0; } EXPORT_SYMBOL(mlxsw_afa_block_continue); -void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id) +int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id) { - if (WARN_ON(block->finished)) - return; + if (block->finished) + return -EINVAL; mlxsw_afa_set_goto_set(block->cur_set, MLXSW_AFA_SET_GOTO_BINDING_CMD_JUMP, group_id); block->finished = true; + return 0; } EXPORT_SYMBOL(mlxsw_afa_block_jump); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 501819c790d68..06b0be432b8f5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -57,8 +57,8 @@ void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block); int mlxsw_afa_block_commit(struct mlxsw_afa_block *block); char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block); u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block); -void mlxsw_afa_block_continue(struct mlxsw_afa_block *block); -void mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); +int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); +int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index e907ec446a73a..9355d914a4c80 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -468,9 +468,9 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei, enum mlxsw_afk_element element, const char *key_value, const char *mask_value, unsigned int len); -void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); -void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, - u16 group_id); +int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); +int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, + u16 group_id); int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index eede75fbd585d..93dcd315f7d6c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -378,15 +378,15 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei, key_value, mask_value, len); } -void mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei) +int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei) { - mlxsw_afa_block_continue(rulei->act_block); + return mlxsw_afa_block_continue(rulei->act_block); } -void mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, - u16 group_id) +int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, + u16 group_id) { - mlxsw_afa_block_jump(rulei->act_block, group_id); + return mlxsw_afa_block_jump(rulei->act_block, group_id); } int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 50b40de1fb911..7e8284b469680 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -608,7 +608,10 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp, goto err_rulei_create; } - mlxsw_sp_acl_rulei_act_continue(rulei); + err = mlxsw_sp_acl_rulei_act_continue(rulei); + if (WARN_ON(err)) + goto err_rulei_act_continue; + err = mlxsw_sp_acl_rulei_commit(rulei); if (err) goto err_rulei_commit; @@ -623,6 +626,7 @@ mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp, err_rule_insert: err_rulei_commit: +err_rulei_act_continue: mlxsw_sp_acl_rulei_destroy(rulei); err_rulei_create: parman_item_remove(region->parman, parman_prio, parman_item); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 8aace9a06a5d8..f1cedccb58cc3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -84,7 +84,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return PTR_ERR(ruleset); group_id = mlxsw_sp_acl_ruleset_group_id(ruleset); - mlxsw_sp_acl_rulei_act_jump(rulei, group_id); + err = mlxsw_sp_acl_rulei_act_jump(rulei, group_id); + if (err) + return err; } else if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); struct net_device *out_dev; -- GitLab From 3b8e9238a8d194e82f0202a5fb68a63686ebe420 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Sep 2017 10:58:21 +0200 Subject: [PATCH 0498/1507] net: sched: introduce helper to identify gact pass action Introduce a helper called is_tcf_gact_pass which could be used to tell if the action is gact pass or not. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 41afe1ce7b16f..d979a0d48f9e7 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -33,6 +33,11 @@ static inline bool __is_tcf_gact_act(const struct tc_action *a, int act, return false; } +static inline bool is_tcf_gact_ok(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_OK, false); +} + static inline bool is_tcf_gact_shot(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_SHOT, false); -- GitLab From b2925957ec1a9349c6ac42fc5ac95bcf0dd4a6a0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Sep 2017 10:58:22 +0200 Subject: [PATCH 0499/1507] mlxsw: spectrum_flower: Offload "ok" termination action If action is "gact_ok", offload it to HW. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index f1cedccb58cc3..2f0e57857ea42 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -63,7 +63,11 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { - if (is_tcf_gact_shot(a)) { + if (is_tcf_gact_ok(a)) { + err = mlxsw_sp_acl_rulei_act_continue(rulei); + if (err) + return err; + } else if (is_tcf_gact_shot(a)) { err = mlxsw_sp_acl_rulei_act_drop(rulei); if (err) return err; -- GitLab From c2cc187e53011c1c4931055984657da9085c763b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 25 Sep 2017 13:19:26 +0300 Subject: [PATCH 0500/1507] sctp: Fix a big endian bug in sctp_diag_dump() The sctp_for_each_transport() function takes an pointer to int. The cb->args[] array holds longs so it's only using the high 32 bits. It works on little endian system but will break on big endian 64 bit machines. Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Dan Carpenter Acked-by: Neil Horman Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/sctp_diag.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 22ed01a76b19c..a72a7d925d463 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -463,6 +463,7 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, .r = r, .net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN), }; + int pos = cb->args[2]; /* eps hashtable dumps * args: @@ -493,7 +494,8 @@ static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, goto done; sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump, - net, (int *)&cb->args[2], &commp); + net, &pos, &commp); + cb->args[2] = pos; done: cb->args[1] = cb->args[4]; -- GitLab From 79ede4ae2d01b0282bfaaf761308a5ac485c8144 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:35 +0200 Subject: [PATCH 0501/1507] nfp: add helper to get flower cmsg length Add a helper function that returns the length of the cmsg data when given the cmsg skb Signed-off-by: John Hurley Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/flower/cmsg.h | 5 +++++ drivers/net/ethernet/netronome/nfp/flower/metadata.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index a2ec603442365..7a5ccf0cc7c21 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -323,6 +323,11 @@ static inline void *nfp_flower_cmsg_get_data(struct sk_buff *skb) return (unsigned char *)skb->data + NFP_FLOWER_CMSG_HLEN; } +static inline int nfp_flower_cmsg_get_data_len(struct sk_buff *skb) +{ + return skb->len - NFP_FLOWER_CMSG_HLEN; +} + struct sk_buff * nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports); void diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 3226ddc55f99b..193520ef23f05 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -140,7 +140,7 @@ nfp_flower_update_stats(struct nfp_app *app, struct nfp_fl_stats_frame *stats) void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb) { - unsigned int msg_len = skb->len - NFP_FLOWER_CMSG_HLEN; + unsigned int msg_len = nfp_flower_cmsg_get_data_len(skb); struct nfp_fl_stats_frame *stats_frame; unsigned char *msg; int i; -- GitLab From 611aec101ab7c19755e8ea6d480f679aaffed5ad Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:36 +0200 Subject: [PATCH 0502/1507] nfp: compile flower vxlan tunnel metadata match fields Compile ovs-tc flower vxlan metadata match fields for offloading. Only support offload of tunnel data when the VXLAN port specifically matches well known port 4789. Signed-off-by: John Hurley Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.h | 38 ++++++++++ .../net/ethernet/netronome/nfp/flower/main.h | 2 + .../net/ethernet/netronome/nfp/flower/match.c | 60 ++++++++++++++-- .../ethernet/netronome/nfp/flower/offload.c | 70 ++++++++++++++++--- 4 files changed, 158 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 7a5ccf0cc7c21..af9165b3b652b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -83,6 +83,14 @@ #define NFP_FL_PUSH_VLAN_CFI BIT(12) #define NFP_FL_PUSH_VLAN_VID GENMASK(11, 0) +/* Tunnel ports */ +#define NFP_FL_PORT_TYPE_TUN 0x50000000 + +enum nfp_flower_tun_type { + NFP_FL_TUNNEL_NONE = 0, + NFP_FL_TUNNEL_VXLAN = 2, +}; + struct nfp_fl_output { __be16 a_op; __be16 flags; @@ -230,6 +238,36 @@ struct nfp_flower_ipv6 { struct in6_addr ipv6_dst; }; +/* Flow Frame VXLAN --> Tunnel details (4W/16B) + * ----------------------------------------------------------------- + * 3 2 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | ipv4_addr_src | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | ipv4_addr_dst | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | tun_flags | tos | ttl | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | gpe_flags | Reserved | Next Protocol | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | VNI | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct nfp_flower_vxlan { + __be32 ip_src; + __be32 ip_dst; + __be16 tun_flags; + u8 tos; + u8 ttl; + u8 gpe_flags; + u8 reserved[2]; + u8 nxt_proto; + __be32 tun_id; +}; + +#define NFP_FL_TUN_VNI_OFFSET 8 + /* The base header for a control message packet. * Defines an 8-bit version, and an 8-bit type, padded * to a 32-bit word. Rest of the packet is type-specific. diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index c20dd00a1caec..cd695eabce02c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -58,6 +58,8 @@ struct nfp_app; #define NFP_FL_MASK_REUSE_TIME_NS 40000 #define NFP_FL_MASK_ID_LOCATION 1 +#define NFP_FL_VXLAN_PORT 4789 + struct nfp_fl_mask_id { struct circ_buf mask_id_free_list; struct timespec64 *last_used; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index d25b5038c3a26..1fd1bab0611f0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -77,14 +77,17 @@ nfp_flower_compile_meta(struct nfp_flower_meta_one *frame, u8 key_type) static int nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port, - bool mask_version) + bool mask_version, enum nfp_flower_tun_type tun_type) { if (mask_version) { frame->in_port = cpu_to_be32(~0); return 0; } - frame->in_port = cpu_to_be32(cmsg_port); + if (tun_type) + frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type); + else + frame->in_port = cpu_to_be32(cmsg_port); return 0; } @@ -189,15 +192,53 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, } } +static void +nfp_flower_compile_vxlan(struct nfp_flower_vxlan *frame, + struct tc_cls_flower_offload *flow, + bool mask_version) +{ + struct fl_flow_key *target = mask_version ? flow->mask : flow->key; + struct flow_dissector_key_ipv4_addrs *vxlan_ips; + struct flow_dissector_key_keyid *vni; + + /* Wildcard TOS/TTL/GPE_FLAGS/NXT_PROTO for now. */ + memset(frame, 0, sizeof(struct nfp_flower_vxlan)); + + if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID)) { + u32 temp_vni; + + vni = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + target); + temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET; + frame->tun_id = cpu_to_be32(temp_vni); + } + + if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + vxlan_ips = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + target); + frame->ip_src = vxlan_ips->src; + frame->ip_dst = vxlan_ips->dst; + } +} + int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, struct nfp_fl_key_ls *key_ls, struct net_device *netdev, struct nfp_fl_payload *nfp_flow) { + enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE; int err; u8 *ext; u8 *msk; + if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN) + tun_type = NFP_FL_TUNNEL_VXLAN; + memset(nfp_flow->unmasked_data, 0, key_ls->key_size); memset(nfp_flow->mask_data, 0, key_ls->key_size); @@ -216,14 +257,14 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, /* Populate Exact Port data. */ err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext, nfp_repr_get_port_id(netdev), - false); + false, tun_type); if (err) return err; /* Populate Mask Port Data. */ err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk, nfp_repr_get_port_id(netdev), - true); + true, tun_type); if (err) return err; @@ -291,5 +332,16 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, msk += sizeof(struct nfp_flower_ipv6); } + if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN) { + /* Populate Exact VXLAN Data. */ + nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)ext, + flow, false); + /* Populate Mask VXLAN Data. */ + nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)msk, + flow, true); + ext += sizeof(struct nfp_flower_vxlan); + msk += sizeof(struct nfp_flower_vxlan); + } + return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index a18b4d2b1d3ea..637372ba8f553 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -52,8 +52,25 @@ BIT(FLOW_DISSECTOR_KEY_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_VLAN) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ BIT(FLOW_DISSECTOR_KEY_IP)) +#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \ + (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)) + +#define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \ + (BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \ + BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)) + static int nfp_flower_xmit_flow(struct net_device *netdev, struct nfp_fl_payload *nfp_flow, u8 mtype) @@ -125,15 +142,58 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) return -EOPNOTSUPP; + /* If any tun dissector is used then the required set must be used. */ + if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR && + (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) + != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) + return -EOPNOTSUPP; + + key_layer_two = 0; + key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC; + key_size = sizeof(struct nfp_flower_meta_one) + + sizeof(struct nfp_flower_in_port) + + sizeof(struct nfp_flower_mac_mpls); + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; + struct flow_dissector_key_ports *mask_enc_ports = NULL; + struct flow_dissector_key_ports *enc_ports = NULL; struct flow_dissector_key_control *mask_enc_ctl = skb_flow_dissector_target(flow->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, flow->mask); - /* We are expecting a tunnel. For now we ignore offloading. */ - if (mask_enc_ctl->addr_type) + struct flow_dissector_key_control *enc_ctl = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + flow->key); + if (mask_enc_ctl->addr_type != 0xffff || + enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) return -EOPNOTSUPP; + + /* These fields are already verified as used. */ + mask_ipv4 = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + flow->mask); + if (mask_ipv4->dst != cpu_to_be32(~0)) + return -EOPNOTSUPP; + + mask_enc_ports = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + flow->mask); + enc_ports = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + flow->key); + + if (mask_enc_ports->dst != cpu_to_be16(~0) || + enc_ports->dst != htons(NFP_FL_VXLAN_PORT)) + return -EOPNOTSUPP; + + key_layer |= NFP_FLOWER_LAYER_VXLAN; + key_size += sizeof(struct nfp_flower_vxlan); } if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { @@ -151,12 +211,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, FLOW_DISSECTOR_KEY_IP, flow->mask); - key_layer_two = 0; - key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC; - key_size = sizeof(struct nfp_flower_meta_one) + - sizeof(struct nfp_flower_in_port) + - sizeof(struct nfp_flower_mac_mpls); - if (mask_basic && mask_basic->n_proto) { /* Ethernet type is present in the key. */ switch (key_basic->n_proto) { -- GitLab From b27d6a95a70de551df828de2b658efd949a9864e Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:37 +0200 Subject: [PATCH 0503/1507] nfp: compile flower vxlan tunnel set actions Compile set tunnel actions for tc flower. Only support VXLAN and ensure a tunnel destination port of 4789 is used. Signed-off-by: John Hurley Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/flower/action.c | 169 ++++++++++++++++-- .../net/ethernet/netronome/nfp/flower/cmsg.h | 31 +++- 2 files changed, 179 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index db9750695dc7f..38f3835ae1767 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "cmsg.h" #include "main.h" @@ -80,14 +81,27 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan, push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci); } +static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev, + enum nfp_flower_tun_type tun_type) +{ + if (!out_dev->rtnl_link_ops) + return false; + + if (!strcmp(out_dev->rtnl_link_ops->kind, "vxlan")) + return tun_type == NFP_FL_TUNNEL_VXLAN; + + return false; +} + static int nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action, struct nfp_fl_payload *nfp_flow, bool last, - struct net_device *in_dev) + struct net_device *in_dev, enum nfp_flower_tun_type tun_type, + int *tun_out_cnt) { size_t act_size = sizeof(struct nfp_fl_output); + u16 tmp_output_op, tmp_flags; struct net_device *out_dev; - u16 tmp_output_op; int ifindex; /* Set action opcode to output action. */ @@ -97,25 +111,114 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action, output->a_op = cpu_to_be16(tmp_output_op); - /* Set action output parameters. */ - output->flags = cpu_to_be16(last ? NFP_FL_OUT_FLAGS_LAST : 0); - ifindex = tcf_mirred_ifindex(action); out_dev = __dev_get_by_index(dev_net(in_dev), ifindex); if (!out_dev) return -EOPNOTSUPP; - /* Only offload egress ports are on the same device as the ingress - * port. + tmp_flags = last ? NFP_FL_OUT_FLAGS_LAST : 0; + + if (tun_type) { + /* Verify the egress netdev matches the tunnel type. */ + if (!nfp_fl_netdev_is_tunnel_type(out_dev, tun_type)) + return -EOPNOTSUPP; + + if (*tun_out_cnt) + return -EOPNOTSUPP; + (*tun_out_cnt)++; + + output->flags = cpu_to_be16(tmp_flags | + NFP_FL_OUT_FLAGS_USE_TUN); + output->port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type); + } else { + /* Set action output parameters. */ + output->flags = cpu_to_be16(tmp_flags); + + /* Only offload if egress ports are on the same device as the + * ingress port. + */ + if (!switchdev_port_same_parent_id(in_dev, out_dev)) + return -EOPNOTSUPP; + + output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev)); + if (!output->port) + return -EOPNOTSUPP; + } + nfp_flow->meta.shortcut = output->port; + + return 0; +} + +static bool nfp_fl_supported_tun_port(const struct tc_action *action) +{ + struct ip_tunnel_info *tun = tcf_tunnel_info(action); + + return tun->key.tp_dst == htons(NFP_FL_VXLAN_PORT); +} + +static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len) +{ + size_t act_size = sizeof(struct nfp_fl_pre_tunnel); + struct nfp_fl_pre_tunnel *pre_tun_act; + u16 tmp_pre_tun_op; + + /* Pre_tunnel action must be first on action list. + * If other actions already exist they need pushed forward. */ - if (!switchdev_port_same_parent_id(in_dev, out_dev)) - return -EOPNOTSUPP; + if (act_len) + memmove(act_data + act_size, act_data, act_len); + + pre_tun_act = (struct nfp_fl_pre_tunnel *)act_data; + + memset(pre_tun_act, 0, act_size); + + tmp_pre_tun_op = + FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) | + FIELD_PREP(NFP_FL_ACT_JMP_ID, NFP_FL_ACTION_OPCODE_PRE_TUNNEL); + + pre_tun_act->a_op = cpu_to_be16(tmp_pre_tun_op); - output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev)); - if (!output->port) + return pre_tun_act; +} + +static int +nfp_fl_set_vxlan(struct nfp_fl_set_vxlan *set_vxlan, + const struct tc_action *action, + struct nfp_fl_pre_tunnel *pre_tun) +{ + struct ip_tunnel_info *vxlan = tcf_tunnel_info(action); + size_t act_size = sizeof(struct nfp_fl_set_vxlan); + u32 tmp_set_vxlan_type_index = 0; + u16 tmp_set_vxlan_op; + /* Currently support one pre-tunnel so index is always 0. */ + int pretun_idx = 0; + + if (vxlan->options_len) { + /* Do not support options e.g. vxlan gpe. */ return -EOPNOTSUPP; + } - nfp_flow->meta.shortcut = output->port; + tmp_set_vxlan_op = + FIELD_PREP(NFP_FL_ACT_LEN_LW, act_size >> NFP_FL_LW_SIZ) | + FIELD_PREP(NFP_FL_ACT_JMP_ID, + NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL); + + set_vxlan->a_op = cpu_to_be16(tmp_set_vxlan_op); + + /* Set tunnel type and pre-tunnel index. */ + tmp_set_vxlan_type_index |= + FIELD_PREP(NFP_FL_IPV4_TUNNEL_TYPE, NFP_FL_TUNNEL_VXLAN) | + FIELD_PREP(NFP_FL_IPV4_PRE_TUN_INDEX, pretun_idx); + + set_vxlan->tun_type_index = cpu_to_be32(tmp_set_vxlan_type_index); + + set_vxlan->tun_id = vxlan->key.tun_id; + set_vxlan->tun_flags = vxlan->key.tun_flags; + set_vxlan->ipv4_ttl = vxlan->key.ttl; + set_vxlan->ipv4_tos = vxlan->key.tos; + + /* Complete pre_tunnel action. */ + pre_tun->ipv4_dst = vxlan->key.u.ipv4.dst; return 0; } @@ -123,8 +226,11 @@ nfp_fl_output(struct nfp_fl_output *output, const struct tc_action *action, static int nfp_flower_loop_action(const struct tc_action *a, struct nfp_fl_payload *nfp_fl, int *a_len, - struct net_device *netdev) + struct net_device *netdev, + enum nfp_flower_tun_type *tun_type, int *tun_out_cnt) { + struct nfp_fl_pre_tunnel *pre_tun; + struct nfp_fl_set_vxlan *s_vxl; struct nfp_fl_push_vlan *psh_v; struct nfp_fl_pop_vlan *pop_v; struct nfp_fl_output *output; @@ -137,7 +243,8 @@ nfp_flower_loop_action(const struct tc_action *a, return -EOPNOTSUPP; output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; - err = nfp_fl_output(output, a, nfp_fl, true, netdev); + err = nfp_fl_output(output, a, nfp_fl, true, netdev, *tun_type, + tun_out_cnt); if (err) return err; @@ -147,7 +254,8 @@ nfp_flower_loop_action(const struct tc_action *a, return -EOPNOTSUPP; output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; - err = nfp_fl_output(output, a, nfp_fl, false, netdev); + err = nfp_fl_output(output, a, nfp_fl, false, netdev, *tun_type, + tun_out_cnt); if (err) return err; @@ -170,6 +278,29 @@ nfp_flower_loop_action(const struct tc_action *a, nfp_fl_push_vlan(psh_v, a); *a_len += sizeof(struct nfp_fl_push_vlan); + } else if (is_tcf_tunnel_set(a) && nfp_fl_supported_tun_port(a)) { + /* Pre-tunnel action is required for tunnel encap. + * This checks for next hop entries on NFP. + * If none, the packet falls back before applying other actions. + */ + if (*a_len + sizeof(struct nfp_fl_pre_tunnel) + + sizeof(struct nfp_fl_set_vxlan) > NFP_FL_MAX_A_SIZ) + return -EOPNOTSUPP; + + *tun_type = NFP_FL_TUNNEL_VXLAN; + pre_tun = nfp_fl_pre_tunnel(nfp_fl->action_data, *a_len); + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + *a_len += sizeof(struct nfp_fl_pre_tunnel); + + s_vxl = (struct nfp_fl_set_vxlan *)&nfp_fl->action_data[*a_len]; + err = nfp_fl_set_vxlan(s_vxl, a, pre_tun); + if (err) + return err; + + *a_len += sizeof(struct nfp_fl_set_vxlan); + } else if (is_tcf_tunnel_release(a)) { + /* Tunnel decap is handled by default so accept action. */ + return 0; } else { /* Currently we do not handle any other actions. */ return -EOPNOTSUPP; @@ -182,18 +313,22 @@ int nfp_flower_compile_action(struct tc_cls_flower_offload *flow, struct net_device *netdev, struct nfp_fl_payload *nfp_flow) { - int act_len, act_cnt, err; + int act_len, act_cnt, err, tun_out_cnt; + enum nfp_flower_tun_type tun_type; const struct tc_action *a; LIST_HEAD(actions); memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); nfp_flow->meta.act_len = 0; + tun_type = NFP_FL_TUNNEL_NONE; act_len = 0; act_cnt = 0; + tun_out_cnt = 0; tcf_exts_to_list(flow->exts, &actions); list_for_each_entry(a, &actions, list) { - err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev); + err = nfp_flower_loop_action(a, nfp_flow, &act_len, netdev, + &tun_type, &tun_out_cnt); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index af9165b3b652b..ff42ce8a1e9c0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -67,10 +67,12 @@ #define NFP_FL_LW_SIZ 2 /* Action opcodes */ -#define NFP_FL_ACTION_OPCODE_OUTPUT 0 -#define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1 -#define NFP_FL_ACTION_OPCODE_POP_VLAN 2 -#define NFP_FL_ACTION_OPCODE_NUM 32 +#define NFP_FL_ACTION_OPCODE_OUTPUT 0 +#define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1 +#define NFP_FL_ACTION_OPCODE_POP_VLAN 2 +#define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 +#define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17 +#define NFP_FL_ACTION_OPCODE_NUM 32 #define NFP_FL_ACT_JMP_ID GENMASK(15, 8) #define NFP_FL_ACT_LEN_LW GENMASK(7, 0) @@ -85,6 +87,8 @@ /* Tunnel ports */ #define NFP_FL_PORT_TYPE_TUN 0x50000000 +#define NFP_FL_IPV4_TUNNEL_TYPE GENMASK(7, 4) +#define NFP_FL_IPV4_PRE_TUN_INDEX GENMASK(2, 0) enum nfp_flower_tun_type { NFP_FL_TUNNEL_NONE = 0, @@ -123,6 +127,25 @@ struct nfp_flower_meta_one { u16 reserved; }; +struct nfp_fl_pre_tunnel { + __be16 a_op; + __be16 reserved; + __be32 ipv4_dst; + /* reserved for use with IPv6 addresses */ + __be32 extra[3]; +}; + +struct nfp_fl_set_vxlan { + __be16 a_op; + __be16 reserved; + __be64 tun_id; + __be32 tun_type_index; + __be16 tun_flags; + u8 ipv4_ttl; + u8 ipv4_tos; + __be32 extra[2]; +} __packed; + /* Metadata with L2 (1W/4B) * ---------------------------------------------------------------- * 3 2 1 -- GitLab From fd0dd1ab1e107369c950796bb9b0e8eab6134bf1 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:38 +0200 Subject: [PATCH 0504/1507] nfp: offload flower vxlan endpoint MAC addresses Generate a list of MAC addresses of netdevs that could be used as VXLAN tunnel end points. Give offloaded MACs an index for storage on the NFP in the ranges: 0x100-0x1ff physical port representors 0x200-0x2ff VF port representors 0x300-0x3ff other offloads (e.g. vxlan netdevs, ovs bridges) Assign phys and vf indexes based on unique 8 bit values in the port num. Maintain list of other netdevs to ensure same netdev is not offloaded twice and each gets a unique ID without exhausting the entries. Because the IDs are unique but constant for a netdev, any changes are implemented by overwriting the index on NFP. Signed-off-by: John Hurley Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/Makefile | 3 +- .../net/ethernet/netronome/nfp/flower/cmsg.c | 7 - .../net/ethernet/netronome/nfp/flower/cmsg.h | 9 + .../net/ethernet/netronome/nfp/flower/main.c | 13 + .../net/ethernet/netronome/nfp/flower/main.h | 18 + .../net/ethernet/netronome/nfp/flower/match.c | 7 + .../netronome/nfp/flower/tunnel_conf.c | 374 ++++++++++++++++++ 7 files changed, 423 insertions(+), 8 deletions(-) create mode 100644 drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index 96e579a15cbe1..becaacf1554d8 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -37,7 +37,8 @@ nfp-objs += \ flower/main.o \ flower/match.o \ flower/metadata.o \ - flower/offload.o + flower/offload.o \ + flower/tunnel_conf.o endif ifeq ($(CONFIG_BPF_SYSCALL),y) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index c3ca05d10fe10..b756006dba6fd 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -38,17 +38,10 @@ #include #include "main.h" -#include "../nfpcore/nfp_cpp.h" #include "../nfp_net.h" #include "../nfp_net_repr.h" #include "./cmsg.h" -#define nfp_flower_cmsg_warn(app, fmt, args...) \ - do { \ - if (net_ratelimit()) \ - nfp_warn((app)->cpp, fmt, ## args); \ - } while (0) - static struct nfp_flower_cmsg_hdr * nfp_flower_cmsg_get_hdr(struct sk_buff *skb) { diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index ff42ce8a1e9c0..dc248193c9962 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -39,6 +39,7 @@ #include #include "../nfp_app.h" +#include "../nfpcore/nfp_cpp.h" #define NFP_FLOWER_LAYER_META BIT(0) #define NFP_FLOWER_LAYER_PORT BIT(1) @@ -90,6 +91,12 @@ #define NFP_FL_IPV4_TUNNEL_TYPE GENMASK(7, 4) #define NFP_FL_IPV4_PRE_TUN_INDEX GENMASK(2, 0) +#define nfp_flower_cmsg_warn(app, fmt, args...) \ + do { \ + if (net_ratelimit()) \ + nfp_warn((app)->cpp, fmt, ## args); \ + } while (0) + enum nfp_flower_tun_type { NFP_FL_TUNNEL_NONE = 0, NFP_FL_TUNNEL_VXLAN = 2, @@ -310,6 +317,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_FLOW_DEL = 2, NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7, NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8, + NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11, NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15, NFP_FLOWER_CMSG_TYPE_PORT_ECHO = 16, NFP_FLOWER_CMSG_TYPE_MAX = 32, @@ -343,6 +351,7 @@ enum nfp_flower_cmsg_port_type { NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC = 0x0, NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT = 0x1, NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT = 0x2, + NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT = 0x3, }; enum nfp_flower_cmsg_port_vnic_type { diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 91fe036171065..e46e7c60d4916 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -436,6 +436,16 @@ static void nfp_flower_clean(struct nfp_app *app) app->priv = NULL; } +static int nfp_flower_start(struct nfp_app *app) +{ + return nfp_tunnel_config_start(app); +} + +static void nfp_flower_stop(struct nfp_app *app) +{ + nfp_tunnel_config_stop(app); +} + const struct nfp_app_type app_flower = { .id = NFP_APP_FLOWER_NIC, .name = "flower", @@ -453,6 +463,9 @@ const struct nfp_app_type app_flower = { .repr_open = nfp_flower_repr_netdev_open, .repr_stop = nfp_flower_repr_netdev_stop, + .start = nfp_flower_start, + .stop = nfp_flower_stop, + .ctrl_msg_rx = nfp_flower_cmsg_rx, .sriov_enable = nfp_flower_sriov_enable, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index cd695eabce02c..9de375acc254c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -84,6 +84,13 @@ struct nfp_fl_stats_id { * @flow_table: Hash table used to store flower rules * @cmsg_work: Workqueue for control messages processing * @cmsg_skbs: List of skbs for control message processing + * @nfp_mac_off_list: List of MAC addresses to offload + * @nfp_mac_index_list: List of unique 8-bit indexes for non NFP netdevs + * @nfp_mac_off_lock: Lock for the MAC address list + * @nfp_mac_index_lock: Lock for the MAC index list + * @nfp_mac_off_ids: IDA to manage id assignment for offloaded macs + * @nfp_mac_off_count: Number of MACs in address list + * @nfp_tun_mac_nb: Notifier to monitor link state */ struct nfp_flower_priv { struct nfp_app *app; @@ -96,6 +103,13 @@ struct nfp_flower_priv { DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS); struct work_struct cmsg_work; struct sk_buff_head cmsg_skbs; + struct list_head nfp_mac_off_list; + struct list_head nfp_mac_index_list; + struct mutex nfp_mac_off_lock; + struct mutex nfp_mac_index_lock; + struct ida nfp_mac_off_ids; + int nfp_mac_off_count; + struct notifier_block nfp_tun_mac_nb; }; struct nfp_fl_key_ls { @@ -165,4 +179,8 @@ nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie); void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb); +int nfp_tunnel_config_start(struct nfp_app *app); +void nfp_tunnel_config_stop(struct nfp_app *app); +void nfp_tunnel_write_macs(struct nfp_app *app); + #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 1fd1bab0611f0..cb3ff6c126e8a 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -232,6 +232,7 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_flow) { enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE; + struct nfp_repr *netdev_repr; int err; u8 *ext; u8 *msk; @@ -341,6 +342,12 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, flow, true); ext += sizeof(struct nfp_flower_vxlan); msk += sizeof(struct nfp_flower_vxlan); + + /* Configure tunnel end point MAC. */ + if (nfp_netdev_is_nfp_repr(netdev)) { + netdev_repr = netdev_priv(netdev); + nfp_tunnel_write_macs(netdev_repr->app); + } } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c new file mode 100644 index 0000000000000..34be85803020b --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -0,0 +1,374 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include + +#include "cmsg.h" +#include "main.h" +#include "../nfp_net_repr.h" +#include "../nfp_net.h" + +/** + * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP + * @reserved: reserved for future use + * @count: number of MAC addresses in the message + * @index: index of MAC address in the lookup table + * @addr: interface MAC address + * @addresses: series of MACs to offload + */ +struct nfp_tun_mac_addr { + __be16 reserved; + __be16 count; + struct index_mac_addr { + __be16 index; + u8 addr[ETH_ALEN]; + } addresses[]; +}; + +/** + * struct nfp_tun_mac_offload_entry - list of MACs to offload + * @index: index of MAC address for offloading + * @addr: interface MAC address + * @list: list pointer + */ +struct nfp_tun_mac_offload_entry { + __be16 index; + u8 addr[ETH_ALEN]; + struct list_head list; +}; + +#define NFP_MAX_MAC_INDEX 0xff + +/** + * struct nfp_tun_mac_non_nfp_idx - converts non NFP netdev ifindex to 8-bit id + * @ifindex: netdev ifindex of the device + * @index: index of netdevs mac on NFP + * @list: list pointer + */ +struct nfp_tun_mac_non_nfp_idx { + int ifindex; + u8 index; + struct list_head list; +}; + +static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev) +{ + if (!netdev->rtnl_link_ops) + return false; + if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch")) + return true; + if (!strcmp(netdev->rtnl_link_ops->kind, "vxlan")) + return true; + + return false; +} + +static int +nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata) +{ + struct sk_buff *skb; + unsigned char *msg; + + skb = nfp_flower_cmsg_alloc(app, plen, mtype); + if (!skb) + return -ENOMEM; + + msg = nfp_flower_cmsg_get_data(skb); + memcpy(msg, pdata, nfp_flower_cmsg_get_data_len(skb)); + + nfp_ctrl_tx(app->ctrl, skb); + return 0; +} + +void nfp_tunnel_write_macs(struct nfp_app *app) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_mac_offload_entry *entry; + struct nfp_tun_mac_addr *payload; + struct list_head *ptr, *storage; + int mac_count, err, pay_size; + + mutex_lock(&priv->nfp_mac_off_lock); + if (!priv->nfp_mac_off_count) { + mutex_unlock(&priv->nfp_mac_off_lock); + return; + } + + pay_size = sizeof(struct nfp_tun_mac_addr) + + sizeof(struct index_mac_addr) * priv->nfp_mac_off_count; + + payload = kzalloc(pay_size, GFP_KERNEL); + if (!payload) { + mutex_unlock(&priv->nfp_mac_off_lock); + return; + } + + payload->count = cpu_to_be16(priv->nfp_mac_off_count); + + mac_count = 0; + list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) { + entry = list_entry(ptr, struct nfp_tun_mac_offload_entry, + list); + payload->addresses[mac_count].index = entry->index; + ether_addr_copy(payload->addresses[mac_count].addr, + entry->addr); + mac_count++; + } + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC, + pay_size, payload); + + kfree(payload); + + if (err) { + mutex_unlock(&priv->nfp_mac_off_lock); + /* Write failed so retain list for future retry. */ + return; + } + + /* If list was successfully offloaded, flush it. */ + list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) { + entry = list_entry(ptr, struct nfp_tun_mac_offload_entry, + list); + list_del(&entry->list); + kfree(entry); + } + + priv->nfp_mac_off_count = 0; + mutex_unlock(&priv->nfp_mac_off_lock); +} + +static int nfp_tun_get_mac_idx(struct nfp_app *app, int ifindex) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_mac_non_nfp_idx *entry; + struct list_head *ptr, *storage; + int idx; + + mutex_lock(&priv->nfp_mac_index_lock); + list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) { + entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list); + if (entry->ifindex == ifindex) { + idx = entry->index; + mutex_unlock(&priv->nfp_mac_index_lock); + return idx; + } + } + + idx = ida_simple_get(&priv->nfp_mac_off_ids, 0, + NFP_MAX_MAC_INDEX, GFP_KERNEL); + if (idx < 0) { + mutex_unlock(&priv->nfp_mac_index_lock); + return idx; + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + mutex_unlock(&priv->nfp_mac_index_lock); + return -ENOMEM; + } + entry->ifindex = ifindex; + entry->index = idx; + list_add_tail(&entry->list, &priv->nfp_mac_index_list); + mutex_unlock(&priv->nfp_mac_index_lock); + + return idx; +} + +static void nfp_tun_del_mac_idx(struct nfp_app *app, int ifindex) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_mac_non_nfp_idx *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_mac_index_lock); + list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) { + entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list); + if (entry->ifindex == ifindex) { + ida_simple_remove(&priv->nfp_mac_off_ids, + entry->index); + list_del(&entry->list); + kfree(entry); + break; + } + } + mutex_unlock(&priv->nfp_mac_index_lock); +} + +static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev, + struct nfp_app *app) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_mac_offload_entry *entry; + u16 nfp_mac_idx; + int port = 0; + + /* Check if MAC should be offloaded. */ + if (!is_valid_ether_addr(netdev->dev_addr)) + return; + + if (nfp_netdev_is_nfp_repr(netdev)) + port = nfp_repr_get_port_id(netdev); + else if (!nfp_tun_is_netdev_to_offload(netdev)) + return; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + nfp_flower_cmsg_warn(app, "Mem fail when offloading MAC.\n"); + return; + } + + if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) == + NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT) { + nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT; + } else if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) == + NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT) { + port = FIELD_GET(NFP_FLOWER_CMSG_PORT_VNIC, port); + nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT; + } else { + /* Must assign our own unique 8-bit index. */ + int idx = nfp_tun_get_mac_idx(app, netdev->ifindex); + + if (idx < 0) { + nfp_flower_cmsg_warn(app, "Can't assign non-repr MAC index.\n"); + kfree(entry); + return; + } + nfp_mac_idx = idx << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT; + } + + entry->index = cpu_to_be16(nfp_mac_idx); + ether_addr_copy(entry->addr, netdev->dev_addr); + + mutex_lock(&priv->nfp_mac_off_lock); + priv->nfp_mac_off_count++; + list_add_tail(&entry->list, &priv->nfp_mac_off_list); + mutex_unlock(&priv->nfp_mac_off_lock); +} + +static int nfp_tun_mac_event_handler(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct nfp_flower_priv *app_priv; + struct net_device *netdev; + struct nfp_app *app; + + if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) { + app_priv = container_of(nb, struct nfp_flower_priv, + nfp_tun_mac_nb); + app = app_priv->app; + netdev = netdev_notifier_info_to_dev(ptr); + + /* If non-nfp netdev then free its offload index. */ + if (nfp_tun_is_netdev_to_offload(netdev)) + nfp_tun_del_mac_idx(app, netdev->ifindex); + } else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR || + event == NETDEV_REGISTER) { + app_priv = container_of(nb, struct nfp_flower_priv, + nfp_tun_mac_nb); + app = app_priv->app; + netdev = netdev_notifier_info_to_dev(ptr); + + nfp_tun_add_to_mac_offload_list(netdev, app); + + /* Force a list write to keep NFP up to date. */ + nfp_tunnel_write_macs(app); + } + return NOTIFY_OK; +} + +int nfp_tunnel_config_start(struct nfp_app *app) +{ + struct nfp_flower_priv *priv = app->priv; + struct net_device *netdev; + int err; + + /* Initialise priv data for MAC offloading. */ + priv->nfp_mac_off_count = 0; + mutex_init(&priv->nfp_mac_off_lock); + INIT_LIST_HEAD(&priv->nfp_mac_off_list); + priv->nfp_tun_mac_nb.notifier_call = nfp_tun_mac_event_handler; + mutex_init(&priv->nfp_mac_index_lock); + INIT_LIST_HEAD(&priv->nfp_mac_index_list); + ida_init(&priv->nfp_mac_off_ids); + + err = register_netdevice_notifier(&priv->nfp_tun_mac_nb); + if (err) + goto err_free_mac_ida; + + /* Parse netdevs already registered for MACs that need offloaded. */ + rtnl_lock(); + for_each_netdev(&init_net, netdev) + nfp_tun_add_to_mac_offload_list(netdev, app); + rtnl_unlock(); + + return 0; + +err_free_mac_ida: + ida_destroy(&priv->nfp_mac_off_ids); + return err; +} + +void nfp_tunnel_config_stop(struct nfp_app *app) +{ + struct nfp_tun_mac_offload_entry *mac_entry; + struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_mac_non_nfp_idx *mac_idx; + struct list_head *ptr, *storage; + + unregister_netdevice_notifier(&priv->nfp_tun_mac_nb); + + /* Free any memory that may be occupied by MAC list. */ + mutex_lock(&priv->nfp_mac_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) { + mac_entry = list_entry(ptr, struct nfp_tun_mac_offload_entry, + list); + list_del(&mac_entry->list); + kfree(mac_entry); + } + mutex_unlock(&priv->nfp_mac_off_lock); + + /* Free any memory that may be occupied by MAC index list. */ + mutex_lock(&priv->nfp_mac_index_lock); + list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) { + mac_idx = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, + list); + list_del(&mac_idx->list); + kfree(mac_idx); + } + mutex_unlock(&priv->nfp_mac_index_lock); + + ida_destroy(&priv->nfp_mac_off_ids); +} -- GitLab From 2d9ad71a8ce67eea9ee38512a215e1893bd5cf87 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:39 +0200 Subject: [PATCH 0505/1507] nfp: offload vxlan IPv4 endpoints of flower rules Maintain a list of IPv4 addresses used as the tunnel destination IP match fields in currently active flower rules. Offload the entire list of NFP_FL_IPV4_ADDRS_MAX (even if some are unused) when new IPs are added or removed. The NFP should only be aware of tunnel end points that are currently used by rules on the device Signed-off-by: John Hurley Reviewed-by: Simon Horman Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.h | 1 + .../net/ethernet/netronome/nfp/flower/main.h | 7 + .../net/ethernet/netronome/nfp/flower/match.c | 14 +- .../ethernet/netronome/nfp/flower/offload.c | 4 + .../netronome/nfp/flower/tunnel_conf.c | 120 ++++++++++++++++++ 5 files changed, 143 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index dc248193c9962..6540bb1ceefb1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -318,6 +318,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7, NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8, NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11, + NFP_FLOWER_CMSG_TYPE_TUN_IPS = 14, NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15, NFP_FLOWER_CMSG_TYPE_PORT_ECHO = 16, NFP_FLOWER_CMSG_TYPE_MAX = 32, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 9de375acc254c..53306af6cfe8a 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -86,8 +86,10 @@ struct nfp_fl_stats_id { * @cmsg_skbs: List of skbs for control message processing * @nfp_mac_off_list: List of MAC addresses to offload * @nfp_mac_index_list: List of unique 8-bit indexes for non NFP netdevs + * @nfp_ipv4_off_list: List of IPv4 addresses to offload * @nfp_mac_off_lock: Lock for the MAC address list * @nfp_mac_index_lock: Lock for the MAC index list + * @nfp_ipv4_off_lock: Lock for the IPv4 address list * @nfp_mac_off_ids: IDA to manage id assignment for offloaded macs * @nfp_mac_off_count: Number of MACs in address list * @nfp_tun_mac_nb: Notifier to monitor link state @@ -105,8 +107,10 @@ struct nfp_flower_priv { struct sk_buff_head cmsg_skbs; struct list_head nfp_mac_off_list; struct list_head nfp_mac_index_list; + struct list_head nfp_ipv4_off_list; struct mutex nfp_mac_off_lock; struct mutex nfp_mac_index_lock; + struct mutex nfp_ipv4_off_lock; struct ida nfp_mac_off_ids; int nfp_mac_off_count; struct notifier_block nfp_tun_mac_nb; @@ -142,6 +146,7 @@ struct nfp_fl_payload { struct rcu_head rcu; spinlock_t lock; /* lock stats */ struct nfp_fl_stats stats; + __be32 nfp_tun_ipv4_addr; char *unmasked_data; char *mask_data; char *action_data; @@ -182,5 +187,7 @@ void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb); int nfp_tunnel_config_start(struct nfp_app *app); void nfp_tunnel_config_stop(struct nfp_app *app); void nfp_tunnel_write_macs(struct nfp_app *app); +void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4); +void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index cb3ff6c126e8a..865a815ab92ae 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -195,7 +195,7 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, static void nfp_flower_compile_vxlan(struct nfp_flower_vxlan *frame, struct tc_cls_flower_offload *flow, - bool mask_version) + bool mask_version, __be32 *tun_dst) { struct fl_flow_key *target = mask_version ? flow->mask : flow->key; struct flow_dissector_key_ipv4_addrs *vxlan_ips; @@ -223,6 +223,7 @@ nfp_flower_compile_vxlan(struct nfp_flower_vxlan *frame, target); frame->ip_src = vxlan_ips->src; frame->ip_dst = vxlan_ips->dst; + *tun_dst = vxlan_ips->dst; } } @@ -232,6 +233,7 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_flow) { enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE; + __be32 tun_dst, tun_dst_mask = 0; struct nfp_repr *netdev_repr; int err; u8 *ext; @@ -336,10 +338,10 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN) { /* Populate Exact VXLAN Data. */ nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)ext, - flow, false); + flow, false, &tun_dst); /* Populate Mask VXLAN Data. */ nfp_flower_compile_vxlan((struct nfp_flower_vxlan *)msk, - flow, true); + flow, true, &tun_dst_mask); ext += sizeof(struct nfp_flower_vxlan); msk += sizeof(struct nfp_flower_vxlan); @@ -347,6 +349,12 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, if (nfp_netdev_is_nfp_repr(netdev)) { netdev_repr = netdev_priv(netdev); nfp_tunnel_write_macs(netdev_repr->app); + + /* Store the tunnel destination in the rule data. + * This must be present and be an exact match. + */ + nfp_flow->nfp_tun_ipv4_addr = tun_dst; + nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst); } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 637372ba8f553..3d9537ebdea40 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -306,6 +306,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) if (!flow_pay->action_data) goto err_free_mask; + flow_pay->nfp_tun_ipv4_addr = 0; flow_pay->meta.flags = 0; spin_lock_init(&flow_pay->lock); @@ -415,6 +416,9 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_free_flow; + if (nfp_flow->nfp_tun_ipv4_addr) + nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr); + err = nfp_flower_xmit_flow(netdev, nfp_flow, NFP_FLOWER_CMSG_TYPE_FLOW_DEL); if (err) diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 34be85803020b..185505140f5ed 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -32,6 +32,7 @@ */ #include +#include #include #include @@ -40,6 +41,30 @@ #include "../nfp_net_repr.h" #include "../nfp_net.h" +#define NFP_FL_IPV4_ADDRS_MAX 32 + +/** + * struct nfp_tun_ipv4_addr - set the IP address list on the NFP + * @count: number of IPs populated in the array + * @ipv4_addr: array of IPV4_ADDRS_MAX 32 bit IPv4 addresses + */ +struct nfp_tun_ipv4_addr { + __be32 count; + __be32 ipv4_addr[NFP_FL_IPV4_ADDRS_MAX]; +}; + +/** + * struct nfp_ipv4_addr_entry - cached IPv4 addresses + * @ipv4_addr: IP address + * @ref_count: number of rules currently using this IP + * @list: list pointer + */ +struct nfp_ipv4_addr_entry { + __be32 ipv4_addr; + int ref_count; + struct list_head list; +}; + /** * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP * @reserved: reserved for future use @@ -112,6 +137,87 @@ nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata) return 0; } +static void nfp_tun_write_ipv4_list(struct nfp_app *app) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_addr_entry *entry; + struct nfp_tun_ipv4_addr payload; + struct list_head *ptr, *storage; + int count; + + memset(&payload, 0, sizeof(struct nfp_tun_ipv4_addr)); + mutex_lock(&priv->nfp_ipv4_off_lock); + count = 0; + list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) { + if (count >= NFP_FL_IPV4_ADDRS_MAX) { + mutex_unlock(&priv->nfp_ipv4_off_lock); + nfp_flower_cmsg_warn(app, "IPv4 offload exceeds limit.\n"); + return; + } + entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list); + payload.ipv4_addr[count++] = entry->ipv4_addr; + } + payload.count = cpu_to_be32(count); + mutex_unlock(&priv->nfp_ipv4_off_lock); + + nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_IPS, + sizeof(struct nfp_tun_ipv4_addr), + &payload); +} + +void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_addr_entry *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_ipv4_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) { + entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list); + if (entry->ipv4_addr == ipv4) { + entry->ref_count++; + mutex_unlock(&priv->nfp_ipv4_off_lock); + return; + } + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + mutex_unlock(&priv->nfp_ipv4_off_lock); + nfp_flower_cmsg_warn(app, "Mem error when offloading IP address.\n"); + return; + } + entry->ipv4_addr = ipv4; + entry->ref_count = 1; + list_add_tail(&entry->list, &priv->nfp_ipv4_off_list); + mutex_unlock(&priv->nfp_ipv4_off_lock); + + nfp_tun_write_ipv4_list(app); +} + +void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_addr_entry *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_ipv4_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) { + entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list); + if (entry->ipv4_addr == ipv4) { + entry->ref_count--; + if (!entry->ref_count) { + list_del(&entry->list); + kfree(entry); + } + break; + } + } + mutex_unlock(&priv->nfp_ipv4_off_lock); + + nfp_tun_write_ipv4_list(app); +} + void nfp_tunnel_write_macs(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; @@ -324,6 +430,10 @@ int nfp_tunnel_config_start(struct nfp_app *app) INIT_LIST_HEAD(&priv->nfp_mac_index_list); ida_init(&priv->nfp_mac_off_ids); + /* Initialise priv data for IPv4 offloading. */ + mutex_init(&priv->nfp_ipv4_off_lock); + INIT_LIST_HEAD(&priv->nfp_ipv4_off_list); + err = register_netdevice_notifier(&priv->nfp_tun_mac_nb); if (err) goto err_free_mac_ida; @@ -346,6 +456,7 @@ void nfp_tunnel_config_stop(struct nfp_app *app) struct nfp_tun_mac_offload_entry *mac_entry; struct nfp_flower_priv *priv = app->priv; struct nfp_tun_mac_non_nfp_idx *mac_idx; + struct nfp_ipv4_addr_entry *ip_entry; struct list_head *ptr, *storage; unregister_netdevice_notifier(&priv->nfp_tun_mac_nb); @@ -371,4 +482,13 @@ void nfp_tunnel_config_stop(struct nfp_app *app) mutex_unlock(&priv->nfp_mac_index_lock); ida_destroy(&priv->nfp_mac_off_ids); + + /* Free any memory that may be occupied by ipv4 list. */ + mutex_lock(&priv->nfp_ipv4_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) { + ip_entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list); + list_del(&ip_entry->list); + kfree(ip_entry); + } + mutex_unlock(&priv->nfp_ipv4_off_lock); } -- GitLab From 8e6a9046b66a7dfb11ae8be226afaaf417649411 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:40 +0200 Subject: [PATCH 0506/1507] nfp: flower vxlan neighbour offload Receive a request when the NFP does not know the next hop for a packet that is to be encapsulated in a VXLAN tunnel. Do a route lookup, determine the next hop entry and update neighbour table on NFP. Monitor the kernel neighbour table for link changes and update NFP with relevant information. Overwrite routes with zero values on the NFP when they expire. Signed-off-by: John Hurley Reviewed-by: Simon Horman Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.c | 6 + .../net/ethernet/netronome/nfp/flower/cmsg.h | 2 + .../net/ethernet/netronome/nfp/flower/main.h | 7 + .../netronome/nfp/flower/tunnel_conf.c | 253 ++++++++++++++++++ 4 files changed, 268 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index b756006dba6fd..862787daaa682 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -181,6 +181,12 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb) case NFP_FLOWER_CMSG_TYPE_FLOW_STATS: nfp_flower_rx_flow_stats(app, skb); break; + case NFP_FLOWER_CMSG_TYPE_NO_NEIGH: + nfp_tunnel_request_route(app, skb); + break; + case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH: + /* Acks from the NFP that the route is added - ignore. */ + break; default: nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n", type); diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 6540bb1ceefb1..1dc72a1ed5777 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -317,7 +317,9 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_FLOW_DEL = 2, NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7, NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8, + NFP_FLOWER_CMSG_TYPE_NO_NEIGH = 10, NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11, + NFP_FLOWER_CMSG_TYPE_TUN_NEIGH = 13, NFP_FLOWER_CMSG_TYPE_TUN_IPS = 14, NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15, NFP_FLOWER_CMSG_TYPE_PORT_ECHO = 16, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 53306af6cfe8a..93ad969c3653f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -87,12 +87,15 @@ struct nfp_fl_stats_id { * @nfp_mac_off_list: List of MAC addresses to offload * @nfp_mac_index_list: List of unique 8-bit indexes for non NFP netdevs * @nfp_ipv4_off_list: List of IPv4 addresses to offload + * @nfp_neigh_off_list: List of neighbour offloads * @nfp_mac_off_lock: Lock for the MAC address list * @nfp_mac_index_lock: Lock for the MAC index list * @nfp_ipv4_off_lock: Lock for the IPv4 address list + * @nfp_neigh_off_lock: Lock for the neighbour address list * @nfp_mac_off_ids: IDA to manage id assignment for offloaded macs * @nfp_mac_off_count: Number of MACs in address list * @nfp_tun_mac_nb: Notifier to monitor link state + * @nfp_tun_neigh_nb: Notifier to monitor neighbour state */ struct nfp_flower_priv { struct nfp_app *app; @@ -108,12 +111,15 @@ struct nfp_flower_priv { struct list_head nfp_mac_off_list; struct list_head nfp_mac_index_list; struct list_head nfp_ipv4_off_list; + struct list_head nfp_neigh_off_list; struct mutex nfp_mac_off_lock; struct mutex nfp_mac_index_lock; struct mutex nfp_ipv4_off_lock; + struct mutex nfp_neigh_off_lock; struct ida nfp_mac_off_ids; int nfp_mac_off_count; struct notifier_block nfp_tun_mac_nb; + struct notifier_block nfp_tun_neigh_nb; }; struct nfp_fl_key_ls { @@ -189,5 +195,6 @@ void nfp_tunnel_config_stop(struct nfp_app *app); void nfp_tunnel_write_macs(struct nfp_app *app); void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4); void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4); +void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 185505140f5ed..8c6b88a1306bf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -33,6 +33,7 @@ #include #include +#include #include #include @@ -41,6 +42,44 @@ #include "../nfp_net_repr.h" #include "../nfp_net.h" +/** + * struct nfp_tun_neigh - neighbour/route entry on the NFP + * @dst_ipv4: destination IPv4 address + * @src_ipv4: source IPv4 address + * @dst_addr: destination MAC address + * @src_addr: source MAC address + * @port_id: NFP port to output packet on - associated with source IPv4 + */ +struct nfp_tun_neigh { + __be32 dst_ipv4; + __be32 src_ipv4; + u8 dst_addr[ETH_ALEN]; + u8 src_addr[ETH_ALEN]; + __be32 port_id; +}; + +/** + * struct nfp_tun_req_route_ipv4 - NFP requests a route/neighbour lookup + * @ingress_port: ingress port of packet that signalled request + * @ipv4_addr: destination ipv4 address for route + * @reserved: reserved for future use + */ +struct nfp_tun_req_route_ipv4 { + __be32 ingress_port; + __be32 ipv4_addr; + __be32 reserved[2]; +}; + +/** + * struct nfp_ipv4_route_entry - routes that are offloaded to the NFP + * @ipv4_addr: destination of route + * @list: list pointer + */ +struct nfp_ipv4_route_entry { + __be32 ipv4_addr; + struct list_head list; +}; + #define NFP_FL_IPV4_ADDRS_MAX 32 /** @@ -137,6 +176,197 @@ nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata) return 0; } +static bool nfp_tun_has_route(struct nfp_app *app, __be32 ipv4_addr) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_route_entry *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_neigh_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) { + entry = list_entry(ptr, struct nfp_ipv4_route_entry, list); + if (entry->ipv4_addr == ipv4_addr) { + mutex_unlock(&priv->nfp_neigh_off_lock); + return true; + } + } + mutex_unlock(&priv->nfp_neigh_off_lock); + return false; +} + +static void nfp_tun_add_route_to_cache(struct nfp_app *app, __be32 ipv4_addr) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_route_entry *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_neigh_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) { + entry = list_entry(ptr, struct nfp_ipv4_route_entry, list); + if (entry->ipv4_addr == ipv4_addr) { + mutex_unlock(&priv->nfp_neigh_off_lock); + return; + } + } + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + mutex_unlock(&priv->nfp_neigh_off_lock); + nfp_flower_cmsg_warn(app, "Mem error when storing new route.\n"); + return; + } + + entry->ipv4_addr = ipv4_addr; + list_add_tail(&entry->list, &priv->nfp_neigh_off_list); + mutex_unlock(&priv->nfp_neigh_off_lock); +} + +static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr) +{ + struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_route_entry *entry; + struct list_head *ptr, *storage; + + mutex_lock(&priv->nfp_neigh_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) { + entry = list_entry(ptr, struct nfp_ipv4_route_entry, list); + if (entry->ipv4_addr == ipv4_addr) { + list_del(&entry->list); + kfree(entry); + break; + } + } + mutex_unlock(&priv->nfp_neigh_off_lock); +} + +static void +nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, + struct flowi4 *flow, struct neighbour *neigh) +{ + struct nfp_tun_neigh payload; + + /* Only offload representor IPv4s for now. */ + if (!nfp_netdev_is_nfp_repr(netdev)) + return; + + memset(&payload, 0, sizeof(struct nfp_tun_neigh)); + payload.dst_ipv4 = flow->daddr; + + /* If entry has expired send dst IP with all other fields 0. */ + if (!(neigh->nud_state & NUD_VALID)) { + nfp_tun_del_route_from_cache(app, payload.dst_ipv4); + /* Trigger ARP to verify invalid neighbour state. */ + neigh_event_send(neigh, NULL); + goto send_msg; + } + + /* Have a valid neighbour so populate rest of entry. */ + payload.src_ipv4 = flow->saddr; + ether_addr_copy(payload.src_addr, netdev->dev_addr); + neigh_ha_snapshot(payload.dst_addr, neigh, netdev); + payload.port_id = cpu_to_be32(nfp_repr_get_port_id(netdev)); + /* Add destination of new route to NFP cache. */ + nfp_tun_add_route_to_cache(app, payload.dst_ipv4); + +send_msg: + nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_NEIGH, + sizeof(struct nfp_tun_neigh), + (unsigned char *)&payload); +} + +static int +nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct nfp_flower_priv *app_priv; + struct netevent_redirect *redir; + struct flowi4 flow = {}; + struct neighbour *n; + struct nfp_app *app; + struct rtable *rt; + int err; + + switch (event) { + case NETEVENT_REDIRECT: + redir = (struct netevent_redirect *)ptr; + n = redir->neigh; + break; + case NETEVENT_NEIGH_UPDATE: + n = (struct neighbour *)ptr; + break; + default: + return NOTIFY_DONE; + } + + flow.daddr = *(__be32 *)n->primary_key; + + /* Only concerned with route changes for representors. */ + if (!nfp_netdev_is_nfp_repr(n->dev)) + return NOTIFY_DONE; + + app_priv = container_of(nb, struct nfp_flower_priv, nfp_tun_neigh_nb); + app = app_priv->app; + + /* Only concerned with changes to routes already added to NFP. */ + if (!nfp_tun_has_route(app, flow.daddr)) + return NOTIFY_DONE; + +#if IS_ENABLED(CONFIG_INET) + /* Do a route lookup to populate flow data. */ + rt = ip_route_output_key(dev_net(n->dev), &flow); + err = PTR_ERR_OR_ZERO(rt); + if (err) + return NOTIFY_DONE; +#else + return NOTIFY_DONE; +#endif + + flow.flowi4_proto = IPPROTO_UDP; + nfp_tun_write_neigh(n->dev, app, &flow, n); + + return NOTIFY_OK; +} + +void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb) +{ + struct nfp_tun_req_route_ipv4 *payload; + struct net_device *netdev; + struct flowi4 flow = {}; + struct neighbour *n; + struct rtable *rt; + int err; + + payload = nfp_flower_cmsg_get_data(skb); + + netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port)); + if (!netdev) + goto route_fail_warning; + + flow.daddr = payload->ipv4_addr; + flow.flowi4_proto = IPPROTO_UDP; + +#if IS_ENABLED(CONFIG_INET) + /* Do a route lookup on same namespace as ingress port. */ + rt = ip_route_output_key(dev_net(netdev), &flow); + err = PTR_ERR_OR_ZERO(rt); + if (err) + goto route_fail_warning; +#else + goto route_fail_warning; +#endif + + /* Get the neighbour entry for the lookup */ + n = dst_neigh_lookup(&rt->dst, &flow.daddr); + ip_rt_put(rt); + if (!n) + goto route_fail_warning; + nfp_tun_write_neigh(n->dev, app, &flow, n); + neigh_release(n); + return; + +route_fail_warning: + nfp_flower_cmsg_warn(app, "Requested route not found.\n"); +} + static void nfp_tun_write_ipv4_list(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; @@ -434,10 +664,19 @@ int nfp_tunnel_config_start(struct nfp_app *app) mutex_init(&priv->nfp_ipv4_off_lock); INIT_LIST_HEAD(&priv->nfp_ipv4_off_list); + /* Initialise priv data for neighbour offloading. */ + mutex_init(&priv->nfp_neigh_off_lock); + INIT_LIST_HEAD(&priv->nfp_neigh_off_list); + priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler; + err = register_netdevice_notifier(&priv->nfp_tun_mac_nb); if (err) goto err_free_mac_ida; + err = register_netevent_notifier(&priv->nfp_tun_neigh_nb); + if (err) + goto err_unreg_mac_nb; + /* Parse netdevs already registered for MACs that need offloaded. */ rtnl_lock(); for_each_netdev(&init_net, netdev) @@ -446,6 +685,8 @@ int nfp_tunnel_config_start(struct nfp_app *app) return 0; +err_unreg_mac_nb: + unregister_netdevice_notifier(&priv->nfp_tun_mac_nb); err_free_mac_ida: ida_destroy(&priv->nfp_mac_off_ids); return err; @@ -455,11 +696,13 @@ void nfp_tunnel_config_stop(struct nfp_app *app) { struct nfp_tun_mac_offload_entry *mac_entry; struct nfp_flower_priv *priv = app->priv; + struct nfp_ipv4_route_entry *route_entry; struct nfp_tun_mac_non_nfp_idx *mac_idx; struct nfp_ipv4_addr_entry *ip_entry; struct list_head *ptr, *storage; unregister_netdevice_notifier(&priv->nfp_tun_mac_nb); + unregister_netevent_notifier(&priv->nfp_tun_neigh_nb); /* Free any memory that may be occupied by MAC list. */ mutex_lock(&priv->nfp_mac_off_lock); @@ -491,4 +734,14 @@ void nfp_tunnel_config_stop(struct nfp_app *app) kfree(ip_entry); } mutex_unlock(&priv->nfp_ipv4_off_lock); + + /* Free any memory that may be occupied by the route list. */ + mutex_lock(&priv->nfp_neigh_off_lock); + list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) { + route_entry = list_entry(ptr, struct nfp_ipv4_route_entry, + list); + list_del(&route_entry->list); + kfree(route_entry); + } + mutex_unlock(&priv->nfp_neigh_off_lock); } -- GitLab From 856f5b135758ad80053a49f7ce9d1dc0166e3006 Mon Sep 17 00:00:00 2001 From: John Hurley Date: Mon, 25 Sep 2017 12:23:41 +0200 Subject: [PATCH 0507/1507] nfp: flower vxlan neighbour keep-alive Periodically receive messages containing the destination IPs of tunnels that have recently forwarded traffic. Update the neighbour entries 'used' value for these IPs next hop. This prevents the neighbour entry from expiring on timeout but rather signals an ARP to verify the connection. From an NFP perspective, packets will not fall back mid-flow unless the link is verified to be down. Signed-off-by: John Hurley Reviewed-by: Simon Horman Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.c | 3 + .../net/ethernet/netronome/nfp/flower/cmsg.h | 1 + .../net/ethernet/netronome/nfp/flower/main.h | 1 + .../netronome/nfp/flower/tunnel_conf.c | 64 +++++++++++++++++++ 4 files changed, 69 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index 862787daaa682..6b71c719deba6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -184,6 +184,9 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb) case NFP_FLOWER_CMSG_TYPE_NO_NEIGH: nfp_tunnel_request_route(app, skb); break; + case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS: + nfp_tunnel_keep_alive(app, skb); + break; case NFP_FLOWER_CMSG_TYPE_TUN_NEIGH: /* Acks from the NFP that the route is added - ignore. */ break; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 1dc72a1ed5777..504ddaa21701a 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -319,6 +319,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8, NFP_FLOWER_CMSG_TYPE_NO_NEIGH = 10, NFP_FLOWER_CMSG_TYPE_TUN_MAC = 11, + NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS = 12, NFP_FLOWER_CMSG_TYPE_TUN_NEIGH = 13, NFP_FLOWER_CMSG_TYPE_TUN_IPS = 14, NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 93ad969c3653f..12c319a219d80 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -196,5 +196,6 @@ void nfp_tunnel_write_macs(struct nfp_app *app); void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4); void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4); void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb); +void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 8c6b88a1306bf..c495f8f385062 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -36,12 +36,36 @@ #include #include #include +#include #include "cmsg.h" #include "main.h" #include "../nfp_net_repr.h" #include "../nfp_net.h" +#define NFP_FL_MAX_ROUTES 32 + +/** + * struct nfp_tun_active_tuns - periodic message of active tunnels + * @seq: sequence number of the message + * @count: number of tunnels report in message + * @flags: options part of the request + * @ipv4: dest IPv4 address of active route + * @egress_port: port the encapsulated packet egressed + * @extra: reserved for future use + * @tun_info: tunnels that have sent traffic in reported period + */ +struct nfp_tun_active_tuns { + __be32 seq; + __be32 count; + __be32 flags; + struct route_ip_info { + __be32 ipv4; + __be32 egress_port; + __be32 extra[2]; + } tun_info[]; +}; + /** * struct nfp_tun_neigh - neighbour/route entry on the NFP * @dst_ipv4: destination IPv4 address @@ -147,6 +171,46 @@ struct nfp_tun_mac_non_nfp_idx { struct list_head list; }; +void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb) +{ + struct nfp_tun_active_tuns *payload; + struct net_device *netdev; + int count, i, pay_len; + struct neighbour *n; + __be32 ipv4_addr; + u32 port; + + payload = nfp_flower_cmsg_get_data(skb); + count = be32_to_cpu(payload->count); + if (count > NFP_FL_MAX_ROUTES) { + nfp_flower_cmsg_warn(app, "Tunnel keep-alive request exceeds max routes.\n"); + return; + } + + pay_len = nfp_flower_cmsg_get_data_len(skb); + if (pay_len != sizeof(struct nfp_tun_active_tuns) + + sizeof(struct route_ip_info) * count) { + nfp_flower_cmsg_warn(app, "Corruption in tunnel keep-alive message.\n"); + return; + } + + for (i = 0; i < count; i++) { + ipv4_addr = payload->tun_info[i].ipv4; + port = be32_to_cpu(payload->tun_info[i].egress_port); + netdev = nfp_app_repr_get(app, port); + if (!netdev) + continue; + + n = neigh_lookup(&arp_tbl, &ipv4_addr, netdev); + if (!n) + continue; + + /* Update the used timestamp of neighbour */ + neigh_event_send(n, NULL); + neigh_release(n); + } +} + static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev) { if (!netdev->rtnl_link_ops) -- GitLab From ce7c47d60bda6c7f09ccf16e978d971c8fa16ff0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 18 Sep 2017 23:00:59 +0300 Subject: [PATCH 0508/1507] platform/x86: fujitsu-laptop: Don't oops when FUJ02E3 is not presnt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit My Fujitsu-Siemens Lifebook S6120 doesn't have the FUJ02E3 device, but it does have FUJ02B1. That means we do register the backlight device (and it even seems to work), but the code will oops as soon as we try to set the backlight brightness because it's trying to call call_fext_func() with a NULL device. Let's just skip those function calls when the FUJ02E3 device is not present. Cc: Jonathan Woithe Cc: Andy Shevchenko Signed-off-by: Ville Syrjälä Cc: # 4.13.x Signed-off-by: Darren Hart (VMware) --- drivers/platform/x86/fujitsu-laptop.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index 85de30f93a9cc..56a8195096a22 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -254,10 +254,12 @@ static int bl_update_status(struct backlight_device *b) { struct acpi_device *device = bl_get_data(b); - if (b->props.power == FB_BLANK_POWERDOWN) - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); - else - call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + if (fext) { + if (b->props.power == FB_BLANK_POWERDOWN) + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3); + else + call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0); + } return set_lcd_level(device, b->props.brightness); } -- GitLab From 4c6bb69663b3a3f2db8f488356e96acb5460f25f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 26 Sep 2017 10:36:05 +0200 Subject: [PATCH 0509/1507] quota: Fix quota corruption with generic/232 test Eric has reported that since commit d2faa415166b "quota: Do not acquire dqio_sem for dquot overwrites in v2 format" test generic/232 occasionally fails due to quota information being incorrect. Indeed that commit was too eager to remove dqio_sem completely from the path that just overwrites quota structure with updated information. Although that is innocent on its own, another process that inserts new quota structure to the same block can perform read-modify-write cycle of that block thus effectively discarding quota information update if they race in a wrong way. Fix the problem by acquiring dqio_sem for reading for overwrites of quota structure. Note that it *is* possible to completely avoid taking dqio_sem in the overwrite path however that will require modifying path inserting / deleting quota structures to avoid RMW cycles of the full block and for now it is not clear whether it is worth the hassle. Fixes: d2faa415166b2883428efa92f451774ef44373ac Reported-and-tested-by: Eric Whitney Signed-off-by: Jan Kara --- fs/quota/quota_v2.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index c0187cda2c1ed..a73e5b34db418 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -328,12 +328,16 @@ static int v2_write_dquot(struct dquot *dquot) if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); + } else { + down_read(&dqopt->dqio_sem); } ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); if (alloc) up_write(&dqopt->dqio_sem); + else + up_read(&dqopt->dqio_sem); return ret; } -- GitLab From 5371513fb338fb9989c569dc071326d369d6ade8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 26 Sep 2017 15:57:16 +0100 Subject: [PATCH 0510/1507] arm64: Make sure SPsel is always set When the kernel is entered at EL2 on an ARMv8.0 system, we construct the EL1 pstate and make sure this uses the the EL1 stack pointer (we perform an exception return to EL1h). But if the kernel is either entered at EL1 or stays at EL2 (because we're on a VHE-capable system), we fail to set SPsel, and use whatever stack selection the higher exception level has choosen for us. Let's not take any chance, and make sure that SPsel is set to one before we decide the mode we're going to run in. Cc: Acked-by: Mark Rutland Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/head.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 7434ec0c7a271..0b243ecaf7ac8 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -384,6 +384,7 @@ ENTRY(kimage_vaddr) * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) + msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 b.eq 1f -- GitLab From cd39e1176d320157831ce030b4c869bd2d5eb142 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 6 Jun 2017 12:57:04 +0200 Subject: [PATCH 0511/1507] KVM: VMX: extract __pi_post_block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Simple code movement patch, preparing for the next one. Cc: Huangweidong Cc: Gonglei Cc: wangxin Cc: Radim Krčmář Tested-by: Longpeng (Mike) Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 71 +++++++++++++++++++++++++--------------------- 1 file changed, 38 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c83d28b0ab056..0002b14307abf 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11705,6 +11705,43 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + unsigned long flags; + + do { + old.control = new.control = pi_desc->control; + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + if(vcpu->pre_pcpu != -1) { + spin_lock_irqsave( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11798,44 +11835,12 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || !irq_remapping_cap(IRQ_POSTING_CAP) || !kvm_vcpu_apicv_active(vcpu)) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + __pi_post_block(vcpu); } static void vmx_post_block(struct kvm_vcpu *vcpu) -- GitLab From 8b306e2f3c41939ea528e6174c88cfbfff893ce1 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 6 Jun 2017 12:57:05 +0200 Subject: [PATCH 0512/1507] KVM: VMX: avoid double list add with VT-d posted interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In some cases, for example involving hot-unplug of assigned devices, pi_post_block can forget to remove the vCPU from the blocked_vcpu_list. When this happens, the next call to pi_pre_block corrupts the list. Fix this in two ways. First, check vcpu->pre_pcpu in pi_pre_block and WARN instead of adding the element twice in the list. Second, always do the list removal in pi_post_block if vcpu->pre_pcpu is set (not -1). The new code keeps interrupts disabled for the whole duration of pi_pre_block/pi_post_block. This is not strictly necessary, but easier to follow. For the same reason, PI.ON is checked only after the cmpxchg, and to handle it we just call the post-block code. This removes duplication of the list removal code. Cc: Huangweidong Cc: Gonglei Cc: wangxin Cc: Radim Krčmář Tested-by: Longpeng (Mike) Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 62 +++++++++++++++++++--------------------------- 1 file changed, 25 insertions(+), 37 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0002b14307abf..0bfe97e50a401 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11710,10 +11710,11 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); struct pi_desc old, new; unsigned int dest; - unsigned long flags; do { old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); dest = cpu_physical_id(vcpu->cpu); @@ -11730,14 +11731,10 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) } while (cmpxchg(&pi_desc->control, old.control, new.control) != old.control); - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); vcpu->pre_pcpu = -1; } } @@ -11757,7 +11754,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11767,34 +11763,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11819,7 +11801,12 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) } while (cmpxchg(&pi_desc->control, old.control, new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11835,12 +11822,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; + WARN_ON(irqs_disabled()); + local_irq_disable(); __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) -- GitLab From 31afb2ea2b10a7d17ce3db4cdb0a12b63b2fe08a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 6 Jun 2017 12:57:06 +0200 Subject: [PATCH 0513/1507] KVM: VMX: simplify and fix vmx_vcpu_pi_load MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The simplify part: do not touch pi_desc.nv, we can set it when the VCPU is first created. Likewise, pi_desc.sn is only handled by vmx_vcpu_pi_load, do not touch it in __pi_post_block. The fix part: do not check kvm_arch_has_assigned_device, instead check the SN bit to figure out whether vmx_vcpu_pi_put ran before. This matches what the previous patch did in pi_post_block. Cc: Huangweidong Cc: Gonglei Cc: wangxin Cc: Radim Krčmář Tested-by: Longpeng (Mike) Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 68 ++++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0bfe97e50a401..b9d2140eb2128 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2202,43 +2202,41 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) + return; + + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); return; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; } while (cmpxchg(&pi_desc->control, old.control, new.control) != old.control); @@ -9592,6 +9590,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -11723,9 +11728,6 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) else new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ - new.sn = 0; - /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; } while (cmpxchg(&pi_desc->control, old.control, -- GitLab From 7e439681af82984045efc215437ebb2ca8d33a4c Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Mon, 25 Sep 2017 10:19:57 +0200 Subject: [PATCH 0514/1507] mtd: Fix partition alignment check on multi-erasesize devices Commit 1eeef2d7483a ("mtd: handle partitioning on devices with 0 erasesize") introduced a regression on heterogeneous erase region devices. Alignment of the partition was tested against the master eraseblock size which can be bigger than the slave one, thus leading to some partitions being marked as read-only. Update wr_alignment to match this slave erasesize after this erasesize has been determined by picking the biggest erasesize of all the regions embedded in the MTD partition. Reported-by: Mathias Thore Fixes: 1eeef2d7483a ("mtd: handle partitioning on devices with 0 erasesize") Cc: Signed-off-by: Boris Brezillon Tested-by: Mathias Thore Reviewed-by: Mathias Thore --- drivers/mtd/mtdpart.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 5736b0c90b339..a308e707392d5 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -581,6 +581,14 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, slave->mtd.erasesize = parent->erasesize; } + /* + * Slave erasesize might differ from the master one if the master + * exposes several regions with different erasesize. Adjust + * wr_alignment accordingly. + */ + if (!(slave->mtd.flags & MTD_NO_ERASE)) + wr_alignment = slave->mtd.erasesize; + tmp = slave->offset; remainder = do_div(tmp, wr_alignment); if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) { -- GitLab From 5c62c1c67903621cfa715d6f690548ee53301620 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 25 Sep 2017 17:28:47 +0800 Subject: [PATCH 0515/1507] iommu/io-pgtable-arm-v7s: Need dma-sync while there is no QUIRK_NO_DMA Fix the commit 81b3c2521844 ("iommu/io-pgtable: Introduce explicit coherency"). If there is no IO_PGTABLE_QUIRK_NO_DMA, we should call dma_sync_single_for_device for cache synchronization. Signed-off-by: Yong Wu Fixes: 81b3c2521844 ('iommu/io-pgtable: Introduce explicit coherency') Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgtable-arm-v7s.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index d665d0dc16e8f..6961fc393f0b2 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -245,7 +245,7 @@ static void __arm_v7s_free_table(void *table, int lvl, static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { - if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) + if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA) return; dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep), -- GitLab From 1ff9b17cedb39bc78f9e3f82485765f9b467177d Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 25 Sep 2017 18:15:26 +0800 Subject: [PATCH 0516/1507] iommu/mediatek: Limit the physical address in 32bit for v7s The ARM short descriptor has already limited the physical address to 32bit after the commit <76557391433c> ("iommu/io-pgtable: Sanitise map/unmap addresses"). But in MediaTek 4GB mode, the physical address is from 0x1_0000_0000 to 0x1_ffff_ffff. this will cause: WARNING: CPU: 4 PID: 3900 at xxx/drivers/iommu/io-pgtable-arm-v7s.c:482 arm_v7s_map+0x40/0xf8 Modules linked in: CPU: 4 PID: 3900 Comm: weston Tainted: G S W 4.9.44 #1 Hardware name: MediaTek MT2712m1v1 board (DT) task: ffffffc0eaa5b280 task.stack: ffffffc0e9858000 PC is at arm_v7s_map+0x40/0xf8 LR is at mtk_iommu_map+0x64/0x90 pc : [] lr : [] pstate: 000001c5 sp : ffffffc0e985b920 x29: ffffffc0e985b920 x28: 0000000127d00000 x27: 0000000000100000 x26: ffffff8008f9e000 x25: 0000000000000003 x24: 0000000000100000 x23: 0000000127d00000 x22: 00000000ff800000 x21: ffffffc0f7ec8ce0 x20: 0000000000000003 x19: 0000000000000003 x18: 0000000000000002 x17: 0000007f7e5d72c0 x16: ffffff80082b0f08 x15: 0000000000000001 x14: 000000000000003f x13: 0000000000000000 x12: 0000000000000028 x11: 0088000000000000 x10: 0000000000000000 x9 : ffffff80092fa000 x8 : ffffffc0e9858000 x7 : ffffff80085b29d8 x6 : 0000000000000000 x5 : ffffff80085b09a8 x4 : 0000000000000003 x3 : 0000000000100000 x2 : 0000000127d00000 x1 : 00000000ff800000 x0 : 0000000000000001 ... Call trace: [] arm_v7s_map+0x40/0xf8 [] mtk_iommu_map+0x64/0x90 [] iommu_map+0x100/0x3a0 [] default_iommu_map_sg+0x104/0x168 [] iommu_dma_alloc+0x238/0x3f8 [] __iommu_alloc_attrs+0xa8/0x260 [] mtk_drm_gem_create+0xac/0x180 [] mtk_drm_gem_dumb_create+0x54/0xc8 [] drm_mode_create_dumb_ioctl+0xa4/0xd8 [] drm_ioctl+0x1c0/0x490 In order to satify this, Limit the physical address to 32bit. Signed-off-by: Yong Wu Acked-by: Will Deacon Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index bd515be5b380e..16d33ac19db0f 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -371,7 +371,8 @@ static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, int ret; spin_lock_irqsave(&dom->pgtlock, flags); - ret = dom->iop->map(dom->iop, iova, paddr, size, prot); + ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32), + size, prot); spin_unlock_irqrestore(&dom->pgtlock, flags); return ret; -- GitLab From 3c6bae62136ba5b24f0b113e68121b783457ca4b Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Tue, 26 Sep 2017 13:07:46 +0530 Subject: [PATCH 0517/1507] iommu/amd: pr_err() strings should end with newlines pr_err() messages should end with a new-line to avoid other messages being concatenated. So replace '/n' with '\n'. Signed-off-by: Arvind Yadav Fixes: 45a01c42933b ('iommu/amd: Add function copy_dev_tables()') Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu_init.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 382de42b83593..6fe2d03460730 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -874,7 +874,7 @@ static bool copy_device_table(void) hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4); entry = (((u64) hi) << 32) + lo; if (last_entry && last_entry != entry) { - pr_err("IOMMU:%d should use the same dev table as others!/n", + pr_err("IOMMU:%d should use the same dev table as others!\n", iommu->index); return false; } @@ -882,7 +882,7 @@ static bool copy_device_table(void) old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12; if (old_devtb_size != dev_table_size) { - pr_err("The device table size of IOMMU:%d is not expected!/n", + pr_err("The device table size of IOMMU:%d is not expected!\n", iommu->index); return false; } @@ -890,7 +890,7 @@ static bool copy_device_table(void) old_devtb_phys = entry & PAGE_MASK; if (old_devtb_phys >= 0x100000000ULL) { - pr_err("The address of old device table is above 4G, not trustworthy!/n"); + pr_err("The address of old device table is above 4G, not trustworthy!\n"); return false; } old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB); @@ -901,7 +901,7 @@ static bool copy_device_table(void) old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag, get_order(dev_table_size)); if (old_dev_tbl_cpy == NULL) { - pr_err("Failed to allocate memory for copying old device table!/n"); + pr_err("Failed to allocate memory for copying old device table!\n"); return false; } -- GitLab From 50ce6312f293e129eedf2affc7bd791c71d8287e Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 26 Sep 2017 19:32:52 +0100 Subject: [PATCH 0518/1507] iommu: Fix comment for iommu_ops.map_sg The definition of map_sg was split during a recent addition to iommu_ops. Put it back together. Fixes: add02cfdc9bc ("iommu: Introduce Interface for IOMMU TLB Flushing") Signed-off-by: Jean-Philippe Brucker Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a7f2ac689d291..41b8c57578591 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,11 +167,11 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue - * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping -- GitLab From df5efdd97029f2cff7e5c91ea1c9f2b94d009b0f Mon Sep 17 00:00:00 2001 From: Sebastian Sanchez Date: Tue, 26 Sep 2017 06:05:57 -0700 Subject: [PATCH 0519/1507] IB/hfi1: Turn off AOC TX after offline substates Offline.quietDuration was added in the 8051 firmware, and the driver only turns off the AOC transmitters when offline.quiet is reached. However, the AOC transmitters need to be turned off at the new state. Therefore, turn off the AOC transmitters at any offline substates including offline.quiet and offline.quietDuration, then recheck we reached offline.quiet to support backwards compatibility. Reviewed-by: Jakub Byczkowski Reviewed-by: Mike Marciniszyn Signed-off-by: Sebastian Sanchez Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 85 +++++++++++++++++++++++-------- drivers/infiniband/hw/hfi1/chip.h | 1 + 2 files changed, 65 insertions(+), 21 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index b2ed4b9cda6ee..1c810d65721a0 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -1066,6 +1066,8 @@ static int read_idle_sma(struct hfi1_devdata *dd, u64 *data); static int thermal_init(struct hfi1_devdata *dd); static void update_statusp(struct hfi1_pportdata *ppd, u32 state); +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs); static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state, int msecs); static void log_state_transition(struct hfi1_pportdata *ppd, u32 state); @@ -10305,6 +10307,7 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) { struct hfi1_devdata *dd = ppd->dd; u32 previous_state; + int offline_state_ret; int ret; update_lcb_cache(dd); @@ -10326,28 +10329,11 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) ppd->offline_disabled_reason = HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT); - /* - * Wait for offline transition. It can take a while for - * the link to go down. - */ - ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000); - if (ret < 0) - return ret; - - /* - * Now in charge of LCB - must be after the physical state is - * offline.quiet and before host_link_state is changed. - */ - set_host_lcb_access(dd); - write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ - - /* make sure the logical state is also down */ - ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); - if (ret) - force_logical_link_state_down(ppd); - - ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + offline_state_ret = wait_phys_link_offline_substates(ppd, 10000); + if (offline_state_ret < 0) + return offline_state_ret; + /* Disabling AOC transmitters */ if (ppd->port_type == PORT_TYPE_QSFP && ppd->qsfp_info.limiting_active && qsfp_mod_present(ppd)) { @@ -10364,6 +10350,30 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) } } + /* + * Wait for the offline.Quiet transition if it hasn't happened yet. It + * can take a while for the link to go down. + */ + if (offline_state_ret != PLS_OFFLINE_QUIET) { + ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000); + if (ret < 0) + return ret; + } + + /* + * Now in charge of LCB - must be after the physical state is + * offline.quiet and before host_link_state is changed. + */ + set_host_lcb_access(dd); + write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */ + + /* make sure the logical state is also down */ + ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000); + if (ret) + force_logical_link_state_down(ppd); + + ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */ + /* * The LNI has a mandatory wait time after the physical state * moves to Offline.Quiet. The wait time may be different @@ -12804,6 +12814,39 @@ static int wait_physical_linkstate(struct hfi1_pportdata *ppd, u32 state, return 0; } +/* + * wait_phys_link_offline_quiet_substates - wait for any offline substate + * @ppd: port device + * @msecs: the number of milliseconds to wait + * + * Wait up to msecs milliseconds for any offline physical link + * state change to occur. + * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT. + */ +static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd, + int msecs) +{ + u32 read_state; + unsigned long timeout; + + timeout = jiffies + msecs_to_jiffies(msecs); + while (1) { + read_state = read_physical_state(ppd->dd); + if ((read_state & 0xF0) == PLS_OFFLINE) + break; + if (time_after(jiffies, timeout)) { + dd_dev_err(ppd->dd, + "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n", + read_state, msecs); + return -ETIMEDOUT; + } + usleep_range(1950, 2050); /* sleep 2ms-ish */ + } + + log_state_transition(ppd, read_state); + return read_state; +} + #define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \ (r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK) diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index b8345a60a0fbc..461f937fe110d 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -204,6 +204,7 @@ #define PLS_OFFLINE_READY_TO_QUIET_LT 0x92 #define PLS_OFFLINE_REPORT_FAILURE 0x93 #define PLS_OFFLINE_READY_TO_QUIET_BCC 0x94 +#define PLS_OFFLINE_QUIET_DURATION 0x95 #define PLS_POLLING 0x20 #define PLS_POLLING_QUIET 0x20 #define PLS_POLLING_ACTIVE 0x21 -- GitLab From 30e10527bcce376114e627abb7fabfbe9bfee91e Mon Sep 17 00:00:00 2001 From: Sebastian Sanchez Date: Tue, 26 Sep 2017 06:06:03 -0700 Subject: [PATCH 0520/1507] IB/hfi1: Only reset QSFP after link up and turn off AOC TX QSFP reset enables AOC transmitters by default. They should be off before moving to high power mode to complete the setup. There is no need to reset the QSFP during LNI failure as it was reset at link down. Reviewed-by: Mike Marciniszyn Reviewed-by: Jakub Byczkowski Signed-off-by: Sebastian Sanchez Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 12 +++++++++++- drivers/infiniband/hw/hfi1/chip.h | 2 +- drivers/infiniband/hw/hfi1/platform.c | 4 +++- 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 1c810d65721a0..27b75a8f5097e 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -9415,7 +9415,7 @@ static void set_qsfp_int_n(struct hfi1_pportdata *ppd, u8 enable) write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask); } -void reset_qsfp(struct hfi1_pportdata *ppd) +int reset_qsfp(struct hfi1_pportdata *ppd) { struct hfi1_devdata *dd = ppd->dd; u64 mask, qsfp_mask; @@ -9445,6 +9445,13 @@ void reset_qsfp(struct hfi1_pportdata *ppd) * for alarms and warnings */ set_qsfp_int_n(ppd, 1); + + /* + * After the reset, AOC transmitters are enabled by default. They need + * to be turned off to complete the QSFP setup before they can be + * enabled again. + */ + return set_qsfp_tx(ppd, 0); } static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd, @@ -10406,6 +10413,9 @@ static int goto_offline(struct hfi1_pportdata *ppd, u8 rem_reason) & (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) { /* went down while attempting link up */ check_lni_states(ppd); + + /* The QSFP doesn't need to be reset on LNI failure */ + ppd->qsfp_info.reset_needed = 0; } /* the active link width (downgrade) is 0 on link down */ diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h index 461f937fe110d..50b8645d0b876 100644 --- a/drivers/infiniband/hw/hfi1/chip.h +++ b/drivers/infiniband/hw/hfi1/chip.h @@ -723,7 +723,7 @@ void handle_link_downgrade(struct work_struct *work); void handle_link_bounce(struct work_struct *work); void handle_start_link(struct work_struct *work); void handle_sma_message(struct work_struct *work); -void reset_qsfp(struct hfi1_pportdata *ppd); +int reset_qsfp(struct hfi1_pportdata *ppd); void qsfp_event(struct work_struct *work); void start_freeze_handling(struct hfi1_pportdata *ppd, int flags); int send_idle_sma(struct hfi1_devdata *dd, u64 message); diff --git a/drivers/infiniband/hw/hfi1/platform.c b/drivers/infiniband/hw/hfi1/platform.c index a8af96d2b1b0a..d486355880cb0 100644 --- a/drivers/infiniband/hw/hfi1/platform.c +++ b/drivers/infiniband/hw/hfi1/platform.c @@ -790,7 +790,9 @@ static int tune_active_qsfp(struct hfi1_pportdata *ppd, u32 *ptr_tx_preset, * reuse of stale settings established in our previous pass through. */ if (ppd->qsfp_info.reset_needed) { - reset_qsfp(ppd); + ret = reset_qsfp(ppd); + if (ret) + return ret; refresh_qsfp_cache(ppd, &ppd->qsfp_info); } else { ppd->qsfp_info.reset_needed = 1; -- GitLab From 753b19afb19dd97d0767df5e8afb13faff605315 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Tue, 26 Sep 2017 06:06:09 -0700 Subject: [PATCH 0521/1507] IB/hfi1: Check eeprom config partition validity Relying on a trailing magic value is incorrect. There are instances where this is not present as trailing magic value has a specific purpose which is not partition validation. Instead use the header magic value which is present in all variants of the platform configuration and is intended for validation. This is also used in other locations in the driver. Fixes: bc5214ee2922 (IB/hfi1: Handle missing magic values in config file) Reviewed-by: Jakub Byczkowski Signed-off-by: Jan Sokolowski Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/eprom.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/eprom.c b/drivers/infiniband/hw/hfi1/eprom.c index d46b171079010..1613af1c58d9d 100644 --- a/drivers/infiniband/hw/hfi1/eprom.c +++ b/drivers/infiniband/hw/hfi1/eprom.c @@ -204,7 +204,10 @@ int eprom_init(struct hfi1_devdata *dd) return ret; } -/* magic character sequence that trails an image */ +/* magic character sequence that begins an image */ +#define IMAGE_START_MAGIC "APO=" + +/* magic character sequence that might trail an image */ #define IMAGE_TRAIL_MAGIC "egamiAPO" /* EPROM file types */ @@ -250,6 +253,7 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, { void *buffer; void *p; + u32 length; int ret; buffer = kmalloc(P1_SIZE, GFP_KERNEL); @@ -262,15 +266,21 @@ static int read_partition_platform_config(struct hfi1_devdata *dd, void **data, return ret; } - /* scan for image magic that may trail the actual data */ - p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); - if (!p) { + /* config partition is valid only if it starts with IMAGE_START_MAGIC */ + if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) { kfree(buffer); return -ENOENT; } + /* scan for image magic that may trail the actual data */ + p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE); + if (p) + length = p - buffer; + else + length = P1_SIZE; + *data = buffer; - *size = p - buffer; + *size = length; return 0; } -- GitLab From 09592af5fdd722615ebe435fb34308de26c74bcf Mon Sep 17 00:00:00 2001 From: Kamenee Arumugam Date: Tue, 26 Sep 2017 06:06:15 -0700 Subject: [PATCH 0522/1507] IB/hfi1: Return correct value in general interrupt handler The general interrupt handler returns IRQ_HANDLED whether an IRQ was handled or not. Determine if an IRQ was handled and return the correct value. Reviewed-by: Dennis Dalessandro Reviewed-by: Michael J. Ruhl Signed-off-by: Kamenee Arumugam Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/chip.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 27b75a8f5097e..0be42787759fa 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8240,6 +8240,7 @@ static irqreturn_t general_interrupt(int irq, void *data) u64 regs[CCE_NUM_INT_CSRS]; u32 bit; int i; + irqreturn_t handled = IRQ_NONE; this_cpu_inc(*dd->int_counter); @@ -8260,9 +8261,10 @@ static irqreturn_t general_interrupt(int irq, void *data) for_each_set_bit(bit, (unsigned long *)®s[0], CCE_NUM_INT_CSRS * 64) { is_interrupt(dd, bit); + handled = IRQ_HANDLED; } - return IRQ_HANDLED; + return handled; } static irqreturn_t sdma_interrupt(int irq, void *data) -- GitLab From 612601d0013f03de9dc134809f242ba6da9ca252 Mon Sep 17 00:00:00 2001 From: Alex Estrin Date: Tue, 26 Sep 2017 06:06:22 -0700 Subject: [PATCH 0523/1507] Revert "IB/ipoib: Update broadcast object if PKey value was changed in index 0" commit 9a9b8112699d will cause core to fail UD QP from being destroyed on ipoib unload, therefore cause resources leakage. On pkey change event above patch modifies mgid before calling underlying driver to detach it from QP. Drivers' detach_mcast() will fail to find modified mgid it was never given to attach in a first place. Core qp->usecnt will never go down, so ib_destroy_qp() will fail. IPoIB driver actually does take care of new broadcast mgid based on new pkey by destroying an old mcast object in ipoib_mcast_dev_flush()) .... if (priv->broadcast) { rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree); list_add_tail(&priv->broadcast->list, &remove_list); priv->broadcast = NULL; } ... then in restarted ipoib_macst_join_task() creating a new broadcast mcast object, sending join request and on completion tells the driver to attach to reinitialized QP: ... if (!priv->broadcast) { ... broadcast = ipoib_mcast_alloc(dev, 0); ... memcpy(broadcast->mcmember.mgid.raw, priv->dev->broadcast + 4, sizeof (union ib_gid)); priv->broadcast = broadcast; ... Fixes: 9a9b8112699d ("IB/ipoib: Update broadcast object if PKey value was changed in index 0") Cc: stable@vger.kernel.org Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Signed-off-by: Alex Estrin Signed-off-by: Dennis Dalessandro Reviewed-by: Feras Daoud Signed-off-by: Doug Ledford --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 2e075377242e2..6cd61638b4414 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1000,19 +1000,6 @@ static inline int update_parent_pkey(struct ipoib_dev_priv *priv) */ priv->dev->broadcast[8] = priv->pkey >> 8; priv->dev->broadcast[9] = priv->pkey & 0xff; - - /* - * Update the broadcast address in the priv->broadcast object, - * in case it already exists, otherwise no one will do that. - */ - if (priv->broadcast) { - spin_lock_irq(&priv->lock); - memcpy(priv->broadcast->mcmember.mgid.raw, - priv->dev->broadcast + 4, - sizeof(union ib_gid)); - spin_unlock_irq(&priv->lock); - } - return 0; } -- GitLab From b8f42738acaddf67731c34935c0994e09a588ca7 Mon Sep 17 00:00:00 2001 From: "Michael J. Ruhl" Date: Tue, 26 Sep 2017 06:06:28 -0700 Subject: [PATCH 0524/1507] IB/hfi1: On error, fix use after free during user context setup During base context setup, if setup_base_ctxt() fails, the context is deallocated. This is incorrect because the context is referenced on return, to notify any waiting subcontext. If there are no subcontexts the pointer will be invalid. Reorganize the error path so that deallocate_ctxt() is called after all the possible subcontexts have been notified. Reviewed-by: Ira Weiny Signed-off-by: Michael J. Ruhl Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/file_ops.c | 41 ++++++++++++++------------- 1 file changed, 22 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 2bc89260235a1..d9a1e98931364 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -930,15 +930,8 @@ static int assign_ctxt(struct hfi1_filedata *fd, struct hfi1_user_info *uinfo) switch (ret) { case 0: ret = setup_base_ctxt(fd, uctxt); - if (uctxt->subctxt_cnt) { - /* - * Base context is done (successfully or not), notify - * anybody using a sub-context that is waiting for - * this completion. - */ - clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); - wake_up(&uctxt->wait); - } + if (ret) + deallocate_ctxt(uctxt); break; case 1: ret = complete_subctxt(fd); @@ -1305,25 +1298,25 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, /* Now allocate the RcvHdr queue and eager buffers. */ ret = hfi1_create_rcvhdrq(dd, uctxt); if (ret) - return ret; + goto done; ret = hfi1_setup_eagerbufs(uctxt); if (ret) - goto setup_failed; + goto done; /* If sub-contexts are enabled, do the appropriate setup */ if (uctxt->subctxt_cnt) ret = setup_subctxt(uctxt); if (ret) - goto setup_failed; + goto done; ret = hfi1_alloc_ctxt_rcv_groups(uctxt); if (ret) - goto setup_failed; + goto done; ret = init_user_ctxt(fd, uctxt); if (ret) - goto setup_failed; + goto done; user_init(uctxt); @@ -1331,12 +1324,22 @@ static int setup_base_ctxt(struct hfi1_filedata *fd, fd->uctxt = uctxt; hfi1_rcd_get(uctxt); - return 0; +done: + if (uctxt->subctxt_cnt) { + /* + * On error, set the failed bit so sub-contexts will clean up + * correctly. + */ + if (ret) + set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); -setup_failed: - /* Set the failed bit so sub-context init can do the right thing */ - set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags); - deallocate_ctxt(uctxt); + /* + * Base context is done (successfully or not), notify anybody + * using a sub-context that is waiting for this completion. + */ + clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags); + wake_up(&uctxt->wait); + } return ret; } -- GitLab From 828bcbdc975fbcfb27946c33d4b1d1bfab70789b Mon Sep 17 00:00:00 2001 From: Harish Chegondi Date: Tue, 26 Sep 2017 06:06:34 -0700 Subject: [PATCH 0525/1507] IB/hfi1: Unsuccessful PCIe caps tuning should not fail driver load Failure to tune PCIe capabilities should not fail driver load. This can cause the driver load to fail on systems with any of the following: 1. HFI's parent is not root. Example: HFI card is behind a PCIe bridge. 2. HFI's parent is not PCI Express capable. In these situations, failure to tune PCIe capabilities should be logged in the system message logs but not cause the driver load to fail. This patch also ensures pcie capability word DevCtl is written only after a successful read and the capability tuning process continues even if read/write of the pcie capability word DevCtl fails. Fixes: c53df62c7a9a ("IB/hfi1: Check return values from PCI config API calls") Fixes: bf70a7757736 ("staging/rdma/hfi1: Enable WFR PCIe extended tags from the driver") Reviewed-by: Michael J. Ruhl Reviewed-by: Mike Marciniszyn Reviewed-by: Jakub Byczkowski Signed-off-by: Harish Chegondi Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- drivers/infiniband/hw/hfi1/pcie.c | 50 +++++++++++++------------------ 1 file changed, 21 insertions(+), 29 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 82447b7cdda1e..09e50fd2a08f0 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -68,7 +68,7 @@ /* * Code to adjust PCIe capabilities. */ -static int tune_pcie_caps(struct hfi1_devdata *); +static void tune_pcie_caps(struct hfi1_devdata *); /* * Do all the common PCIe setup and initialization. @@ -351,7 +351,7 @@ int pcie_speeds(struct hfi1_devdata *dd) */ int request_msix(struct hfi1_devdata *dd, u32 msireq) { - int nvec, ret; + int nvec; nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq, PCI_IRQ_MSIX | PCI_IRQ_LEGACY); @@ -360,12 +360,7 @@ int request_msix(struct hfi1_devdata *dd, u32 msireq) return nvec; } - ret = tune_pcie_caps(dd); - if (ret) { - dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret); - pci_free_irq_vectors(dd->pcidev); - return ret; - } + tune_pcie_caps(dd); /* check for legacy IRQ */ if (nvec == 1 && !dd->pcidev->msix_enabled) @@ -502,7 +497,7 @@ uint aspm_mode = ASPM_MODE_DISABLED; module_param_named(aspm, aspm_mode, uint, S_IRUGO); MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic"); -static int tune_pcie_caps(struct hfi1_devdata *dd) +static void tune_pcie_caps(struct hfi1_devdata *dd) { struct pci_dev *parent; u16 rc_mpss, rc_mps, ep_mpss, ep_mps; @@ -513,22 +508,14 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * Turn on extended tags in DevCtl in case the BIOS has turned it off * to improve WFR SDMA bandwidth */ - ret = pcie_capability_read_word(dd->pcidev, - PCI_EXP_DEVCTL, &ectl); - if (ret) { - dd_dev_err(dd, "Unable to read from PCI config\n"); - return ret; - } - - if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { + ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl); + if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) { dd_dev_info(dd, "Enabling PCIe extended tags\n"); ectl |= PCI_EXP_DEVCTL_EXT_TAG; ret = pcie_capability_write_word(dd->pcidev, PCI_EXP_DEVCTL, ectl); - if (ret) { - dd_dev_err(dd, "Unable to write to PCI config\n"); - return ret; - } + if (ret) + dd_dev_info(dd, "Unable to write to PCI config\n"); } /* Find out supported and configured values for parent (root) */ parent = dd->pcidev->bus->self; @@ -536,15 +523,22 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) * The driver cannot perform the tuning if it does not have * access to the upstream component. */ - if (!parent) - return -EINVAL; + if (!parent) { + dd_dev_info(dd, "Parent not found\n"); + return; + } if (!pci_is_root_bus(parent->bus)) { dd_dev_info(dd, "Parent not root\n"); - return -EINVAL; + return; + } + if (!pci_is_pcie(parent)) { + dd_dev_info(dd, "Parent is not PCI Express capable\n"); + return; + } + if (!pci_is_pcie(dd->pcidev)) { + dd_dev_info(dd, "PCI device is not PCI Express capable\n"); + return; } - - if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev)) - return -EINVAL; rc_mpss = parent->pcie_mpss; rc_mps = ffs(pcie_get_mps(parent)) - 8; /* Find out supported and configured values for endpoint (us) */ @@ -590,8 +584,6 @@ static int tune_pcie_caps(struct hfi1_devdata *dd) ep_mrrs = max_mrrs; pcie_set_readrq(dd->pcidev, ep_mrrs); } - - return 0; } /* End of PCIe capability tuning */ -- GitLab From 36de80740008e6a4a55115b4a92e2059e47c1cba Mon Sep 17 00:00:00 2001 From: Richard Genoud Date: Wed, 27 Sep 2017 14:49:17 +0200 Subject: [PATCH 0526/1507] mtd: nand: atmel: fix buffer overflow in atmel_pmecc_user When calculating the size needed by struct atmel_pmecc_user *user, the dmu and delta buffer sizes were forgotten. This lead to a memory corruption (especially with a large ecc_strength). Link: http://lkml.kernel.org/r/1506503157.3016.5.camel@gmail.com Fixes: f88fc122cc34 ("mtd: nand: Cleanup/rework the atmel_nand driver") Cc: stable@vger.kernel.org Reported-by: Richard Genoud Pointed-at-by: Boris Brezillon Signed-off-by: Richard Genoud Reviewed-by: Nicolas Ferre Signed-off-by: Boris Brezillon --- drivers/mtd/nand/atmel/pmecc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/nand/atmel/pmecc.c b/drivers/mtd/nand/atmel/pmecc.c index 146af82183145..8268636675efc 100644 --- a/drivers/mtd/nand/atmel/pmecc.c +++ b/drivers/mtd/nand/atmel/pmecc.c @@ -363,7 +363,7 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, size += (req->ecc.strength + 1) * sizeof(u16); /* Reserve space for mu, dmu and delta. */ size = ALIGN(size, sizeof(s32)); - size += (req->ecc.strength + 1) * sizeof(s32); + size += (req->ecc.strength + 1) * sizeof(s32) * 3; user = kzalloc(size, GFP_KERNEL); if (!user) -- GitLab From 85e482285bbbd508483cbe08de69c8fe00cdbbfe Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:11 +0200 Subject: [PATCH 0527/1507] fib: notifier: Add VIF add and delete event types In order for an interface to forward packets according to the kernel multicast routing table, it must be configured with a VIF index according to the mroute user API. The VIF index is then used to refer to that interface in the mroute user API, for example, to set the iif and oifs of an MFC entry. In order to allow drivers to be aware and offload multicast routes, they have to be aware of the VIF add and delete notifications. Due to the fact that a specific VIF can be deleted and re-added pointing to another netdevice, and the MFC routes that point to it will forward the matching packets to the new netdevice, a driver willing to offload MFC cache entries must be aware of the VIF add and delete events in addition to MFC routes notifications. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/fib_notifier.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index 669b9716dc7a6..54cd6b839d2f6 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -20,6 +20,8 @@ enum fib_event_type { FIB_EVENT_RULE_DEL, FIB_EVENT_NH_ADD, FIB_EVENT_NH_DEL, + FIB_EVENT_VIF_ADD, + FIB_EVENT_VIF_DEL, }; struct fib_notifier_ops { -- GitLab From 310ebbba3b7396b00bce08a33f1d2de2c74fa257 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:12 +0200 Subject: [PATCH 0528/1507] ipmr: Add reference count to MFC entries Next commits will introduce MFC notifications through the atomic fib_notification chain, thus allowing modules to be aware of MFC entries. Due to the fact that modules may need to hold a reference to an MFC entry, add reference count to MFC entries to prevent them from being freed while these modules use them. The reference counting is done only on resolved MFC entries currently. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 21 +++++++++++++++++++++ net/ipv4/ipmr.c | 8 +++++--- 2 files changed, 26 insertions(+), 3 deletions(-) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index d7f63339ef0b4..10028f208efb6 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -109,6 +109,7 @@ struct mfc_cache_cmp_arg { * @wrong_if: number of wrong source interface hits * @lastuse: time of last use of the group (traffic or update) * @ttls: OIF TTL threshold array + * @refcount: reference count for this entry * @list: global entry list * @rcu: used for entry destruction */ @@ -138,6 +139,7 @@ struct mfc_cache { unsigned long wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; + refcount_t refcount; } res; } mfc_un; struct list_head list; @@ -148,4 +150,23 @@ struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid); + +#ifdef CONFIG_IP_MROUTE +void ipmr_cache_free(struct mfc_cache *mfc_cache); +#else +static inline void ipmr_cache_free(struct mfc_cache *mfc_cache) +{ +} +#endif + +static inline void ipmr_cache_put(struct mfc_cache *c) +{ + if (refcount_dec_and_test(&c->mfc_un.res.refcount)) + ipmr_cache_free(c); +} +static inline void ipmr_cache_hold(struct mfc_cache *c) +{ + refcount_inc(&c->mfc_un.res.refcount); +} + #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c9b3e6e069aea..86dc5f98c5dd7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -652,10 +652,11 @@ static void ipmr_cache_free_rcu(struct rcu_head *head) kmem_cache_free(mrt_cachep, c); } -static inline void ipmr_cache_free(struct mfc_cache *c) +void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->rcu, ipmr_cache_free_rcu); } +EXPORT_SYMBOL(ipmr_cache_free); /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. @@ -949,6 +950,7 @@ static struct mfc_cache *ipmr_cache_alloc(void) if (c) { c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->mfc_un.res.minvif = MAXVIFS; + refcount_set(&c->mfc_un.res.refcount, 1); } return c; } @@ -1162,7 +1164,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); return 0; } @@ -1264,7 +1266,7 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_free(c); + ipmr_cache_put(c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { -- GitLab From 4d65b9487831170e699b2fc64a91b839d729bd78 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:13 +0200 Subject: [PATCH 0529/1507] ipmr: Add FIB notification access functions Make the ipmr module register as a FIB notifier. To do that, implement both the ipmr_seq_read and ipmr_dump ops. The ipmr_seq_read op returns a sequence counter that is incremented on every notification related operation done by the ipmr. To implement that, add a sequence counter in the netns_ipv4 struct and increment it whenever a new MFC route or VIF are added or deleted. The sequence operations are protected by the RTNL lock. The ipmr_dump iterates the list of MFC routes and the list of VIF entries and sends notifications about them. The entries dump is done under RCU where the VIF dump uses the mrt_lock too, as the vif->dev field can change under RCU. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 15 +++++ include/net/netns/ipv4.h | 3 + net/ipv4/ipmr.c | 137 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 153 insertions(+), 2 deletions(-) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 10028f208efb6..54c5cb82ddcb1 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #ifdef CONFIG_IP_MROUTE @@ -58,6 +59,14 @@ struct vif_device { int link; /* Physical interface index */ }; +struct vif_entry_notifier_info { + struct fib_notifier_info info; + struct net_device *dev; + vifi_t vif_index; + unsigned short vif_flags; + u32 tb_id; +}; + #define VIFF_STATIC 0x8000 #define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) @@ -146,6 +155,12 @@ struct mfc_cache { struct rcu_head rcu; }; +struct mfc_entry_notifier_info { + struct fib_notifier_info info; + struct mfc_cache *mfc; + u32 tb_id; +}; + struct rtmsg; int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 8387f099115e5..abc84d986da49 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -163,6 +163,9 @@ struct netns_ipv4 { struct fib_notifier_ops *notifier_ops; unsigned int fib_seq; /* protected by rtnl_mutex */ + struct fib_notifier_ops *ipmr_notifier_ops; + unsigned int ipmr_seq; /* protected by rtnl_mutex */ + atomic_t rt_genid; }; #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 86dc5f98c5dd7..49879c3383575 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -264,6 +264,16 @@ static void __net_exit ipmr_rules_exit(struct net *net) fib_rules_unregister(net->ipv4.mr_rules_ops); rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); +} #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) @@ -298,6 +308,16 @@ static void __net_exit ipmr_rules_exit(struct net *net) net->ipv4.mrt = NULL; rtnl_unlock(); } + +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} + +static unsigned int ipmr_rules_seq_read(struct net *net) +{ + return 0; +} #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, @@ -587,6 +607,43 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } #endif +static int call_ipmr_vif_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + +static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, + struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + return call_fib_notifier(nb, net, event_type, &info.info); +} + /** * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call @@ -3050,14 +3107,87 @@ static const struct net_protocol pim_protocol = { }; #endif +static unsigned int ipmr_seq_read(struct net *net) +{ + ASSERT_RTNL(); + + return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); +} + +static int ipmr_dump(struct net *net, struct notifier_block *nb) +{ + struct mr_table *mrt; + int err; + + err = ipmr_rules_dump(net, nb); + if (err) + return err; + + ipmr_for_each_table(mrt, net) { + struct vif_device *v = &mrt->vif_table[0]; + struct mfc_cache *mfc; + int vifi; + + /* Notifiy on table VIF entries */ + read_lock(&mrt_lock); + for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { + if (!v->dev) + continue; + + call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD, + v, vifi, mrt->id); + } + read_unlock(&mrt_lock); + + /* Notify on table MFC entries */ + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + call_ipmr_mfc_entry_notifier(nb, net, + FIB_EVENT_ENTRY_ADD, mfc, + mrt->id); + } + + return 0; +} + +static const struct fib_notifier_ops ipmr_notifier_ops_template = { + .family = RTNL_FAMILY_IPMR, + .fib_seq_read = ipmr_seq_read, + .fib_dump = ipmr_dump, + .owner = THIS_MODULE, +}; + +int __net_init ipmr_notifier_init(struct net *net) +{ + struct fib_notifier_ops *ops; + + net->ipv4.ipmr_seq = 0; + + ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv4.ipmr_notifier_ops = ops; + + return 0; +} + +static void __net_exit ipmr_notifier_exit(struct net *net) +{ + fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); + net->ipv4.ipmr_notifier_ops = NULL; +} + /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; + err = ipmr_notifier_init(net); + if (err) + goto ipmr_notifier_fail; + err = ipmr_rules_init(net); if (err < 0) - goto fail; + goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -3074,7 +3204,9 @@ static int __net_init ipmr_net_init(struct net *net) proc_vif_fail: ipmr_rules_exit(net); #endif -fail: +ipmr_rules_fail: + ipmr_notifier_exit(net); +ipmr_notifier_fail: return err; } @@ -3084,6 +3216,7 @@ static void __net_exit ipmr_net_exit(struct net *net) remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif + ipmr_notifier_exit(net); ipmr_rules_exit(net); } -- GitLab From b362053a7cc0fcc09b92642ba5dd1ca7fddc9004 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:14 +0200 Subject: [PATCH 0530/1507] ipmr: Send FIB notifications on MFC and VIF entries Use the newly introduced notification chain to send events upon VIF and MFC addition and deletion. The MFC notifications are sent only on resolved MFC entries, as unresolved cannot be offloaded. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 49879c3383575..ba71bc4023369 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -627,6 +627,27 @@ static int call_ipmr_vif_entry_notifier(struct notifier_block *nb, return call_fib_notifier(nb, net, event_type, &info.info); } +static int call_ipmr_vif_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct vif_device *vif, + vifi_t vif_index, u32 tb_id) +{ + struct vif_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .dev = vif->dev, + .vif_index = vif_index, + .vif_flags = vif->flags, + .tb_id = tb_id, + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, @@ -644,6 +665,24 @@ static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, return call_fib_notifier(nb, net, event_type, &info.info); } +static int call_ipmr_mfc_entry_notifiers(struct net *net, + enum fib_event_type event_type, + struct mfc_cache *mfc, u32 tb_id) +{ + struct mfc_entry_notifier_info info = { + .info = { + .family = RTNL_FAMILY_IPMR, + .net = net, + }, + .mfc = mfc, + .tb_id = tb_id + }; + + ASSERT_RTNL(); + net->ipv4.ipmr_seq++; + return call_fib_notifiers(net, event_type, &info.info); +} + /** * vif_delete - Delete a VIF entry * @notify: Set to 1, if the caller is a notifier_call @@ -651,6 +690,7 @@ static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { + struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; @@ -660,6 +700,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, v = &mrt->vif_table[vifi]; + if (VIF_EXISTS(mrt, vifi)) + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, vifi, + mrt->id); + write_lock_bh(&mrt_lock); dev = v->dev; v->dev = NULL; @@ -909,6 +953,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, if (vifi+1 > mrt->maxvif) mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); + call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, vifi, mrt->id); return 0; } @@ -1209,6 +1254,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ @@ -1220,6 +1266,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_put(c); @@ -1248,6 +1295,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1297,6 +1346,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } @@ -1304,6 +1354,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, bool all) { + struct net *net = read_pnet(&mrt->net); struct mfc_cache *c, *tmp; LIST_HEAD(list); int i; @@ -1322,6 +1373,8 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, + mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_put(c); } -- GitLab From c7c0bbeae9501a7e42f2fd306d6a6399aca688b6 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:15 +0200 Subject: [PATCH 0531/1507] net: ipmr: Add MFC offload indication Allow drivers, registered to the fib notification chain indicate whether a multicast MFC route is offloaded or not, similarly to unicast routes. The indication of whether a route is offloaded is done using the mfc_flags field on an mfc_cache struct, and the information is sent to the userspace via the RTNetlink interface only. Currently, MFC routes are either offloaded or not, thus there is no need to add per-VIF offload indication. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 2 ++ net/ipv4/ipmr.c | 3 +++ 2 files changed, 5 insertions(+) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 54c5cb82ddcb1..5566580811ce6 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -90,9 +90,11 @@ struct mr_table { /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) + * MFC_OFFLOAD - the entry was offloaded to the hardware */ enum { MFC_STATIC = BIT(0), + MFC_OFFLOAD = BIT(1), }; struct mfc_cache_cmp_arg { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index ba71bc4023369..2a795d2c05029 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2268,6 +2268,9 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) return -EMSGSIZE; + if (c->mfc_flags & MFC_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; + if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) return -EMSGSIZE; -- GitLab From 478e4c2f0067d57d7c17059caafab026ca32084a Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:16 +0200 Subject: [PATCH 0532/1507] net: mroute: Check if rule is a default rule When the ipmr starts, it adds one default FIB rule that matches all packets and sends them to the DEFAULT (multicast) FIB table. A more complex rule can be added by user to specify that for a specific interface, a packet should be look up at either an arbitrary table or according to the l3mdev of the interface. For drivers willing to offload the ipmr logic into a hardware but don't want to offload all the FIB rules functionality, provide a function that can indicate whether the FIB rule is the default multicast rule, thus only one routing table is needed. This way, a driver can register to the FIB notification chain, get notifications about FIB rules added and trigger some kind of an internal abort mechanism when a non default rule is added by the user. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 7 +++++++ net/ipv4/ipmr.c | 12 ++++++++++++ 2 files changed, 19 insertions(+) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 5566580811ce6..b072a84fbe1c7 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -19,6 +20,7 @@ int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); +bool ipmr_rule_default(const struct fib_rule *rule); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, char __user *optval, unsigned int optlen) @@ -46,6 +48,11 @@ static inline int ip_mroute_opt(int opt) { return 0; } + +static inline bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} #endif struct vif_device { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2a795d2c05029..292a8e80bdfaa 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -274,6 +274,12 @@ static unsigned int ipmr_rules_seq_read(struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); } + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; +} +EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) @@ -318,6 +324,12 @@ static unsigned int ipmr_rules_seq_read(struct net *net) { return 0; } + +bool ipmr_rule_default(const struct fib_rule *rule) +{ + return true; +} +EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, -- GitLab From c011ec1bbfd69e091ca8d77e13fc251a07be57dc Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:17 +0200 Subject: [PATCH 0533/1507] mlxsw: spectrum: Add the multicast routing offloading logic Add the multicast router offloading logic, which is in charge of handling the VIF and MFC notifications and translating it to the hardware logic API. The offloading logic has to overcome several obstacles in order to safely comply with the kernel multicast router user API: - It must keep track of the mapping between VIFs to netdevices. The user can add an MFC cache entry pointing to a VIF, delete the VIF and add re-add it with a different netdevice. The offloading logic has to handle this in order to be compatible with the kernel logic. - It must keep track of the mapping between netdevices to spectrum RIFs, as the current hardware implementation assume having a RIF for every port in a multicast router. - It must handle routes pointing to pimreg device to be trapped to the kernel, as the packet should be delivered to userspace. - It must handle routes pointing tunnel VIFs. The current implementation does not support multicast forwarding to tunnels, thus routes that point to a tunnel should be trapped to the kernel. - It must be aware of proxy multicast routes, which include both (*,*) routes and duplicate routes. Currently proxy routes are not offloaded and trigger the abort mechanism: removal of all routes from hardware and triggering the traffic to go through the kernel. The multicast routing offloading logic also updates the counters of the offloaded MFC routes in a periodic work. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/Makefile | 3 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 1 + .../net/ethernet/mellanox/mlxsw/spectrum_mr.c | 1014 +++++++++++++++++ .../net/ethernet/mellanox/mlxsw/spectrum_mr.h | 133 +++ 4 files changed, 1150 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 4b88158173f39..9b29764905f34 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -17,7 +17,8 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_kvdl.o spectrum_acl_tcam.o \ spectrum_acl.o spectrum_flower.o \ spectrum_cnt.o spectrum_fid.o \ - spectrum_ipip.o spectrum_acl_flex_actions.o + spectrum_ipip.o spectrum_acl_flex_actions.o \ + spectrum_mr.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 9355d914a4c80..44c5259e5548b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -153,6 +153,7 @@ struct mlxsw_sp { struct mlxsw_sp_sb *sb; struct mlxsw_sp_bridge *bridge; struct mlxsw_sp_router *router; + struct mlxsw_sp_mr *mr; struct mlxsw_afa *afa; struct mlxsw_sp_acl *acl; struct mlxsw_sp_fid_core *fid_core; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c new file mode 100644 index 0000000000000..09120259a45df --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -0,0 +1,1014 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Yotam Gigi + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include + +#include "spectrum_mr.h" +#include "spectrum_router.h" + +struct mlxsw_sp_mr { + const struct mlxsw_sp_mr_ops *mr_ops; + void *catchall_route_priv; + struct delayed_work stats_update_dw; + struct list_head table_list; +#define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */ + unsigned long priv[0]; + /* priv has to be always the last item */ +}; + +struct mlxsw_sp_mr_vif { + struct net_device *dev; + const struct mlxsw_sp_rif *rif; + unsigned long vif_flags; + + /* A list of route_vif_entry structs that point to routes that the VIF + * instance is used as one of the egress VIFs + */ + struct list_head route_evif_list; + + /* A list of route_vif_entry structs that point to routes that the VIF + * instance is used as an ingress VIF + */ + struct list_head route_ivif_list; +}; + +struct mlxsw_sp_mr_route_vif_entry { + struct list_head vif_node; + struct list_head route_node; + struct mlxsw_sp_mr_vif *mr_vif; + struct mlxsw_sp_mr_route *mr_route; +}; + +struct mlxsw_sp_mr_table { + struct list_head node; + enum mlxsw_sp_l3proto proto; + struct mlxsw_sp *mlxsw_sp; + u32 vr_id; + struct mlxsw_sp_mr_vif vifs[MAXVIFS]; + struct list_head route_list; + struct rhashtable route_ht; + char catchall_route_priv[0]; + /* catchall_route_priv has to be always the last item */ +}; + +struct mlxsw_sp_mr_route { + struct list_head node; + struct rhash_head ht_node; + struct mlxsw_sp_mr_route_key key; + enum mlxsw_sp_mr_route_action route_action; + u16 min_mtu; + struct mfc_cache *mfc4; + void *route_priv; + const struct mlxsw_sp_mr_table *mr_table; + /* A list of route_vif_entry structs that point to the egress VIFs */ + struct list_head evif_list; + /* A route_vif_entry struct that point to the ingress VIF */ + struct mlxsw_sp_mr_route_vif_entry ivif; +}; + +static const struct rhashtable_params mlxsw_sp_mr_route_ht_params = { + .key_len = sizeof(struct mlxsw_sp_mr_route_key), + .key_offset = offsetof(struct mlxsw_sp_mr_route, key), + .head_offset = offsetof(struct mlxsw_sp_mr_route, ht_node), + .automatic_shrinking = true, +}; + +static bool mlxsw_sp_mr_vif_regular(const struct mlxsw_sp_mr_vif *vif) +{ + return !(vif->vif_flags & (VIFF_TUNNEL | VIFF_REGISTER)); +} + +static bool mlxsw_sp_mr_vif_valid(const struct mlxsw_sp_mr_vif *vif) +{ + return mlxsw_sp_mr_vif_regular(vif) && vif->dev && vif->rif; +} + +static bool mlxsw_sp_mr_vif_rif_invalid(const struct mlxsw_sp_mr_vif *vif) +{ + return mlxsw_sp_mr_vif_regular(vif) && vif->dev && !vif->rif; +} + +static bool +mlxsw_sp_mr_route_ivif_in_evifs(const struct mlxsw_sp_mr_route *mr_route) +{ + vifi_t ivif; + + switch (mr_route->mr_table->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + ivif = mr_route->mfc4->mfc_parent; + return mr_route->mfc4->mfc_un.res.ttls[ivif] != 255; + case MLXSW_SP_L3_PROTO_IPV6: + /* fall through */ + default: + WARN_ON_ONCE(1); + } + return false; +} + +static int +mlxsw_sp_mr_route_valid_evifs_num(const struct mlxsw_sp_mr_route *mr_route) +{ + struct mlxsw_sp_mr_route_vif_entry *rve; + int valid_evifs; + + valid_evifs = 0; + list_for_each_entry(rve, &mr_route->evif_list, route_node) + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) + valid_evifs++; + return valid_evifs; +} + +static bool mlxsw_sp_mr_route_starg(const struct mlxsw_sp_mr_route *mr_route) +{ + switch (mr_route->mr_table->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return mr_route->key.source_mask.addr4 == INADDR_ANY; + case MLXSW_SP_L3_PROTO_IPV6: + /* fall through */ + default: + WARN_ON_ONCE(1); + } + return false; +} + +static enum mlxsw_sp_mr_route_action +mlxsw_sp_mr_route_action(const struct mlxsw_sp_mr_route *mr_route) +{ + struct mlxsw_sp_mr_route_vif_entry *rve; + + /* If the ingress port is not regular and resolved, trap the route */ + if (!mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif)) + return MLXSW_SP_MR_ROUTE_ACTION_TRAP; + + /* The kernel does not match a (*,G) route that the ingress interface is + * not one of the egress interfaces, so trap these kind of routes. + */ + if (mlxsw_sp_mr_route_starg(mr_route) && + !mlxsw_sp_mr_route_ivif_in_evifs(mr_route)) + return MLXSW_SP_MR_ROUTE_ACTION_TRAP; + + /* If the route has no valid eVIFs, trap it. */ + if (!mlxsw_sp_mr_route_valid_evifs_num(mr_route)) + return MLXSW_SP_MR_ROUTE_ACTION_TRAP; + + /* If either one of the eVIFs is not regular (VIF of type pimreg or + * tunnel) or one of the VIFs has no matching RIF, trap the packet. + */ + list_for_each_entry(rve, &mr_route->evif_list, route_node) { + if (!mlxsw_sp_mr_vif_regular(rve->mr_vif) || + mlxsw_sp_mr_vif_rif_invalid(rve->mr_vif)) + return MLXSW_SP_MR_ROUTE_ACTION_TRAP; + } + return MLXSW_SP_MR_ROUTE_ACTION_FORWARD; +} + +static enum mlxsw_sp_mr_route_prio +mlxsw_sp_mr_route_prio(const struct mlxsw_sp_mr_route *mr_route) +{ + return mlxsw_sp_mr_route_starg(mr_route) ? + MLXSW_SP_MR_ROUTE_PRIO_STARG : MLXSW_SP_MR_ROUTE_PRIO_SG; +} + +static void mlxsw_sp_mr_route4_key(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route_key *key, + const struct mfc_cache *mfc) +{ + bool starg = (mfc->mfc_origin == INADDR_ANY); + + memset(key, 0, sizeof(*key)); + key->vrid = mr_table->vr_id; + key->proto = mr_table->proto; + key->group.addr4 = mfc->mfc_mcastgrp; + key->group_mask.addr4 = 0xffffffff; + key->source.addr4 = mfc->mfc_origin; + key->source_mask.addr4 = starg ? 0 : 0xffffffff; +} + +static int mlxsw_sp_mr_route_evif_link(struct mlxsw_sp_mr_route *mr_route, + struct mlxsw_sp_mr_vif *mr_vif) +{ + struct mlxsw_sp_mr_route_vif_entry *rve; + + rve = kzalloc(sizeof(*rve), GFP_KERNEL); + if (!rve) + return -ENOMEM; + rve->mr_route = mr_route; + rve->mr_vif = mr_vif; + list_add_tail(&rve->route_node, &mr_route->evif_list); + list_add_tail(&rve->vif_node, &mr_vif->route_evif_list); + return 0; +} + +static void +mlxsw_sp_mr_route_evif_unlink(struct mlxsw_sp_mr_route_vif_entry *rve) +{ + list_del(&rve->route_node); + list_del(&rve->vif_node); + kfree(rve); +} + +static void mlxsw_sp_mr_route_ivif_link(struct mlxsw_sp_mr_route *mr_route, + struct mlxsw_sp_mr_vif *mr_vif) +{ + mr_route->ivif.mr_route = mr_route; + mr_route->ivif.mr_vif = mr_vif; + list_add_tail(&mr_route->ivif.vif_node, &mr_vif->route_ivif_list); +} + +static void mlxsw_sp_mr_route_ivif_unlink(struct mlxsw_sp_mr_route *mr_route) +{ + list_del(&mr_route->ivif.vif_node); +} + +static int +mlxsw_sp_mr_route_info_create(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route, + struct mlxsw_sp_mr_route_info *route_info) +{ + struct mlxsw_sp_mr_route_vif_entry *rve; + u16 *erif_indices; + u16 irif_index; + u16 erif = 0; + + erif_indices = kmalloc_array(MAXVIFS, sizeof(*erif_indices), + GFP_KERNEL); + if (!erif_indices) + return -ENOMEM; + + list_for_each_entry(rve, &mr_route->evif_list, route_node) { + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) { + u16 rifi = mlxsw_sp_rif_index(rve->mr_vif->rif); + + erif_indices[erif++] = rifi; + } + } + + if (mlxsw_sp_mr_vif_valid(mr_route->ivif.mr_vif)) + irif_index = mlxsw_sp_rif_index(mr_route->ivif.mr_vif->rif); + else + irif_index = 0; + + route_info->irif_index = irif_index; + route_info->erif_indices = erif_indices; + route_info->min_mtu = mr_route->min_mtu; + route_info->route_action = mr_route->route_action; + route_info->erif_num = erif; + return 0; +} + +static void +mlxsw_sp_mr_route_info_destroy(struct mlxsw_sp_mr_route_info *route_info) +{ + kfree(route_info->erif_indices); +} + +static int mlxsw_sp_mr_route_write(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route, + bool replace) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + struct mlxsw_sp_mr_route_info route_info; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + int err; + + err = mlxsw_sp_mr_route_info_create(mr_table, mr_route, &route_info); + if (err) + return err; + + if (!replace) { + struct mlxsw_sp_mr_route_params route_params; + + mr_route->route_priv = kzalloc(mr->mr_ops->route_priv_size, + GFP_KERNEL); + if (!mr_route->route_priv) { + err = -ENOMEM; + goto out; + } + + route_params.key = mr_route->key; + route_params.value = route_info; + route_params.prio = mlxsw_sp_mr_route_prio(mr_route); + err = mr->mr_ops->route_create(mlxsw_sp, mr->priv, + mr_route->route_priv, + &route_params); + if (err) + kfree(mr_route->route_priv); + } else { + err = mr->mr_ops->route_update(mlxsw_sp, mr_route->route_priv, + &route_info); + } +out: + mlxsw_sp_mr_route_info_destroy(&route_info); + return err; +} + +static void mlxsw_sp_mr_route_erase(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + + mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, mr_route->route_priv); + kfree(mr_route->route_priv); +} + +static struct mlxsw_sp_mr_route * +mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table, + struct mfc_cache *mfc) +{ + struct mlxsw_sp_mr_route_vif_entry *rve, *tmp; + struct mlxsw_sp_mr_route *mr_route; + int err; + int i; + + /* Allocate and init a new route and fill it with parameters */ + mr_route = kzalloc(sizeof(*mr_route), GFP_KERNEL); + if (!mr_route) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&mr_route->evif_list); + mlxsw_sp_mr_route4_key(mr_table, &mr_route->key, mfc); + + /* Find min_mtu and link iVIF and eVIFs */ + mr_route->min_mtu = ETH_MAX_MTU; + ipmr_cache_hold(mfc); + mr_route->mfc4 = mfc; + mr_route->mr_table = mr_table; + for (i = 0; i < MAXVIFS; i++) { + if (mfc->mfc_un.res.ttls[i] != 255) { + err = mlxsw_sp_mr_route_evif_link(mr_route, + &mr_table->vifs[i]); + if (err) + goto err; + if (mr_table->vifs[i].dev && + mr_table->vifs[i].dev->mtu < mr_route->min_mtu) + mr_route->min_mtu = mr_table->vifs[i].dev->mtu; + } + } + mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]); + if (err) + goto err; + + mr_route->route_action = mlxsw_sp_mr_route_action(mr_route); + return mr_route; +err: + ipmr_cache_put(mfc); + list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node) + mlxsw_sp_mr_route_evif_unlink(rve); + kfree(mr_route); + return ERR_PTR(err); +} + +static void mlxsw_sp_mr_route4_destroy(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route) +{ + struct mlxsw_sp_mr_route_vif_entry *rve, *tmp; + + mlxsw_sp_mr_route_ivif_unlink(mr_route); + ipmr_cache_put(mr_route->mfc4); + list_for_each_entry_safe(rve, tmp, &mr_route->evif_list, route_node) + mlxsw_sp_mr_route_evif_unlink(rve); + kfree(mr_route); +} + +static void mlxsw_sp_mr_route_destroy(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route) +{ + switch (mr_table->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + mlxsw_sp_mr_route4_destroy(mr_table, mr_route); + break; + case MLXSW_SP_L3_PROTO_IPV6: + /* fall through */ + default: + WARN_ON_ONCE(1); + } +} + +static void mlxsw_sp_mr_mfc_offload_set(struct mlxsw_sp_mr_route *mr_route, + bool offload) +{ + switch (mr_route->mr_table->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + if (offload) + mr_route->mfc4->mfc_flags |= MFC_OFFLOAD; + else + mr_route->mfc4->mfc_flags &= ~MFC_OFFLOAD; + break; + case MLXSW_SP_L3_PROTO_IPV6: + /* fall through */ + default: + WARN_ON_ONCE(1); + } +} + +static void mlxsw_sp_mr_mfc_offload_update(struct mlxsw_sp_mr_route *mr_route) +{ + bool offload; + + offload = mr_route->route_action != MLXSW_SP_MR_ROUTE_ACTION_TRAP; + mlxsw_sp_mr_mfc_offload_set(mr_route, offload); +} + +static void __mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route *mr_route) +{ + mlxsw_sp_mr_mfc_offload_set(mr_route, false); + mlxsw_sp_mr_route_erase(mr_table, mr_route); + rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, + mlxsw_sp_mr_route_ht_params); + list_del(&mr_route->node); + mlxsw_sp_mr_route_destroy(mr_table, mr_route); +} + +int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table, + struct mfc_cache *mfc, bool replace) +{ + struct mlxsw_sp_mr_route *mr_orig_route = NULL; + struct mlxsw_sp_mr_route *mr_route; + int err; + + /* If the route is a (*,*) route, abort, as these kind of routes are + * used for proxy routes. + */ + if (mfc->mfc_origin == INADDR_ANY && mfc->mfc_mcastgrp == INADDR_ANY) { + dev_warn(mr_table->mlxsw_sp->bus_info->dev, + "Offloading proxy routes is not supported.\n"); + return -EINVAL; + } + + /* Create a new route */ + mr_route = mlxsw_sp_mr_route4_create(mr_table, mfc); + if (IS_ERR(mr_route)) + return PTR_ERR(mr_route); + + /* Find any route with a matching key */ + mr_orig_route = rhashtable_lookup_fast(&mr_table->route_ht, + &mr_route->key, + mlxsw_sp_mr_route_ht_params); + if (replace) { + /* On replace case, make the route point to the new route_priv. + */ + if (WARN_ON(!mr_orig_route)) { + err = -ENOENT; + goto err_no_orig_route; + } + mr_route->route_priv = mr_orig_route->route_priv; + } else if (mr_orig_route) { + /* On non replace case, if another route with the same key was + * found, abort, as duplicate routes are used for proxy routes. + */ + dev_warn(mr_table->mlxsw_sp->bus_info->dev, + "Offloading proxy routes is not supported.\n"); + err = -EINVAL; + goto err_duplicate_route; + } + + /* Put it in the table data-structures */ + list_add_tail(&mr_route->node, &mr_table->route_list); + err = rhashtable_insert_fast(&mr_table->route_ht, + &mr_route->ht_node, + mlxsw_sp_mr_route_ht_params); + if (err) + goto err_rhashtable_insert; + + /* Write the route to the hardware */ + err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace); + if (err) + goto err_mr_route_write; + + /* Destroy the original route */ + if (replace) { + rhashtable_remove_fast(&mr_table->route_ht, + &mr_orig_route->ht_node, + mlxsw_sp_mr_route_ht_params); + list_del(&mr_orig_route->node); + mlxsw_sp_mr_route4_destroy(mr_table, mr_orig_route); + } + + mlxsw_sp_mr_mfc_offload_update(mr_route); + return 0; + +err_mr_route_write: + rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, + mlxsw_sp_mr_route_ht_params); +err_rhashtable_insert: + list_del(&mr_route->node); +err_no_orig_route: +err_duplicate_route: + mlxsw_sp_mr_route4_destroy(mr_table, mr_route); + return err; +} + +void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table, + struct mfc_cache *mfc) +{ + struct mlxsw_sp_mr_route *mr_route; + struct mlxsw_sp_mr_route_key key; + + mlxsw_sp_mr_route4_key(mr_table, &key, mfc); + mr_route = rhashtable_lookup_fast(&mr_table->route_ht, &key, + mlxsw_sp_mr_route_ht_params); + if (mr_route) + __mlxsw_sp_mr_route_del(mr_table, mr_route); +} + +/* Should be called after the VIF struct is updated */ +static int +mlxsw_sp_mr_route_ivif_resolve(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route_vif_entry *rve) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + enum mlxsw_sp_mr_route_action route_action; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + u16 irif_index; + int err; + + route_action = mlxsw_sp_mr_route_action(rve->mr_route); + if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP) + return 0; + + /* rve->mr_vif->rif is guaranteed to be valid at this stage */ + irif_index = mlxsw_sp_rif_index(rve->mr_vif->rif); + err = mr->mr_ops->route_irif_update(mlxsw_sp, rve->mr_route->route_priv, + irif_index); + if (err) + return err; + + err = mr->mr_ops->route_action_update(mlxsw_sp, + rve->mr_route->route_priv, + route_action); + if (err) + /* No need to rollback here because the iRIF change only takes + * place after the action has been updated. + */ + return err; + + rve->mr_route->route_action = route_action; + mlxsw_sp_mr_mfc_offload_update(rve->mr_route); + return 0; +} + +static void +mlxsw_sp_mr_route_ivif_unresolve(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route_vif_entry *rve) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + + mr->mr_ops->route_action_update(mlxsw_sp, rve->mr_route->route_priv, + MLXSW_SP_MR_ROUTE_ACTION_TRAP); + rve->mr_route->route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP; + mlxsw_sp_mr_mfc_offload_update(rve->mr_route); +} + +/* Should be called after the RIF struct is updated */ +static int +mlxsw_sp_mr_route_evif_resolve(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route_vif_entry *rve) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + enum mlxsw_sp_mr_route_action route_action; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + u16 erif_index = 0; + int err; + + /* Update the route action, as the new eVIF can be a tunnel or a pimreg + * device which will require updating the action. + */ + route_action = mlxsw_sp_mr_route_action(rve->mr_route); + if (route_action != rve->mr_route->route_action) { + err = mr->mr_ops->route_action_update(mlxsw_sp, + rve->mr_route->route_priv, + route_action); + if (err) + return err; + } + + /* Add the eRIF */ + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) { + erif_index = mlxsw_sp_rif_index(rve->mr_vif->rif); + err = mr->mr_ops->route_erif_add(mlxsw_sp, + rve->mr_route->route_priv, + erif_index); + if (err) + goto err_route_erif_add; + } + + /* Update the minimum MTU */ + if (rve->mr_vif->dev->mtu < rve->mr_route->min_mtu) { + rve->mr_route->min_mtu = rve->mr_vif->dev->mtu; + err = mr->mr_ops->route_min_mtu_update(mlxsw_sp, + rve->mr_route->route_priv, + rve->mr_route->min_mtu); + if (err) + goto err_route_min_mtu_update; + } + + rve->mr_route->route_action = route_action; + mlxsw_sp_mr_mfc_offload_update(rve->mr_route); + return 0; + +err_route_min_mtu_update: + if (mlxsw_sp_mr_vif_valid(rve->mr_vif)) + mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, + erif_index); +err_route_erif_add: + if (route_action != rve->mr_route->route_action) + mr->mr_ops->route_action_update(mlxsw_sp, + rve->mr_route->route_priv, + rve->mr_route->route_action); + return err; +} + +/* Should be called before the RIF struct is updated */ +static void +mlxsw_sp_mr_route_evif_unresolve(struct mlxsw_sp_mr_table *mr_table, + struct mlxsw_sp_mr_route_vif_entry *rve) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + enum mlxsw_sp_mr_route_action route_action; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + u16 rifi; + + /* If the unresolved RIF was not valid, no need to delete it */ + if (!mlxsw_sp_mr_vif_valid(rve->mr_vif)) + return; + + /* Update the route action: if there is only one valid eVIF in the + * route, set the action to trap as the VIF deletion will lead to zero + * valid eVIFs. On any other case, use the mlxsw_sp_mr_route_action to + * determine the route action. + */ + if (mlxsw_sp_mr_route_valid_evifs_num(rve->mr_route) == 1) + route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP; + else + route_action = mlxsw_sp_mr_route_action(rve->mr_route); + if (route_action != rve->mr_route->route_action) + mr->mr_ops->route_action_update(mlxsw_sp, + rve->mr_route->route_priv, + route_action); + + /* Delete the erif from the route */ + rifi = mlxsw_sp_rif_index(rve->mr_vif->rif); + mr->mr_ops->route_erif_del(mlxsw_sp, rve->mr_route->route_priv, rifi); + rve->mr_route->route_action = route_action; + mlxsw_sp_mr_mfc_offload_update(rve->mr_route); +} + +static int mlxsw_sp_mr_vif_resolve(struct mlxsw_sp_mr_table *mr_table, + struct net_device *dev, + struct mlxsw_sp_mr_vif *mr_vif, + unsigned long vif_flags, + const struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp_mr_route_vif_entry *irve, *erve; + int err; + + /* Update the VIF */ + mr_vif->dev = dev; + mr_vif->rif = rif; + mr_vif->vif_flags = vif_flags; + + /* Update all routes where this VIF is used as an unresolved iRIF */ + list_for_each_entry(irve, &mr_vif->route_ivif_list, vif_node) { + err = mlxsw_sp_mr_route_ivif_resolve(mr_table, irve); + if (err) + goto err_irif_unresolve; + } + + /* Update all routes where this VIF is used as an unresolved eRIF */ + list_for_each_entry(erve, &mr_vif->route_evif_list, vif_node) { + err = mlxsw_sp_mr_route_evif_resolve(mr_table, erve); + if (err) + goto err_erif_unresolve; + } + return 0; + +err_erif_unresolve: + list_for_each_entry_from_reverse(erve, &mr_vif->route_evif_list, + vif_node) + mlxsw_sp_mr_route_evif_unresolve(mr_table, erve); +err_irif_unresolve: + list_for_each_entry_from_reverse(irve, &mr_vif->route_ivif_list, + vif_node) + mlxsw_sp_mr_route_ivif_unresolve(mr_table, irve); + mr_vif->rif = NULL; + return err; +} + +static void mlxsw_sp_mr_vif_unresolve(struct mlxsw_sp_mr_table *mr_table, + struct net_device *dev, + struct mlxsw_sp_mr_vif *mr_vif) +{ + struct mlxsw_sp_mr_route_vif_entry *rve; + + /* Update all routes where this VIF is used as an unresolved eRIF */ + list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node) + mlxsw_sp_mr_route_evif_unresolve(mr_table, rve); + + /* Update all routes where this VIF is used as an unresolved iRIF */ + list_for_each_entry(rve, &mr_vif->route_ivif_list, vif_node) + mlxsw_sp_mr_route_ivif_unresolve(mr_table, rve); + + /* Update the VIF */ + mr_vif->dev = dev; + mr_vif->rif = NULL; +} + +int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table, + struct net_device *dev, vifi_t vif_index, + unsigned long vif_flags, const struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index]; + + if (WARN_ON(vif_index >= MAXVIFS)) + return -EINVAL; + if (mr_vif->dev) + return -EEXIST; + return mlxsw_sp_mr_vif_resolve(mr_table, dev, mr_vif, vif_flags, rif); +} + +void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index) +{ + struct mlxsw_sp_mr_vif *mr_vif = &mr_table->vifs[vif_index]; + + if (WARN_ON(vif_index >= MAXVIFS)) + return; + if (WARN_ON(!mr_vif->dev)) + return; + mlxsw_sp_mr_vif_unresolve(mr_table, NULL, mr_vif); +} + +struct mlxsw_sp_mr_vif * +mlxsw_sp_mr_dev_vif_lookup(struct mlxsw_sp_mr_table *mr_table, + const struct net_device *dev) +{ + vifi_t vif_index; + + for (vif_index = 0; vif_index < MAXVIFS; vif_index++) + if (mr_table->vifs[vif_index].dev == dev) + return &mr_table->vifs[vif_index]; + return NULL; +} + +int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif) +{ + const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); + struct mlxsw_sp_mr_vif *mr_vif; + + if (!rif_dev) + return 0; + + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + if (!mr_vif) + return 0; + return mlxsw_sp_mr_vif_resolve(mr_table, mr_vif->dev, mr_vif, + mr_vif->vif_flags, rif); +} + +void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif) +{ + const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); + struct mlxsw_sp_mr_vif *mr_vif; + + if (!rif_dev) + return; + + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + if (!mr_vif) + return; + mlxsw_sp_mr_vif_unresolve(mr_table, mr_vif->dev, mr_vif); +} + +void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif, int mtu) +{ + const struct net_device *rif_dev = mlxsw_sp_rif_dev(rif); + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + struct mlxsw_sp_mr_route_vif_entry *rve; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + struct mlxsw_sp_mr_vif *mr_vif; + + if (!rif_dev) + return; + + /* Search for a VIF that use that RIF */ + mr_vif = mlxsw_sp_mr_dev_vif_lookup(mr_table, rif_dev); + if (!mr_vif) + return; + + /* Update all the routes that uses that VIF as eVIF */ + list_for_each_entry(rve, &mr_vif->route_evif_list, vif_node) { + if (mtu < rve->mr_route->min_mtu) { + rve->mr_route->min_mtu = mtu; + mr->mr_ops->route_min_mtu_update(mlxsw_sp, + rve->mr_route->route_priv, + mtu); + } + } +} + +struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, + u32 vr_id, + enum mlxsw_sp_l3proto proto) +{ + struct mlxsw_sp_mr_route_params catchall_route_params = { + .prio = MLXSW_SP_MR_ROUTE_PRIO_CATCHALL, + .key = { + .vrid = vr_id, + }, + .value = { + .route_action = MLXSW_SP_MR_ROUTE_ACTION_TRAP, + } + }; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + struct mlxsw_sp_mr_table *mr_table; + int err; + int i; + + mr_table = kzalloc(sizeof(*mr_table) + mr->mr_ops->route_priv_size, + GFP_KERNEL); + if (!mr_table) + return ERR_PTR(-ENOMEM); + + mr_table->vr_id = vr_id; + mr_table->mlxsw_sp = mlxsw_sp; + mr_table->proto = proto; + INIT_LIST_HEAD(&mr_table->route_list); + + err = rhashtable_init(&mr_table->route_ht, + &mlxsw_sp_mr_route_ht_params); + if (err) + goto err_route_rhashtable_init; + + for (i = 0; i < MAXVIFS; i++) { + INIT_LIST_HEAD(&mr_table->vifs[i].route_evif_list); + INIT_LIST_HEAD(&mr_table->vifs[i].route_ivif_list); + } + + err = mr->mr_ops->route_create(mlxsw_sp, mr->priv, + mr_table->catchall_route_priv, + &catchall_route_params); + if (err) + goto err_ops_route_create; + list_add_tail(&mr_table->node, &mr->table_list); + return mr_table; + +err_ops_route_create: + rhashtable_destroy(&mr_table->route_ht); +err_route_rhashtable_init: + kfree(mr_table); + return ERR_PTR(err); +} + +void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table) +{ + struct mlxsw_sp *mlxsw_sp = mr_table->mlxsw_sp; + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + + WARN_ON(!mlxsw_sp_mr_table_empty(mr_table)); + list_del(&mr_table->node); + mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, + &mr_table->catchall_route_priv); + rhashtable_destroy(&mr_table->route_ht); + kfree(mr_table); +} + +void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table) +{ + struct mlxsw_sp_mr_route *mr_route, *tmp; + int i; + + list_for_each_entry_safe(mr_route, tmp, &mr_table->route_list, node) + __mlxsw_sp_mr_route_del(mr_table, mr_route); + + for (i = 0; i < MAXVIFS; i++) { + mr_table->vifs[i].dev = NULL; + mr_table->vifs[i].rif = NULL; + } +} + +bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table) +{ + int i; + + for (i = 0; i < MAXVIFS; i++) + if (mr_table->vifs[i].dev) + return false; + return list_empty(&mr_table->route_list); +} + +static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_route *mr_route) +{ + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + u64 packets, bytes; + + if (mr_route->route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP) + return; + + mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets, + &bytes); + + switch (mr_route->mr_table->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + if (mr_route->mfc4->mfc_un.res.pkt != packets) + mr_route->mfc4->mfc_un.res.lastuse = jiffies; + mr_route->mfc4->mfc_un.res.pkt = packets; + mr_route->mfc4->mfc_un.res.bytes = bytes; + break; + case MLXSW_SP_L3_PROTO_IPV6: + /* fall through */ + default: + WARN_ON_ONCE(1); + } +} + +static void mlxsw_sp_mr_stats_update(struct work_struct *work) +{ + struct mlxsw_sp_mr *mr = container_of(work, struct mlxsw_sp_mr, + stats_update_dw.work); + struct mlxsw_sp_mr_table *mr_table; + struct mlxsw_sp_mr_route *mr_route; + unsigned long interval; + + rtnl_lock(); + list_for_each_entry(mr_table, &mr->table_list, node) + list_for_each_entry(mr_route, &mr_table->route_list, node) + mlxsw_sp_mr_route_stats_update(mr_table->mlxsw_sp, + mr_route); + rtnl_unlock(); + + interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL); + mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); +} + +int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_mr_ops *mr_ops) +{ + struct mlxsw_sp_mr *mr; + unsigned long interval; + int err; + + mr = kzalloc(sizeof(*mr) + mr_ops->priv_size, GFP_KERNEL); + if (!mr) + return -ENOMEM; + mr->mr_ops = mr_ops; + mlxsw_sp->mr = mr; + INIT_LIST_HEAD(&mr->table_list); + + err = mr_ops->init(mlxsw_sp, mr->priv); + if (err) + goto err; + + /* Create the delayed work for counter updates */ + INIT_DELAYED_WORK(&mr->stats_update_dw, mlxsw_sp_mr_stats_update); + interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL); + mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); + return 0; +err: + kfree(mr); + return err; +} + +void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_mr *mr = mlxsw_sp->mr; + + cancel_delayed_work_sync(&mr->stats_update_dw); + mr->mr_ops->fini(mr->priv); + kfree(mr); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h new file mode 100644 index 0000000000000..c851b237d2530 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h @@ -0,0 +1,133 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Yotam Gigi + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_SPECTRUM_MCROUTER_H +#define _MLXSW_SPECTRUM_MCROUTER_H + +#include +#include "spectrum_router.h" +#include "spectrum.h" + +enum mlxsw_sp_mr_route_action { + MLXSW_SP_MR_ROUTE_ACTION_FORWARD, + MLXSW_SP_MR_ROUTE_ACTION_TRAP, +}; + +enum mlxsw_sp_mr_route_prio { + MLXSW_SP_MR_ROUTE_PRIO_SG, + MLXSW_SP_MR_ROUTE_PRIO_STARG, + MLXSW_SP_MR_ROUTE_PRIO_CATCHALL, + __MLXSW_SP_MR_ROUTE_PRIO_MAX +}; + +#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1) + +struct mlxsw_sp_mr_route_key { + int vrid; + enum mlxsw_sp_l3proto proto; + union mlxsw_sp_l3addr group; + union mlxsw_sp_l3addr group_mask; + union mlxsw_sp_l3addr source; + union mlxsw_sp_l3addr source_mask; +}; + +struct mlxsw_sp_mr_route_info { + enum mlxsw_sp_mr_route_action route_action; + u16 irif_index; + u16 *erif_indices; + size_t erif_num; + u16 min_mtu; +}; + +struct mlxsw_sp_mr_route_params { + struct mlxsw_sp_mr_route_key key; + struct mlxsw_sp_mr_route_info value; + enum mlxsw_sp_mr_route_prio prio; +}; + +struct mlxsw_sp_mr_ops { + int priv_size; + int route_priv_size; + int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv); + int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv, + void *route_priv, + struct mlxsw_sp_mr_route_params *route_params); + int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + struct mlxsw_sp_mr_route_info *route_info); + int (*route_stats)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + u64 *packets, u64 *bytes); + int (*route_action_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + enum mlxsw_sp_mr_route_action route_action); + int (*route_min_mtu_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + u16 min_mtu); + int (*route_irif_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + u16 irif_index); + int (*route_erif_add)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + u16 erif_index); + int (*route_erif_del)(struct mlxsw_sp *mlxsw_sp, void *route_priv, + u16 erif_index); + void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv, + void *route_priv); + void (*fini)(void *priv); +}; + +struct mlxsw_sp_mr; +struct mlxsw_sp_mr_table; + +int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_mr_ops *mr_ops); +void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_mr_route4_add(struct mlxsw_sp_mr_table *mr_table, + struct mfc_cache *mfc, bool replace); +void mlxsw_sp_mr_route4_del(struct mlxsw_sp_mr_table *mr_table, + struct mfc_cache *mfc); +int mlxsw_sp_mr_vif_add(struct mlxsw_sp_mr_table *mr_table, + struct net_device *dev, vifi_t vif_index, + unsigned long vif_flags, + const struct mlxsw_sp_rif *rif); +void mlxsw_sp_mr_vif_del(struct mlxsw_sp_mr_table *mr_table, vifi_t vif_index); +int mlxsw_sp_mr_rif_add(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif); +void mlxsw_sp_mr_rif_del(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif); +void mlxsw_sp_mr_rif_mtu_update(struct mlxsw_sp_mr_table *mr_table, + const struct mlxsw_sp_rif *rif, int mtu); +struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, + u32 tb_id, + enum mlxsw_sp_l3proto proto); +void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table); +void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table); +bool mlxsw_sp_mr_table_empty(const struct mlxsw_sp_mr_table *mr_table); + +#endif -- GitLab From 0e14c7777acb6d58250cb746685dde0a74d60fe8 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:18 +0200 Subject: [PATCH 0534/1507] mlxsw: spectrum: Add the multicast routing hardware logic Implement the multicast routing hardware API introduced in previous patch for the specific spectrum hardware. The spectrum hardware multicast routes are written using the RMFT2 register and point to an ACL flexible action set. The actions used for multicast routes are: - Counter action, which allows counting bytes and packets on multicast routes. - Multicast route action, which provide RPF check and do the actual packet duplication to a list of RIFs. - Trap action, in the case the route action specified by the called is trap. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/Makefile | 2 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 1 + .../mellanox/mlxsw/spectrum_mr_tcam.c | 828 ++++++++++++++++++ .../mellanox/mlxsw/spectrum_mr_tcam.h | 43 + 4 files changed, 873 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 9b29764905f34..4816504419fcb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -18,7 +18,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_acl.o spectrum_flower.o \ spectrum_cnt.o spectrum_fid.o \ spectrum_ipip.o spectrum_acl_flex_actions.o \ - spectrum_mr.o + spectrum_mr.o spectrum_mr_tcam.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 44c5259e5548b..ae67e6046098c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -139,6 +139,7 @@ struct mlxsw_sp_port_mall_tc_entry { struct mlxsw_sp_sb; struct mlxsw_sp_bridge; struct mlxsw_sp_router; +struct mlxsw_sp_mr; struct mlxsw_sp_acl; struct mlxsw_sp_counter_pool; struct mlxsw_sp_fid_core; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c new file mode 100644 index 0000000000000..cda9e9ad10e38 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -0,0 +1,828 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Yotam Gigi + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include +#include +#include + +#include "reg.h" +#include "spectrum.h" +#include "core_acl_flex_actions.h" +#include "spectrum_mr.h" + +struct mlxsw_sp_mr_tcam_region { + struct mlxsw_sp *mlxsw_sp; + enum mlxsw_reg_rtar_key_type rtar_key_type; + struct parman *parman; + struct parman_prio *parman_prios; +}; + +struct mlxsw_sp_mr_tcam { + struct mlxsw_sp_mr_tcam_region ipv4_tcam_region; +}; + +/* This struct maps to one RIGR2 register entry */ +struct mlxsw_sp_mr_erif_sublist { + struct list_head list; + u32 rigr2_kvdl_index; + int num_erifs; + u16 erif_indices[MLXSW_REG_RIGR2_MAX_ERIFS]; + bool synced; +}; + +struct mlxsw_sp_mr_tcam_erif_list { + struct list_head erif_sublists; + u32 kvdl_index; +}; + +static bool +mlxsw_sp_mr_erif_sublist_full(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_erif_sublist *erif_sublist) +{ + int erif_list_entries = MLXSW_CORE_RES_GET(mlxsw_sp->core, + MC_ERIF_LIST_ENTRIES); + + return erif_sublist->num_erifs == erif_list_entries; +} + +static void +mlxsw_sp_mr_erif_list_init(struct mlxsw_sp_mr_tcam_erif_list *erif_list) +{ + INIT_LIST_HEAD(&erif_list->erif_sublists); +} + +#define MLXSW_SP_KVDL_RIGR2_SIZE 1 + +static struct mlxsw_sp_mr_erif_sublist * +mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_erif_list *erif_list) +{ + struct mlxsw_sp_mr_erif_sublist *erif_sublist; + int err; + + erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL); + if (!erif_sublist) + return ERR_PTR(-ENOMEM); + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE, + &erif_sublist->rigr2_kvdl_index); + if (err) { + kfree(erif_sublist); + return ERR_PTR(err); + } + + list_add_tail(&erif_sublist->list, &erif_list->erif_sublists); + return erif_sublist; +} + +static void +mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_erif_sublist *erif_sublist) +{ + list_del(&erif_sublist->list); + mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index); + kfree(erif_sublist); +} + +static int +mlxsw_sp_mr_erif_list_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_erif_list *erif_list, + u16 erif_index) +{ + struct mlxsw_sp_mr_erif_sublist *sublist; + + /* If either there is no erif_entry or the last one is full, allocate a + * new one. + */ + if (list_empty(&erif_list->erif_sublists)) { + sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp, erif_list); + if (IS_ERR(sublist)) + return PTR_ERR(sublist); + erif_list->kvdl_index = sublist->rigr2_kvdl_index; + } else { + sublist = list_last_entry(&erif_list->erif_sublists, + struct mlxsw_sp_mr_erif_sublist, + list); + sublist->synced = false; + if (mlxsw_sp_mr_erif_sublist_full(mlxsw_sp, sublist)) { + sublist = mlxsw_sp_mr_erif_sublist_create(mlxsw_sp, + erif_list); + if (IS_ERR(sublist)) + return PTR_ERR(sublist); + } + } + + /* Add the eRIF to the last entry's last index */ + sublist->erif_indices[sublist->num_erifs++] = erif_index; + return 0; +} + +static void +mlxsw_sp_mr_erif_list_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_erif_list *erif_list) +{ + struct mlxsw_sp_mr_erif_sublist *erif_sublist, *tmp; + + list_for_each_entry_safe(erif_sublist, tmp, &erif_list->erif_sublists, + list) + mlxsw_sp_mr_erif_sublist_destroy(mlxsw_sp, erif_sublist); +} + +static int +mlxsw_sp_mr_erif_list_commit(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_erif_list *erif_list) +{ + struct mlxsw_sp_mr_erif_sublist *curr_sublist; + char rigr2_pl[MLXSW_REG_RIGR2_LEN]; + int err; + int i; + + list_for_each_entry(curr_sublist, &erif_list->erif_sublists, list) { + if (curr_sublist->synced) + continue; + + /* If the sublist is not the last one, pack the next index */ + if (list_is_last(&curr_sublist->list, + &erif_list->erif_sublists)) { + mlxsw_reg_rigr2_pack(rigr2_pl, + curr_sublist->rigr2_kvdl_index, + false, 0); + } else { + struct mlxsw_sp_mr_erif_sublist *next_sublist; + + next_sublist = list_next_entry(curr_sublist, list); + mlxsw_reg_rigr2_pack(rigr2_pl, + curr_sublist->rigr2_kvdl_index, + true, + next_sublist->rigr2_kvdl_index); + } + + /* Pack all the erifs */ + for (i = 0; i < curr_sublist->num_erifs; i++) { + u16 erif_index = curr_sublist->erif_indices[i]; + + mlxsw_reg_rigr2_erif_entry_pack(rigr2_pl, i, true, + erif_index); + } + + /* Write the entry */ + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rigr2), + rigr2_pl); + if (err) + /* No need of a rollback here because this + * hardware entry should not be pointed yet. + */ + return err; + curr_sublist->synced = true; + } + return 0; +} + +static void mlxsw_sp_mr_erif_list_move(struct mlxsw_sp_mr_tcam_erif_list *to, + struct mlxsw_sp_mr_tcam_erif_list *from) +{ + list_splice(&from->erif_sublists, &to->erif_sublists); + to->kvdl_index = from->kvdl_index; +} + +struct mlxsw_sp_mr_tcam_route { + struct mlxsw_sp_mr_tcam_erif_list erif_list; + struct mlxsw_afa_block *afa_block; + u32 counter_index; + struct parman_item parman_item; + struct parman_prio *parman_prio; + enum mlxsw_sp_mr_route_action action; + struct mlxsw_sp_mr_route_key key; + u16 irif_index; + u16 min_mtu; +}; + +static struct mlxsw_afa_block * +mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_mr_route_action route_action, + u16 irif_index, u32 counter_index, + u16 min_mtu, + struct mlxsw_sp_mr_tcam_erif_list *erif_list) +{ + struct mlxsw_afa_block *afa_block; + int err; + + afa_block = mlxsw_afa_block_create(mlxsw_sp->afa); + if (IS_ERR(afa_block)) + return afa_block; + + err = mlxsw_afa_block_append_counter(afa_block, counter_index); + if (err) + goto err; + + switch (route_action) { + case MLXSW_SP_MR_ROUTE_ACTION_TRAP: + err = mlxsw_afa_block_append_trap(afa_block, + MLXSW_TRAP_ID_ACL1); + if (err) + goto err; + break; + case MLXSW_SP_MR_ROUTE_ACTION_FORWARD: + /* If we are about to append a multicast router action, commit + * the erif_list. + */ + err = mlxsw_sp_mr_erif_list_commit(mlxsw_sp, erif_list); + if (err) + goto err; + + err = mlxsw_afa_block_append_mcrouter(afa_block, irif_index, + min_mtu, false, + erif_list->kvdl_index); + if (err) + goto err; + break; + default: + err = -EINVAL; + goto err; + } + + err = mlxsw_afa_block_commit(afa_block); + if (err) + goto err; + return afa_block; +err: + mlxsw_afa_block_destroy(afa_block); + return ERR_PTR(err); +} + +static void +mlxsw_sp_mr_tcam_afa_block_destroy(struct mlxsw_afa_block *afa_block) +{ + mlxsw_afa_block_destroy(afa_block); +} + +static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp, + struct parman_item *parman_item, + struct mlxsw_sp_mr_route_key *key, + struct mlxsw_afa_block *afa_block) +{ + char rmft2_pl[MLXSW_REG_RMFT2_LEN]; + + switch (key->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index, + key->vrid, + MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0, + ntohl(key->group.addr4), + ntohl(key->group_mask.addr4), + ntohl(key->source.addr4), + ntohl(key->source_mask.addr4), + mlxsw_afa_block_first_set(afa_block)); + break; + case MLXSW_SP_L3_PROTO_IPV6: + default: + WARN_ON_ONCE(1); + } + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl); +} + +static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid, + struct parman_item *parman_item) +{ + char rmft2_pl[MLXSW_REG_RMFT2_LEN]; + + mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index, vrid, + 0, 0, 0, 0, 0, 0, NULL); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl); +} + +static int +mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_erif_list *erif_list, + struct mlxsw_sp_mr_route_info *route_info) +{ + int err; + int i; + + for (i = 0; i < route_info->erif_num; i++) { + u16 erif_index = route_info->erif_indices[i]; + + err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, erif_list, + erif_index); + if (err) + return err; + } + return 0; +} + +static int +mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam, + struct mlxsw_sp_mr_tcam_route *route, + enum mlxsw_sp_mr_route_prio prio) +{ + struct parman_prio *parman_prio = NULL; + int err; + + switch (route->key.proto) { + case MLXSW_SP_L3_PROTO_IPV4: + parman_prio = &mr_tcam->ipv4_tcam_region.parman_prios[prio]; + err = parman_item_add(mr_tcam->ipv4_tcam_region.parman, + parman_prio, &route->parman_item); + if (err) + return err; + break; + case MLXSW_SP_L3_PROTO_IPV6: + default: + WARN_ON_ONCE(1); + } + route->parman_prio = parman_prio; + return 0; +} + +static void +mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam, + struct mlxsw_sp_mr_tcam_route *route) +{ + switch (route->key.proto) { + case MLXSW_SP_L3_PROTO_IPV4: + parman_item_remove(mr_tcam->ipv4_tcam_region.parman, + route->parman_prio, &route->parman_item); + break; + case MLXSW_SP_L3_PROTO_IPV6: + default: + WARN_ON_ONCE(1); + } +} + +static int +mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv, + void *route_priv, + struct mlxsw_sp_mr_route_params *route_params) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_sp_mr_tcam *mr_tcam = priv; + int err; + + route->key = route_params->key; + route->irif_index = route_params->value.irif_index; + route->min_mtu = route_params->value.min_mtu; + route->action = route_params->value.route_action; + + /* Create the egress RIFs list */ + mlxsw_sp_mr_erif_list_init(&route->erif_list); + err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &route->erif_list, + &route_params->value); + if (err) + goto err_erif_populate; + + /* Create the flow counter */ + err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &route->counter_index); + if (err) + goto err_counter_alloc; + + /* Create the flexible action block */ + route->afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, + route->action, + route->irif_index, + route->counter_index, + route->min_mtu, + &route->erif_list); + if (IS_ERR(route->afa_block)) { + err = PTR_ERR(route->afa_block); + goto err_afa_block_create; + } + + /* Allocate place in the TCAM */ + err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route, + route_params->prio); + if (err) + goto err_parman_item_add; + + /* Write the route to the TCAM */ + err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item, + &route->key, route->afa_block); + if (err) + goto err_route_replace; + return 0; + +err_route_replace: + mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route); +err_parman_item_add: + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); +err_afa_block_create: + mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index); +err_erif_populate: +err_counter_alloc: + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list); + return err; +} + +static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, + void *priv, void *route_priv) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_sp_mr_tcam *mr_tcam = priv; + + mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid, + &route->parman_item); + mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route); + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); + mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index); + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list); +} + +static int mlxsw_sp_mr_tcam_route_stats(struct mlxsw_sp *mlxsw_sp, + void *route_priv, u64 *packets, + u64 *bytes) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + + return mlxsw_sp_flow_counter_get(mlxsw_sp, route->counter_index, + packets, bytes); +} + +static int +mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp, + void *route_priv, + enum mlxsw_sp_mr_route_action route_action) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_afa_block *afa_block; + int err; + + /* Create a new flexible action block */ + afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route_action, + route->irif_index, + route->counter_index, + route->min_mtu, + &route->erif_list); + if (IS_ERR(afa_block)) + return PTR_ERR(afa_block); + + /* Update the TCAM route entry */ + err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item, + &route->key, afa_block); + if (err) + goto err; + + /* Delete the old one */ + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); + route->afa_block = afa_block; + route->action = route_action; + return 0; +err: + mlxsw_sp_mr_tcam_afa_block_destroy(afa_block); + return err; +} + +static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp, + void *route_priv, u16 min_mtu) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_afa_block *afa_block; + int err; + + /* Create a new flexible action block */ + afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, + route->action, + route->irif_index, + route->counter_index, + min_mtu, + &route->erif_list); + if (IS_ERR(afa_block)) + return PTR_ERR(afa_block); + + /* Update the TCAM route entry */ + err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item, + &route->key, afa_block); + if (err) + goto err; + + /* Delete the old one */ + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); + route->afa_block = afa_block; + route->min_mtu = min_mtu; + return 0; +err: + mlxsw_sp_mr_tcam_afa_block_destroy(afa_block); + return err; +} + +static int mlxsw_sp_mr_tcam_route_irif_update(struct mlxsw_sp *mlxsw_sp, + void *route_priv, u16 irif_index) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + + if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP) + return -EINVAL; + route->irif_index = irif_index; + return 0; +} + +static int mlxsw_sp_mr_tcam_route_erif_add(struct mlxsw_sp *mlxsw_sp, + void *route_priv, u16 erif_index) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + int err; + + err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &route->erif_list, + erif_index); + if (err) + return err; + + /* Commit the action only if the route action is not TRAP */ + if (route->action != MLXSW_SP_MR_ROUTE_ACTION_TRAP) + return mlxsw_sp_mr_erif_list_commit(mlxsw_sp, + &route->erif_list); + return 0; +} + +static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp, + void *route_priv, u16 erif_index) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_sp_mr_erif_sublist *erif_sublist; + struct mlxsw_sp_mr_tcam_erif_list erif_list; + struct mlxsw_afa_block *afa_block; + int err; + int i; + + /* Create a copy of the original erif_list without the deleted entry */ + mlxsw_sp_mr_erif_list_init(&erif_list); + list_for_each_entry(erif_sublist, &route->erif_list.erif_sublists, list) { + for (i = 0; i < erif_sublist->num_erifs; i++) { + u16 curr_erif = erif_sublist->erif_indices[i]; + + if (curr_erif == erif_index) + continue; + err = mlxsw_sp_mr_erif_list_add(mlxsw_sp, &erif_list, + curr_erif); + if (err) + goto err_erif_list_add; + } + } + + /* Create the flexible action block pointing to the new erif_list */ + afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, route->action, + route->irif_index, + route->counter_index, + route->min_mtu, + &erif_list); + if (IS_ERR(afa_block)) { + err = PTR_ERR(afa_block); + goto err_afa_block_create; + } + + /* Update the TCAM route entry */ + err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item, + &route->key, afa_block); + if (err) + goto err_route_write; + + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list); + route->afa_block = afa_block; + mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list); + return 0; + +err_route_write: + mlxsw_sp_mr_tcam_afa_block_destroy(afa_block); +err_afa_block_create: +err_erif_list_add: + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list); + return err; +} + +static int +mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv, + struct mlxsw_sp_mr_route_info *route_info) +{ + struct mlxsw_sp_mr_tcam_route *route = route_priv; + struct mlxsw_sp_mr_tcam_erif_list erif_list; + struct mlxsw_afa_block *afa_block; + int err; + + /* Create a new erif_list */ + mlxsw_sp_mr_erif_list_init(&erif_list); + err = mlxsw_sp_mr_tcam_erif_populate(mlxsw_sp, &erif_list, route_info); + if (err) + goto err_erif_populate; + + /* Create the flexible action block pointing to the new erif_list */ + afa_block = mlxsw_sp_mr_tcam_afa_block_create(mlxsw_sp, + route_info->route_action, + route_info->irif_index, + route->counter_index, + route_info->min_mtu, + &erif_list); + if (IS_ERR(afa_block)) { + err = PTR_ERR(afa_block); + goto err_afa_block_create; + } + + /* Update the TCAM route entry */ + err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item, + &route->key, afa_block); + if (err) + goto err_route_write; + + mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block); + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list); + route->afa_block = afa_block; + mlxsw_sp_mr_erif_list_move(&route->erif_list, &erif_list); + route->action = route_info->route_action; + route->irif_index = route_info->irif_index; + route->min_mtu = route_info->min_mtu; + return 0; + +err_route_write: + mlxsw_sp_mr_tcam_afa_block_destroy(afa_block); +err_afa_block_create: +err_erif_populate: + mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &erif_list); + return err; +} + +#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16 +#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16 + +static int +mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region) +{ + struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp; + char rtar_pl[MLXSW_REG_RTAR_LEN]; + + mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE, + mr_tcam_region->rtar_key_type, + MLXSW_SP_MR_TCAM_REGION_BASE_COUNT); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl); +} + +static void +mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region) +{ + struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp; + char rtar_pl[MLXSW_REG_RTAR_LEN]; + + mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE, + mr_tcam_region->rtar_key_type, 0); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl); +} + +static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv, + unsigned long new_count) +{ + struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv; + struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp; + char rtar_pl[MLXSW_REG_RTAR_LEN]; + u64 max_tcam_rules; + + max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES); + if (new_count > max_tcam_rules) + return -EINVAL; + mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE, + mr_tcam_region->rtar_key_type, new_count); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl); +} + +static void mlxsw_sp_mr_tcam_region_parman_move(void *priv, + unsigned long from_index, + unsigned long to_index, + unsigned long count) +{ + struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv; + struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp; + char rrcr_pl[MLXSW_REG_RRCR_LEN]; + + mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE, + from_index, count, + mr_tcam_region->rtar_key_type, to_index); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl); +} + +static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = { + .base_count = MLXSW_SP_MR_TCAM_REGION_BASE_COUNT, + .resize_step = MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP, + .resize = mlxsw_sp_mr_tcam_region_parman_resize, + .move = mlxsw_sp_mr_tcam_region_parman_move, + .algo = PARMAN_ALGO_TYPE_LSORT, +}; + +static int +mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mr_tcam_region *mr_tcam_region, + enum mlxsw_reg_rtar_key_type rtar_key_type) +{ + struct parman_prio *parman_prios; + struct parman *parman; + int err; + int i; + + mr_tcam_region->rtar_key_type = rtar_key_type; + mr_tcam_region->mlxsw_sp = mlxsw_sp; + + err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region); + if (err) + return err; + + parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops, + mr_tcam_region); + if (!parman) { + err = -ENOMEM; + goto err_parman_create; + } + mr_tcam_region->parman = parman; + + parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1, + sizeof(*parman_prios), GFP_KERNEL); + if (!parman_prios) + goto err_parman_prios_alloc; + mr_tcam_region->parman_prios = parman_prios; + + for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++) + parman_prio_init(mr_tcam_region->parman, + &mr_tcam_region->parman_prios[i], i); + return 0; + +err_parman_prios_alloc: + parman_destroy(parman); +err_parman_create: + mlxsw_sp_mr_tcam_region_free(mr_tcam_region); + return err; +} + +static void +mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region) +{ + int i; + + for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++) + parman_prio_fini(&mr_tcam_region->parman_prios[i]); + kfree(mr_tcam_region->parman_prios); + parman_destroy(mr_tcam_region->parman); + mlxsw_sp_mr_tcam_region_free(mr_tcam_region); +} + +static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv) +{ + struct mlxsw_sp_mr_tcam *mr_tcam = priv; + + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) || + !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES)) + return -EIO; + + return mlxsw_sp_mr_tcam_region_init(mlxsw_sp, + &mr_tcam->ipv4_tcam_region, + MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST); +} + +static void mlxsw_sp_mr_tcam_fini(void *priv) +{ + struct mlxsw_sp_mr_tcam *mr_tcam = priv; + + mlxsw_sp_mr_tcam_region_fini(&mr_tcam->ipv4_tcam_region); +} + +const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = { + .priv_size = sizeof(struct mlxsw_sp_mr_tcam), + .route_priv_size = sizeof(struct mlxsw_sp_mr_tcam_route), + .init = mlxsw_sp_mr_tcam_init, + .route_create = mlxsw_sp_mr_tcam_route_create, + .route_update = mlxsw_sp_mr_tcam_route_update, + .route_stats = mlxsw_sp_mr_tcam_route_stats, + .route_action_update = mlxsw_sp_mr_tcam_route_action_update, + .route_min_mtu_update = mlxsw_sp_mr_tcam_route_min_mtu_update, + .route_irif_update = mlxsw_sp_mr_tcam_route_irif_update, + .route_erif_add = mlxsw_sp_mr_tcam_route_erif_add, + .route_erif_del = mlxsw_sp_mr_tcam_route_erif_del, + .route_destroy = mlxsw_sp_mr_tcam_route_destroy, + .fini = mlxsw_sp_mr_tcam_fini, +}; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h new file mode 100644 index 0000000000000..f9b59ee25406b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h @@ -0,0 +1,43 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Yotam Gigi + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_SPECTRUM_MCROUTER_TCAM_H +#define _MLXSW_SPECTRUM_MCROUTER_TCAM_H + +#include "spectrum.h" +#include "spectrum_mr.h" + +extern const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops; + +#endif -- GitLab From 7e50d435759accec4e17764a8d5a1ef63b79ffd6 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:19 +0200 Subject: [PATCH 0535/1507] mlxsw: spectrum: router: Squash the default route table to main Currently, the mlxsw Spectrum driver offloads only either the RT_TABLE_MAIN FIB table or the VRF tables, so the RT_TABLE_LOCAL table is squashed to the RT_TABLE_MAIN table to allow local routes to be offloaded too. By default, multicast MFC routes which are not assigned to any user requested table are put in the RT_TABLE_DEFAULT table. Due to the fact that offloading multicast MFC routes support in Spectrum router logic is going to be introduced soon, squash the default table to MAIN too. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 321f7356073ca..28c0c84bc966f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -693,8 +693,8 @@ static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, static u32 mlxsw_sp_fix_tb_id(u32 tb_id) { - /* For our purpose, squash main and local table into one */ - if (tb_id == RT_TABLE_LOCAL) + /* For our purpose, squash main, default and local tables into one */ + if (tb_id == RT_TABLE_LOCAL || tb_id == RT_TABLE_DEFAULT) tb_id = RT_TABLE_MAIN; return tb_id; } -- GitLab From d42b0965b1d4fe0808a2103a3f7c015515b1112e Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:20 +0200 Subject: [PATCH 0536/1507] mlxsw: spectrum_router: Add multicast routes notification handling functionality Add functionality for calling the multicast routing offloading logic upon MFC and VIF add and delete notifications. In addition, call the multicast routing upon RIF addition and deletion events. As the multicast routing offload logic may sleep, the actual calls are done in a deferred work. To ensure the MFC object is not freed in that interval, a reference is held to it. In case of a failure, the abort mechanism is used, which ejects all the routes from the hardware and triggers the traffic to flow through the kernel. Note: At that stage, the FIB notifications are still ignored, and will be enabled in a further patch. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 187 +++++++++++++++++- 1 file changed, 185 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 28c0c84bc966f..77584422ed082 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -65,6 +65,8 @@ #include "spectrum_cnt.h" #include "spectrum_dpipe.h" #include "spectrum_ipip.h" +#include "spectrum_mr.h" +#include "spectrum_mr_tcam.h" #include "spectrum_router.h" struct mlxsw_sp_vr; @@ -459,6 +461,7 @@ struct mlxsw_sp_vr { unsigned int rif_count; struct mlxsw_sp_fib *fib4; struct mlxsw_sp_fib *fib6; + struct mlxsw_sp_mr_table *mr4_table; }; static const struct rhashtable_params mlxsw_sp_fib_ht_params; @@ -653,7 +656,7 @@ static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp) static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) { - return !!vr->fib4 || !!vr->fib6; + return !!vr->fib4 || !!vr->fib6 || !!vr->mr4_table; } static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) @@ -744,9 +747,18 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, err = PTR_ERR(vr->fib6); goto err_fib6_create; } + vr->mr4_table = mlxsw_sp_mr_table_create(mlxsw_sp, vr->id, + MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(vr->mr4_table)) { + err = PTR_ERR(vr->mr4_table); + goto err_mr_table_create; + } vr->tb_id = tb_id; return vr; +err_mr_table_create: + mlxsw_sp_fib_destroy(vr->fib6); + vr->fib6 = NULL; err_fib6_create: mlxsw_sp_fib_destroy(vr->fib4); vr->fib4 = NULL; @@ -755,6 +767,8 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) { + mlxsw_sp_mr_table_destroy(vr->mr4_table); + vr->mr4_table = NULL; mlxsw_sp_fib_destroy(vr->fib6); vr->fib6 = NULL; mlxsw_sp_fib_destroy(vr->fib4); @@ -775,7 +789,8 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { if (!vr->rif_count && list_empty(&vr->fib4->node_list) && - list_empty(&vr->fib6->node_list)) + list_empty(&vr->fib6->node_list) && + mlxsw_sp_mr_table_empty(vr->mr4_table)) mlxsw_sp_vr_destroy(vr); } @@ -4731,6 +4746,75 @@ static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp, return 0; } +static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp, + struct mfc_entry_notifier_info *men_info, + bool replace) +{ + struct mlxsw_sp_vr *vr; + + if (mlxsw_sp->router->aborted) + return 0; + + vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id); + if (IS_ERR(vr)) + return PTR_ERR(vr); + + return mlxsw_sp_mr_route4_add(vr->mr4_table, men_info->mfc, replace); +} + +static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp, + struct mfc_entry_notifier_info *men_info) +{ + struct mlxsw_sp_vr *vr; + + if (mlxsw_sp->router->aborted) + return; + + vr = mlxsw_sp_vr_find(mlxsw_sp, men_info->tb_id); + if (WARN_ON(!vr)) + return; + + mlxsw_sp_mr_route4_del(vr->mr4_table, men_info->mfc); + mlxsw_sp_vr_put(vr); +} + +static int +mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp, + struct vif_entry_notifier_info *ven_info) +{ + struct mlxsw_sp_rif *rif; + struct mlxsw_sp_vr *vr; + + if (mlxsw_sp->router->aborted) + return 0; + + vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id); + if (IS_ERR(vr)) + return PTR_ERR(vr); + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, ven_info->dev); + return mlxsw_sp_mr_vif_add(vr->mr4_table, ven_info->dev, + ven_info->vif_index, + ven_info->vif_flags, rif); +} + +static void +mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp, + struct vif_entry_notifier_info *ven_info) +{ + struct mlxsw_sp_vr *vr; + + if (mlxsw_sp->router->aborted) + return; + + vr = mlxsw_sp_vr_find(mlxsw_sp, ven_info->tb_id); + if (WARN_ON(!vr)) + return; + + mlxsw_sp_mr_vif_del(vr->mr4_table, ven_info->vif_index); + mlxsw_sp_vr_put(vr); +} + static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) { enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4; @@ -4741,6 +4825,10 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) if (err) return err; + /* The multicast router code does not need an abort trap as by default, + * packets that don't match any routes are trapped to the CPU. + */ + proto = MLXSW_REG_RALXX_PROTOCOL_IPV6; return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, MLXSW_SP_LPM_TREE_MIN + 1); @@ -4822,6 +4910,8 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp_vr_is_used(vr)) continue; + + mlxsw_sp_mr_table_flush(vr->mr4_table); mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); /* If virtual router was only used for IPv4, then it's no @@ -4854,6 +4944,8 @@ struct mlxsw_sp_fib_event_work { struct fib_entry_notifier_info fen_info; struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; + struct mfc_entry_notifier_info men_info; + struct vif_entry_notifier_info ven_info; }; struct mlxsw_sp *mlxsw_sp; unsigned long event; @@ -4940,6 +5032,55 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) kfree(fib_work); } +static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) +{ + struct mlxsw_sp_fib_event_work *fib_work = + container_of(work, struct mlxsw_sp_fib_event_work, work); + struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; + struct fib_rule *rule; + bool replace; + int err; + + rtnl_lock(); + switch (fib_work->event) { + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_ADD: + replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; + + err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info, + replace); + if (err) + mlxsw_sp_router_fib_abort(mlxsw_sp); + ipmr_cache_put(fib_work->men_info.mfc); + break; + case FIB_EVENT_ENTRY_DEL: + mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info); + ipmr_cache_put(fib_work->men_info.mfc); + break; + case FIB_EVENT_VIF_ADD: + err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp, + &fib_work->ven_info); + if (err) + mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_put(fib_work->ven_info.dev); + break; + case FIB_EVENT_VIF_DEL: + mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, + &fib_work->ven_info); + dev_put(fib_work->ven_info.dev); + break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + rule = fib_work->fr_info.rule; + if (!ipmr_rule_default(rule) && !rule->l3mdev) + mlxsw_sp_router_fib_abort(mlxsw_sp); + fib_rule_put(rule); + break; + } + rtnl_unlock(); + kfree(fib_work); +} + static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { @@ -4985,6 +5126,30 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, } } +static void +mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work, + struct fib_notifier_info *info) +{ + switch (fib_work->event) { + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_ADD: /* fall through */ + case FIB_EVENT_ENTRY_DEL: + memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info)); + ipmr_cache_hold(fib_work->men_info.mfc); + break; + case FIB_EVENT_VIF_ADD: /* fall through */ + case FIB_EVENT_VIF_DEL: + memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info)); + dev_hold(fib_work->ven_info.dev); + break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; + } +} + /* Called with rcu_read_lock() */ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, unsigned long event, void *ptr) @@ -5014,6 +5179,10 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work); mlxsw_sp_router_fib6_event(fib_work, info); break; + case RTNL_FAMILY_IPMR: + INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work); + mlxsw_sp_router_fibmr_event(fib_work, info); + break; } mlxsw_core_schedule_work(&fib_work->work); @@ -5227,12 +5396,18 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_configure; + err = mlxsw_sp_mr_rif_add(vr->mr4_table, rif); + if (err) + goto err_mr_rif_add; + mlxsw_sp_rif_counters_alloc(rif); mlxsw_sp->router->rifs[rif_index] = rif; vr->rif_count++; return rif; +err_mr_rif_add: + ops->deconfigure(rif); err_configure: if (fid) mlxsw_sp_fid_put(fid); @@ -5257,6 +5432,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) vr->rif_count--; mlxsw_sp->router->rifs[rif->rif_index] = NULL; mlxsw_sp_rif_counters_free(rif); + mlxsw_sp_mr_rif_del(vr->mr4_table, rif); ops->deconfigure(rif); if (fid) /* Loopback RIFs are not associated with a FID. */ @@ -6120,6 +6296,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_lpm_init; + err = mlxsw_sp_mr_init(mlxsw_sp, &mlxsw_sp_mr_tcam_ops); + if (err) + goto err_mr_init; + err = mlxsw_sp_vrs_init(mlxsw_sp); if (err) goto err_vrs_init; @@ -6141,6 +6321,8 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); err_vrs_init: + mlxsw_sp_mr_fini(mlxsw_sp); +err_mr_init: mlxsw_sp_lpm_fini(mlxsw_sp); err_lpm_init: rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht); @@ -6162,6 +6344,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(&mlxsw_sp->router->fib_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); + mlxsw_sp_mr_fini(mlxsw_sp); mlxsw_sp_lpm_fini(mlxsw_sp); rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht); rhashtable_destroy(&mlxsw_sp->router->nexthop_ht); -- GitLab From fd890fe98f8b026642d39011d03d22fb4aa66b0f Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:21 +0200 Subject: [PATCH 0537/1507] mlxsw: spectrum: Notify multicast router on RIF MTU changes Due to the fact that multicast routes hold the minimum MTU of all the egress RIFs and trap packets that don't meet it, notify the mulitcast router code on RIF MTU changes. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 77584422ed082..dbd9c196fcfb0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5773,6 +5773,17 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev) if (err) goto err_rif_fdb_op; + if (rif->mtu != dev->mtu) { + struct mlxsw_sp_vr *vr; + + /* The RIF is relevant only to its mr_table instance, as unlike + * unicast routing, in multicast routing a RIF cannot be shared + * between several multicast routing tables. + */ + vr = &mlxsw_sp->router->vrs[rif->vr_id]; + mlxsw_sp_mr_rif_mtu_update(vr->mr4_table, rif, dev->mtu); + } + ether_addr_copy(rif->addr, dev->dev_addr); rif->mtu = dev->mtu; -- GitLab From 664375e9567b5eeece8d9ebf85eaf5107cab382d Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Wed, 27 Sep 2017 08:23:22 +0200 Subject: [PATCH 0538/1507] mlxsw: spectrum: router: Don't ignore IPMR notifications Make the Spectrum router logic not ignore the RTNL_FAMILY_IPMR FIB notifications. Past commits added the IPMR VIF and MFC add/del notifications via the fib_notifier chain. In addition, a code for handling these notifications in the Spectrum router logic was added. Make the Spectrum router logic not ignore these notifications and forward the requests to the Spectrum multicast router offloading logic. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index dbd9c196fcfb0..ef4b86b3aa9b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5159,7 +5159,8 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct mlxsw_sp_router *router; if (!net_eq(info->net, &init_net) || - (info->family != AF_INET && info->family != AF_INET6)) + (info->family != AF_INET && info->family != AF_INET6 && + info->family != RTNL_FAMILY_IPMR)) return NOTIFY_DONE; fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); -- GitLab From a5f3d8a5eaaf917878f07998e6f1ea46024e6bab Mon Sep 17 00:00:00 2001 From: Coly Li Date: Tue, 26 Sep 2017 17:54:12 +0800 Subject: [PATCH 0539/1507] bcache: use llist_for_each_entry_safe() in __closure_wake_up() Commit 09b3efec ("bcache: Don't reinvent the wheel but use existing llist API") replaces the following while loop by llist_for_each_entry(), - - while (reverse) { - cl = container_of(reverse, struct closure, list); - reverse = llist_next(reverse); - + llist_for_each_entry(cl, reverse, list) { closure_set_waiting(cl, 0); closure_sub(cl, CLOSURE_WAITING + 1); } This modification introduces a potential race by iterating a corrupted list. Here is how it happens. In the above modification, closure_sub() may wake up a process which is waiting on reverse list. If this process decides to wait again by calling closure_wait(), its cl->list will be added to another wait list. Then when llist_for_each_entry() continues to iterate next node, it will travel on another new wait list which is added in closure_wait(), not the original reverse list in __closure_wake_up(). It is more probably to happen on UP machine because the waked up process may preempt the process which wakes up it. Use llist_for_each_entry_safe() will fix the issue, the safe version fetch next node before waking up a process. Then the copy of next node will make sure list iteration stays on original reverse list. Fixes: 09b3efec81de ("bcache: Don't reinvent the wheel but use existing llist API") Signed-off-by: Coly Li Reported-by: Michael Lyle Reviewed-by: Byungchul Park Signed-off-by: Jens Axboe --- drivers/md/bcache/closure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 7d5286b050369..1841d0359bace 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -64,7 +64,7 @@ EXPORT_SYMBOL(closure_put); void __closure_wake_up(struct closure_waitlist *wait_list) { struct llist_node *list; - struct closure *cl; + struct closure *cl, *t; struct llist_node *reverse = NULL; list = llist_del_all(&wait_list->list); @@ -73,7 +73,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list) reverse = llist_reverse_order(list); /* Then do the wakeups */ - llist_for_each_entry(cl, reverse, list) { + llist_for_each_entry_safe(cl, t, reverse, list) { closure_set_waiting(cl, 0); closure_sub(cl, CLOSURE_WAITING + 1); } -- GitLab From aaf2c2fb0f51f91c699039440862b6ae9c25c10e Mon Sep 17 00:00:00 2001 From: Tyler Baicar Date: Mon, 28 Aug 2017 10:53:41 -0600 Subject: [PATCH 0540/1507] ACPI / APEI: clear error status before acknowledging the error Currently we acknowledge errors before clearing the error status. This could cause a new error to be populated by firmware in-between the error acknowledgment and the error status clearing which would cause the second error's status to be cleared without being handled. So, clear the error status before acknowledging the errors. Also, make sure to acknowledge the error if the error status read fails. Signed-off-by: Tyler Baicar Reviewed-by: Borislav Petkov Signed-off-by: Rafael J. Wysocki --- drivers/acpi/apei/ghes.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 077f9bad6f44a..3c3a37b8503bd 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -743,17 +743,19 @@ static int ghes_proc(struct ghes *ghes) } ghes_do_proc(ghes, ghes->estatus); +out: + ghes_clear_estatus(ghes); + + if (rc == -ENOENT) + return rc; + /* * GHESv2 type HEST entries introduce support for error acknowledgment, * so only acknowledge the error if this support is present. */ - if (is_hest_type_generic_v2(ghes)) { - rc = ghes_ack_error(ghes->generic_v2); - if (rc) - return rc; - } -out: - ghes_clear_estatus(ghes); + if (is_hest_type_generic_v2(ghes)) + return ghes_ack_error(ghes->generic_v2); + return rc; } -- GitLab From 2e08d20d777e997bf37806b22b471f98fbe6b693 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 27 Sep 2017 16:34:59 -0500 Subject: [PATCH 0541/1507] percpu: fix starting offset for chunk statistics traversal This patch fixes the starting offset used when scanning chunks to compute the chunk statistics. The value start_offset (and end_offset) are managed in bytes while the traversal occurs over bits. Thus for the reserved and dynamic chunk, it may incorrectly skip over the initial allocations. Signed-off-by: Dennis Zhou Signed-off-by: Tejun Heo --- mm/percpu-stats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index 6142484e88f79..7a58460bfd27a 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -73,7 +73,7 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk, last_alloc + 1 : 0; as_len = 0; - start = chunk->start_offset; + start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; /* * If a bit is set in the allocation map, the bound_map identifies -- GitLab From 8aba2333904f9b1c1ea038df261bf7ae8fefb98e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 28 Sep 2017 02:08:43 +0200 Subject: [PATCH 0542/1507] cpufreq: docs: Drop intel-pstate.txt from index.txt Commit 33fc30b47098 (cpufreq: intel_pstate: Document the current behavior and user interface) dropped the intel-pstate.txt file from Documentation/cpu-freq/, but it did not update the index.txt file in there accordingly, so do that now. Fixes: 33fc30b47098 (cpufreq: intel_pstate: Document the current behavior and user interface) Signed-off-by: Rafael J. Wysocki --- Documentation/cpu-freq/index.txt | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt index 03a7cee6ac73a..c15e75386a052 100644 --- a/Documentation/cpu-freq/index.txt +++ b/Documentation/cpu-freq/index.txt @@ -32,8 +32,6 @@ cpufreq-stats.txt - General description of sysfs cpufreq stats. index.txt - File index, Mailing list and Links (this document) -intel-pstate.txt - Intel pstate cpufreq driver specific file. - pcc-cpufreq.txt - PCC cpufreq driver specific file. -- GitLab From d1b490939d8c117a06dfc562c41d933f71d30289 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Tue, 19 Sep 2017 12:11:55 -0300 Subject: [PATCH 0543/1507] scsi: aacraid: Add a small delay after IOP reset Commit 0e9973ed3382 ("scsi: aacraid: Add periodic checks to see IOP reset status") changed the way driver checks if a reset succeeded. Now, after an IOP reset, aacraid immediately start polling a register to verify the reset is complete. This behavior cause regressions on the reset path in PowerPC (at least). Since the delay after the IOP reset was removed by the aforementioned patch, the fact driver just starts to read a register instantly after the reset was issued (by writing in another register) "corrupts" the reset procedure, which ends up failing all the time. The issue highly impacted kdump on PowerPC, since on kdump path we proactively issue a reset in adapter (through the reset_devices kernel parameter). This patch (re-)adds a delay right after IOP reset is issued. Empirically we measured that 3 seconds is enough, but for safety reasons we delay for 5s (and since it was 30s before, 5s is still a small amount). For reference, without this patch we observe the following messages on kdump kernel boot process: [ 76.294] aacraid 0003:01:00.0: IOP reset failed [ 76.294] aacraid 0003:01:00.0: ARC Reset attempt failed [ 86.524] aacraid 0003:01:00.0: adapter kernel panic'd ff. [ 86.524] aacraid 0003:01:00.0: Controller reset type is 3 [ 86.524] aacraid 0003:01:00.0: Issuing IOP reset [146.534] aacraid 0003:01:00.0: IOP reset failed [146.534] aacraid 0003:01:00.0: ARC Reset attempt failed Fixes: 0e9973ed3382 ("scsi: aacraid: Add periodic checks to see IOP reset status") Cc: stable@vger.kernel.org # v4.13+ Signed-off-by: Guilherme G. Piccoli Acked-by: Dave Carroll Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/src.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 48c2b2b34b722..0c9361c87ec8d 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -740,6 +740,8 @@ static void aac_send_iop_reset(struct aac_dev *dev) aac_set_intx_mode(dev); src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK); + + msleep(5000); } static void aac_send_hardware_soft_reset(struct aac_dev *dev) -- GitLab From d0b7a9095c0730b92a0a2eecaba2e6b77ed87339 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Wed, 27 Sep 2017 14:44:19 +0200 Subject: [PATCH 0544/1507] scsi: ILLEGAL REQUEST + ASC==27 => target failure ASC 0x27 is "WRITE PROTECTED". This error code is returned e.g. by Fujitsu ETERNUS systems under certain conditions for WRITE SAME 16 commands with UNMAP bit set. It should not be treated as a path error. In general, it makes sense to assume that being write protected is a target rather than a path property. Signed-off-by: Martin Wilck Acked-by: Lee Duncan Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 38942050b2656..dab876c654739 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -580,7 +580,8 @@ int scsi_check_sense(struct scsi_cmnd *scmd) if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x24 || /* Invalid field in cdb */ - sshdr.asc == 0x26) { /* Parameter value invalid */ + sshdr.asc == 0x26 || /* Parameter value invalid */ + sshdr.asc == 0x27) { /* Write protected */ set_host_byte(scmd, DID_TARGET_FAILURE); } return SUCCESS; -- GitLab From 393debc23c7820211d1c8253dd6a8408a7628fe7 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 21 Sep 2017 10:23:35 -0700 Subject: [PATCH 0545/1507] md: separate request handling With commit cc27b0c78c79, pers->make_request could bail out without handling the bio. If that happens, we should retry. The commit fixes md_make_request but not other call sites. Separate the request handling part, so other call sites can use it. Reported-by: Nate Dailey Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start()) Cc: stable@vger.kernel.org Reviewed-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/md.c | 58 ++++++++++++++++++++++++++++--------------------- drivers/md/md.h | 1 + 2 files changed, 34 insertions(+), 25 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 08fcaebc61bdb..1db1a22ed835a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * call has finished, the bio has been linked into some internal structure * and so is visible to ->quiesce(), so we don't need the refcount any more. */ +void md_handle_request(struct mddev *mddev, struct bio *bio) +{ +check_suspended: + rcu_read_lock(); + if (mddev->suspended) { + DEFINE_WAIT(__wait); + for (;;) { + prepare_to_wait(&mddev->sb_wait, &__wait, + TASK_UNINTERRUPTIBLE); + if (!mddev->suspended) + break; + rcu_read_unlock(); + schedule(); + rcu_read_lock(); + } + finish_wait(&mddev->sb_wait, &__wait); + } + atomic_inc(&mddev->active_io); + rcu_read_unlock(); + + if (!mddev->pers->make_request(mddev, bio)) { + atomic_dec(&mddev->active_io); + wake_up(&mddev->sb_wait); + goto check_suspended; + } + + if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) + wake_up(&mddev->sb_wait); +} +EXPORT_SYMBOL(md_handle_request); + static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); @@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) bio_endio(bio); return BLK_QC_T_NONE; } -check_suspended: - rcu_read_lock(); - if (mddev->suspended) { - DEFINE_WAIT(__wait); - for (;;) { - prepare_to_wait(&mddev->sb_wait, &__wait, - TASK_UNINTERRUPTIBLE); - if (!mddev->suspended) - break; - rcu_read_unlock(); - schedule(); - rcu_read_lock(); - } - finish_wait(&mddev->sb_wait, &__wait); - } - atomic_inc(&mddev->active_io); - rcu_read_unlock(); /* * save the sectors now since our bio can @@ -310,20 +324,14 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; - if (!mddev->pers->make_request(mddev, bio)) { - atomic_dec(&mddev->active_io); - wake_up(&mddev->sb_wait); - goto check_suspended; - } + + md_handle_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); - if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) - wake_up(&mddev->sb_wait); - return BLK_QC_T_NONE; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 561d22b9a9a8a..d8287d3cd1bf8 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -692,6 +692,7 @@ extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); +extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, -- GitLab From 79bf31a3b2a7ca467cfec8ff97d359a77065d01f Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 21 Sep 2017 09:55:28 -0700 Subject: [PATCH 0546/1507] md: fix a race condition for flush request handling md_submit_flush_data calls pers->make_request, which missed the suspend check. Fix it with the new md_handle_request API. Reported-by: Nate Dailey Tested-by: Nate Dailey Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start()) Cc: stable@vger.kernel.org Reviewed-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/md.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 1db1a22ed835a..0ff1bbf6c90e5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -447,16 +447,22 @@ static void md_submit_flush_data(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); else { bio->bi_opf &= ~REQ_PREFLUSH; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); } - - mddev->flush_bio = NULL; - wake_up(&mddev->sb_wait); } void md_flush_request(struct mddev *mddev, struct bio *bio) -- GitLab From c4d6a1b8e8ea79c439a4871cba540443c9eb13b9 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 21 Sep 2017 10:29:22 -0700 Subject: [PATCH 0547/1507] dm-raid: fix a race condition in request handling raid_map calls pers->make_request, which missed the suspend check. Fix it with the new md_handle_request API. Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start()) Cc: Heinz Mauelshagen Cc: Mike Snitzer Cc: stable@vger.kernel.org Reviewed-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/dm-raid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285ea9d1c..1ac58c5651b7f 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3238,7 +3238,7 @@ static int raid_map(struct dm_target *ti, struct bio *bio) if (unlikely(bio_end_sector(bio) > mddev->array_sectors)) return DM_MAPIO_REQUEUE; - mddev->pers->make_request(mddev, bio); + md_handle_request(mddev, bio); return DM_MAPIO_SUBMITTED; } -- GitLab From 7d5d7b5058fbd638914e42504677141a69f43011 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 21 Sep 2017 11:03:52 -0700 Subject: [PATCH 0548/1507] md/raid5: cap worker count static checker reports a potential integer overflow. Cap the worker count to avoid the overflow. Reported:-by: Dan Carpenter Signed-off-by: Shaohua Li --- drivers/md/raid5.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 076409455b603..928e24a071338 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6575,14 +6575,17 @@ static ssize_t raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len) { struct r5conf *conf; - unsigned long new; + unsigned int new; int err; struct r5worker_group *new_groups, *old_groups; int group_cnt, worker_cnt_per_group; if (len >= PAGE_SIZE) return -EINVAL; - if (kstrtoul(page, 10, &new)) + if (kstrtouint(page, 10, &new)) + return -EINVAL; + /* 8192 should be big enough */ + if (new > 8192) return -EINVAL; err = mddev_lock(mddev); -- GitLab From 38e8a5c040d3ec99a8351c688dcdf0f549611565 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Mon, 21 Aug 2017 12:04:50 +0300 Subject: [PATCH 0549/1507] net/mlx5e: IPoIB, Fix access to invalid memory address When cleaning rdma netdevice we need to save the mdev pointer because priv is released when we release netdev. This bug was found using the kernel address sanitizer (KASAN). use-after-free in mlx5_rdma_netdev_free+0xe3/0x100 [mlx5_core] Fixes: 48935bbb7ae8 ("net/mlx5e: IPoIB, Add netdevice profile skeleton") Signed-off-by: Roi Dayan Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 85298051a3e4f..145e392ab8497 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -572,12 +572,13 @@ void mlx5_rdma_netdev_free(struct net_device *netdev) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); const struct mlx5e_profile *profile = priv->profile; + struct mlx5_core_dev *mdev = priv->mdev; mlx5e_detach_netdev(priv); profile->cleanup(priv); destroy_workqueue(priv->wq); free_netdev(netdev); - mlx5e_destroy_mdev_resources(priv->mdev); + mlx5e_destroy_mdev_resources(mdev); } EXPORT_SYMBOL(mlx5_rdma_netdev_free); -- GitLab From 99d3cd27f755d63fd6cf85169eaa873d90769aa5 Mon Sep 17 00:00:00 2001 From: Inbar Karmy Date: Thu, 24 Aug 2017 17:21:44 +0300 Subject: [PATCH 0550/1507] net/mlx5: Fix FPGA capability location Currently, FPGA capability is located in (mdev)->caps.hca_cur, change the location to be (mdev)->caps.fpga, since hca_cur is reserved for HCA device capabilities. Fixes: e29341fb3a5b ("net/mlx5: FPGA, Add basic support for Innova") Signed-off-by: Inbar Karmy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c | 3 +-- include/linux/mlx5/device.h | 5 ++--- include/linux/mlx5/driver.h | 1 + 5 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c index e37453d838dbb..c0fd2212e8908 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.c @@ -71,11 +71,11 @@ int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr, return 0; } -int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps) +int mlx5_fpga_caps(struct mlx5_core_dev *dev) { u32 in[MLX5_ST_SZ_DW(fpga_cap)] = {0}; - return mlx5_core_access_reg(dev, in, sizeof(in), caps, + return mlx5_core_access_reg(dev, in, sizeof(in), dev->caps.fpga, MLX5_ST_SZ_BYTES(fpga_cap), MLX5_REG_FPGA_CAP, 0, 0); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h index 94bdfd47c3f09..d05233c9b4f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h @@ -65,7 +65,7 @@ struct mlx5_fpga_qp_counters { u64 rx_total_drop; }; -int mlx5_fpga_caps(struct mlx5_core_dev *dev, u32 *caps); +int mlx5_fpga_caps(struct mlx5_core_dev *dev); int mlx5_fpga_query(struct mlx5_core_dev *dev, struct mlx5_fpga_query *query); int mlx5_fpga_ctrl_op(struct mlx5_core_dev *dev, u8 op); int mlx5_fpga_access_reg(struct mlx5_core_dev *dev, u8 size, u64 addr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index 9034e9960a761..dc8970346521d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -139,8 +139,7 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) if (err) goto out; - err = mlx5_fpga_caps(fdev->mdev, - fdev->mdev->caps.hca_cur[MLX5_CAP_FPGA]); + err = mlx5_fpga_caps(fdev->mdev); if (err) goto out; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index eaf4ad209c8fa..e32dbc4934dbb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -980,7 +980,6 @@ enum mlx5_cap_type { MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, MLX5_CAP_QOS, - MLX5_CAP_FPGA, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1110,10 +1109,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) #define MLX5_CAP_FPGA(mdev, cap) \ - MLX5_GET(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap) #define MLX5_CAP64_FPGA(mdev, cap) \ - MLX5_GET64(fpga_cap, (mdev)->caps.hca_cur[MLX5_CAP_FPGA], cap) + MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap) enum { MLX5_CMD_STAT_OK = 0x0, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02ff700e4f30c..401c8972cc3a8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -774,6 +774,7 @@ struct mlx5_core_dev { u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 pcam[MLX5_ST_SZ_DW(pcam_reg)]; u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; + u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; } caps; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; -- GitLab From 16f1c5bb3ed75b3cf3ced537db40f7e1a244debe Mon Sep 17 00:00:00 2001 From: Raed Salem Date: Sun, 30 Jul 2017 11:02:51 +0300 Subject: [PATCH 0551/1507] net/mlx5: Check device capability for maximum flow counters Added check for the maximal number of flow counters attached to rule (FTE). Fixes: bd5251dbf156b ('net/mlx5_core: Introduce flow steering destination of type counter') Signed-off-by: Raed Salem Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 8 ++++++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 11 +++++++++++ include/linux/mlx5/mlx5_ifc.h | 3 ++- 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index e0d0efd903bc9..36ecc2b2e1873 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -293,6 +293,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, } if (fte->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev, + log_max_flow_counter, + ft->type)); int list_size = 0; list_for_each_entry(dst, &fte->node.children, node.list) { @@ -305,12 +308,17 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); list_size++; } + if (list_size > max_list_size) { + err = -EINVAL; + goto err_out; + } MLX5_SET(flow_context, in_flow_context, flow_counter_list_size, list_size); } err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); +err_out: kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 5509a752f98e7..48dd78975062c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -52,6 +52,7 @@ enum fs_flow_table_type { FS_FT_FDB = 0X4, FS_FT_SNIFFER_RX = 0X5, FS_FT_SNIFFER_TX = 0X6, + FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX, }; enum fs_flow_table_op_mod { @@ -260,4 +261,14 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev); #define fs_for_each_dst(pos, fte) \ fs_list_for_each_entry(pos, &(fte)->node.children) +#define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) ( \ + (type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) : \ + (type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) : \ + (type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) : \ + (type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ + (type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) : \ + (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\ + ) + #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a528b35a022e0..69772347f8666 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -327,7 +327,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_80[0x18]; u8 log_max_destination[0x8]; - u8 reserved_at_a0[0x18]; + u8 log_max_flow_counter[0x8]; + u8 reserved_at_a8[0x10]; u8 log_max_flow[0x8]; u8 reserved_at_c0[0x40]; -- GitLab From ace743214ea205c7d433562c5fa24e33bdfda7ab Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 5 Sep 2017 15:05:51 +0300 Subject: [PATCH 0552/1507] net/mlx5e: Fix erroneous freeing of encap header buffer In case the neighbour for the tunnel destination isn't valid, we send a neighbour update request but we free the encap header buffer. This is wrong, because we still need it for allocating a HW encap entry once the neighbour is available. Fix that by skipping freeing it if we wait for neighbour. Fixes: 232c001398ae ('net/mlx5e: Add support to neighbour update flow') Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index da503e6411da0..4e2fc016bdd65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1564,7 +1564,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, break; default: err = -EOPNOTSUPP; - goto out; + goto free_encap; } fl4.flowi4_tos = tun_key->tos; fl4.daddr = tun_key->u.ipv4.dst; @@ -1573,7 +1573,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &fl4, &n, &ttl); if (err) - goto out; + goto free_encap; /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -1590,7 +1590,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, */ err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); if (err) - goto out; + goto free_encap; read_lock_bh(&n->lock); nud_state = n->nud_state; @@ -1630,8 +1630,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -out: +free_encap: kfree(encap_header); +out: if (n) neigh_release(n); return err; @@ -1668,7 +1669,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, break; default: err = -EOPNOTSUPP; - goto out; + goto free_encap; } fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label); @@ -1678,7 +1679,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &fl6, &n, &ttl); if (err) - goto out; + goto free_encap; /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -1695,7 +1696,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, */ err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e); if (err) - goto out; + goto free_encap; read_lock_bh(&n->lock); nud_state = n->nud_state; @@ -1736,8 +1737,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); -out: +free_encap: kfree(encap_header); +out: if (n) neigh_release(n); return err; -- GitLab From bdd66ac0aeed971d1cb42b3aa0d11b0ea3842e09 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 11 Jun 2017 21:13:25 +0300 Subject: [PATCH 0553/1507] net/mlx5e: Disallow TC offloading of unsupported match/action combinations When offloading header re-write, the HW may need to adjust checksums along the packet. For IP traffic, and a case where we are asked to modify fields in the IP header, current HW supports that only for TCP and UDP. Enforce it, in this case fail the offloading attempt for non TCP/UDP packets. Fixes: d7e75a325cb2 ('net/mlx5e: Add offloading of E-Switch TC pedit (header re-write) actions') Fixes: 2f4fe4cab073 ('net/mlx5e: Add offloading of NIC TC pedit (header re-write) actions') Signed-off-by: Or Gerlitz Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 70 +++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 4e2fc016bdd65..d3786005fba7d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1317,6 +1317,69 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, u32 action, u32 upda return true; } +static bool modify_header_match_supported(struct mlx5_flow_spec *spec, + struct tcf_exts *exts) +{ + const struct tc_action *a; + bool modify_ip_header; + LIST_HEAD(actions); + u8 htype, ip_proto; + void *headers_v; + u16 ethertype; + int nkeys, i; + + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); + ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); + + /* for non-IP we only re-write MACs, so we're okay */ + if (ethertype != ETH_P_IP && ethertype != ETH_P_IPV6) + goto out_ok; + + modify_ip_header = false; + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { + if (!is_tcf_pedit(a)) + continue; + + nkeys = tcf_pedit_nkeys(a); + for (i = 0; i < nkeys; i++) { + htype = tcf_pedit_htype(a, i); + if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 || + htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) { + modify_ip_header = true; + break; + } + } + } + + ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); + if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { + pr_info("can't offload re-write of ip proto %d\n", ip_proto); + return false; + } + +out_ok: + return true; +} + +static bool actions_match_supported(struct mlx5e_priv *priv, + struct tcf_exts *exts, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct mlx5e_tc_flow *flow) +{ + u32 actions; + + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + actions = flow->esw_attr->action; + else + actions = flow->nic_attr->action; + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + return modify_header_match_supported(&parse_attr->spec, exts); + + return true; +} + static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow) @@ -1378,6 +1441,9 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return -EINVAL; } + if (!actions_match_supported(priv, exts, parse_attr, flow)) + return -EOPNOTSUPP; + return 0; } @@ -1936,6 +2002,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return -EINVAL; } + + if (!actions_match_supported(priv, exts, parse_attr, flow)) + return -EOPNOTSUPP; + return err; } -- GitLab From b281208911a549e391d92ee6cb680dcd3d71783b Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 8 Aug 2017 11:45:28 +0300 Subject: [PATCH 0554/1507] net/mlx5e: Check encap entry state when offloading tunneled flows Encap entries cached by the driver could be invalidated due to tunnel destination neighbour state changes. When attempting to offload a flow that uses a cached encap entry, we must check the entry validity and defer the offloading if the entry exists but not valid. When EAGAIN is returned, the flow offloading to hardware takes place by the neigh update code when the tunnel destination neighbour becomes connected. Fixes: 232c001398ae ("net/mlx5e: Add support to neighbour update flow") Signed-off-by: Vlad Buslov Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index d3786005fba7d..1aa2028ed995d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1859,6 +1859,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, } } + /* must verify if encap is valid or not */ if (found) goto attach_flow; @@ -1885,6 +1886,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, *encap_dev = e->out_dev; if (e->flags & MLX5_ENCAP_ENTRY_VALID) attr->encap_id = e->encap_id; + else + err = -EAGAIN; return err; -- GitLab From b20eab15a1d5091e45022401e75b49948e8be33f Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 12 Sep 2017 17:51:12 +0300 Subject: [PATCH 0555/1507] net/mlx5e: Print netdev features correctly in error message Use the correct formatting for netdev features. Fixes: 0e405443e803 ("net/mlx5e: Improve set features ndo resiliency") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dfc29720ab774..84b013dc62e93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3333,8 +3333,8 @@ static int mlx5e_handle_feature(struct net_device *netdev, err = feature_handler(netdev, enable); if (err) { - netdev_err(netdev, "%s feature 0x%llx failed err %d\n", - enable ? "Enable" : "Disable", feature, err); + netdev_err(netdev, "%s feature %pNF failed, err %d\n", + enable ? "Enable" : "Disable", &feature, err); return err; } -- GitLab From 1456f69ff5fbba48ed5bc86e858e945e693ba0b7 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 10 Sep 2017 10:36:06 +0300 Subject: [PATCH 0556/1507] net/mlx5e: Don't add/remove 802.1ad rules when changing 802.1Q VLAN filter Toggling of C-tag VLAN filter should not affect the "any S-tag" steering rule. Fixes: 8a271746a264 ("net/mlx5e: Receive s-tagged packets in promiscuous mode") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index f11fd07ac4dd1..850cdc980ab5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -291,7 +291,7 @@ void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv) priv->fs.vlan.filter_disabled = false; if (priv->netdev->flags & IFF_PROMISC) return; - mlx5e_del_any_vid_rules(priv); + mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0); } void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) @@ -302,7 +302,7 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv) priv->fs.vlan.filter_disabled = true; if (priv->netdev->flags & IFF_PROMISC) return; - mlx5e_add_any_vid_rules(priv); + mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_CTAG_VID, 0); } int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, -- GitLab From 603e1f5bd3ca76f16688e10040545594d2e91ba4 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Wed, 13 Sep 2017 15:37:50 +0300 Subject: [PATCH 0557/1507] net/mlx5e: Fix calculated checksum offloads counters Instead of calculating the offloads counters, count them explicitly. The calculations done for these counters would result in bugs in some cases, for example: When running TCP traffic over a VXLAN tunnel with TSO enabled the following counters would increase: tx_csum_partial: 1,333,284 tx_csum_partial_inner: 29,286 tx4_csum_partial_inner: 384 tx7_csum_partial_inner: 8 tx9_csum_partial_inner: 34 tx10_csum_partial_inner: 26,807 tx11_csum_partial_inner: 287 tx12_csum_partial_inner: 27 tx16_csum_partial_inner: 6 tx25_csum_partial_inner: 1,733 Seems like tx_csum_partial increased out of nowhere. The issue is in the following calculation in mlx5e_update_sw_counters: s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner; While tx_packets increases by the number of GSO segments for each SKB, tx_csum_partial_inner will only increase by one, resulting in wrong tx_csum_partial counter. Fixes: bfe6d8d1d433 ("net/mlx5e: Reorganize ethtool statistics") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 9 +++------ drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 6 ++++++ drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 1 + 4 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 84b013dc62e93..cc11bbbd0309d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -184,7 +184,6 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) struct mlx5e_sw_stats temp, *s = &temp; struct mlx5e_rq_stats *rq_stats; struct mlx5e_sq_stats *sq_stats; - u64 tx_offload_none = 0; int i, j; memset(s, 0, sizeof(*s)); @@ -199,6 +198,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->rx_lro_bytes += rq_stats->lro_bytes; s->rx_csum_none += rq_stats->csum_none; s->rx_csum_complete += rq_stats->csum_complete; + s->rx_csum_unnecessary += rq_stats->csum_unnecessary; s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; s->rx_xdp_drop += rq_stats->xdp_drop; s->rx_xdp_tx += rq_stats->xdp_tx; @@ -229,14 +229,11 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->tx_queue_dropped += sq_stats->dropped; s->tx_xmit_more += sq_stats->xmit_more; s->tx_csum_partial_inner += sq_stats->csum_partial_inner; - tx_offload_none += sq_stats->csum_none; + s->tx_csum_none += sq_stats->csum_none; + s->tx_csum_partial += sq_stats->csum_partial; } } - /* Update calculated offload counters */ - s->tx_csum_partial = s->tx_packets - tx_offload_none - s->tx_csum_partial_inner; - s->rx_csum_unnecessary = s->rx_packets - s->rx_csum_none - s->rx_csum_complete; - s->link_down_events_phy = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters, counter_set.phys_layer_cntrs.link_down_events); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638384d38..15a1687483cc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -627,6 +627,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (lro) { skb->ip_summed = CHECKSUM_UNNECESSARY; + rq->stats.csum_unnecessary++; return; } @@ -644,7 +645,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, skb->csum_level = 1; skb->encapsulation = 1; rq->stats.csum_unnecessary_inner++; + return; } + rq->stats.csum_unnecessary++; return; } csum_none: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 6d199ffb1c0b5..f8637213afc0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -68,6 +68,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_drop; u64 rx_xdp_tx; u64 rx_xdp_tx_full; + u64 tx_csum_none; u64 tx_csum_partial; u64 tx_csum_partial_inner; u64 tx_queue_stopped; @@ -108,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, @@ -339,6 +341,7 @@ struct mlx5e_rq_stats { u64 packets; u64 bytes; u64 csum_complete; + u64 csum_unnecessary; u64 csum_unnecessary_inner; u64 csum_none; u64 lro_packets; @@ -363,6 +366,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) }, @@ -392,6 +396,7 @@ struct mlx5e_sq_stats { u64 tso_bytes; u64 tso_inner_packets; u64 tso_inner_bytes; + u64 csum_partial; u64 csum_partial_inner; u64 nop; /* less likely accessed in data path */ @@ -408,6 +413,7 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_bytes) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tso_inner_bytes) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index fee43e40fa16a..1d6925d4369af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -193,6 +193,7 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct sq->stats.csum_partial_inner++; } else { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; + sq->stats.csum_partial++; } } else sq->stats.csum_none++; -- GitLab From 480df991b869eff02a004e8fe7707900437cfcd4 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Thu, 31 Aug 2017 18:52:14 +0300 Subject: [PATCH 0558/1507] net/mlx5: Fix static checker warning on steering tracepoints code Fix this sparse complaint: drivers/net/ethernet/mellanox/mlx5/core/./diag/fs_tracepoint.h:172:1: warning: odd constant _Bool cast (ffffffffffffffff becomes 1) Fixes: d9fea79171ee ('net/mlx5: Add tracepoints') Signed-off-by: Matan Barak Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h index 1e3a6c3e41323..80eef4163f52e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -139,7 +139,7 @@ TRACE_EVENT(mlx5_fs_del_fg, {MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"} TRACE_EVENT(mlx5_fs_set_fte, - TP_PROTO(const struct fs_fte *fte, bool new_fte), + TP_PROTO(const struct fs_fte *fte, int new_fte), TP_ARGS(fte, new_fte), TP_STRUCT__entry( __field(const struct fs_fte *, fte) @@ -149,7 +149,7 @@ TRACE_EVENT(mlx5_fs_set_fte, __field(u32, action) __field(u32, flow_tag) __field(u8, mask_enable) - __field(bool, new_fte) + __field(int, new_fte) __array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) __array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) __array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc)) -- GitLab From 353f59f4d41e9c5798a15c5c52958f25b579a3d5 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 24 Sep 2017 09:54:00 +0200 Subject: [PATCH 0559/1507] net/mlx5: Fix wrong indentation in enable SRIOV code Smatch is screaming: drivers/net/ethernet/mellanox/mlx5/core/sriov.c:112 mlx5_device_enable_sriov() warn: inconsistent indenting fix that. Fixes: 7ecf6d8ff154 ('IB/mlx5: Restore IB guid/policy for virtual functions') Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 6c48e9959b654..2a8b529ce6dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -109,7 +109,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) mlx5_core_warn(dev, "failed to restore VF %d settings, err %d\n", vf, err); - continue; + continue; } } mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf); -- GitLab From da541b20021c781f8b65492eeaee824e729599eb Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 27 Sep 2017 17:34:23 -0500 Subject: [PATCH 0560/1507] objtool: Skip unreachable warnings for GCC 4.4 and older The kbuild bot occasionally reports warnings like: drivers/scsi/pcmcia/aha152x_core.o: warning: objtool: seldo_run()+0x130: unreachable instruction These warnings are always with GCC 4.4. That version of GCC sometimes places unreachable instructions after calls to noreturn functions. The unreachable warnings aren't very important anyway. Just ignore them for old versions of GCC. Reported-by: kbuild test robot Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/bc89b807d965b98ec18a0bb94f96a594bd58f2f2.1506551639.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- scripts/Makefile.build | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2e3a10e79ca9e..061d0c3a420ad 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -265,6 +265,8 @@ objtool_args += --no-fp endif ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable +else +objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory -- GitLab From 607a4029d439cdfa258aff5da32bb9cd6ed1a66d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 27 Sep 2017 10:36:38 -0500 Subject: [PATCH 0561/1507] objtool: Support unoptimized frame pointer setup Arnd Bergmann reported a bunch of warnings like: crypto/jitterentropy.o: warning: objtool: jent_fold_time()+0x3b: call without frame pointer save/setup crypto/jitterentropy.o: warning: objtool: jent_stuck()+0x1d: call without frame pointer save/setup crypto/jitterentropy.o: warning: objtool: jent_unbiased_bit()+0x15: call without frame pointer save/setup crypto/jitterentropy.o: warning: objtool: jent_read_entropy()+0x32: call without frame pointer save/setup crypto/jitterentropy.o: warning: objtool: jent_entropy_collector_free()+0x19: call without frame pointer save/setup and arch/x86/events/core.o: warning: objtool: collect_events uses BP as a scratch register arch/x86/events/core.o: warning: objtool: events_ht_sysfs_show()+0x22: call without frame pointer save/setup With certain rare configurations, GCC sometimes sets up the frame pointer with: lea (%rsp),%rbp instead of: mov %rsp,%rbp The instructions are equivalent, so treat the former like the latter. Reported-by: Arnd Bergmann Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/a468af8b28a69b83fffc6d7668be9b6fcc873699.1506526584.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- tools/objtool/arch/x86/decode.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 0f22768c0d4d0..34a579f806e39 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -284,11 +284,16 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, case 0x8d: if (sib == 0x24 && rex_w && !rex_b && !rex_x) { - /* lea disp(%rsp), reg */ *type = INSN_STACK; - op->src.type = OP_SRC_ADD; + if (!insn.displacement.value) { + /* lea (%rsp), reg */ + op->src.type = OP_SRC_REG; + } else { + /* lea disp(%rsp), reg */ + op->src.type = OP_SRC_ADD; + op->src.offset = insn.displacement.value; + } op->src.reg = CFI_SP; - op->src.offset = insn.displacement.value; op->dest.type = OP_DEST_REG; op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r]; -- GitLab From 66a733ea6b611aecf0119514d2dddab5f9d6c01e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 27 Sep 2017 09:25:30 -0600 Subject: [PATCH 0562/1507] seccomp: fix the usage of get/put_seccomp_filter() in seccomp_get_filter() As Chris explains, get_seccomp_filter() and put_seccomp_filter() can end up using different filters. Once we drop ->siglock it is possible for task->seccomp.filter to have been replaced by SECCOMP_FILTER_FLAG_TSYNC. Fixes: f8e529ed941b ("seccomp, ptrace: add support for dumping seccomp filters") Reported-by: Chris Salls Cc: stable@vger.kernel.org # needs s/refcount_/atomic_/ for v4.12 and earlier Signed-off-by: Oleg Nesterov [tycho: add __get_seccomp_filter vs. open coding refcount_inc()] Signed-off-by: Tycho Andersen [kees: tweak commit log] Signed-off-by: Kees Cook --- kernel/seccomp.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index c24579dfa7a14..bb3a38005b9cc 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -473,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -491,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -503,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -1025,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: -- GitLab From dd269db84908d4d3f7c0efed85bf9d8939fb0b9b Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Wed, 27 Sep 2017 14:25:37 +0200 Subject: [PATCH 0563/1507] xfrm: don't call xfrm_policy_cache_flush under xfrm_state_lock I might be wrong but it doesn't look like xfrm_state_lock is required for xfrm_policy_cache_flush and calling it under this lock triggers both "sleeping function called from invalid context" and "possible circular locking dependency detected" warnings on flush. Fixes: ec30d78c14a8 xfrm: add xdst pcpu cache Signed-off-by: Artem Savkov Acked-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0dab1cd79ce4d..12213477cd3ad 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -732,12 +732,12 @@ int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) } } } +out: + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) { err = 0; xfrm_policy_cache_flush(); } -out: - spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_flush); -- GitLab From fe659bcc9b173bcfdd958ce2aec75e47651e74e1 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 26 Sep 2017 15:15:22 -0400 Subject: [PATCH 0564/1507] USB: dummy-hcd: fix connection failures (wrong speed) The dummy-hcd UDC driver is not careful about the way it handles connection speeds. It ignores the module parameter that is supposed to govern the maximum connection speed and it doesn't set the HCD flags properly for the case where it ends up running at full speed. The result is that in many cases, gadget enumeration over dummy-hcd fails because the bMaxPacketSize byte in the device descriptor is set incorrectly. For example, the default settings call for a high-speed connection, but the maxpacket value for ep0 ends up being set for a Super-Speed connection. This patch fixes the problem by initializing the gadget's max_speed and the HCD flags correctly. Signed-off-by: Alan Stern CC: Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/dummy_hcd.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index b1e21b3be6e11..d515ec31afe44 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -1036,7 +1036,12 @@ static int dummy_udc_probe(struct platform_device *pdev) memzero_explicit(&dum->gadget, sizeof(struct usb_gadget)); dum->gadget.name = gadget_name; dum->gadget.ops = &dummy_ops; - dum->gadget.max_speed = USB_SPEED_SUPER; + if (mod_data.is_super_speed) + dum->gadget.max_speed = USB_SPEED_SUPER; + else if (mod_data.is_high_speed) + dum->gadget.max_speed = USB_SPEED_HIGH; + else + dum->gadget.max_speed = USB_SPEED_FULL; dum->gadget.dev.parent = &pdev->dev; init_dummy_udc_hw(dum); @@ -2560,8 +2565,6 @@ static struct hc_driver dummy_hcd = { .product_desc = "Dummy host controller", .hcd_priv_size = sizeof(struct dummy_hcd), - .flags = HCD_USB3 | HCD_SHARED, - .reset = dummy_setup, .start = dummy_start, .stop = dummy_stop, @@ -2590,8 +2593,12 @@ static int dummy_hcd_probe(struct platform_device *pdev) dev_info(&pdev->dev, "%s, driver " DRIVER_VERSION "\n", driver_desc); dum = *((void **)dev_get_platdata(&pdev->dev)); - if (!mod_data.is_super_speed) + if (mod_data.is_super_speed) + dummy_hcd.flags = HCD_USB3 | HCD_SHARED; + else if (mod_data.is_high_speed) dummy_hcd.flags = HCD_USB2; + else + dummy_hcd.flags = HCD_USB11; hs_hcd = usb_create_hcd(&dummy_hcd, &pdev->dev, dev_name(&pdev->dev)); if (!hs_hcd) return -ENOMEM; -- GitLab From 0173a68bfb0ad1c72a6ee39cc485aa2c97540b98 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 26 Sep 2017 15:15:40 -0400 Subject: [PATCH 0565/1507] USB: dummy-hcd: fix infinite-loop resubmission bug The dummy-hcd HCD/UDC emulator tries not to do too much work during each timer interrupt. But it doesn't try very hard; currently all it does is limit the total amount of bulk data transferred. Other transfer types aren't limited, and URBs that transfer no data (because of an error, perhaps) don't count toward the limit, even though on a real USB bus they would consume at least a minimum overhead. This means it's possible to get the driver stuck in an infinite loop, for example, if the host class driver resubmits an URB every time it completes (which is common for interrupt URBs). Each time the URB is resubmitted it gets added to the end of the pending-URBs list, and dummy-hcd doesn't stop until that list is empty. Andrey Konovalov was able to trigger this failure mode using the syzkaller fuzzer. This patch fixes the infinite-loop problem by restricting the URBs handled during each timer interrupt to those that were already on the pending list when the interrupt routine started. Newly added URBs won't be processed until the next timer interrupt. The problem of properly accounting for non-bulk bandwidth (as well as packet and transaction overhead) is not addressed here. Signed-off-by: Alan Stern Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov CC: Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/dummy_hcd.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index d515ec31afe44..b2ab9cc33fec4 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -237,6 +237,8 @@ struct dummy_hcd { struct usb_device *udev; struct list_head urbp_list; + struct urbp *next_frame_urbp; + u32 stream_en_ep; u8 num_stream[30 / 2]; @@ -1250,6 +1252,8 @@ static int dummy_urb_enqueue( list_add_tail(&urbp->urbp_list, &dum_hcd->urbp_list); urb->hcpriv = urbp; + if (!dum_hcd->next_frame_urbp) + dum_hcd->next_frame_urbp = urbp; if (usb_pipetype(urb->pipe) == PIPE_CONTROL) urb->error_count = 1; /* mark as a new urb */ @@ -1766,6 +1770,7 @@ static void dummy_timer(unsigned long _dum_hcd) spin_unlock_irqrestore(&dum->lock, flags); return; } + dum_hcd->next_frame_urbp = NULL; for (i = 0; i < DUMMY_ENDPOINTS; i++) { if (!ep_info[i].name) @@ -1782,6 +1787,10 @@ static void dummy_timer(unsigned long _dum_hcd) int type; int status = -EINPROGRESS; + /* stop when we reach URBs queued after the timer interrupt */ + if (urbp == dum_hcd->next_frame_urbp) + break; + urb = urbp->urb; if (urb->unlinked) goto return_urb; -- GitLab From 7dbd8f4cabd96db5a50513de9d83a8105a5ffc81 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 26 Sep 2017 15:15:49 -0400 Subject: [PATCH 0566/1507] USB: dummy-hcd: Fix erroneous synchronization change A recent change to the synchronization in dummy-hcd was incorrect. The issue was that dummy_udc_stop() contained no locking and therefore could race with various gadget driver callbacks, and the fix was to add locking and issue the callbacks with the private spinlock held. UDC drivers aren't supposed to do this. Gadget driver callback routines are allowed to invoke functions in the UDC driver, and these functions will generally try to acquire the private spinlock. This would deadlock the driver. The correct solution is to drop the spinlock before issuing callbacks, and avoid races by emulating the synchronize_irq() call that all real UDC drivers must perform in their ->udc_stop() routines after disabling interrupts. This involves adding a flag to dummy-hcd's private structure to keep track of whether interrupts are supposed to be enabled, and adding a counter to keep track of ongoing callbacks so that dummy_udc_stop() can wait for them all to finish. A real UDC driver won't receive disconnect, reset, suspend, resume, or setup events once it has disabled interrupts. dummy-hcd will receive them but won't try to issue any gadget driver callbacks, which should be just as good. Signed-off-by: Alan Stern Fixes: f16443a034c7 ("USB: gadgetfs, dummy-hcd, net2280: fix locking for callbacks") CC: Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/dummy_hcd.c | 32 ++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index b2ab9cc33fec4..b17618a55f1b9 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -255,11 +255,13 @@ struct dummy { */ struct dummy_ep ep[DUMMY_ENDPOINTS]; int address; + int callback_usage; struct usb_gadget gadget; struct usb_gadget_driver *driver; struct dummy_request fifo_req; u8 fifo_buf[FIFO_SIZE]; u16 devstatus; + unsigned ints_enabled:1; unsigned udc_suspended:1; unsigned pullup:1; @@ -441,18 +443,27 @@ static void set_link_state(struct dummy_hcd *dum_hcd) (~dum_hcd->old_status) & dum_hcd->port_status; /* Report reset and disconnect events to the driver */ - if (dum->driver && (disconnect || reset)) { + if (dum->ints_enabled && (disconnect || reset)) { stop_activity(dum); + ++dum->callback_usage; + spin_unlock(&dum->lock); if (reset) usb_gadget_udc_reset(&dum->gadget, dum->driver); else dum->driver->disconnect(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } - } else if (dum_hcd->active != dum_hcd->old_active) { + } else if (dum_hcd->active != dum_hcd->old_active && + dum->ints_enabled) { + ++dum->callback_usage; + spin_unlock(&dum->lock); if (dum_hcd->old_active && dum->driver->suspend) dum->driver->suspend(&dum->gadget); else if (!dum_hcd->old_active && dum->driver->resume) dum->driver->resume(&dum->gadget); + spin_lock(&dum->lock); + --dum->callback_usage; } dum_hcd->old_status = dum_hcd->port_status; @@ -973,8 +984,11 @@ static int dummy_udc_start(struct usb_gadget *g, * can't enumerate without help from the driver we're binding. */ + spin_lock_irq(&dum->lock); dum->devstatus = 0; dum->driver = driver; + dum->ints_enabled = 1; + spin_unlock_irq(&dum->lock); return 0; } @@ -985,6 +999,16 @@ static int dummy_udc_stop(struct usb_gadget *g) struct dummy *dum = dum_hcd->dum; spin_lock_irq(&dum->lock); + dum->ints_enabled = 0; + stop_activity(dum); + + /* emulate synchronize_irq(): wait for callbacks to finish */ + while (dum->callback_usage > 0) { + spin_unlock_irq(&dum->lock); + usleep_range(1000, 2000); + spin_lock_irq(&dum->lock); + } + dum->driver = NULL; spin_unlock_irq(&dum->lock); @@ -1529,6 +1553,8 @@ static struct dummy_ep *find_endpoint(struct dummy *dum, u8 address) if (!is_active((dum->gadget.speed == USB_SPEED_SUPER ? dum->ss_hcd : dum->hs_hcd))) return NULL; + if (!dum->ints_enabled) + return NULL; if ((address & ~USB_DIR_IN) == 0) return &dum->ep[0]; for (i = 1; i < DUMMY_ENDPOINTS; i++) { @@ -1870,10 +1896,12 @@ static void dummy_timer(unsigned long _dum_hcd) * until setup() returns; no reentrancy issues etc. */ if (value > 0) { + ++dum->callback_usage; spin_unlock(&dum->lock); value = dum->driver->setup(&dum->gadget, &setup); spin_lock(&dum->lock); + --dum->callback_usage; if (value >= 0) { /* no delays (max 64KB data stage) */ -- GitLab From 4dcf4bab4a409e81284b8202137e4a85b96b34de Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Sep 2017 17:01:23 +0900 Subject: [PATCH 0567/1507] usb: gadget: udc: renesas_usb3: fix for no-data control transfer When bRequestType & USB_DIR_IN is false and req.length is 0 in control transfer, since it means non-data, this driver should not set the mode as control write. So, this patch fixes it. Fixes: 746bfe63bba3 ("usb: gadget: renesas_usb3: add support for Renesas USB3.0 peripheral controller") Cc: # v4.5+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/renesas_usb3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index df37c1e6e9d5c..555c105e82df2 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1150,7 +1150,8 @@ static void usb3_start_pipe0(struct renesas_usb3_ep *usb3_ep, usb3_set_p0_con_for_ctrl_read_data(usb3); } else { usb3_clear_bit(usb3, P0_MOD_DIR, USB3_P0_MOD); - usb3_set_p0_con_for_ctrl_write_data(usb3); + if (usb3_req->req.length) + usb3_set_p0_con_for_ctrl_write_data(usb3); } usb3_p0_xfer(usb3_ep, usb3_req); -- GitLab From 73f2f5745f18b4ccfe9484deac4e84a1378d19fd Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Sep 2017 17:01:24 +0900 Subject: [PATCH 0568/1507] usb: gadget: udc: renesas_usb3: fix Pn_RAMMAP.Pn_MPKT value According to the datasheet of R-Car Gen3, the Pn_RAMMAP.Pn_MPKT should be set to one of 8, 16, 32, 64, 512 and 1024. Otherwise, when a gadget driver uses an interrupt endpoint, unexpected behavior happens. So, this patch fixes it. Fixes: 746bfe63bba3 ("usb: gadget: renesas_usb3: add support for Renesas USB3.0 peripheral controller") Cc: # v4.5+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/renesas_usb3.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 555c105e82df2..7e0c53492356f 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2054,7 +2054,16 @@ static u32 usb3_calc_ramarea(int ram_size) static u32 usb3_calc_rammap_val(struct renesas_usb3_ep *usb3_ep, const struct usb_endpoint_descriptor *desc) { - return usb3_ep->rammap_val | PN_RAMMAP_MPKT(usb_endpoint_maxp(desc)); + int i; + const u32 max_packet_array[] = {8, 16, 32, 64, 512}; + u32 mpkt = PN_RAMMAP_MPKT(1024); + + for (i = 0; i < ARRAY_SIZE(max_packet_array); i++) { + if (usb_endpoint_maxp(desc) <= max_packet_array[i]) + mpkt = PN_RAMMAP_MPKT(max_packet_array[i]); + } + + return usb3_ep->rammap_val | mpkt; } static int usb3_enable_pipe_n(struct renesas_usb3_ep *usb3_ep, -- GitLab From 447b8a01b84f048d93d43bfe1fcaa4fcc56595cc Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Sep 2017 17:01:25 +0900 Subject: [PATCH 0569/1507] usb: gadget: udc: renesas_usb3: Fix return value of usb3_write_pipe() This patch fixes an issue that this driver cannot go status stage in control read when the req.zero is set to 1 and the len in usb3_write_pipe() is set to 0. Otherwise, if we use g_ncm driver, usb enumeration takes long time (5 seconds or more). Fixes: 746bfe63bba3 ("usb: gadget: renesas_usb3: add support for Renesas USB3.0 peripheral controller") Cc: # v4.5+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/renesas_usb3.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 7e0c53492356f..63a2061220589 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -1038,7 +1038,7 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_ep->ep.maxpacket); u8 *buf = usb3_req->req.buf + usb3_req->req.actual; u32 tmp = 0; - bool is_last; + bool is_last = !len ? true : false; if (usb3_wait_pipe_status(usb3_ep, PX_STA_BUFSTS) < 0) return -EBUSY; @@ -1059,7 +1059,8 @@ static int usb3_write_pipe(struct renesas_usb3_ep *usb3_ep, usb3_write(usb3, tmp, fifo_reg); } - is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); + if (!is_last) + is_last = usb3_is_transfer_complete(usb3_ep, usb3_req); /* Send the data */ usb3_set_px_con_send(usb3_ep, len, is_last); -- GitLab From 6124607acc88fffeaadf3aacfeb3cc1304c87387 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 27 Sep 2017 18:47:12 +0900 Subject: [PATCH 0570/1507] usb: renesas_usbhs: fix the BCLR setting condition for non-DCP pipe This patch fixes an issue that the driver sets the BCLR bit of {C,Dn}FIFOCTR register to 1 even when it's non-DCP pipe and the FRDY bit of {C,Dn}FIFOCTR register is set to 1. Fixes: e8d548d54968 ("usb: renesas_usbhs: fifo became independent from pipe.") Cc: # v3.1+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/renesas_usbhs/fifo.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index d1af831f43eba..03cac07f57b50 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -282,11 +282,17 @@ static void usbhsf_fifo_clear(struct usbhs_pipe *pipe, struct usbhs_fifo *fifo) { struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); + int ret = 0; if (!usbhs_pipe_is_dcp(pipe)) - usbhsf_fifo_barrier(priv, fifo); + ret = usbhsf_fifo_barrier(priv, fifo); - usbhs_write(priv, fifo->ctr, BCLR); + /* + * if non-DCP pipe, this driver should set BCLR when + * usbhsf_fifo_barrier() returns 0. + */ + if (!ret) + usbhs_write(priv, fifo->ctr, BCLR); } static int usbhsf_fifo_rcv_len(struct usbhs_priv *priv, -- GitLab From 0a2ce62b61f2c76d0213edf4e37aaf54a8ddf295 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 27 Sep 2017 18:47:13 +0900 Subject: [PATCH 0571/1507] usb: renesas_usbhs: fix usbhsf_fifo_clear() for RX direction This patch fixes an issue that the usbhsf_fifo_clear() is possible to cause 10 msec delay if the pipe is RX direction and empty because the FRDY bit will never be set to 1 in such case. Fixes: e8d548d54968 ("usb: renesas_usbhs: fifo became independent from pipe.") Cc: # v3.1+ Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/renesas_usbhs/fifo.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 03cac07f57b50..68f26904c316d 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -284,8 +284,17 @@ static void usbhsf_fifo_clear(struct usbhs_pipe *pipe, struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); int ret = 0; - if (!usbhs_pipe_is_dcp(pipe)) - ret = usbhsf_fifo_barrier(priv, fifo); + if (!usbhs_pipe_is_dcp(pipe)) { + /* + * This driver checks the pipe condition first to avoid -EBUSY + * from usbhsf_fifo_barrier() with about 10 msec delay in + * the interrupt handler if the pipe is RX direction and empty. + */ + if (usbhs_pipe_is_dir_in(pipe)) + ret = usbhs_pipe_is_accessible(pipe); + if (!ret) + ret = usbhsf_fifo_barrier(priv, fifo); + } /* * if non-DCP pipe, this driver should set BCLR when -- GitLab From addfc5823dbf3e6ed400e98e49c7e64b10e191d6 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 12 Sep 2017 10:24:40 +0100 Subject: [PATCH 0572/1507] usb: gadget: ffs: handle I/O completion in-order By submitting completed transfers to the system workqueue there is no guarantee that completion events will be queued up in the correct order, as in multi-processor systems there is a thread running for each processor and the work items are not bound to a particular core. This means that several completions are in the queue at the same time, they may be processed in parallel and complete out of order, resulting in data appearing corrupt when read by userspace. Create a single-threaded workqueue for FunctionFS so that data completed requests is passed to userspace in the order in which they complete. Acked-by: Michal Nazarewicz Signed-off-by: John Keeping Signed-off-by: Felipe Balbi --- drivers/usb/gadget/function/f_fs.c | 17 +++++++++++++---- drivers/usb/gadget/function/u_fs.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 9990944a72458..8b342587f8ad6 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -46,7 +46,8 @@ static void ffs_data_get(struct ffs_data *ffs); static void ffs_data_put(struct ffs_data *ffs); /* Creates new ffs_data object. */ -static struct ffs_data *__must_check ffs_data_new(void) __attribute__((malloc)); +static struct ffs_data *__must_check ffs_data_new(const char *dev_name) + __attribute__((malloc)); /* Opened counter handling. */ static void ffs_data_opened(struct ffs_data *ffs); @@ -780,11 +781,12 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct usb_request *req) { struct ffs_io_data *io_data = req->context; + struct ffs_data *ffs = io_data->ffs; ENTER(); INIT_WORK(&io_data->work, ffs_user_copy_worker); - schedule_work(&io_data->work); + queue_work(ffs->io_completion_wq, &io_data->work); } static void __ffs_epfile_read_buffer_free(struct ffs_epfile *epfile) @@ -1500,7 +1502,7 @@ ffs_fs_mount(struct file_system_type *t, int flags, if (unlikely(ret < 0)) return ERR_PTR(ret); - ffs = ffs_data_new(); + ffs = ffs_data_new(dev_name); if (unlikely(!ffs)) return ERR_PTR(-ENOMEM); ffs->file_perms = data.perms; @@ -1610,6 +1612,7 @@ static void ffs_data_put(struct ffs_data *ffs) BUG_ON(waitqueue_active(&ffs->ev.waitq) || waitqueue_active(&ffs->ep0req_completion.wait) || waitqueue_active(&ffs->wait)); + destroy_workqueue(ffs->io_completion_wq); kfree(ffs->dev_name); kfree(ffs); } @@ -1642,7 +1645,7 @@ static void ffs_data_closed(struct ffs_data *ffs) ffs_data_put(ffs); } -static struct ffs_data *ffs_data_new(void) +static struct ffs_data *ffs_data_new(const char *dev_name) { struct ffs_data *ffs = kzalloc(sizeof *ffs, GFP_KERNEL); if (unlikely(!ffs)) @@ -1650,6 +1653,12 @@ static struct ffs_data *ffs_data_new(void) ENTER(); + ffs->io_completion_wq = alloc_ordered_workqueue("%s", 0, dev_name); + if (!ffs->io_completion_wq) { + kfree(ffs); + return NULL; + } + refcount_set(&ffs->ref, 1); atomic_set(&ffs->opened, 0); ffs->state = FFS_READ_DESCRIPTORS; diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index 540f1c48c1a8d..79f70ebf85dc3 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -279,6 +279,7 @@ struct ffs_data { } file_perms; struct eventfd_ctx *ffs_eventfd; + struct workqueue_struct *io_completion_wq; bool no_disconnect; struct work_struct reset_work; -- GitLab From 6baeda120d90aa637b08f7604de104ab00ce9126 Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Thu, 31 Aug 2017 14:51:40 +0200 Subject: [PATCH 0573/1507] usb: gadget: udc: atmel: set vbus irqflags explicitly The driver triggers actions on both edges of the vbus signal. The former PIO controller was triggering IRQs on both falling and rising edges by default. Newer PIO controller don't, so it's better to set it explicitly to IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING. Without this patch we may trigger the connection with host but only on some bouncing signal conditions and thus lose connecting events. Acked-by: Ludovic Desroches Signed-off-by: Nicolas Ferre Cc: stable # v4.4+ Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/atmel_usba_udc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 98d71400f8a13..a884c022df7a5 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -29,6 +29,8 @@ #include #include "atmel_usba_udc.h" +#define USBA_VBUS_IRQFLAGS (IRQF_ONESHOT \ + | IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING) #ifdef CONFIG_USB_GADGET_DEBUG_FS #include @@ -2361,7 +2363,7 @@ static int usba_udc_probe(struct platform_device *pdev) IRQ_NOAUTOEN); ret = devm_request_threaded_irq(&pdev->dev, gpio_to_irq(udc->vbus_pin), NULL, - usba_vbus_irq_thread, IRQF_ONESHOT, + usba_vbus_irq_thread, USBA_VBUS_IRQFLAGS, "atmel_usba_udc", udc); if (ret) { udc->vbus_pin = -ENODEV; -- GitLab From c3cdce45f8d3dfa5c3467894aa89798314920328 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 30 Aug 2017 19:03:52 +0800 Subject: [PATCH 0574/1507] usb: dwc3: of-simple: Add compatible for Spreadtrum SC9860 platform Add compatible string to use this generic glue layer to support Spreadtrum SC9860 platform's dwc3 controller. Signed-off-by: Baolin Wang Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/dwc3-of-simple.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 4cef7d4f9cd06..a26d1fde0f5e4 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -177,6 +177,7 @@ static const struct of_device_id of_dwc3_simple_match[] = { { .compatible = "rockchip,rk3399-dwc3" }, { .compatible = "xlnx,zynqmp-dwc3" }, { .compatible = "cavium,octeon-7130-usb-uctl" }, + { .compatible = "sprd,sc9860-dwc3" }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_dwc3_simple_match); -- GitLab From 72364d320644c12948786962673772f271039a4a Mon Sep 17 00:00:00 2001 From: Jeffy Chen Date: Thu, 28 Sep 2017 12:37:31 +0800 Subject: [PATCH 0575/1507] irq/generic-chip: Don't replace domain's name When generic irq chips are allocated for an irq domain the domain name is set to the irq chip name. That was done to have named domains before the recent changes which enforce domain naming were done. Since then the overwrite causes a memory leak when the domain name is dynamically allocated and even worse it would cause the domain free code to free the wrong name pointer, which might point to a constant. Remove the name assignment to prevent this. Fixes: d59f6617eef0 ("genirq: Allow fwnode to carry name information only") Signed-off-by: Jeffy Chen Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20170928043731.4764-1-jeffy.chen@rock-chips.com --- kernel/irq/generic-chip.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b78ad6e1..5270a54b9fa4d 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); -- GitLab From 77c01d11bbb2b5c005347061bf543ab94878314c Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 26 Sep 2017 10:36:03 +0100 Subject: [PATCH 0576/1507] watchdog/hardlockup/perf: Fix spelling mistake: "permanetely" -> "permanently" Trivial fix to spelling mistake in pr_info message Signed-off-by: Colin Ian King Signed-off-by: Thomas Gleixner Acked-by: Don Zickus Cc: Andrew Morton Cc: Babu Moger Link: https://lkml.kernel.org/r/20170926093603.7756-1-colin.king@canonical.com --- kernel/watchdog_hld.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 204a8cadb7170..71a62ceacdc88 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -280,7 +280,7 @@ int __init hardlockup_detector_perf_init(void) int ret = hardlockup_detector_event_create(); if (ret) { - pr_info("Perf NMI watchdog permanetely disabled\n"); + pr_info("Perf NMI watchdog permanently disabled\n"); } else { perf_event_release_kernel(this_cpu_read(watchdog_ev)); this_cpu_write(watchdog_ev, NULL); -- GitLab From 8c28ef3f1c1c57b6f468343d5959e5125b30334d Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 25 Sep 2017 02:01:01 -0600 Subject: [PATCH 0577/1507] xen-pciback: relax BAR sizing write value check Just like done in d2bd05d88d ("xen-pciback: return proper values during BAR sizing") for the ROM BAR, ordinary ones also shouldn't compare the written value directly against ~0, but consider the r/o bits at the bottom (if any). Signed-off-by: Jan Beulich Reviewed-by: Juergen Gross Signed-off-by: Boris Ostrovsky --- drivers/xen/xen-pciback/conf_space_header.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 5fbfd9cfb6d63..5b3d57fc82d39 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -169,6 +169,9 @@ static int rom_write(struct pci_dev *dev, int offset, u32 value, void *data) static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) { struct pci_bar_info *bar = data; + unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4; + const struct resource *res = dev->resource; + u32 mask; if (unlikely(!bar)) { pr_warn(DRV_NAME ": driver data not found for %s\n", @@ -179,7 +182,13 @@ static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data) /* A write to obtain the length must happen as a 32-bit write. * This does not (yet) support writing individual bytes */ - if (value == ~0) + if (res[pos].flags & IORESOURCE_IO) + mask = ~PCI_BASE_ADDRESS_IO_MASK; + else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64)) + mask = 0; + else + mask = ~PCI_BASE_ADDRESS_MEM_MASK; + if ((value | mask) == ~0U) bar->which = 1; else { u32 tmpval; -- GitLab From 0d805ee70a69eabd38160dc199e183ac2f13fe4b Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Wed, 27 Sep 2017 02:41:25 -0700 Subject: [PATCH 0578/1507] xen/mmu: Call xen_cleanhighmap() with 4MB aligned for page tables mapping When bootup a PVM guest with large memory(Ex.240GB), XEN provided initial mapping overlaps with kernel module virtual space. When mapping in this space is cleared by xen_cleanhighmap(), in certain case there could be an 2MB mapping left. This is due to XEN initialize 4MB aligned mapping but xen_cleanhighmap() finish at 2MB boundary. When module loading is just on top of the 2MB space, got below warning: WARNING: at mm/vmalloc.c:106 vmap_pte_range+0x14e/0x190() Call Trace: [] warn_alloc_failed+0xf3/0x160 [] __vmalloc_area_node+0x182/0x1c0 [] ? module_alloc_update_bounds+0x1e/0x80 [] __vmalloc_node_range+0xa7/0x110 [] ? module_alloc_update_bounds+0x1e/0x80 [] module_alloc+0x64/0x70 [] ? module_alloc_update_bounds+0x1e/0x80 [] module_alloc_update_bounds+0x1e/0x80 [] move_module+0x27/0x150 [] layout_and_allocate+0x120/0x1b0 [] load_module+0x78/0x640 [] ? security_file_permission+0x8b/0x90 [] sys_init_module+0x62/0x1e0 [] system_call_fastpath+0x16/0x1b Then the mapping of 2MB is cleared, finally oops when the page in that space is accessed. BUG: unable to handle kernel paging request at ffff880022600000 IP: [] clear_page_c_e+0x7/0x10 PGD 1788067 PUD 178c067 PMD 22434067 PTE 0 Oops: 0002 [#1] SMP Call Trace: [] ? prep_new_page+0x127/0x1c0 [] get_page_from_freelist+0x1e2/0x550 [] ? ii_iovec_copy_to_user+0x90/0x140 [] __alloc_pages_nodemask+0x12d/0x230 [] alloc_pages_vma+0xc6/0x1a0 [] ? pte_mfn_to_pfn+0x7d/0x100 [] do_anonymous_page+0x16b/0x350 [] handle_pte_fault+0x1e4/0x200 [] ? xen_pmd_val+0xe/0x10 [] ? __raw_callee_save_xen_pmd_val+0x11/0x1e [] handle_mm_fault+0x15b/0x270 [] do_page_fault+0x140/0x470 [] page_fault+0x25/0x30 Call xen_cleanhighmap() with 4MB aligned for page tables mapping to fix it. The unnecessory call of xen_cleanhighmap() in DEBUG mode is also removed. -v2: add comment about XEN alignment from Juergen. References: https://lists.xen.org/archives/html/xen-devel/2012-07/msg01562.html Signed-off-by: Zhenzhong Duan Reviewed-by: Juergen Gross [boris: added 'xen/mmu' tag to commit subject] Signed-off-by: Boris Ostrovsky --- arch/x86/xen/mmu_pv.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 509f560bd0c6d..58b09fcadbaa9 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1238,21 +1238,16 @@ static void __init xen_pagetable_cleanhighmap(void) * from _brk_limit way up to the max_pfn_mapped (which is the end of * the ramdisk). We continue on, erasing PMD entries that point to page * tables - do note that they are accessible at this stage via __va. - * For good measure we also round up to the PMD - which means that if + * As Xen is aligning the memory end to a 4MB boundary, for good + * measure we also round up to PMD_SIZE * 2 - which means that if * anybody is using __ka address to the initial boot-stack - and try * to use it - they are going to crash. The xen_start_info has been * taken care of already in xen_setup_kernel_pagetable. */ addr = xen_start_info->pt_base; - size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + size = xen_start_info->nr_pt_frames * PAGE_SIZE; - xen_cleanhighmap(addr, addr + size); + xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); -#ifdef DEBUG - /* This is superfluous and is not necessary, but you know what - * lets do it. The MODULES_VADDR -> MODULES_END should be clear of - * anything at this stage. */ - xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); -#endif } #endif -- GitLab From 686fef928bba6be13cabe639f154af7d72b63120 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 28 Sep 2017 06:38:17 -0700 Subject: [PATCH 0579/1507] timer: Prepare to change timer callback argument type Modern kernel callback systems pass the structure associated with a given callback to the callback function. The timer callback remains one of the legacy cases where an arbitrary unsigned long argument continues to be passed as the callback argument. This has several problems: - This bloats the timer_list structure with a normally redundant .data field. - No type checking is being performed, forcing callbacks to do explicit type casts of the unsigned long argument into the object that was passed, rather than using container_of(), as done in most of the other callback infrastructure. - Neighboring buffer overflows can overwrite both the .function and the .data field, providing attackers with a way to elevate from a buffer overflow into a simplistic ROP-like mechanism that allows calling arbitrary functions with a controlled first argument. - For future Control Flow Integrity work, this creates a unique function prototype for timer callbacks, instead of allowing them to continue to be clustered with other void functions that take a single unsigned long argument. This adds a new timer initialization API, which will ultimately replace the existing setup_timer(), setup_{deferrable,pinned,etc}_timer() family, named timer_setup() (to mirror hrtimer_setup(), making instances of its use much easier to grep for). In order to support the migration of existing timers into the new callback arguments, timer_setup() casts its arguments to the existing legacy types, and explicitly passes the timer pointer as the legacy data argument. Once all setup_*timer() callers have been replaced with timer_setup(), the casts can be removed, and the data argument can be dropped with the timer expiration code changed to just pass the timer to the callback directly. Since the regular pattern of using container_of() during local variable declaration repeats the need for the variable type declaration to be included, this adds a helper modeled after other from_*() helpers that wrap container_of(), named from_timer(). This helper uses typeof(*variable), removing the type redundancy and minimizing the need for line wraps in forthcoming conversions from "unsigned data long" to "struct timer_list *" in the timer callbacks: -void callback(unsigned long data) +void callback(struct timer_list *t) { - struct some_data_structure *local = (struct some_data_structure *)data; + struct some_data_structure *local = from_timer(local, t, timer); Finally, in order to support the handful of timer users that perform open-coded assignments of the .function (and .data) fields, provide cast macros (TIMER_FUNC_TYPE and TIMER_DATA_TYPE) that can be used temporarily. Once conversion has been completed, these can be globally trivially removed. Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20170928133817.GA113410@beast --- include/linux/timer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/timer.h b/include/linux/timer.h index e6789b8757d50..6383c528b1484 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -168,6 +168,20 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) +#define TIMER_DATA_TYPE unsigned long +#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE) + +static inline void timer_setup(struct timer_list *timer, + void (*callback)(struct timer_list *), + unsigned int flags) +{ + __setup_timer(timer, (TIMER_FUNC_TYPE)callback, + (TIMER_DATA_TYPE)timer, flags); +} + +#define from_timer(var, callback_timer, timer_fieldname) \ + container_of(callback_timer, typeof(*var), timer_fieldname) + /** * timer_pending - is a timer pending? * @timer: the timer in question -- GitLab From 1fa4df3e688902d033dfda796eb83ae6ad8d0488 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Wed, 27 Sep 2017 16:35:00 -0500 Subject: [PATCH 0580/1507] percpu: fix iteration to prevent skipping over block The iterator functions pcpu_next_md_free_region and pcpu_next_fit_region use the block offset to determine if they have checked the area in the prior iteration. However, this causes an issue when the block offset is greater than subsequent block contig hints. If within the iterator it moves to check subsequent blocks, it may fail in the second predicate due to the block offset not being cleared. Thus, this causes the allocator to skip over blocks leading to false failures when allocating from the reserved chunk. While this happens in the general case as well, it will only fail if it cannot allocate a new chunk. This patch resets the block offset to 0 to pass the second predicate when checking subseqent blocks within the iterator function. Signed-off-by: Dennis Zhou Reported-and-tested-by: Luis Henriques Signed-off-by: Tejun Heo --- mm/percpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/percpu.c b/mm/percpu.c index 59d44d61f5f19..aa121cef76de3 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -353,6 +353,8 @@ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, block->contig_hint_start); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; @@ -407,6 +409,8 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, *bit_off = pcpu_block_off_to_off(i, block->first_free); return; } + /* reset to satisfy the second predicate above */ + block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); -- GitLab From 7e7c1afb67074596f6ff96e5276d6084d1648ec1 Mon Sep 17 00:00:00 2001 From: Simon Wunderlich Date: Thu, 28 Sep 2017 13:44:39 +0200 Subject: [PATCH 0581/1507] batman-adv: Start new development cycle Signed-off-by: Simon Wunderlich --- net/batman-adv/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 05cc7637c0642..edb2f239d04d7 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2017.3" +#define BATADV_SOURCE_VERSION "2017.4" #endif /* B.A.T.M.A.N. parameters */ -- GitLab From 825ffe1f7b875127bc03faffec0ecfb05906650a Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Wed, 23 Aug 2017 21:52:13 +0200 Subject: [PATCH 0582/1507] batman-adv: Remove unnecessary parentheses checkpatch introduced with commit 63b7c73ec86b ("checkpatch: add --strict check for ifs with unnecessary parentheses") an additional test which identifies some unnecessary parentheses. Remove these unnecessary parentheses to avoid the warnings and to unify the coding style slightly more. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/bat_iv_ogm.c | 24 ++++++++++++------------ net/batman-adv/bat_v.c | 2 +- net/batman-adv/bat_v_elp.c | 6 +++--- net/batman-adv/bat_v_ogm.c | 12 ++++++------ net/batman-adv/distributed-arp-table.c | 4 ++-- net/batman-adv/gateway_client.c | 8 ++++---- net/batman-adv/gateway_common.c | 18 +++++++++--------- net/batman-adv/hard-interface.c | 12 ++++++------ net/batman-adv/icmp_socket.c | 4 ++-- net/batman-adv/main.c | 4 ++-- net/batman-adv/multicast.c | 2 +- net/batman-adv/originator.c | 26 +++++++++++++------------- net/batman-adv/routing.c | 6 +++--- net/batman-adv/send.c | 6 +++--- net/batman-adv/soft-interface.c | 2 +- net/batman-adv/sysfs.c | 4 ++-- net/batman-adv/tp_meter.c | 2 +- 17 files changed, 71 insertions(+), 71 deletions(-) diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 83ba5483455a3..1b659ab652fb0 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -916,8 +916,8 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; - if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) || - (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)) + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) return; /* the interface gets activated here to avoid race conditions between @@ -1264,7 +1264,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, * drops as they can't send and receive at the same time. */ tq_iface_penalty = BATADV_TQ_MAX_VALUE; - if (if_outgoing && (if_incoming == if_outgoing) && + if (if_outgoing && if_incoming == if_outgoing && batadv_is_wifi_hardif(if_outgoing)) tq_iface_penalty = batadv_hop_penalty(BATADV_TQ_MAX_VALUE, bat_priv); @@ -1369,7 +1369,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, ret = BATADV_NEIGH_DUP; } else { set_mark = 0; - if (is_dup && (ret != BATADV_NEIGH_DUP)) + if (is_dup && ret != BATADV_NEIGH_DUP) ret = BATADV_ORIG_DUP; } @@ -1515,7 +1515,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, /* drop packet if sender is not a direct neighbor and if we * don't route towards it */ - if (!is_single_hop_neigh && (!orig_neigh_router)) { + if (!is_single_hop_neigh && !orig_neigh_router) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM via unknown neighbor!\n"); goto out_neigh; @@ -1535,7 +1535,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, sameseq = orig_ifinfo->last_real_seqno == ntohl(ogm_packet->seqno); similar_ttl = (orig_ifinfo->last_ttl - 3) <= ogm_packet->ttl; - if (is_bidirect && ((dup_status == BATADV_NO_DUP) || + if (is_bidirect && (dup_status == BATADV_NO_DUP || (sameseq && similar_ttl))) { batadv_iv_ogm_orig_update(bat_priv, orig_node, orig_ifinfo, ethhdr, @@ -1553,8 +1553,8 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, /* OGMs from secondary interfaces should only scheduled once * per interface where it has been received, not multiple times */ - if ((ogm_packet->ttl <= 2) && - (if_incoming != if_outgoing)) { + if (ogm_packet->ttl <= 2 && + if_incoming != if_outgoing) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM from secondary interface and wrong outgoing interface\n"); goto out_neigh; @@ -1590,7 +1590,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset, if_incoming, if_outgoing); out_neigh: - if ((orig_neigh_node) && (!is_single_hop_neigh)) + if (orig_neigh_node && !is_single_hop_neigh) batadv_orig_node_put(orig_neigh_node); out: if (router_ifinfo) @@ -2523,9 +2523,9 @@ batadv_iv_gw_get_best_gw_node(struct batadv_priv *bat_priv) tmp_gw_factor *= 100 * 100; tmp_gw_factor >>= 18; - if ((tmp_gw_factor > max_gw_factor) || - ((tmp_gw_factor == max_gw_factor) && - (tq_avg > max_tq))) { + if (tmp_gw_factor > max_gw_factor || + (tmp_gw_factor == max_gw_factor && + tq_avg > max_tq)) { if (curr_gw) batadv_gw_node_put(curr_gw); curr_gw = gw_node; diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 4e2724c5b33d8..93ef1c06227e6 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -767,7 +767,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv) if (batadv_v_gw_throughput_get(gw_node, &bw) < 0) goto next; - if (curr_gw && (bw <= max_bw)) + if (curr_gw && bw <= max_bw) goto next; if (curr_gw) diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index bd1064d98e16a..1de992c58b351 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -134,7 +134,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX; throughput = link_settings.base.speed; - if (throughput && (throughput != SPEED_UNKNOWN)) + if (throughput && throughput != SPEED_UNKNOWN) return throughput * 10; } @@ -263,8 +263,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) goto out; /* we are in the process of shutting this interface down */ - if ((hard_iface->if_status == BATADV_IF_NOT_IN_USE) || - (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)) + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) goto out; /* the interface was enabled but may not be ready yet */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 8be61734fc43c..c251445a42a07 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -304,8 +304,8 @@ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv, * due to the store & forward characteristics of WIFI. * Very low throughput values are the exception. */ - if ((throughput > 10) && - (if_incoming == if_outgoing) && + if (throughput > 10 && + if_incoming == if_outgoing && !(if_incoming->bat_v.flags & BATADV_FULL_DUPLEX)) return throughput / 2; @@ -455,7 +455,7 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv, /* drop packets with old seqnos, however accept the first packet after * a host has been rebooted. */ - if ((seq_diff < 0) && !protection_started) + if (seq_diff < 0 && !protection_started) goto out; neigh_node->last_seen = jiffies; @@ -568,8 +568,8 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv, router_throughput = router_ifinfo->bat_v.throughput; neigh_throughput = neigh_ifinfo->bat_v.throughput; - if ((neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF) && - (router_throughput >= neigh_throughput)) + if (neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF && + router_throughput >= neigh_throughput) goto out; } @@ -621,7 +621,7 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, return; /* only unknown & newer OGMs contain TVLVs we are interested in */ - if ((seqno_age > 0) && (if_outgoing == BATADV_IF_DEFAULT)) + if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT) batadv_tvlv_containers_process(bat_priv, true, orig_node, NULL, NULL, (unsigned char *)(ogm2 + 1), diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b6cfa78e9381f..760c0de725826 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -492,8 +492,8 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, /* this is an hash collision with the temporary selected node. Choose * the one with the lowest address */ - if ((tmp_max == max) && max_orig_node && - (batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0)) + if (tmp_max == max && max_orig_node && + batadv_compare_eth(candidate->orig, max_orig_node->orig) > 0) goto out; ret = true; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index de9955d5224d2..10d521f0b17f6 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -248,12 +248,12 @@ void batadv_gw_election(struct batadv_priv *bat_priv) } } - if ((curr_gw) && (!next_gw)) { + if (curr_gw && !next_gw) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Removing selected gateway - no gateway in range\n"); batadv_throw_uevent(bat_priv, BATADV_UEV_GW, BATADV_UEV_DEL, NULL); - } else if ((!curr_gw) && (next_gw)) { + } else if (!curr_gw && next_gw) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Adding route to gateway %pM (bandwidth: %u.%u/%u.%u MBit, tq: %i)\n", next_gw->orig_node->orig, @@ -411,8 +411,8 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, goto out; } - if ((gw_node->bandwidth_down == ntohl(gateway->bandwidth_down)) && - (gw_node->bandwidth_up == ntohl(gateway->bandwidth_up))) + if (gw_node->bandwidth_down == ntohl(gateway->bandwidth_down) && + gw_node->bandwidth_up == ntohl(gateway->bandwidth_up)) goto out; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 33940c5c74a87..2c26039c23fcd 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -56,8 +56,8 @@ bool batadv_parse_throughput(struct net_device *net_dev, char *buff, if (strncasecmp(tmp_ptr, "mbit", 4) == 0) bw_unit_type = BATADV_BW_UNIT_MBIT; - if ((strncasecmp(tmp_ptr, "kbit", 4) == 0) || - (bw_unit_type == BATADV_BW_UNIT_MBIT)) + if (strncasecmp(tmp_ptr, "kbit", 4) == 0 || + bw_unit_type == BATADV_BW_UNIT_MBIT) *tmp_ptr = '\0'; } @@ -190,7 +190,7 @@ ssize_t batadv_gw_bandwidth_set(struct net_device *net_dev, char *buff, if (!up_new) up_new = 1; - if ((down_curr == down_new) && (up_curr == up_new)) + if (down_curr == down_new && up_curr == up_new) return count; batadv_gw_reselect(bat_priv); @@ -224,16 +224,16 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, /* only fetch the tvlv value if the handler wasn't called via the * CIFNOTFND flag and if there is data to fetch */ - if ((flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) || - (tvlv_value_len < sizeof(gateway))) { + if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND || + tvlv_value_len < sizeof(gateway)) { gateway.bandwidth_down = 0; gateway.bandwidth_up = 0; } else { gateway_ptr = tvlv_value; gateway.bandwidth_down = gateway_ptr->bandwidth_down; gateway.bandwidth_up = gateway_ptr->bandwidth_up; - if ((gateway.bandwidth_down == 0) || - (gateway.bandwidth_up == 0)) { + if (gateway.bandwidth_down == 0 || + gateway.bandwidth_up == 0) { gateway.bandwidth_down = 0; gateway.bandwidth_up = 0; } @@ -242,8 +242,8 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, batadv_gw_node_update(bat_priv, orig, &gateway); /* restart gateway selection */ - if ((gateway.bandwidth_down != 0) && - (atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT)) + if (gateway.bandwidth_down != 0 && + atomic_read(&bat_priv->gw.mode) == BATADV_GW_MODE_CLIENT) batadv_gw_check_election(bat_priv, orig); } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e348f76ea8c15..d4aa99c060f91 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -504,8 +504,8 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev) rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->net_dev == net_dev) @@ -568,8 +568,8 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->soft_iface != soft_iface) @@ -654,8 +654,8 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) static void batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) { - if ((hard_iface->if_status != BATADV_IF_ACTIVE) && - (hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)) + if (hard_iface->if_status != BATADV_IF_ACTIVE && + hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) return; hard_iface->if_status = BATADV_IF_INACTIVE; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 8ead292886d1f..bded31121d122 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -132,10 +132,10 @@ static ssize_t batadv_socket_read(struct file *file, char __user *buf, size_t packet_len; int error; - if ((file->f_flags & O_NONBLOCK) && (socket_client->queue_len == 0)) + if ((file->f_flags & O_NONBLOCK) && socket_client->queue_len == 0) return -EAGAIN; - if ((!buf) || (count < sizeof(struct batadv_icmp_packet))) + if (!buf || count < sizeof(struct batadv_icmp_packet)) return -EINVAL; if (!access_ok(VERIFY_WRITE, buf, count)) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index fb381fb26a661..033819aefc390 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -544,8 +544,8 @@ batadv_recv_handler_register(u8 packet_type, struct batadv_hard_iface *); curr = batadv_rx_handler[packet_type]; - if ((curr != batadv_recv_unhandled_packet) && - (curr != batadv_recv_unhandled_unicast_packet)) + if (curr != batadv_recv_unhandled_packet && + curr != batadv_recv_unhandled_unicast_packet) return -EBUSY; batadv_rx_handler[packet_type] = recv_handler; diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index d327670641ac3..e553a8770a89a 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1126,7 +1126,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, bool orig_initialized; if (orig_mcast_enabled && tvlv_value && - (tvlv_value_len >= sizeof(mcast_flags))) + tvlv_value_len >= sizeof(mcast_flags)) mcast_flags = *(u8 *)tvlv_value; spin_lock_bh(&orig->mcast_handler_lock); diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8e2a4b2052579..2967b86c13da1 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1062,9 +1062,9 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, continue; /* don't purge if the interface is not (going) down */ - if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && - (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && - (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + if (if_outgoing->if_status != BATADV_IF_INACTIVE && + if_outgoing->if_status != BATADV_IF_NOT_IN_USE && + if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -1106,9 +1106,9 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, continue; /* don't purge if the interface is not (going) down */ - if ((if_outgoing->if_status != BATADV_IF_INACTIVE) && - (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) && - (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED)) + if (if_outgoing->if_status != BATADV_IF_INACTIVE && + if_outgoing->if_status != BATADV_IF_NOT_IN_USE && + if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -1155,13 +1155,13 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; - if ((batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT)) || - (if_incoming->if_status == BATADV_IF_INACTIVE) || - (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || - (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) { - if ((if_incoming->if_status == BATADV_IF_INACTIVE) || - (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || - (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) + if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) || + if_incoming->if_status == BATADV_IF_INACTIVE || + if_incoming->if_status == BATADV_IF_NOT_IN_USE || + if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) { + if (if_incoming->if_status == BATADV_IF_INACTIVE || + if_incoming->if_status == BATADV_IF_NOT_IN_USE || + if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", orig_node->orig, neigh_node->addr, diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f10e3ff26f9dc..40d9bf3e5bfe2 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -93,14 +93,14 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, batadv_orig_ifinfo_put(orig_ifinfo); /* route deleted */ - if ((curr_router) && (!neigh_node)) { + if (curr_router && !neigh_node) { batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", orig_node->orig); batadv_tt_global_del_orig(bat_priv, orig_node, -1, "Deleted route towards originator"); /* route added */ - } else if ((!curr_router) && (neigh_node)) { + } else if (!curr_router && neigh_node) { batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); @@ -381,7 +381,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, /* add record route information if not full */ if ((icmph->msg_type == BATADV_ECHO_REPLY || icmph->msg_type == BATADV_ECHO_REQUEST) && - (skb->len >= sizeof(struct batadv_icmp_packet_rr))) { + skb->len >= sizeof(struct batadv_icmp_packet_rr)) { if (skb_linearize(skb) < 0) goto free_skb; diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 054a65e6eb68b..7895323fd2a79 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -142,7 +142,7 @@ int batadv_send_unicast_skb(struct sk_buff *skb, #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); - if ((hardif_neigh) && (ret != NET_XMIT_DROP)) + if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; if (hardif_neigh) @@ -615,8 +615,8 @@ batadv_forw_packet_list_steal(struct hlist_head *forw_list, * we delete only packets belonging to the given interface */ if (hard_iface && - (forw_packet->if_incoming != hard_iface) && - (forw_packet->if_outgoing != hard_iface)) + forw_packet->if_incoming != hard_iface && + forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c2c986746d0b6..7c8288245f808 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -160,7 +160,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { /* check ranges */ - if ((new_mtu < 68) || (new_mtu > batadv_hardif_min_mtu(dev))) + if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 0ae8b30e4eaaf..aa187fd424754 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -925,8 +925,8 @@ static int batadv_store_mesh_iface_finish(struct net_device *net_dev, if (hard_iface->if_status == status_tmp) goto out; - if ((hard_iface->soft_iface) && - (strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)) + if (hard_iface->soft_iface && + strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0) goto out; if (status_tmp == BATADV_IF_NOT_IN_USE) { diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index bfe8effe9238a..4b90033f35a85 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1206,7 +1206,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst, /* send the ack */ r = batadv_send_skb_to_orig(skb, orig_node, NULL); - if (unlikely(r < 0) || (r == NET_XMIT_DROP)) { + if (unlikely(r < 0) || r == NET_XMIT_DROP) { ret = BATADV_TP_REASON_DST_UNREACHABLE; goto out; } -- GitLab From 48915aed60c9615e5eaa0f1683640635dade788e Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Thu, 28 Sep 2017 17:16:51 +0200 Subject: [PATCH 0583/1507] batman-adv: Fix "line over 80 characters" checkpatch warning Fixes: 242c1a28eb61 ("net: Remove useless function skb_header_release") Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/soft-interface.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 7c8288245f808..3af4b0b29b230 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -69,8 +69,8 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len) int result; /* TODO: We must check if we can release all references to non-payload - * data using __skb_header_release in our skbs to allow skb_cow_header to - * work optimally. This means that those skbs are not allowed to read + * data using __skb_header_release in our skbs to allow skb_cow_header + * to work optimally. This means that those skbs are not allowed to read * or write any data which is before the current position of skb->data * after that call and thus allow other skbs with the same data buffer * to write freely in that area. -- GitLab From 2580c4c17aee3ad58e9751012bad278dd074ccae Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 28 Sep 2017 11:32:37 +0200 Subject: [PATCH 0584/1507] tun: bail out from tun_get_user() if the skb is empty KMSAN (https://github.com/google/kmsan) reported accessing uninitialized skb->data[0] in the case the skb is empty (i.e. skb->len is 0): ================================================ BUG: KMSAN: use of uninitialized memory in tun_get_user+0x19ba/0x3770 CPU: 0 PID: 3051 Comm: probe Not tainted 4.13.0+ #3140 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: ... __msan_warning_32+0x66/0xb0 mm/kmsan/kmsan_instr.c:477 tun_get_user+0x19ba/0x3770 drivers/net/tun.c:1301 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365 call_write_iter ./include/linux/fs.h:1743 new_sync_write fs/read_write.c:457 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470 vfs_write+0x3e4/0x770 fs/read_write.c:518 SYSC_write+0x12f/0x2b0 fs/read_write.c:565 SyS_write+0x55/0x80 fs/read_write.c:557 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:245 ... origin: ... kmsan_poison_shadow+0x6e/0xc0 mm/kmsan/kmsan.c:211 slab_alloc_node mm/slub.c:2732 __kmalloc_node_track_caller+0x351/0x370 mm/slub.c:4351 __kmalloc_reserve net/core/skbuff.c:138 __alloc_skb+0x26a/0x810 net/core/skbuff.c:231 alloc_skb ./include/linux/skbuff.h:903 alloc_skb_with_frags+0x1d7/0xc80 net/core/skbuff.c:4756 sock_alloc_send_pskb+0xabf/0xfe0 net/core/sock.c:2037 tun_alloc_skb drivers/net/tun.c:1144 tun_get_user+0x9a8/0x3770 drivers/net/tun.c:1274 tun_chr_write_iter+0x19f/0x300 drivers/net/tun.c:1365 call_write_iter ./include/linux/fs.h:1743 new_sync_write fs/read_write.c:457 __vfs_write+0x6c3/0x7f0 fs/read_write.c:470 vfs_write+0x3e4/0x770 fs/read_write.c:518 SYSC_write+0x12f/0x2b0 fs/read_write.c:565 SyS_write+0x55/0x80 fs/read_write.c:557 do_syscall_64+0x242/0x330 arch/x86/entry/common.c:284 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:245 ================================================ Make sure tun_get_user() doesn't touch skb->data[0] unless there is actual data. C reproducer below: ========================== // autogenerated by syzkaller (http://github.com/google/syzkaller) #define _GNU_SOURCE #include #include #include #include #include #include int main() { int sock = socket(PF_INET, SOCK_STREAM, IPPROTO_IP); int tun_fd = open("/dev/net/tun", O_RDWR); struct ifreq req; memset(&req, 0, sizeof(struct ifreq)); strcpy((char*)&req.ifr_name, "gre0"); req.ifr_flags = IFF_UP | IFF_MULTICAST; ioctl(tun_fd, TUNSETIFF, &req); ioctl(sock, SIOCSIFFLAGS, "gre0"); write(tun_fd, "hi", 0); return 0; } ========================== Signed-off-by: Alexander Potapenko Signed-off-by: David S. Miller --- drivers/net/tun.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3c9985f299503..5ce580f413b93 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1496,11 +1496,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, switch (tun->flags & TUN_TYPE_MASK) { case IFF_TUN: if (tun->flags & IFF_NO_PI) { - switch (skb->data[0] & 0xf0) { - case 0x40: + u8 ip_version = skb->len ? (skb->data[0] >> 4) : 0; + + switch (ip_version) { + case 4: pi.proto = htons(ETH_P_IP); break; - case 0x60: + case 6: pi.proto = htons(ETH_P_IPV6); break; default: -- GitLab From c0a1666bcb2a33e84187a15eabdcd54056be9a97 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 28 Sep 2017 17:58:41 +0200 Subject: [PATCH 0585/1507] KVM: VMX: use cmpxchg64 This fixes a compilation failure on 32-bit systems. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b9d2140eb2128..7f62c94196d1b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2238,8 +2238,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.ndst = (dest << 8) & 0xFF00; new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -11730,8 +11730,8 @@ static void __pi_post_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'notification vector' */ new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); @@ -11800,8 +11800,8 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); /* We should not block the vCPU if an interrupt is posted for it. */ if (pi_test_on(pi_desc) == 1) -- GitLab From b28503a3fe6400757817e4460090f96bc1b9d6e7 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:03 +0200 Subject: [PATCH 0586/1507] perf test: Fix vmlinux failure on s390x On s390x perf test 1 failed. It turned out that commit 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit 4a084ecfc821. Signed-off-by: Thomas-Mich Richter Cc: Hendrik Brueckner Cc: Zvonko Kosic Fixes: 4a084ecfc821 ("perf report: Fix module symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-1-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-5ani7ly57zji7s0hmzkx416l@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/sym-handling.c | 8 -------- tools/perf/util/symbol-elf.c | 8 +------- tools/perf/util/symbol.h | 3 --- 3 files changed, 1 insertion(+), 18 deletions(-) diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c index e103f6e46afe2..581d4c5a896b8 100644 --- a/tools/perf/arch/s390/util/sym-handling.c +++ b/tools/perf/arch/s390/util/sym-handling.c @@ -18,12 +18,4 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) return false; return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; } - -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map) -{ - if (map->type == MAP__FUNCTION) - sym->st_value += map->start; -} #endif diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 5c39f420111e5..9cf781f0d8a2d 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap) void __weak arch__sym_update(struct symbol *s __maybe_unused, GElf_Sym *sym __maybe_unused) { } -void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr, - struct map *map __maybe_unused) -{ - sym->st_value -= shdr->sh_addr - shdr->sh_offset; -} - int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, struct symsrc *runtime_ss, int kmodule) { @@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, /* Adjust symbol to map to file offset */ if (adjust_kernel_syms) - arch__adjust_sym_map_offset(&sym, &shdr, map); + sym.st_value -= shdr.sh_addr - shdr.sh_offset; if (strcmp(section_name, (curr_dso->short_name + diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2bd6a1f01a1cc..aad99e7e179bb 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str, #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr); void arch__sym_update(struct symbol *s, GElf_Sym *sym); -void arch__adjust_sym_map_offset(GElf_Sym *sym, - GElf_Shdr *shdr __maybe_unused, - struct map *map __maybe_unused); #endif #define SYMBOL_A 0 -- GitLab From 5357413f5c067f60933e4b8d79d483fbe62b2bb5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 15 Sep 2017 09:14:04 +0200 Subject: [PATCH 0587/1507] perf test: Fix vmlinux failure on s390x part 2 On s390x perf test 1 failed. It turned out that commit cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") was incorrect. The previous implementation in dso__load_sym() is also suitable for s390x. Therefore this patch undoes commit cf6383f73cf2 Signed-off-by: Thomas-Mich Richter Cc: Zvonko Kosic Cc: Hendrik Brueckner Fixes: cf6383f73cf2 ("perf report: Fix kernel symbol adjustment for s390x") LPU-Reference: 20170915071404.58398-2-tmricht@linux.vnet.ibm.com Link: http://lkml.kernel.org/n/tip-v101o8k25vuja2ogosgf15yy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/Build | 1 - tools/perf/arch/s390/util/sym-handling.c | 21 --------------------- 2 files changed, 22 deletions(-) delete mode 100644 tools/perf/arch/s390/util/sym-handling.c diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index bd518b623d7a2..5bd7b9260cc08 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -1,5 +1,4 @@ libperf-y += header.o -libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-$(CONFIG_DWARF) += dwarf-regs.o diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c deleted file mode 100644 index 581d4c5a896b8..0000000000000 --- a/tools/perf/arch/s390/util/sym-handling.c +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Architecture specific ELF symbol handling and relocation mapping. - * - * Copyright 2017 IBM Corp. - * Author(s): Thomas Richter - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2 only) - * as published by the Free Software Foundation. - */ - -#include "symbol.h" - -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - if (ehdr.e_type == ET_EXEC) - return false; - return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN; -} -#endif -- GitLab From bd86e32059526e2d0d13ca1e4447dfbbddb6e5cc Mon Sep 17 00:00:00 2001 From: Jeffy Chen Date: Wed, 27 Sep 2017 20:28:57 +0800 Subject: [PATCH 0588/1507] dm crypt: fix memory leak in crypt_ctr_cipher_old() Fix memory leak of cipher_api. Fixes: 33d2f09fcb35 (dm crypt: introduce new format of cipher with "capi:" prefix) Cc: stable@vger.kernel.org # 4.12+ Signed-off-by: Jeffy Chen Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index a55ffd4f5933f..75341fdca4b6b 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2466,6 +2466,7 @@ static int crypt_ctr_cipher_old(struct dm_target *ti, char *cipher_in, char *key kfree(cipher_api); return ret; } + kfree(cipher_api); return 0; bad_mem: -- GitLab From aff3da39211105a42b2108b8af79bf8e16f670fd Mon Sep 17 00:00:00 2001 From: Stefan Chulski Date: Mon, 25 Sep 2017 14:59:46 +0200 Subject: [PATCH 0589/1507] net: mvpp2: fix parsing fragmentation detection Parsing fragmentation detection failed due to wrong configured parser TCAM entry's. Some traffic was marked as fragmented in RX descriptor, even it wasn't IP fragmented. The hardware also failed to calculate checksums which lead to use software checksum and caused performance degradation. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Antoine Tenart Signed-off-by: Stefan Chulski Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index dd0ee2691c863..da04939a2748c 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -676,6 +676,7 @@ enum mvpp2_tag_type { #define MVPP2_PRS_RI_L3_MCAST BIT(15) #define MVPP2_PRS_RI_L3_BCAST (BIT(15) | BIT(16)) #define MVPP2_PRS_RI_IP_FRAG_MASK 0x20000 +#define MVPP2_PRS_RI_IP_FRAG_TRUE BIT(17) #define MVPP2_PRS_RI_UDF3_MASK 0x300000 #define MVPP2_PRS_RI_UDF3_RX_SPECIAL BIT(21) #define MVPP2_PRS_RI_L4_PROTO_MASK 0x1c00000 @@ -2315,7 +2316,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, (proto != IPPROTO_IGMP)) return -EINVAL; - /* Fragmented packet */ + /* Not fragmented packet */ tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, MVPP2_PE_LAST_FREE_TID); if (tid < 0) @@ -2334,8 +2335,12 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, MVPP2_PRS_SRAM_OP_SEL_UDF_ADD); mvpp2_prs_sram_ai_update(&pe, MVPP2_PRS_IPV4_DIP_AI_BIT, MVPP2_PRS_IPV4_DIP_AI_BIT); - mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_MASK, - ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + mvpp2_prs_sram_ri_update(&pe, ri, ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + + mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, + MVPP2_PRS_TCAM_PROTO_MASK_L); + mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, + MVPP2_PRS_TCAM_PROTO_MASK); mvpp2_prs_tcam_data_byte_set(&pe, 5, proto, MVPP2_PRS_TCAM_PROTO_MASK); mvpp2_prs_tcam_ai_update(&pe, 0, MVPP2_PRS_IPV4_DIP_AI_BIT); @@ -2346,7 +2351,7 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4); mvpp2_prs_hw_write(priv, &pe); - /* Not fragmented packet */ + /* Fragmented packet */ tid = mvpp2_prs_tcam_first_free(priv, MVPP2_PE_FIRST_FREE_TID, MVPP2_PE_LAST_FREE_TID); if (tid < 0) @@ -2358,8 +2363,11 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto, pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0; mvpp2_prs_sram_ri_update(&pe, ri, ri_mask); - mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, MVPP2_PRS_TCAM_PROTO_MASK_L); - mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, MVPP2_PRS_TCAM_PROTO_MASK); + mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE, + ri_mask | MVPP2_PRS_RI_IP_FRAG_MASK); + + mvpp2_prs_tcam_data_byte_set(&pe, 2, 0x00, 0x0); + mvpp2_prs_tcam_data_byte_set(&pe, 3, 0x00, 0x0); /* Update shadow table and hw entry */ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_IP4); -- GitLab From 6bf69a1d6334bed776875c5ca852594ab4e5b209 Mon Sep 17 00:00:00 2001 From: Yan Markman Date: Mon, 25 Sep 2017 14:59:47 +0200 Subject: [PATCH 0590/1507] net: mvpp2: fix port list indexing The private port_list array has a list of pointers to mvpp2_port instances. This list is allocated given the number of ports enabled in the device tree, but the pointers are set using the port-id property. If on a single port is enabled, the port_list array will be of size 1, but when registering the port, if its id is not 0 the driver will crash. Other crashes were encountered in various situations. This fixes the issue by using an index not equal to the value of the port-id property. Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Antoine Tenart Signed-off-by: Yan Markman Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index da04939a2748c..b2f99df81e9cf 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -7504,7 +7504,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node, - struct mvpp2 *priv) + struct mvpp2 *priv, int index) { struct device_node *phy_node; struct phy *comphy; @@ -7678,7 +7678,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); - priv->port_list[id] = port; + priv->port_list[index] = port; return 0; err_free_port_pcpu: @@ -8013,10 +8013,12 @@ static int mvpp2_probe(struct platform_device *pdev) } /* Initialize ports */ + i = 0; for_each_available_child_of_node(dn, port_node) { - err = mvpp2_port_probe(pdev, port_node, priv); + err = mvpp2_port_probe(pdev, port_node, priv, i); if (err < 0) goto err_mg_clk; + i++; } platform_set_drvdata(pdev, priv); -- GitLab From c7dfc8c848a48f176096f66a14879fb3333a460f Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 25 Sep 2017 14:59:48 +0200 Subject: [PATCH 0591/1507] net: mvpp2: do not select the internal source clock This patch stops the internal MAC Tx clock from being enabled as the internal clock isn't used. The definition used for the bit controlling this behaviour is renamed as well as it was wrongly named (bit 4 of GMAC_CTRL_2_REG). Fixes: 3919357fb0bb ("net: mvpp2: initialize the GMAC when using a port") Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index b2f99df81e9cf..1610555647201 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -333,7 +333,7 @@ #define MVPP2_GMAC_INBAND_AN_MASK BIT(0) #define MVPP2_GMAC_FLOW_CTRL_MASK GENMASK(2, 1) #define MVPP2_GMAC_PCS_ENABLE_MASK BIT(3) -#define MVPP2_GMAC_PORT_RGMII_MASK BIT(4) +#define MVPP2_GMAC_INTERNAL_CLK_MASK BIT(4) #define MVPP2_GMAC_DISABLE_PADDING BIT(5) #define MVPP2_GMAC_PORT_RESET_MASK BIT(6) #define MVPP2_GMAC_AUTONEG_CONFIG 0xc @@ -4599,7 +4599,6 @@ static void mvpp2_port_mii_gmac_configure(struct mvpp2_port *port) val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK; } else if (phy_interface_mode_is_rgmii(port->phy_interface)) { val &= ~MVPP2_GMAC_PCS_ENABLE_MASK; - val |= MVPP2_GMAC_PORT_RGMII_MASK; } writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); -- GitLab From 35f493b87ec072c5a2497ffbee243095ef725827 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 25 Sep 2017 08:40:02 -0700 Subject: [PATCH 0592/1507] inetpeer: fix RCU lookup() again My prior fix was not complete, as we were dereferencing a pointer three times per node, not twice as I initially thought. Fixes: 4cc5b44b29a9 ("inetpeer: fix RCU lookup()") Fixes: b145425f269a ("inetpeer: remove AVL implementation in favor of RB tree") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/inetpeer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e7eb590c86ce2..b20c8ac640811 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -128,9 +128,9 @@ static struct inet_peer *lookup(const struct inetpeer_addr *daddr, break; } if (cmp == -1) - pp = &(*pp)->rb_left; + pp = &next->rb_left; else - pp = &(*pp)->rb_right; + pp = &next->rb_right; } *parent_p = parent; *pp_p = pp; -- GitLab From 8f1975e31d8ed0c021a1993a4d9123dd39c740ea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 25 Sep 2017 09:14:14 -0700 Subject: [PATCH 0593/1507] inetpeer: speed up inetpeer_invalidate_tree() As measured in my prior patch ("sch_netem: faster rb tree removal"), rbtree_postorder_for_each_entry_safe() is nice looking but much slower than using rb_next() directly, except when tree is small enough to fit in CPU caches (then the cost is the same) From: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/inetpeer.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e7eb590c86ce2..6e5626cc366c1 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -284,14 +284,17 @@ EXPORT_SYMBOL(inet_peer_xrlim_allow); void inetpeer_invalidate_tree(struct inet_peer_base *base) { - struct inet_peer *p, *n; + struct rb_node *p = rb_first(&base->rb_root); - rbtree_postorder_for_each_entry_safe(p, n, &base->rb_root, rb_node) { - inet_putpeer(p); + while (p) { + struct inet_peer *peer = rb_entry(p, struct inet_peer, rb_node); + + p = rb_next(p); + rb_erase(&peer->rb_node, &base->rb_root); + inet_putpeer(peer); cond_resched(); } - base->rb_root = RB_ROOT; base->total = 0; } EXPORT_SYMBOL(inetpeer_invalidate_tree); -- GitLab From 76cf546c2802f6e25113ba481d7e85d0298768c6 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 25 Sep 2017 10:13:49 -0700 Subject: [PATCH 0594/1507] net_sched: use idr to allocate bpf filter handles Instead of calling cls_bpf_get() in a loop to find a unused handle, just switch to idr API to allocate new handles. Cc: Daniel Borkmann Cc: Chris Mi Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_bpf.c | 57 ++++++++++++++++++++++----------------------- 1 file changed, 28 insertions(+), 29 deletions(-) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 36671b0fb1253..6c6b21f6ba62a 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -32,7 +33,7 @@ MODULE_DESCRIPTION("TC BPF based classifier"); struct cls_bpf_head { struct list_head plist; - u32 hgen; + struct idr handle_idr; struct rcu_head rcu; }; @@ -238,6 +239,7 @@ static int cls_bpf_init(struct tcf_proto *tp) return -ENOBUFS; INIT_LIST_HEAD_RCU(&head->plist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; @@ -264,6 +266,9 @@ static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog) { + struct cls_bpf_head *head = rtnl_dereference(tp->root); + + idr_remove_ext(&head->handle_idr, prog->handle); cls_bpf_stop_offload(tp, prog); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); @@ -287,6 +292,7 @@ static void cls_bpf_destroy(struct tcf_proto *tp) list_for_each_entry_safe(prog, tmp, &head->plist, link) __cls_bpf_delete(tp, prog); + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -421,27 +427,6 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, return 0; } -static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp, - struct cls_bpf_head *head) -{ - unsigned int i = 0x80000000; - u32 handle; - - do { - if (++head->hgen == 0x7FFFFFFF) - head->hgen = 1; - } while (--i > 0 && cls_bpf_get(tp, head->hgen)); - - if (unlikely(i == 0)) { - pr_err("Insufficient number of handles\n"); - handle = 0; - } else { - handle = head->hgen; - } - - return handle; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -451,6 +436,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; struct cls_bpf_prog *prog; + unsigned long idr_index; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -476,21 +462,30 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, } } - if (handle == 0) - prog->handle = cls_bpf_grab_new_handle(tp, head); - else + if (handle == 0) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (ret) + goto errout; + prog->handle = idr_index; + } else { + if (!oldprog) { + ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (ret) + goto errout; + } prog->handle = handle; - if (prog->handle == 0) { - ret = -EINVAL; - goto errout; } ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr); if (ret < 0) - goto errout; + goto errout_idr; ret = cls_bpf_offload(tp, prog, oldprog); if (ret) { + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); __cls_bpf_delete_prog(prog); return ret; } @@ -499,6 +494,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (oldprog) { + idr_replace_ext(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu); @@ -509,6 +505,9 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, *arg = prog; return 0; +errout_idr: + if (!oldprog) + idr_remove_ext(&head->handle_idr, prog->handle); errout: tcf_exts_destroy(&prog->exts); kfree(prog); -- GitLab From 1d8134fea2eb460698a281f91c03c400f7e546ce Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 25 Sep 2017 10:13:50 -0700 Subject: [PATCH 0595/1507] net_sched: use idr to allocate basic filter handles Instead of calling basic_get() in a loop to find a unused handle, just switch to idr API to allocate new handles. Cc: Chris Mi Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_basic.c | 37 ++++++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 15 deletions(-) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index d89ebafd22390..cfeb6f1585669 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -17,13 +17,14 @@ #include #include #include +#include #include #include #include struct basic_head { - u32 hgenerator; struct list_head flist; + struct idr handle_idr; struct rcu_head rcu; }; @@ -78,6 +79,7 @@ static int basic_init(struct tcf_proto *tp) if (head == NULL) return -ENOBUFS; INIT_LIST_HEAD(&head->flist); + idr_init(&head->handle_idr); rcu_assign_pointer(tp->root, head); return 0; } @@ -99,8 +101,10 @@ static void basic_destroy(struct tcf_proto *tp) list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); call_rcu(&f->rcu, basic_delete_filter); } + idr_destroy(&head->handle_idr); kfree_rcu(head, rcu); } @@ -111,6 +115,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last) list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); + idr_remove_ext(&head->handle_idr, f->handle); call_rcu(&f->rcu, basic_delete_filter); *last = list_empty(&head->flist); return 0; @@ -154,6 +159,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *fold = (struct basic_filter *) *arg; struct basic_filter *fnew; + unsigned long idr_index; if (tca[TCA_OPTIONS] == NULL) return -EINVAL; @@ -179,30 +185,31 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, err = -EINVAL; if (handle) { fnew->handle = handle; - } else if (fold) { - fnew->handle = fold->handle; + if (!fold) { + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + handle, handle + 1, GFP_KERNEL); + if (err) + goto errout; + } } else { - unsigned int i = 0x80000000; - do { - if (++head->hgenerator == 0x7FFFFFFF) - head->hgenerator = 1; - } while (--i > 0 && basic_get(tp, head->hgenerator)); - - if (i <= 0) { - pr_err("Insufficient number of handles\n"); + err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, + 1, 0x7FFFFFFF, GFP_KERNEL); + if (err) goto errout; - } - - fnew->handle = head->hgenerator; + fnew->handle = idr_index; } err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr); - if (err < 0) + if (err < 0) { + if (!fold) + idr_remove_ext(&head->handle_idr, fnew->handle); goto errout; + } *arg = fnew; if (fold) { + idr_replace_ext(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); call_rcu(&fold->rcu, basic_delete_filter); -- GitLab From e7614370d6f04711c4e4b48f7055e5008fa4ed42 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 25 Sep 2017 10:13:51 -0700 Subject: [PATCH 0596/1507] net_sched: use idr to allocate u32 filter handles Instead of calling u32_lookup_ht() in a loop to find a unused handle, just switch to idr API to allocate new handles. u32 filters are special as the handle could contain a hash table id and a key id, so we need two IDR to allocate each of them. Cc: Chris Mi Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_u32.c | 108 +++++++++++++++++++++++++++----------------- 1 file changed, 67 insertions(+), 41 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 10b8d851fc6be..094d224411a93 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -46,6 +46,7 @@ #include #include #include +#include struct tc_u_knode { struct tc_u_knode __rcu *next; @@ -82,6 +83,7 @@ struct tc_u_hnode { struct tc_u_common *tp_c; int refcnt; unsigned int divisor; + struct idr handle_idr; struct rcu_head rcu; /* The 'ht' field MUST be the last field in structure to allow for * more entries allocated at end of structure. @@ -93,7 +95,7 @@ struct tc_u_common { struct tc_u_hnode __rcu *hlist; struct Qdisc *q; int refcnt; - u32 hgenerator; + struct idr handle_idr; struct hlist_node hnode; struct rcu_head rcu; }; @@ -311,19 +313,19 @@ static void *u32_get(struct tcf_proto *tp, u32 handle) return u32_lookup_key(ht, handle); } -static u32 gen_new_htid(struct tc_u_common *tp_c) +static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) { - int i = 0x800; + unsigned long idr_index; + int err; - /* hgenerator only used inside rtnl lock it is safe to increment + /* This is only used inside rtnl lock it is safe to increment * without read _copy_ update semantics */ - do { - if (++tp_c->hgenerator == 0x7FF) - tp_c->hgenerator = 1; - } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); - - return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; + err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index, + 1, 0x7FF, GFP_KERNEL); + if (err) + return 0; + return (u32)(idr_index | 0x800) << 20; } static struct hlist_head *tc_u_common_hash; @@ -366,8 +368,9 @@ static int u32_init(struct tcf_proto *tp) return -ENOBUFS; root_ht->refcnt++; - root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000; + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; root_ht->prio = tp->prio; + idr_init(&root_ht->handle_idr); if (tp_c == NULL) { tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); @@ -377,6 +380,7 @@ static int u32_init(struct tcf_proto *tp) } tp_c->q = tp->q; INIT_HLIST_NODE(&tp_c->hnode); + idr_init(&tp_c->handle_idr); h = tc_u_hash(tp); hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]); @@ -565,6 +569,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n->handle); + idr_remove_ext(&ht->handle_idr, n->handle); call_rcu(&n->rcu, u32_delete_key_freepf_rcu); } } @@ -586,6 +591,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) hn = &phn->next, phn = rtnl_dereference(*hn)) { if (phn == ht) { u32_clear_hw_hnode(tp, ht); + idr_destroy(&ht->handle_idr); + idr_remove_ext(&tp_c->handle_idr, ht->handle); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -633,6 +640,7 @@ static void u32_destroy(struct tcf_proto *tp) kfree_rcu(ht, rcu); } + idr_destroy(&tp_c->handle_idr); kfree(tp_c); } @@ -701,27 +709,21 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last) return ret; } -#define NR_U32_NODE (1<<12) -static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) +static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { - struct tc_u_knode *n; - unsigned long i; - unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long), - GFP_KERNEL); - if (!bitmap) - return handle | 0xFFF; - - for (n = rtnl_dereference(ht->ht[TC_U32_HASH(handle)]); - n; - n = rtnl_dereference(n->next)) - set_bit(TC_U32_NODE(n->handle), bitmap); - - i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800); - if (i >= NR_U32_NODE) - i = find_next_zero_bit(bitmap, NR_U32_NODE, 1); + unsigned long idr_index; + u32 start = htid | 0x800; + u32 max = htid | 0xFFF; + u32 min = htid; + + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + start, max + 1, GFP_KERNEL)) { + if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, + min + 1, max + 1, GFP_KERNEL)) + return max; + } - kfree(bitmap); - return handle | (i >= NR_U32_NODE ? 0xFFF : i); + return (u32)idr_index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -806,6 +808,7 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, if (pins->handle == n->handle) break; + idr_replace_ext(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } @@ -937,22 +940,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; if (TC_U32_KEY(handle)) return -EINVAL; - if (handle == 0) { - handle = gen_new_htid(tp->data); - if (handle == 0) - return -ENOMEM; - } ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; + if (handle == 0) { + handle = gen_new_htid(tp->data, ht); + if (handle == 0) { + kfree(ht); + return -ENOMEM; + } + } else { + err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL, + handle, handle + 1, GFP_KERNEL); + if (err) { + kfree(ht); + return err; + } + } ht->tp_c = tp_c; ht->refcnt = 1; ht->divisor = divisor; ht->handle = handle; ht->prio = tp->prio; + idr_init(&ht->handle_idr); err = u32_replace_hw_hnode(tp, ht, flags); if (err) { + idr_remove_ext(&tp_c->handle_idr, handle); kfree(ht); return err; } @@ -986,24 +1000,33 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid)) return -EINVAL; handle = htid | TC_U32_NODE(handle); + err = idr_alloc_ext(&ht->handle_idr, NULL, NULL, + handle, handle + 1, + GFP_KERNEL); + if (err) + return err; } else handle = gen_new_kid(ht, htid); - if (tb[TCA_U32_SEL] == NULL) - return -EINVAL; + if (tb[TCA_U32_SEL] == NULL) { + err = -EINVAL; + goto erridr; + } s = nla_data(tb[TCA_U32_SEL]); n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); - if (n == NULL) - return -ENOBUFS; + if (n == NULL) { + err = -ENOBUFS; + goto erridr; + } #ifdef CONFIG_CLS_U32_PERF size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64); n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt)); if (!n->pf) { - kfree(n); - return -ENOBUFS; + err = -ENOBUFS; + goto errfree; } #endif @@ -1066,9 +1089,12 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, errout: tcf_exts_destroy(&n->exts); #ifdef CONFIG_CLS_U32_PERF +errfree: free_percpu(n->pf); #endif kfree(n); +erridr: + idr_remove_ext(&ht->handle_idr, handle); return err; } -- GitLab From db06ae41945b14feb7f696dcafe8048cc37e8a20 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 25 Sep 2017 23:32:20 +0200 Subject: [PATCH 0597/1507] net: dsa: mv88e6xxx: Allow dsa and cpu ports in multiple vlans Ports with the same VLAN must all be in the same bridge. However the CPU and DSA ports need to be in multiple VLANs spread over multiple bridges. So exclude them when performing this test. Fixes: b2f81d304cee ("net: dsa: add CPU and DSA ports as VLAN members") Signed-off-by: Andrew Lunn Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c6678aa9b4ef0..674dab71d71c1 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1100,6 +1100,10 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, }; int i, err; + /* DSA and CPU ports have to be members of multiple vlans */ + if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + return 0; + if (!vid_begin) return -EOPNOTSUPP; -- GitLab From e804441cfe0b60f6c430901946a69c01eac09df1 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 25 Sep 2017 15:55:53 -0700 Subject: [PATCH 0598/1507] net: dsa: Fix network device registration order We cannot be registering the network device first, then setting its carrier off and finally connecting it to a PHY, doing that leaves a window during which the carrier is at best inconsistent, and at worse the device is not usable without a down/up sequence since the network device is visible to user space with possibly no PHY device attached. Re-order steps so that they make logical sense. This fixes some devices where the port was not usable after e.g: an unbind then bind of the driver. Fixes: 0071f56e46da ("dsa: Register netdev before phy") Fixes: 91da11f870f0 ("net: Distributed Switch Architecture protocol support") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 2afa99506f8b4..865e29e62bad8 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1301,28 +1301,33 @@ int dsa_slave_create(struct dsa_port *port, const char *name) p->old_duplex = -1; port->netdev = slave_dev; - ret = register_netdev(slave_dev); - if (ret) { - netdev_err(master, "error %d registering interface %s\n", - ret, slave_dev->name); - port->netdev = NULL; - free_percpu(p->stats64); - free_netdev(slave_dev); - return ret; - } netif_carrier_off(slave_dev); ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); - unregister_netdev(slave_dev); - free_percpu(p->stats64); - free_netdev(slave_dev); - return ret; + goto out_free; + } + + ret = register_netdev(slave_dev); + if (ret) { + netdev_err(master, "error %d registering interface %s\n", + ret, slave_dev->name); + goto out_phy; } return 0; + +out_phy: + phy_disconnect(p->phy); + if (of_phy_is_fixed_link(p->dp->dn)) + of_phy_deregister_fixed_link(p->dp->dn); +out_free: + free_percpu(p->stats64); + free_netdev(slave_dev); + port->netdev = NULL; + return ret; } void dsa_slave_destroy(struct net_device *slave_dev) -- GitLab From 61f26d92510ea1e30f9b69097b34b6a522daa1d2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 07:40:42 +0200 Subject: [PATCH 0599/1507] selftests: rtnetlink.sh: add rudimentary vrf test Acked-by: David Ahern Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 42 ++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 4b48de565caef..a048f7a5f94c6 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -291,6 +291,47 @@ kci_test_ifalias() echo "PASS: set ifalias $namewant for $devdummy" } +kci_test_vrf() +{ + vrfname="test-vrf" + ret=0 + + ip link show type vrf 2>/dev/null + if [ $? -ne 0 ]; then + echo "SKIP: vrf: iproute2 too old" + return 0 + fi + + ip link add "$vrfname" type vrf table 10 + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: can't add vrf interface, skipping test" + return 0 + fi + + ip -br link show type vrf | grep -q "$vrfname" + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: created vrf device not found" + return 1 + fi + + ip link set dev "$vrfname" up + check_err $? + + ip link set dev "$devdummy" master "$vrfname" + check_err $? + ip link del dev "$vrfname" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: vrf" + return 1 + fi + + echo "PASS: vrf" +} + kci_test_rtnl() { kci_add_dummy @@ -306,6 +347,7 @@ kci_test_rtnl() kci_test_bridge kci_test_addrlabel kci_test_ifalias + kci_test_vrf kci_del_dummy } -- GitLab From 06d7a1b932c26afe2c0a1f4520ddd417d8eeda79 Mon Sep 17 00:00:00 2001 From: Ed Blake Date: Tue, 26 Sep 2017 11:43:46 +0100 Subject: [PATCH 0600/1507] net: stmmac: dwc-qos: Add suspend / resume support Add hook to stmmac_pltfr_pm_ops for suspend / resume handling. Signed-off-by: Ed Blake Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index dd6a2f9791cc1..5efef8001edf2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -511,6 +511,7 @@ static struct platform_driver dwc_eth_dwmac_driver = { .remove = dwc_eth_dwmac_remove, .driver = { .name = "dwc-eth-dwmac", + .pm = &stmmac_pltfr_pm_ops, .of_match_table = dwc_eth_dwmac_match, }, }; -- GitLab From 1579f678fb4397f9e439d2e373d4ade036c673b4 Mon Sep 17 00:00:00 2001 From: Ed Blake Date: Tue, 26 Sep 2017 11:44:53 +0100 Subject: [PATCH 0601/1507] net: stmmac: dwmac4: Re-enable MAC Rx before powering down Re-enable the MAC receiver by setting CONFIG_RE before powering down, as instructed in section 6.3.5.1 of [1]. Without this the MAC fails to receive WoL packets and never wakes up. [1] DWC Ethernet QoS Databook 4.10a October 2014 Signed-off-by: Ed Blake Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c4407e8e39a35..2f7d7ec59962a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -296,6 +296,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) { void __iomem *ioaddr = hw->pcsr; unsigned int pmt = 0; + u32 config; if (mode & WAKE_MAGIC) { pr_debug("GMAC: WOL Magic frame\n"); @@ -306,6 +307,12 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) pmt |= power_down | global_unicast | wake_up_frame_en; } + if (pmt) { + /* The receiver must be enabled for WOL before powering down */ + config = readl(ioaddr + GMAC_CONFIG); + config |= GMAC_CONFIG_RE; + writel(config, ioaddr + GMAC_CONFIG); + } writel(pmt, ioaddr + GMAC_PMT); } -- GitLab From 79110a0426d8179a51bf3cb698a84f6ec98ca60c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 13:58:40 +0200 Subject: [PATCH 0602/1507] rtnetlink: add helper to put master and link ifindexes rtnl_fill_ifinfo currently requires caller to hold the rtnl mutex. Unfortunately the function is quite large which makes it harder to see which spots require the lock, which spots assume it and which ones could do without. Add helpers to factor out the ifindex dumping, one can use rcu to avoid rtnl dependency. Reviewed-by: David Ahern Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a78fd61da0ec5..c801212ee40e8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1307,6 +1307,31 @@ static u32 rtnl_get_event(unsigned long event) return rtnl_event_type; } +static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) +{ + const struct net_device *upper_dev; + int ret = 0; + + rcu_read_lock(); + + upper_dev = netdev_master_upper_dev_get_rcu(dev); + if (upper_dev) + ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex); + + rcu_read_unlock(); + return ret; +} + +static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) +{ + int ifindex = dev_get_iflink(dev); + + if (dev->ifindex == ifindex) + return 0; + + return nla_put_u32(skb, IFLA_LINK, ifindex); +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, @@ -1316,7 +1341,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct nlmsghdr *nlh; struct nlattr *af_spec; struct rtnl_af_ops *af_ops; - struct net_device *upper_dev = netdev_master_upper_dev_get(dev); ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1345,10 +1369,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif - (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || - (upper_dev && - nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_iflink(skb, dev) || + put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || -- GitLab From 250fc3dfdbd3e8b5c751ce7b5a26176ec62ca0f8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 13:58:41 +0200 Subject: [PATCH 0603/1507] rtnetlink: add helpers to dump vf information similar to earlier patches, split out more parts of this function to better see what is happening and where we assume rtnl is locked. Reviewed-by: David Ahern Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 50 +++++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 19 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index c801212ee40e8..d504e78cd01fb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1211,6 +1211,36 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, return -EMSGSIZE; } +static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb, + struct net_device *dev, + u32 ext_filter_mask) +{ + struct nlattr *vfinfo; + int i, num_vfs; + + if (!dev->dev.parent || ((ext_filter_mask & RTEXT_FILTER_VF) == 0)) + return 0; + + num_vfs = dev_num_vf(dev->dev.parent); + if (nla_put_u32(skb, IFLA_NUM_VF, num_vfs)) + return -EMSGSIZE; + + if (!dev->netdev_ops->ndo_get_vf_config) + return 0; + + vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); + if (!vfinfo) + return -EMSGSIZE; + + for (i = 0; i < num_vfs; i++) { + if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) + return -EMSGSIZE; + } + + nla_nest_end(skb, vfinfo); + return 0; +} + static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) { struct rtnl_link_ifmap map; @@ -1407,27 +1437,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_fill_stats(skb, dev)) goto nla_put_failure; - if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && - nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) + if (rtnl_fill_vf(skb, dev, ext_filter_mask)) goto nla_put_failure; - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent && - ext_filter_mask & RTEXT_FILTER_VF) { - int i; - struct nlattr *vfinfo; - int num_vfs = dev_num_vf(dev->dev.parent); - - vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); - if (!vfinfo) - goto nla_put_failure; - for (i = 0; i < num_vfs; i++) { - if (rtnl_fill_vfinfo(skb, dev, i, vfinfo)) - goto nla_put_failure; - } - - nla_nest_end(skb, vfinfo); - } - if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; -- GitLab From b1e66b9a67d67d0e73091b04b51e524581c8c887 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 13:58:42 +0200 Subject: [PATCH 0604/1507] rtnetlink: add helpers to dump netnsid information Reviewed-by: David Ahern Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d504e78cd01fb..d524609c587c1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1362,6 +1362,23 @@ static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) return nla_put_u32(skb, IFLA_LINK, ifindex); } +static int rtnl_fill_link_netnsid(struct sk_buff *skb, + const struct net_device *dev) +{ + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) { + struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); + + if (!net_eq(dev_net(dev), link_net)) { + int id = peernet2id_alloc(dev_net(dev), link_net); + + if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) + return -EMSGSIZE; + } + } + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, @@ -1451,17 +1468,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } - if (dev->rtnl_link_ops && - dev->rtnl_link_ops->get_link_net) { - struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); - - if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(dev_net(dev), link_net); - - if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) - goto nla_put_failure; - } - } + if (rtnl_fill_link_netnsid(skb, dev)) + goto nla_put_failure; if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) goto nla_put_failure; -- GitLab From 4c82a95e523721637d44e0e8d879fa11fa825eec Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Sep 2017 13:58:43 +0200 Subject: [PATCH 0605/1507] rtnetlink: rtnl_have_link_slave_info doesn't need rtnl it can be switched to rcu. Reviewed-by: David Ahern Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d524609c587c1..e6955da0d58d8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -522,11 +522,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev, static bool rtnl_have_link_slave_info(const struct net_device *dev) { struct net_device *master_dev; + bool ret = false; - master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + rcu_read_lock(); + + master_dev = netdev_master_upper_dev_get_rcu((struct net_device *)dev); if (master_dev && master_dev->rtnl_link_ops) - return true; - return false; + ret = true; + rcu_read_unlock(); + return ret; } static int rtnl_link_slave_info_fill(struct sk_buff *skb, -- GitLab From 4d8806fd14e1492cd4fb2021f709b163ea3364ad Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 26 Sep 2017 16:14:09 +0100 Subject: [PATCH 0606/1507] cxgb4: make function ch_flower_stats_cb, fixes warning The function ch_flower_stats_cb is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warnings: symbol 'ch_flower_stats_cb' was not declared. Should it be static? Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index a36bd66d2834b..92a3117673818 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -366,7 +366,7 @@ int cxgb4_tc_flower_destroy(struct net_device *dev, return ret; } -void ch_flower_stats_cb(unsigned long data) +static void ch_flower_stats_cb(unsigned long data) { struct adapter *adap = (struct adapter *)data; struct ch_tc_flower_entry *flower_entry; -- GitLab From 2b7c6ba945fd3c10ca3e030be402098aff2f89d3 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 26 Sep 2017 16:35:13 +0100 Subject: [PATCH 0607/1507] bpf/verifier: improve disassembly of BPF_END instructions print_bpf_insn() was treating all BPF_ALU[64] the same, but BPF_END has a different structure: it has a size in insn->imm (even if it's BPF_X) and uses the BPF_SRC (X or K) to indicate which endianness to use. So it needs different code to print it. Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f849eca36052c..e8d7bb8e6b988 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -332,26 +332,40 @@ static const char *const bpf_jmp_string[16] = { [BPF_EXIT >> 4] = "exit", }; +static void print_bpf_end_insn(const struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose("(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", + insn->imm, insn->dst_reg); +} + static void print_bpf_insn(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); if (class == BPF_ALU || class == BPF_ALU64) { - if (BPF_SRC(insn->code) == BPF_X) + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose("BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(env, insn); + } else if (BPF_SRC(insn->code) == BPF_X) { verbose("(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->src_reg); - else + } else { verbose("(%02x) %sr%d %s %s%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->imm); + } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", -- GitLab From 73c864b38383f4abc9b559025cd663f4a81afa89 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 26 Sep 2017 16:35:29 +0100 Subject: [PATCH 0608/1507] bpf/verifier: improve disassembly of BPF_NEG instructions BPF_NEG takes only one operand, unlike the bulk of BPF_ALU[64] which are compound-assignments. So give it its own format in print_bpf_insn(). Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e8d7bb8e6b988..4cf9b72c59a06 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -351,6 +351,11 @@ static void print_bpf_insn(const struct bpf_verifier_env *env, verbose("BUG_alu64_%02x\n", insn->code); else print_bpf_end_insn(env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose("(%02x) r%d = %s-r%d\n", + insn->code, insn->dst_reg, + class == BPF_ALU ? "(u32) " : "", + insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { verbose("(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", -- GitLab From 4971613c1639d8e5f102c4e797c3bf8f83a5a69e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 26 Sep 2017 12:19:37 -0400 Subject: [PATCH 0609/1507] packet: in packet_do_bind, test fanout with bind_lock held Once a socket has po->fanout set, it remains a member of the group until it is destroyed. The prot_hook must be constant and identical across sockets in the group. If fanout_add races with packet_do_bind between the test of po->fanout and taking the lock, the bind call may make type or dev inconsistent with that of the fanout group. Hold po->bind_lock when testing po->fanout to avoid this race. I had to introduce artificial delay (local_bh_enable) to actually observe the race. Fixes: dc99f600698d ("packet: Add fanout support.") Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/packet/af_packet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d288f52c53f7c..a10c2836465cf 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3069,13 +3069,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, int ret = 0; bool unlisted = false; - if (po->fanout) - return -EINVAL; - lock_sock(sk); spin_lock(&po->bind_lock); rcu_read_lock(); + if (po->fanout) { + ret = -EINVAL; + goto out_unlock; + } + if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { -- GitLab From da7c9561015e93d10fe6aab73e9288e0d09d65a6 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 26 Sep 2017 12:20:17 -0400 Subject: [PATCH 0610/1507] packet: only test po->has_vnet_hdr once in packet_snd Packet socket option po->has_vnet_hdr can be updated concurrently with other operations if no ring is attached. Do not test the option twice in packet_snd, as the value may change in between calls. A race on setsockopt disable may cause a packet > mtu to be sent without having GSO options set. Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.") Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/packet/af_packet.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a10c2836465cf..bec01a3daf5b0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2840,6 +2840,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); + bool has_vnet_hdr = false; int hlen, tlen, linear; int extra_len = 0; @@ -2883,6 +2884,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) err = packet_snd_vnet_parse(msg, &len, &vnet_hdr); if (err) goto out_unlock; + has_vnet_hdr = true; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { @@ -2941,7 +2943,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = sk->sk_priority; skb->mark = sockc.mark; - if (po->has_vnet_hdr) { + if (has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; -- GitLab From 352f58b0d9f26d283b10f4c9f21e8717141c1334 Mon Sep 17 00:00:00 2001 From: Aviad Krawczyk Date: Wed, 27 Sep 2017 01:57:50 +0800 Subject: [PATCH 0611/1507] net-next/hinic: Set Rxq irq to specific cpu for NUMA Set Rxq irq to specific cpu for allocating and receiving the skb from the same node. Signed-off-by: Aviad Krawczyk Signed-off-by: David S. Miller --- drivers/net/ethernet/huawei/hinic/hinic_rx.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 1d4f712b15a82..e2e5cdc7119c3 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "hinic_common.h" @@ -171,11 +172,10 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq) struct hinic_sge sge; dma_addr_t dma_addr; struct sk_buff *skb; - int i, alloc_more; u16 prod_idx; + int i; free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq); - alloc_more = 0; /* Limit the allocation chunks */ if (free_wqebbs > nic_dev->rx_weight) @@ -185,7 +185,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq) skb = rx_alloc_skb(rxq, &dma_addr); if (!skb) { netdev_err(rxq->netdev, "Failed to alloc Rx skb\n"); - alloc_more = 1; goto skb_out; } @@ -195,7 +194,6 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq) &prod_idx); if (!rq_wqe) { rx_free_skb(rxq, skb, dma_addr); - alloc_more = 1; goto skb_out; } @@ -211,9 +209,7 @@ static int rx_alloc_pkts(struct hinic_rxq *rxq) hinic_rq_update(rxq->rq, prod_idx); } - if (alloc_more) - tasklet_schedule(&rxq->rx_task); - + tasklet_schedule(&rxq->rx_task); return i; } @@ -357,7 +353,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget) } if (pkts) - tasklet_schedule(&rxq->rx_task); /* hinic_rx_alloc_pkts */ + tasklet_schedule(&rxq->rx_task); /* rx_alloc_pkts */ u64_stats_update_begin(&rxq->rxq_stats.syncp); rxq->rxq_stats.pkts += pkts; @@ -417,6 +413,8 @@ static int rx_request_irq(struct hinic_rxq *rxq) struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_rq *rq = rxq->rq; + struct hinic_qp *qp; + struct cpumask mask; int err; rx_add_napi(rxq); @@ -432,7 +430,9 @@ static int rx_request_irq(struct hinic_rxq *rxq) return err; } - return 0; + qp = container_of(rq, struct hinic_qp, rq); + cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask); + return irq_set_affinity_hint(rq->irq, &mask); } static void rx_free_irq(struct hinic_rxq *rxq) -- GitLab From bbdc9e687fb3c2920961d7716f1c5519ff7bc595 Mon Sep 17 00:00:00 2001 From: Aviad Krawczyk Date: Wed, 27 Sep 2017 02:11:33 +0800 Subject: [PATCH 0612/1507] net-next/hinic: Fix a case of Tx Queue is Stopped forever Fix the following scenario: 1. tx_free_poll is running on cpu X 2. xmit function is running on cpu Y and fails to get sq wqe 3. tx_free_poll frees wqes on cpu X and checks the queue is not stopped 4. xmit function stops the queue after failed to get sq wqe 5. The queue is stopped forever Signed-off-by: Aviad Krawczyk Signed-off-by: David S. Miller --- drivers/net/ethernet/huawei/hinic/hinic_tx.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index abe3e38cd3423..9128858479c4a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -212,10 +212,19 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx); if (!sq_wqe) { - tx_unmap_skb(nic_dev, skb, txq->sges); - netif_stop_subqueue(netdev, qp->q_id); + /* Check for the case free_tx_poll is called in another cpu + * and we stopped the subqueue after free_tx_poll check. + */ + sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx); + if (sq_wqe) { + netif_wake_subqueue(nic_dev->netdev, qp->q_id); + goto process_sq_wqe; + } + + tx_unmap_skb(nic_dev, skb, txq->sges); + u64_stats_update_begin(&txq->txq_stats.syncp); txq->txq_stats.tx_busy++; u64_stats_update_end(&txq->txq_stats.syncp); @@ -223,6 +232,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) goto flush_skbs; } +process_sq_wqe: hinic_sq_prepare_wqe(txq->sq, prod_idx, sq_wqe, txq->sges, nr_sges); hinic_sq_write_wqe(txq->sq, prod_idx, sq_wqe, skb, wqe_size); -- GitLab From b32ca44a88def4bf92626d8777494c6f14638c42 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 26 Sep 2017 14:57:21 -0400 Subject: [PATCH 0613/1507] net: dsa: mv88e6xxx: lock mutex when freeing IRQs mv88e6xxx_g2_irq_free locks the registers mutex, but not mv88e6xxx_g1_irq_free, which results in a stack trace from assert_reg_lock when unloading the mv88e6xxx module. Fix this. Fixes: 3460a5770ce9 ("net: dsa: mv88e6xxx: Mask g1 interrupts and free interrupt") Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 674dab71d71c1..d74c7335c512d 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3951,7 +3951,9 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->irq > 0) { if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); + mutex_lock(&chip->reg_lock); mv88e6xxx_g1_irq_free(chip); + mutex_unlock(&chip->reg_lock); } } -- GitLab From 6ade97da601f8af793f6c7a861af754d0f0b6767 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 26 Sep 2017 23:12:28 +0300 Subject: [PATCH 0614/1507] arp: make arp_hdr_len() return unsigned int Negative ARP header length are not a thing. Constify arguments while I'm at it. Space savings: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-3 (-3) function old new delta arpt_do_table 1163 1160 -3 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- include/linux/if_arp.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c99dc59d729b3..d2e94b8559f0f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2491,7 +2491,8 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; - int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); + int is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); + unsigned int alen; if (!slave_do_arp_validate(bond, slave)) { if ((slave_do_arp_validate_only(bond) && is_arp) || diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 3355efc897816..6756fea18b69f 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -31,7 +31,7 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb) return (struct arphdr *)skb_network_header(skb); } -static inline int arp_hdr_len(struct net_device *dev) +static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) -- GitLab From 9d538fa60bad4f7b23193c89e843797a1cf71ef3 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Tue, 26 Sep 2017 17:38:50 -0700 Subject: [PATCH 0615/1507] net: Set sk_prot_creator when cloning sockets to the right proto sk->sk_prot and sk->sk_prot_creator can differ when the app uses IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one). Which is why sk_prot_creator is there to make sure that sk_prot_free() does the kmem_cache_free() on the right kmem_cache slab. Now, if such a socket gets transformed back to a listening socket (using connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through sk_clone_lock() when a new connection comes in. But sk_prot_creator will still point to the IPv6 kmem_cache (as everything got copied in sk_clone_lock()). When freeing, we will thus put this memory back into the IPv6 kmem_cache although it was allocated in the IPv4 cache. I have seen memory corruption happening because of this. With slub-debugging and MEMCG_KMEM enabled this gives the warning "cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP" A C-program to trigger this: void main(void) { int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP); int new_fd, newest_fd, client_fd; struct sockaddr_in6 bind_addr; struct sockaddr_in bind_addr4, client_addr1, client_addr2; struct sockaddr unsp; int val; memset(&bind_addr, 0, sizeof(bind_addr)); bind_addr.sin6_family = AF_INET6; bind_addr.sin6_port = ntohs(42424); memset(&client_addr1, 0, sizeof(client_addr1)); client_addr1.sin_family = AF_INET; client_addr1.sin_port = ntohs(42424); client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&client_addr2, 0, sizeof(client_addr2)); client_addr2.sin_family = AF_INET; client_addr2.sin_port = ntohs(42421); client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&unsp, 0, sizeof(unsp)); unsp.sa_family = AF_UNSPEC; bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr)); listen(fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1)); new_fd = accept(fd, NULL, NULL); close(fd); val = AF_INET; setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val)); connect(new_fd, &unsp, sizeof(unsp)); memset(&bind_addr4, 0, sizeof(bind_addr4)); bind_addr4.sin_family = AF_INET; bind_addr4.sin_port = ntohs(42421); bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4)); listen(new_fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2)); newest_fd = accept(new_fd, NULL, NULL); close(new_fd); close(client_fd); close(new_fd); } As far as I can see, this bug has been there since the beginning of the git-days. Signed-off-by: Christoph Paasch Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/sock.c b/net/core/sock.c index 9b7b6bbb2a23e..7d55c05f449d3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1654,6 +1654,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); + newsk->sk_prot_creator = sk->sk_prot; + /* SANITY */ if (likely(newsk->sk_net_refcnt)) get_net(sock_net(newsk)); -- GitLab From 9ffe79a9c2eec0f30687c2fd8b452bda5c8287b0 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:23 +0800 Subject: [PATCH 0616/1507] net: hns3: Support for dynamically assigning tx buffer to TC This patch add support of dynamically assigning tx buffer to TC when the TC is enabled. It will save buffer for rx direction to avoid packet loss. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.h | 1 + .../hisilicon/hns3/hns3pf/hclge_main.c | 64 ++++++++++++++++--- 2 files changed, 55 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 758cf39481312..a81c6cb93ed57 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -311,6 +311,7 @@ struct hclge_tc_thrd { struct hclge_priv_buf { struct hclge_waterline wl; /* Waterline for low and high*/ u32 buf_size; /* TC private buffer size */ + u32 tx_buf_size; u32 enable; /* Enable TC private buffer or not */ }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e0685e630afec..eaa3fc355568b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1324,7 +1324,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) return 0; } -static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size) +static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev) { /* TX buffer size is unit by 128 byte */ #define HCLGE_BUF_SIZE_UNIT_SHIFT 7 @@ -1337,10 +1337,13 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size) req = (struct hclge_tx_buff_alloc *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); - for (i = 0; i < HCLGE_TC_NUM; i++) + for (i = 0; i < HCLGE_TC_NUM; i++) { + u32 buf_size = hdev->priv_buf[i].tx_buf_size; + req->tx_pkt_buff[i] = cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) | HCLGE_BUF_SIZE_UPDATE_EN_MSK); + } ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -1352,9 +1355,9 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size) return 0; } -static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, u32 buf_size) +static int hclge_tx_buffer_alloc(struct hclge_dev *hdev) { - int ret = hclge_cmd_alloc_tx_buff(hdev, buf_size); + int ret = hclge_cmd_alloc_tx_buff(hdev); if (ret) { dev_err(&hdev->pdev->dev, @@ -1433,6 +1436,16 @@ static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev) return rx_priv; } +static u32 hclge_get_tx_buff_alloced(struct hclge_dev *hdev) +{ + u32 i, total_tx_size = 0; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) + total_tx_size += hdev->priv_buf[i].tx_buf_size; + + return total_tx_size; +} + static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) { u32 shared_buf_min, shared_buf_tc, shared_std; @@ -1477,18 +1490,43 @@ static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) return true; } +static int hclge_tx_buffer_calc(struct hclge_dev *hdev) +{ + u32 i, total_size; + + total_size = hdev->pkt_buf_size; + + /* alloc tx buffer for all enabled tc */ + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + struct hclge_priv_buf *priv = &hdev->priv_buf[i]; + + if (total_size < HCLGE_DEFAULT_TX_BUF) + return -ENOMEM; + + if (hdev->hw_tc_map & BIT(i)) + priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF; + else + priv->tx_buf_size = 0; + + total_size -= priv->tx_buf_size; + } + + return 0; +} + /* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs * @hdev: pointer to struct hclge_dev - * @tx_size: the allocated tx buffer for all TCs * @return: 0: calculate sucessful, negative: fail */ -int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size) +int hclge_rx_buffer_calc(struct hclge_dev *hdev) { - u32 rx_all = hdev->pkt_buf_size - tx_size; + u32 rx_all = hdev->pkt_buf_size; int no_pfc_priv_num, pfc_priv_num; struct hclge_priv_buf *priv; int i; + rx_all -= hclge_get_tx_buff_alloced(hdev); + /* When DCB is not supported, rx private * buffer is not allocated. */ @@ -1771,7 +1809,6 @@ static int hclge_common_wl_config(struct hclge_dev *hdev) int hclge_buffer_alloc(struct hclge_dev *hdev) { - u32 tx_buf_size = HCLGE_DEFAULT_TX_BUF; int ret; hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM, @@ -1780,14 +1817,21 @@ int hclge_buffer_alloc(struct hclge_dev *hdev) if (!hdev->priv_buf) return -ENOMEM; - ret = hclge_tx_buffer_alloc(hdev, tx_buf_size); + ret = hclge_tx_buffer_calc(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not calc tx buffer size for all TCs %d\n", ret); + return ret; + } + + ret = hclge_tx_buffer_alloc(hdev); if (ret) { dev_err(&hdev->pdev->dev, "could not alloc tx buffers %d\n", ret); return ret; } - ret = hclge_rx_buffer_calc(hdev, tx_buf_size); + ret = hclge_rx_buffer_calc(hdev); if (ret) { dev_err(&hdev->pdev->dev, "could not calc rx priv buffer size for all TCs %d\n", -- GitLab From acf61ecd44feae2a78c13d0d7cb8e386741c5cf0 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:24 +0800 Subject: [PATCH 0617/1507] net: hns3: Add support for dynamically buffer reallocation Current buffer allocation can only happen at init, when doing buffer reallocation after init, care must be taken care of memory which priv_buf points to. This patch fixes it by using a dynamic allocated temporary memory. Because we only do buffer reallocation at init or when setting up the DCB parameter, and priv_buf is only used at buffer allocation process, so it is ok to use a dynamic allocated temporary memory. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.h | 5 + .../hisilicon/hns3/hns3pf/hclge_main.c | 150 ++++++++++-------- .../hisilicon/hns3/hns3pf/hclge_main.h | 2 - 3 files changed, 87 insertions(+), 70 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index a81c6cb93ed57..6b6d28eff664a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -322,6 +322,11 @@ struct hclge_shared_buf { u32 buf_size; }; +struct hclge_pkt_buf_alloc { + struct hclge_priv_buf priv_buf[HCLGE_MAX_TC_NUM]; + struct hclge_shared_buf s_buf; +}; + #define HCLGE_RX_COM_WL_EN_B 15 struct hclge_rx_com_wl_buf { __le16 high_wl; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index eaa3fc355568b..61632feb8c4ea 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1324,7 +1324,8 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) return 0; } -static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev) +static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { /* TX buffer size is unit by 128 byte */ #define HCLGE_BUF_SIZE_UNIT_SHIFT 7 @@ -1338,7 +1339,7 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev) hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); for (i = 0; i < HCLGE_TC_NUM; i++) { - u32 buf_size = hdev->priv_buf[i].tx_buf_size; + u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size; req->tx_pkt_buff[i] = cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) | @@ -1355,9 +1356,10 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev) return 0; } -static int hclge_tx_buffer_alloc(struct hclge_dev *hdev) +static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { - int ret = hclge_cmd_alloc_tx_buff(hdev); + int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc); if (ret) { dev_err(&hdev->pdev->dev, @@ -1390,13 +1392,14 @@ static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev) } /* Get the number of pfc enabled TCs, which have private buffer */ -static int hclge_get_pfc_priv_num(struct hclge_dev *hdev) +static int hclge_get_pfc_priv_num(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { struct hclge_priv_buf *priv; int i, cnt = 0; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if ((hdev->tm_info.hw_pfc_map & BIT(i)) && priv->enable) cnt++; @@ -1406,13 +1409,14 @@ static int hclge_get_pfc_priv_num(struct hclge_dev *hdev) } /* Get the number of pfc disabled TCs, which have private buffer */ -static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev) +static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { struct hclge_priv_buf *priv; int i, cnt = 0; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i) && !(hdev->tm_info.hw_pfc_map & BIT(i)) && priv->enable) @@ -1422,31 +1426,33 @@ static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev) return cnt; } -static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev) +static u32 hclge_get_rx_priv_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc) { struct hclge_priv_buf *priv; u32 rx_priv = 0; int i; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if (priv->enable) rx_priv += priv->buf_size; } return rx_priv; } -static u32 hclge_get_tx_buff_alloced(struct hclge_dev *hdev) +static u32 hclge_get_tx_buff_alloced(struct hclge_pkt_buf_alloc *buf_alloc) { u32 i, total_tx_size = 0; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) - total_tx_size += hdev->priv_buf[i].tx_buf_size; + total_tx_size += buf_alloc->priv_buf[i].tx_buf_size; return total_tx_size; } -static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) +static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc, + u32 rx_all) { u32 shared_buf_min, shared_buf_tc, shared_std; int tc_num, pfc_enable_num; @@ -1467,30 +1473,31 @@ static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) hdev->mps; shared_std = max_t(u32, shared_buf_min, shared_buf_tc); - rx_priv = hclge_get_rx_priv_buff_alloced(hdev); + rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc); if (rx_all <= rx_priv + shared_std) return false; shared_buf = rx_all - rx_priv; - hdev->s_buf.buf_size = shared_buf; - hdev->s_buf.self.high = shared_buf; - hdev->s_buf.self.low = 2 * hdev->mps; + buf_alloc->s_buf.buf_size = shared_buf; + buf_alloc->s_buf.self.high = shared_buf; + buf_alloc->s_buf.self.low = 2 * hdev->mps; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { if ((hdev->hw_tc_map & BIT(i)) && (hdev->tm_info.hw_pfc_map & BIT(i))) { - hdev->s_buf.tc_thrd[i].low = hdev->mps; - hdev->s_buf.tc_thrd[i].high = 2 * hdev->mps; + buf_alloc->s_buf.tc_thrd[i].low = hdev->mps; + buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps; } else { - hdev->s_buf.tc_thrd[i].low = 0; - hdev->s_buf.tc_thrd[i].high = hdev->mps; + buf_alloc->s_buf.tc_thrd[i].low = 0; + buf_alloc->s_buf.tc_thrd[i].high = hdev->mps; } } return true; } -static int hclge_tx_buffer_calc(struct hclge_dev *hdev) +static int hclge_tx_buffer_calc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { u32 i, total_size; @@ -1498,7 +1505,7 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev) /* alloc tx buffer for all enabled tc */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - struct hclge_priv_buf *priv = &hdev->priv_buf[i]; + struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; if (total_size < HCLGE_DEFAULT_TX_BUF) return -ENOMEM; @@ -1516,22 +1523,24 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev) /* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs * @hdev: pointer to struct hclge_dev + * @buf_alloc: pointer to buffer calculation data * @return: 0: calculate sucessful, negative: fail */ -int hclge_rx_buffer_calc(struct hclge_dev *hdev) +int hclge_rx_buffer_calc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { u32 rx_all = hdev->pkt_buf_size; int no_pfc_priv_num, pfc_priv_num; struct hclge_priv_buf *priv; int i; - rx_all -= hclge_get_tx_buff_alloced(hdev); + rx_all -= hclge_get_tx_buff_alloced(buf_alloc); /* When DCB is not supported, rx private * buffer is not allocated. */ if (!hnae3_dev_dcb_supported(hdev)) { - if (!hclge_is_rx_buf_ok(hdev, rx_all)) + if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) return -ENOMEM; return 0; @@ -1539,7 +1548,7 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev) /* step 1, try to alloc private buffer for all enabled tc */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i)) { priv->enable = 1; if (hdev->tm_info.hw_pfc_map & BIT(i)) { @@ -1560,14 +1569,14 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev) } } - if (hclge_is_rx_buf_ok(hdev, rx_all)) + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) return 0; /* step 2, try to decrease the buffer size of * no pfc TC's private buffer */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; priv->enable = 0; priv->wl.low = 0; @@ -1590,18 +1599,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev) } } - if (hclge_is_rx_buf_ok(hdev, rx_all)) + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) return 0; /* step 3, try to reduce the number of pfc disabled TCs, * which have private buffer */ /* get the total no pfc enable TC number, which have private buffer */ - no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev); + no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc); /* let the last to be cleared first */ for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i) && !(hdev->tm_info.hw_pfc_map & BIT(i))) { @@ -1613,22 +1622,22 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev) no_pfc_priv_num--; } - if (hclge_is_rx_buf_ok(hdev, rx_all) || + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) || no_pfc_priv_num == 0) break; } - if (hclge_is_rx_buf_ok(hdev, rx_all)) + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) return 0; /* step 4, try to reduce the number of pfc enabled TCs * which have private buffer. */ - pfc_priv_num = hclge_get_pfc_priv_num(hdev); + pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc); /* let the last to be cleared first */ for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { - priv = &hdev->priv_buf[i]; + priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i) && hdev->tm_info.hw_pfc_map & BIT(i)) { @@ -1640,17 +1649,18 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev) pfc_priv_num--; } - if (hclge_is_rx_buf_ok(hdev, rx_all) || + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all) || pfc_priv_num == 0) break; } - if (hclge_is_rx_buf_ok(hdev, rx_all)) + if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) return 0; return -ENOMEM; } -static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) +static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { struct hclge_rx_priv_buff *req; struct hclge_desc desc; @@ -1662,7 +1672,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) /* Alloc private buffer TCs */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - struct hclge_priv_buf *priv = &hdev->priv_buf[i]; + struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; req->buf_num[i] = cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S); @@ -1671,7 +1681,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) } req->shared_buf = - cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) | + cpu_to_le16((buf_alloc->s_buf.buf_size >> HCLGE_BUF_UNIT_S) | (1 << HCLGE_TC0_PRI_BUF_EN_B)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -1686,7 +1696,8 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) #define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0) -static int hclge_rx_priv_wl_config(struct hclge_dev *hdev) +static int hclge_rx_priv_wl_config(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { struct hclge_rx_priv_wl_buf *req; struct hclge_priv_buf *priv; @@ -1706,7 +1717,9 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev) desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT); for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) { - priv = &hdev->priv_buf[i * HCLGE_TC_NUM_ONE_DESC + j]; + u32 idx = i * HCLGE_TC_NUM_ONE_DESC + j; + + priv = &buf_alloc->priv_buf[idx]; req->tc_wl[j].high = cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S); req->tc_wl[j].high |= @@ -1731,9 +1744,10 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev) return 0; } -static int hclge_common_thrd_config(struct hclge_dev *hdev) +static int hclge_common_thrd_config(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { - struct hclge_shared_buf *s_buf = &hdev->s_buf; + struct hclge_shared_buf *s_buf = &buf_alloc->s_buf; struct hclge_rx_com_thrd *req; struct hclge_desc desc[2]; struct hclge_tc_thrd *tc; @@ -1777,9 +1791,10 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev) return 0; } -static int hclge_common_wl_config(struct hclge_dev *hdev) +static int hclge_common_wl_config(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { - struct hclge_shared_buf *buf = &hdev->s_buf; + struct hclge_shared_buf *buf = &buf_alloc->s_buf; struct hclge_rx_com_wl *req; struct hclge_desc desc; int ret; @@ -1809,69 +1824,68 @@ static int hclge_common_wl_config(struct hclge_dev *hdev) int hclge_buffer_alloc(struct hclge_dev *hdev) { + struct hclge_pkt_buf_alloc *pkt_buf; int ret; - hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM, - sizeof(struct hclge_priv_buf), - GFP_KERNEL | __GFP_ZERO); - if (!hdev->priv_buf) + pkt_buf = kzalloc(sizeof(*pkt_buf), GFP_KERNEL); + if (!pkt_buf) return -ENOMEM; - ret = hclge_tx_buffer_calc(hdev); + ret = hclge_tx_buffer_calc(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not calc tx buffer size for all TCs %d\n", ret); - return ret; + goto out; } - ret = hclge_tx_buffer_alloc(hdev); + ret = hclge_tx_buffer_alloc(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not alloc tx buffers %d\n", ret); - return ret; + goto out; } - ret = hclge_rx_buffer_calc(hdev); + ret = hclge_rx_buffer_calc(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not calc rx priv buffer size for all TCs %d\n", ret); - return ret; + goto out; } - ret = hclge_rx_priv_buf_alloc(hdev); + ret = hclge_rx_priv_buf_alloc(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not alloc rx priv buffer %d\n", ret); - return ret; + goto out; } if (hnae3_dev_dcb_supported(hdev)) { - ret = hclge_rx_priv_wl_config(hdev); + ret = hclge_rx_priv_wl_config(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not configure rx private waterline %d\n", ret); - return ret; + goto out; } - ret = hclge_common_thrd_config(hdev); + ret = hclge_common_thrd_config(hdev, pkt_buf); if (ret) { dev_err(&hdev->pdev->dev, "could not configure common threshold %d\n", ret); - return ret; + goto out; } } - ret = hclge_common_wl_config(hdev); - if (ret) { + ret = hclge_common_wl_config(hdev, pkt_buf); + if (ret) dev_err(&hdev->pdev->dev, "could not configure common waterline %d\n", ret); - return ret; - } - return 0; +out: + kfree(pkt_buf); + return ret; } static int hclge_init_roce_base_info(struct hclge_vport *vport) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 9fcfd93954245..4fc36f04c9712 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -463,8 +463,6 @@ struct hclge_dev { u32 pkt_buf_size; /* Total pf buf size for tx/rx */ u32 mps; /* Max packet size */ - struct hclge_priv_buf *priv_buf; - struct hclge_shared_buf s_buf; enum hclge_mta_dmac_sel_type mta_mac_sel_type; bool enable_mta; /* Mutilcast filter enable */ -- GitLab From 9dc2145d910e94d1987fd165ac7643777fcf17c4 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:25 +0800 Subject: [PATCH 0618/1507] net: hns3: Add support for PFC setting in TM module This patch add a pfc_pause_en cmd, and use it to configure PFC option according to fc_mode in hdev->tm_info. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 68 +++++++++++++++++-- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 5 ++ 2 files changed, 68 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 73a75d7cc5517..0b4b5d9b07982 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -124,6 +124,20 @@ static int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } +static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) +{ + struct hclge_desc desc; + struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false); + + pfc->tx_rx_en_bitmap = tx_rx_bitmap; + pfc->pri_en_bitmap = pfc_bitmap; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id) { u8 tc; @@ -969,20 +983,64 @@ static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev) return hclge_tm_schd_mode_hw(hdev); } +static int hclge_pfc_setup_hw(struct hclge_dev *hdev) +{ + u8 enable_bitmap = 0; + + if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) + enable_bitmap = HCLGE_TX_MAC_PAUSE_EN_MSK | + HCLGE_RX_MAC_PAUSE_EN_MSK; + + return hclge_pfc_pause_en_cfg(hdev, enable_bitmap, + hdev->tm_info.hw_pfc_map); +} + +static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) +{ + bool tx_en, rx_en; + + switch (hdev->tm_info.fc_mode) { + case HCLGE_FC_NONE: + tx_en = false; + rx_en = false; + break; + case HCLGE_FC_RX_PAUSE: + tx_en = false; + rx_en = true; + break; + case HCLGE_FC_TX_PAUSE: + tx_en = true; + rx_en = false; + break; + case HCLGE_FC_FULL: + tx_en = true; + rx_en = true; + break; + default: + tx_en = true; + rx_en = true; + } + + return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en); +} + int hclge_pause_setup_hw(struct hclge_dev *hdev) { - bool en = hdev->tm_info.fc_mode != HCLGE_FC_PFC; int ret; u8 i; - ret = hclge_mac_pause_en_cfg(hdev, en, en); - if (ret) - return ret; + if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) + return hclge_mac_pause_setup_hw(hdev); - /* Only DCB-supported dev supports qset back pressure setting */ + /* Only DCB-supported dev supports qset back pressure and pfc cmd */ if (!hnae3_dev_dcb_supported(hdev)) return 0; + /* When MAC is GE Mode, hdev does not support pfc setting */ + ret = hclge_pfc_setup_hw(hdev); + if (ret) + dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret); + for (i = 0; i < hdev->tm_info.num_tc; i++) { ret = hclge_tm_qs_bp_cfg(hdev, i); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 85158b0d73fe3..8ecd83c50f47f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -94,6 +94,11 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +struct hclge_pfc_en_cmd { + u8 tx_rx_en_bitmap; + u8 pri_en_bitmap; +}; + #define hclge_tm_set_field(dest, string, val) \ hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \ (HCLGE_TM_SHAP_##string##_LSH), val) -- GitLab From 0a5677d39ef12739c9c10ef6e8e5f4b0805bfe71 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:26 +0800 Subject: [PATCH 0619/1507] net: hns3: Add support for port shaper setting in TM module This patch add a tm_port_shaper cmd and set port shaper to HCLGE_ETHER_MAX_RATE on TM initialization process. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 32 +++++++++++++++++++ .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 4 +++ 2 files changed, 36 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 0b4b5d9b07982..f79cebd7c95b8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -301,6 +301,34 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, return hclge_cmd_send(&hdev->hw, &desc, 1); } +static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev) +{ + struct hclge_port_shapping_cmd *shap_cfg_cmd; + struct hclge_desc desc; + u32 shapping_para = 0; + u8 ir_u, ir_b, ir_s; + int ret; + + ret = hclge_shaper_para_calc(HCLGE_ETHER_MAX_RATE, + HCLGE_SHAPER_LVL_PORT, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false); + shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data; + + hclge_tm_set_field(shapping_para, IR_B, ir_b); + hclge_tm_set_field(shapping_para, IR_U, ir_u); + hclge_tm_set_field(shapping_para, IR_S, ir_s); + hclge_tm_set_field(shapping_para, BS_B, HCLGE_SHAPER_BS_U_DEF); + hclge_tm_set_field(shapping_para, BS_S, HCLGE_SHAPER_BS_S_DEF); + + shap_cfg_cmd->port_shapping_para = cpu_to_le32(shapping_para); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, enum hclge_shap_bucket bucket, u8 pri_id, u8 ir_b, u8 ir_u, u8 ir_s, @@ -864,6 +892,10 @@ static int hclge_tm_shaper_cfg(struct hclge_dev *hdev) { int ret; + ret = hclge_tm_port_shaper_cfg(hdev); + if (ret) + return ret; + ret = hclge_tm_pg_shaper_cfg(hdev); if (ret) return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 8ecd83c50f47f..19a01e41c8b07 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -99,6 +99,10 @@ struct hclge_pfc_en_cmd { u8 pri_en_bitmap; }; +struct hclge_port_shapping_cmd { + __le32 port_shapping_para; +}; + #define hclge_tm_set_field(dest, string, val) \ hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \ (HCLGE_TM_SHAP_##string##_LSH), val) -- GitLab From cc9bb43ab394f14096a55ee6101af0e804c05f0f Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:27 +0800 Subject: [PATCH 0620/1507] net: hns3: Add tc-based TM support for sriov enabled port When sriov is enabled and TM is in tc-based mode, vf's TM parameters is not set in TM initialization process. This patch add the tc_based TM support for sriov enabled using the information in vport struct. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 49 ++++++++++++------- 1 file changed, 31 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index f79cebd7c95b8..ea94d23a79f71 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -388,13 +388,13 @@ static int hclge_tm_pri_schd_mode_cfg(struct hclge_dev *hdev, u8 pri_id) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id) +static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id, u8 mode) { struct hclge_desc desc; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, false); - if (hdev->tm_info.tc_info[qs_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR) + if (mode == HCLGE_SCH_MODE_DWRR) desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK); else desc.data[1] = 0; @@ -638,17 +638,18 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev) { struct hclge_vport *vport = hdev->vport; int ret; - u32 i; + u32 i, k; if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { /* Cfg qs -> pri mapping, one by one mapping */ - for (i = 0; i < hdev->tm_info.num_tc; i++) { - ret = hclge_tm_qs_to_pri_map_cfg(hdev, i, i); - if (ret) - return ret; - } + for (k = 0; k < hdev->num_alloc_vport; k++) + for (i = 0; i < hdev->tm_info.num_tc; i++) { + ret = hclge_tm_qs_to_pri_map_cfg( + hdev, vport[k].qs_offset + i, i); + if (ret) + return ret; + } } else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) { - int k; /* Cfg qs -> pri mapping, qs = tc, pri = vf, 8 qs -> 1 pri */ for (k = 0; k < hdev->num_alloc_vport; k++) for (i = 0; i < HNAE3_MAX_TC; i++) { @@ -797,10 +798,11 @@ static int hclge_tm_pri_shaper_cfg(struct hclge_dev *hdev) static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev) { + struct hclge_vport *vport = hdev->vport; struct hclge_pg_info *pg_info; u8 dwrr; int ret; - u32 i; + u32 i, k; for (i = 0; i < hdev->tm_info.num_tc; i++) { pg_info = @@ -811,9 +813,13 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev) if (ret) return ret; - ret = hclge_tm_qs_weight_cfg(hdev, i, dwrr); - if (ret) - return ret; + for (k = 0; k < hdev->num_alloc_vport; k++) { + ret = hclge_tm_qs_weight_cfg( + hdev, vport[k].qs_offset + i, + vport[k].dwrr); + if (ret) + return ret; + } } return 0; @@ -944,7 +950,10 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport) return ret; for (i = 0; i < kinfo->num_tc; i++) { - ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i); + u8 sch_mode = hdev->tm_info.tc_info[i].tc_sch_mode; + + ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i, + sch_mode); if (ret) return ret; } @@ -956,7 +965,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev) { struct hclge_vport *vport = hdev->vport; int ret; - u8 i; + u8 i, k; if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { for (i = 0; i < hdev->tm_info.num_tc; i++) { @@ -964,9 +973,13 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev) if (ret) return ret; - ret = hclge_tm_qs_schd_mode_cfg(hdev, i); - if (ret) - return ret; + for (k = 0; k < hdev->num_alloc_vport; k++) { + ret = hclge_tm_qs_schd_mode_cfg( + hdev, vport[k].qs_offset + i, + HCLGE_SCH_MODE_DWRR); + if (ret) + return ret; + } } } else { for (i = 0; i < hdev->num_alloc_vport; i++) { -- GitLab From 77f255c1c695c72acb1d1c47d30323a273774ae6 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:28 +0800 Subject: [PATCH 0621/1507] net: hns3: Add some interface for the support of DCB feature This patch add some interface and export some interface from hclge_tm and hclgc_main to support the upcoming DCB feature. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_main.c | 3 +- .../hisilicon/hns3/hns3pf/hclge_main.h | 3 ++ .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 48 +++++++++++++++++-- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 6 +++ 4 files changed, 55 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 61632feb8c4ea..644f7ff540816 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -30,7 +30,6 @@ #define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f)) #define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f)) -static int hclge_rss_init_hw(struct hclge_dev *hdev); static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, enum hclge_mta_dmac_sel_type mta_mac_sel, bool enable); @@ -2655,7 +2654,7 @@ static int hclge_get_tc_size(struct hnae3_handle *handle) return hdev->rss_size_max; } -static int hclge_rss_init_hw(struct hclge_dev *hdev) +int hclge_rss_init_hw(struct hclge_dev *hdev) { const u8 hfunc = HCLGE_RSS_HASH_ALGO_TOEPLITZ; struct hclge_vport *vport = hdev->vport; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 4fc36f04c9712..394b587880659 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -515,4 +515,7 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue) int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex); int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid, bool is_kill, u16 vlan, u8 qos, __be16 proto); + +int hclge_buffer_alloc(struct hclge_dev *hdev); +int hclge_rss_init_hw(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index ea94d23a79f71..8295684da5baf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -883,10 +883,14 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev) return 0; } -static int hclge_tm_map_cfg(struct hclge_dev *hdev) +int hclge_tm_map_cfg(struct hclge_dev *hdev) { int ret; + ret = hclge_up_to_tc_map(hdev); + if (ret) + return ret; + ret = hclge_tm_pg_to_pri_map(hdev); if (ret) return ret; @@ -994,7 +998,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev) return 0; } -static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev) +int hclge_tm_schd_mode_hw(struct hclge_dev *hdev) { int ret; @@ -1092,7 +1096,45 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev) return ret; } - return hclge_up_to_tc_map(hdev); + return 0; +} + +int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc) +{ + struct hclge_vport *vport = hdev->vport; + struct hnae3_knic_private_info *kinfo; + u32 i, k; + + for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) { + if (prio_tc[i] >= hdev->tm_info.num_tc) + return -EINVAL; + hdev->tm_info.prio_tc[i] = prio_tc[i]; + + for (k = 0; k < hdev->num_alloc_vport; k++) { + kinfo = &vport[k].nic.kinfo; + kinfo->prio_tc[i] = prio_tc[i]; + } + } + return 0; +} + +void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc) +{ + u8 i, bit_map = 0; + + hdev->tm_info.num_tc = num_tc; + + for (i = 0; i < hdev->tm_info.num_tc; i++) + bit_map |= BIT(i); + + if (!bit_map) { + bit_map = 1; + hdev->tm_info.num_tc = 1; + } + + hdev->hw_tc_map = bit_map; + + hclge_tm_schd_info_init(hdev); } int hclge_tm_init_hw(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 19a01e41c8b07..bf59961918ab5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -112,4 +112,10 @@ struct hclge_port_shapping_cmd { int hclge_tm_schd_init(struct hclge_dev *hdev); int hclge_pause_setup_hw(struct hclge_dev *hdev); +int hclge_tm_schd_mode_hw(struct hclge_dev *hdev); +int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc); +void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); +int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); +int hclge_tm_map_cfg(struct hclge_dev *hdev); +int hclge_tm_init_hw(struct hclge_dev *hdev); #endif -- GitLab From cacde272dd00496c2c1c36606a56b340cd967603 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:29 +0800 Subject: [PATCH 0622/1507] net: hns3: Add hclge_dcb module for the support of DCB feature The hclge_dcb module calls the interface from hclge_main/tm and provide interface for the dcb netlink interface. This patch also update Makefiles required to build the DCB supported code in HNS3 Ethernet driver and update the existing Kconfig file in the hisilicon folder. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/Kconfig | 9 + drivers/net/ethernet/hisilicon/hns3/hnae3.h | 17 + .../ethernet/hisilicon/hns3/hns3pf/Makefile | 2 + .../hisilicon/hns3/hns3pf/hclge_dcb.c | 304 ++++++++++++++++++ .../hisilicon/hns3/hns3pf/hclge_dcb.h | 21 ++ .../hisilicon/hns3/hns3pf/hclge_main.c | 25 +- .../hisilicon/hns3/hns3pf/hclge_main.h | 3 + 7 files changed, 375 insertions(+), 6 deletions(-) create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 91c7bdb9b43cc..9d7cb0387bf70 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -103,4 +103,13 @@ config HNS3_ENET family of SoCs. This module depends upon HNAE3 driver to access the HNAE3 devices and their associated operations. +config HNS3_DCB + bool "Hisilicon HNS3 Data Center Bridge Support" + default n + depends on HNS3 && HNS3_HCLGE && DCB + ---help--- + Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver. + + If unsure, say N. + endif # NET_VENDOR_HISILICON diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 1a01cadfe5f30..c677530841cf6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -28,6 +28,7 @@ */ #include +#include #include #include #include @@ -131,6 +132,7 @@ struct hnae3_client_ops { int (*init_instance)(struct hnae3_handle *handle); void (*uninit_instance)(struct hnae3_handle *handle, bool reset); void (*link_status_change)(struct hnae3_handle *handle, bool state); + int (*setup_tc)(struct hnae3_handle *handle, u8 tc); }; #define HNAE3_CLIENT_NAME_LENGTH 16 @@ -363,6 +365,20 @@ struct hnae3_ae_ops { u16 vlan, u8 qos, __be16 proto); }; +struct hnae3_dcb_ops { + /* IEEE 802.1Qaz std */ + int (*ieee_getets)(struct hnae3_handle *, struct ieee_ets *); + int (*ieee_setets)(struct hnae3_handle *, struct ieee_ets *); + int (*ieee_getpfc)(struct hnae3_handle *, struct ieee_pfc *); + int (*ieee_setpfc)(struct hnae3_handle *, struct ieee_pfc *); + + /* DCBX configuration */ + u8 (*getdcbx)(struct hnae3_handle *); + u8 (*setdcbx)(struct hnae3_handle *, u8); + + int (*map_update)(struct hnae3_handle *); +}; + struct hnae3_ae_algo { const struct hnae3_ae_ops *ops; struct list_head node; @@ -394,6 +410,7 @@ struct hnae3_knic_private_info { u16 num_tqps; /* total number of TQPs in this handle */ struct hnae3_queue **tqp; /* array base of all TQPs in this instance */ + const struct hnae3_dcb_ops *dcb_ops; }; struct hnae3_roce_private_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index 162e8a42acd01..7023dc8780860 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -7,5 +7,7 @@ ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3 obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o +hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o + obj-$(CONFIG_HNS3_ENET) += hns3.o hns3-objs = hns3_enet.o hns3_ethtool.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c new file mode 100644 index 0000000000000..1b30a6f966d82 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -0,0 +1,304 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "hclge_main.h" +#include "hclge_tm.h" +#include "hnae3.h" + +#define BW_PERCENT 100 + +static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev, + struct ieee_ets *ets) +{ + u8 i; + + for (i = 0; i < HNAE3_MAX_TC; i++) { + switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_STRICT: + hdev->tm_info.tc_info[i].tc_sch_mode = + HCLGE_SCH_MODE_SP; + hdev->tm_info.pg_info[0].tc_dwrr[i] = 0; + break; + case IEEE_8021QAZ_TSA_ETS: + hdev->tm_info.tc_info[i].tc_sch_mode = + HCLGE_SCH_MODE_DWRR; + hdev->tm_info.pg_info[0].tc_dwrr[i] = + ets->tc_tx_bw[i]; + break; + default: + /* Hardware only supports SP (strict priority) + * or ETS (enhanced transmission selection) + * algorithms, if we receive some other value + * from dcbnl, then throw an error. + */ + return -EINVAL; + } + } + + return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc); +} + +static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev, + struct ieee_ets *ets) +{ + u32 i; + + memset(ets, 0, sizeof(*ets)); + ets->willing = 1; + ets->ets_cap = hdev->tc_max; + + for (i = 0; i < HNAE3_MAX_TC; i++) { + ets->prio_tc[i] = hdev->tm_info.prio_tc[i]; + ets->tc_tx_bw[i] = hdev->tm_info.pg_info[0].tc_dwrr[i]; + + if (hdev->tm_info.tc_info[i].tc_sch_mode == + HCLGE_SCH_MODE_SP) + ets->tc_tsa[i] = IEEE_8021QAZ_TSA_STRICT; + else + ets->tc_tsa[i] = IEEE_8021QAZ_TSA_ETS; + } +} + +/* IEEE std */ +static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + + hclge_tm_info_to_ieee_ets(hdev, ets); + + return 0; +} + +static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets, + u8 *tc, bool *changed) +{ + u32 total_ets_bw = 0; + u8 max_tc = 0; + u8 i; + + for (i = 0; i < HNAE3_MAX_TC; i++) { + if (ets->prio_tc[i] >= hdev->tc_max || + i >= hdev->tc_max) + return -EINVAL; + + if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i]) + *changed = true; + + if (ets->prio_tc[i] > max_tc) + max_tc = ets->prio_tc[i]; + + switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_STRICT: + if (hdev->tm_info.tc_info[i].tc_sch_mode != + HCLGE_SCH_MODE_SP) + *changed = true; + break; + case IEEE_8021QAZ_TSA_ETS: + if (hdev->tm_info.tc_info[i].tc_sch_mode != + HCLGE_SCH_MODE_DWRR) + *changed = true; + + total_ets_bw += ets->tc_tx_bw[i]; + break; + default: + return -EINVAL; + } + } + + if (total_ets_bw != BW_PERCENT) + return -EINVAL; + + *tc = max_tc + 1; + if (*tc != hdev->tm_info.num_tc) + *changed = true; + + return 0; +} + +static int hclge_map_update(struct hnae3_handle *h) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_tm_map_cfg(hdev); + if (ret) + return ret; + + ret = hclge_tm_schd_mode_hw(hdev); + if (ret) + return ret; + + ret = hclge_pause_setup_hw(hdev); + if (ret) + return ret; + + ret = hclge_buffer_alloc(hdev); + if (ret) + return ret; + + return hclge_rss_init_hw(hdev); +} + +static int hclge_client_setup_tc(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + struct hnae3_client *client; + struct hnae3_handle *handle; + int ret; + u32 i; + + for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { + handle = &vport[i].nic; + client = handle->client; + + if (!client || !client->ops || !client->ops->setup_tc) + continue; + + ret = client->ops->setup_tc(handle, hdev->tm_info.num_tc); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + bool map_changed = false; + u8 num_tc = 0; + int ret; + + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed); + if (ret) + return ret; + + hclge_tm_schd_info_update(hdev, num_tc); + + ret = hclge_ieee_ets_to_tm_info(hdev, ets); + if (ret) + return ret; + + if (map_changed) { + ret = hclge_client_setup_tc(hdev); + if (ret) + return ret; + } + + return hclge_tm_dwrr_cfg(hdev); +} + +static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + u8 i, j, pfc_map, *prio_tc; + + memset(pfc, 0, sizeof(*pfc)); + pfc->pfc_cap = hdev->pfc_max; + prio_tc = hdev->tm_info.prio_tc; + pfc_map = hdev->tm_info.hw_pfc_map; + + /* Pfc setting is based on TC */ + for (i = 0; i < hdev->tm_info.num_tc; i++) { + for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) { + if ((prio_tc[j] == i) && (pfc_map & BIT(i))) + pfc->pfc_en |= BIT(j); + } + } + + return 0; +} + +static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + u8 i, j, pfc_map, *prio_tc; + + if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + prio_tc = hdev->tm_info.prio_tc; + pfc_map = 0; + + for (i = 0; i < hdev->tm_info.num_tc; i++) { + for (j = 0; j < HNAE3_MAX_USER_PRIO; j++) { + if ((prio_tc[j] == i) && (pfc->pfc_en & BIT(j))) { + pfc_map |= BIT(i); + break; + } + } + } + + if (pfc_map == hdev->tm_info.hw_pfc_map) + return 0; + + hdev->tm_info.hw_pfc_map = pfc_map; + + return hclge_pause_setup_hw(hdev); +} + +/* DCBX configuration */ +static u8 hclge_getdcbx(struct hnae3_handle *h) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + + return hdev->dcbx_cap; +} + +static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode) +{ + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + + /* No support for LLD_MANAGED modes or CEE */ + if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || + (mode & DCB_CAP_DCBX_VER_CEE) || + !(mode & DCB_CAP_DCBX_HOST)) + return 1; + + hdev->dcbx_cap = mode; + + return 0; +} + +static const struct hnae3_dcb_ops hns3_dcb_ops = { + .ieee_getets = hclge_ieee_getets, + .ieee_setets = hclge_ieee_setets, + .ieee_getpfc = hclge_ieee_getpfc, + .ieee_setpfc = hclge_ieee_setpfc, + .getdcbx = hclge_getdcbx, + .setdcbx = hclge_setdcbx, + .map_update = hclge_map_update, +}; + +void hclge_dcb_ops_set(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + struct hnae3_knic_private_info *kinfo; + + /* Hdev does not support DCB or vport is + * not a pf, then dcb_ops is not set. + */ + if (!hnae3_dev_dcb_supported(hdev) || + vport->vport_id != 0) + return; + + kinfo = &vport->nic.kinfo; + kinfo->dcb_ops = &hns3_dcb_ops; + hdev->dcbx_cap = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_HOST; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h new file mode 100644 index 0000000000000..7d808ee96694f --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h @@ -0,0 +1,21 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HCLGE_DCB_H__ +#define __HCLGE_DCB_H__ + +#include "hclge_main.h" + +#ifdef CONFIG_HNS3_DCB +void hclge_dcb_ops_set(struct hclge_dev *hdev); +#else +static inline void hclge_dcb_ops_set(struct hclge_dev *hdev) {} +#endif + +#endif /* __HCLGE_DCB_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 644f7ff540816..dd220eab7f53c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -19,6 +19,7 @@ #include #include "hclge_cmd.h" +#include "hclge_dcb.h" #include "hclge_main.h" #include "hclge_mdio.h" #include "hclge_tm.h" @@ -1057,7 +1058,7 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->hw.mac.phy_addr = cfg.phy_addr; hdev->num_desc = cfg.tqp_desc_num; hdev->tm_info.num_pg = 1; - hdev->tm_info.num_tc = cfg.tc_num; + hdev->tc_max = cfg.tc_num; hdev->tm_info.hw_pfc_map = 0; ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed); @@ -1066,15 +1067,25 @@ static int hclge_configure(struct hclge_dev *hdev) return ret; } - if ((hdev->tm_info.num_tc > HNAE3_MAX_TC) || - (hdev->tm_info.num_tc < 1)) { + if ((hdev->tc_max > HNAE3_MAX_TC) || + (hdev->tc_max < 1)) { dev_warn(&hdev->pdev->dev, "TC num = %d.\n", - hdev->tm_info.num_tc); - hdev->tm_info.num_tc = 1; + hdev->tc_max); + hdev->tc_max = 1; } + /* Dev does not support DCB */ + if (!hnae3_dev_dcb_supported(hdev)) { + hdev->tc_max = 1; + hdev->pfc_max = 0; + } else { + hdev->pfc_max = hdev->tc_max; + } + + hdev->tm_info.num_tc = hdev->tc_max; + /* Currently not support uncontiuous tc */ - for (i = 0; i < cfg.tc_num; i++) + for (i = 0; i < hdev->tm_info.num_tc; i++) hnae_set_bit(hdev->hw_tc_map, i, 1); if (!hdev->num_vmdq_vport && !hdev->num_req_vfs) @@ -4238,6 +4249,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + hclge_dcb_ops_set(hdev); + setup_timer(&hdev->service_timer, hclge_service_timer, (unsigned long)hdev); INIT_WORK(&hdev->service_task, hclge_service_task); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 394b587880659..7c66c00e8a3ef 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -421,8 +421,11 @@ struct hclge_dev { #define HCLGE_FLAG_TC_BASE_SCH_MODE 1 #define HCLGE_FLAG_VNET_BASE_SCH_MODE 2 u8 tx_sch_mode; + u8 tc_max; + u8 pfc_max; u8 default_up; + u8 dcbx_cap; struct hclge_tm_info tm_info; u16 num_msi; -- GitLab From 986743dbf0a70211bba594b5abee33b6661feaa9 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:30 +0800 Subject: [PATCH 0623/1507] net: hns3: Add dcb netlink interface for the support of DCB feature This patch add dcb netlink interface by calling the interface from hclge_dcb module. This patch also update Makefile in order to build hns3_dcbnl module. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/Makefile | 2 + .../hisilicon/hns3/hns3pf/hns3_dcbnl.c | 106 ++++++++++++++++++ .../hisilicon/hns3/hns3pf/hns3_enet.c | 2 + .../hisilicon/hns3/hns3pf/hns3_enet.h | 7 ++ 4 files changed, 117 insertions(+) create mode 100644 drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index 7023dc8780860..d2b20d01a58c5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -11,3 +11,5 @@ hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o obj-$(CONFIG_HNS3_ENET) += hns3.o hns3-objs = hns3_enet.o hns3_ethtool.o + +hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c new file mode 100644 index 0000000000000..9832172bfb08e --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c @@ -0,0 +1,106 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "hnae3.h" +#include "hns3_enet.h" + +static +int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->ieee_getets) + return h->kinfo.dcb_ops->ieee_getets(h, ets); + + return -EOPNOTSUPP; +} + +static +int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->ieee_setets) + return h->kinfo.dcb_ops->ieee_setets(h, ets); + + return -EOPNOTSUPP; +} + +static +int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->ieee_getpfc) + return h->kinfo.dcb_ops->ieee_getpfc(h, pfc); + + return -EOPNOTSUPP; +} + +static +int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->ieee_setpfc) + return h->kinfo.dcb_ops->ieee_setpfc(h, pfc); + + return -EOPNOTSUPP; +} + +/* DCBX configuration */ +static u8 hns3_dcbnl_getdcbx(struct net_device *ndev) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->getdcbx) + return h->kinfo.dcb_ops->getdcbx(h); + + return 0; +} + +/* return 0 if successful, otherwise fail */ +static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->kinfo.dcb_ops->setdcbx) + return h->kinfo.dcb_ops->setdcbx(h, mode); + + return 1; +} + +static const struct dcbnl_rtnl_ops hns3_dcbnl_ops = { + .ieee_getets = hns3_dcbnl_ieee_getets, + .ieee_setets = hns3_dcbnl_ieee_setets, + .ieee_getpfc = hns3_dcbnl_ieee_getpfc, + .ieee_setpfc = hns3_dcbnl_ieee_setpfc, + .getdcbx = hns3_dcbnl_getdcbx, + .setdcbx = hns3_dcbnl_setdcbx, +}; + +/* hclge_dcbnl_setup - DCBNL setup + * @handle: the corresponding vport handle + * Set up DCBNL + */ +void hns3_dcbnl_setup(struct hnae3_handle *handle) +{ + struct net_device *dev = handle->kinfo.netdev; + + if (!handle->kinfo.dcb_ops) + return; + + dev->dcbnl_ops = &hns3_dcbnl_ops; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index 35369e1c8036f..11dab26f35432 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -2790,6 +2790,8 @@ static int hns3_client_init(struct hnae3_handle *handle) goto out_reg_netdev_fail; } + hns3_dcbnl_setup(handle); + /* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */ netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h index 7e87461897475..481eada73e2d8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -590,4 +590,11 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) void hns3_ethtool_set_ops(struct net_device *netdev); int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); + +#ifdef CONFIG_HNS3_DCB +void hns3_dcbnl_setup(struct hnae3_handle *handle); +#else +static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {} +#endif + #endif -- GitLab From 7979a223305016625d211dd051569933c433f81e Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:31 +0800 Subject: [PATCH 0624/1507] net: hns3: Setting for fc_mode and dcb enable flag in TM module After the DCB feature is supported, fc_mode and dcb enable flag must be set according to the DCB parameter. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 34 ++++++++++++++++--- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 8295684da5baf..359ee670d1e17 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -486,7 +486,11 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev) hdev->tm_info.prio_tc[i] = (i >= hdev->tm_info.num_tc) ? 0 : i; - hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; + /* DCB is enabled if we have more than 1 TC */ + if (hdev->tm_info.num_tc > 1) + hdev->flag |= HCLGE_FLAG_DCB_ENABLE; + else + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; } static void hclge_tm_pg_info_init(struct hclge_dev *hdev) @@ -512,6 +516,24 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev) } } +static void hclge_pfc_info_init(struct hclge_dev *hdev) +{ + if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE)) { + if (hdev->fc_mode_last_time == HCLGE_FC_PFC) + dev_warn(&hdev->pdev->dev, + "DCB is disable, but last mode is FC_PFC\n"); + + hdev->tm_info.fc_mode = hdev->fc_mode_last_time; + } else if (hdev->tm_info.fc_mode != HCLGE_FC_PFC) { + /* fc_mode_last_time record the last fc_mode when + * DCB is enabled, so that fc_mode can be set to + * the correct value when DCB is disabled. + */ + hdev->fc_mode_last_time = hdev->tm_info.fc_mode; + hdev->tm_info.fc_mode = HCLGE_FC_PFC; + } +} + static int hclge_tm_schd_info_init(struct hclge_dev *hdev) { if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) && @@ -524,8 +546,7 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev) hclge_tm_vport_info_update(hdev); - hdev->tm_info.fc_mode = HCLGE_FC_NONE; - hdev->fc_mode_last_time = hdev->tm_info.fc_mode; + hclge_pfc_info_init(hdev); return 0; } @@ -1158,8 +1179,13 @@ int hclge_tm_init_hw(struct hclge_dev *hdev) int hclge_tm_schd_init(struct hclge_dev *hdev) { - int ret = hclge_tm_schd_info_init(hdev); + int ret; + + /* fc_mode is HCLGE_FC_FULL on reset */ + hdev->tm_info.fc_mode = HCLGE_FC_FULL; + hdev->fc_mode_last_time = hdev->tm_info.fc_mode; + ret = hclge_tm_schd_info_init(hdev); if (ret) return ret; -- GitLab From 9df8f79a4d2957fa3083e8fda0843d8c010351a7 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 27 Sep 2017 09:45:32 +0800 Subject: [PATCH 0625/1507] net: hns3: Add DCB support when interacting with network stack When using lldptool to configure DCB parameter, hclge_dcb module call the client_ops->setup_tc to tell network stack which queue and priority is using for specific tc. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hns3_enet.c | 102 +++++++++++++++--- 1 file changed, 87 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index 11dab26f35432..4a0890f98b706 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -196,6 +196,32 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector) tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW; } +static int hns3_nic_set_real_num_queue(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct hnae3_knic_private_info *kinfo = &h->kinfo; + unsigned int queue_size = kinfo->rss_size * kinfo->num_tc; + int ret; + + ret = netif_set_real_num_tx_queues(netdev, queue_size); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_tx_queues fail, ret=%d!\n", + ret); + return ret; + } + + ret = netif_set_real_num_rx_queues(netdev, queue_size); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_rx_queues fail, ret=%d!\n", ret); + return ret; + } + + return 0; +} + static int hns3_nic_net_up(struct net_device *netdev) { struct hns3_nic_priv *priv = netdev_priv(netdev); @@ -232,26 +258,13 @@ static int hns3_nic_net_up(struct net_device *netdev) static int hns3_nic_net_open(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; int ret; netif_carrier_off(netdev); - ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps); - if (ret) { - netdev_err(netdev, - "netif_set_real_num_tx_queues fail, ret=%d!\n", - ret); - return ret; - } - - ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps); - if (ret) { - netdev_err(netdev, - "netif_set_real_num_rx_queues fail, ret=%d!\n", ret); + ret = hns3_nic_set_real_num_queue(netdev); + if (ret) return ret; - } ret = hns3_nic_net_up(netdev); if (ret) { @@ -2848,10 +2861,69 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) } } +static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct net_device *ndev = kinfo->netdev; + bool if_running = netif_running(ndev); + int ret; + u8 i; + + if (tc > HNAE3_MAX_TC) + return -EINVAL; + + if (!ndev) + return -ENODEV; + + ret = netdev_set_num_tc(ndev, tc); + if (ret) + return ret; + + if (if_running) { + (void)hns3_nic_net_stop(ndev); + msleep(100); + } + + ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ? + kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP; + if (ret) + goto err_out; + + if (tc <= 1) { + netdev_reset_tc(ndev); + goto out; + } + + for (i = 0; i < HNAE3_MAX_TC; i++) { + struct hnae3_tc_info *tc_info = &kinfo->tc_info[i]; + + if (tc_info->enable) + netdev_set_tc_queue(ndev, + tc_info->tc, + tc_info->tqp_count, + tc_info->tqp_offset); + } + + for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) { + netdev_set_prio_tc_map(ndev, i, + kinfo->prio_tc[i]); + } + +out: + ret = hns3_nic_set_real_num_queue(ndev); + +err_out: + if (if_running) + (void)hns3_nic_net_open(ndev); + + return ret; +} + const struct hnae3_client_ops client_ops = { .init_instance = hns3_client_init, .uninit_instance = hns3_client_uninit, .link_status_change = hns3_link_status_change, + .setup_tc = hns3_client_setup_tc, }; /* hns3_init_module - Driver registration routine -- GitLab From e49aa15ef6c179f69e5578a271801f31a09e9a3f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 28 Sep 2017 13:20:32 -0700 Subject: [PATCH 0626/1507] Revert "Bluetooth: Add option for disabling legacy ioctl interfaces" This reverts commit dbbccdc4ced015cdd4051299bd87fbe0254ad351. It turns out that the "legacy" users aren't so legacy at all, and that turning off the legacy ioctl will break the current Qt bluetooth stack for bluetooth LE devices that were released just a couple of months ago. So it's simply not true that this was a legacy interface that hasn't been needed and is only limited to old legacy BT devices. Because I actually read Kconfig help messages, and actively try to turn off features that I don't need, I turned the option off. Then I spent _way_ too much time debugging BLE issues until I realized that it wasn't the Qt and subsurface development that had broken one of my dive computer BLE downloads, but simply my broken kernel config. Maybe in a decade it will be true that this is a legacy interface. And maybe with a better help-text and correct dependencies, this kind of legacy removal might be acceptable. But as things are right now both the commit message and the Kconfig help text were misleading, and the Kconfig option had the wrong dependenencies. There's no reason to keep that broken Kconfig option in the tree. Cc: Marcel Holtmann Cc: Johan Hedberg Signed-off-by: Linus Torvalds --- net/bluetooth/Kconfig | 10 ---------- net/bluetooth/hci_sock.c | 6 ------ 2 files changed, 16 deletions(-) diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index c18115d22f00b..db82a40875e8d 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -126,14 +126,4 @@ config BT_DEBUGFS Provide extensive information about internal Bluetooth states in debugfs. -config BT_LEGACY_IOCTL - bool "Enable legacy ioctl interfaces" - depends on BT && BT_BREDR - default y - help - Enable support for legacy ioctl interfaces. This is only needed - for old and deprecated applications using direct ioctl calls for - controller management. Since Linux 3.4 all configuration and - setup is done via mgmt interface and this is no longer needed. - source "drivers/bluetooth/Kconfig" diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 0bad296fe0af9..65d734c165bd6 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -878,7 +878,6 @@ static int hci_sock_release(struct socket *sock) return 0; } -#ifdef CONFIG_BT_LEGACY_IOCTL static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; @@ -1050,7 +1049,6 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, release_sock(sk); return err; } -#endif static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) @@ -1971,11 +1969,7 @@ static const struct proto_ops hci_sock_ops = { .getname = hci_sock_getname, .sendmsg = hci_sock_sendmsg, .recvmsg = hci_sock_recvmsg, -#ifdef CONFIG_BT_LEGACY_IOCTL .ioctl = hci_sock_ioctl, -#else - .ioctl = sock_no_ioctl, -#endif .poll = datagram_poll, .listen = sock_no_listen, .shutdown = sock_no_shutdown, -- GitLab From 87cbde8d9081b91df86a21d0d743cd700e04890a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 28 Sep 2017 01:45:10 +0200 Subject: [PATCH 0627/1507] PM / s2idle: Invoke the ->wake() platform callback earlier The role of the ->wake() platform callback for suspend-to-idle is to deal with possible spurious wakeups, among other things. The ACPI implementation of it, acpi_s2idle_wake(), additionally checks the conditions for entering the Low Power S0 Idle state by the platform and reports the ones that have not been met. However, the ->wake() platform callback is invoked after calling dpm_noirq_resume_devices(), which means that the power states of some devices may have changed since s2idle_enter() returned, so some unmet Low Power S0 Idle conditions may be reported incorrectly as a result of that. To avoid these false positives, reorder the invocations of the dpm_noirq_resume_devices() routine and the ->wake() platform callback in s2idle_loop(). Fixes: 726fb6b4f2a8 (ACPI / PM: Check low power idle constraints for debug only) Tested-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- kernel/power/suspend.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 3e2b4f5190097..ccd2d20e6b067 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -120,22 +120,26 @@ static void s2idle_loop(void) * frozen processes + suspended devices + idle processors. * Thus s2idle_enter() should be called right after * all devices have been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, + * so prevent them from terminating the loop right away. */ error = dpm_noirq_suspend_devices(PMSG_SUSPEND); if (!error) s2idle_enter(); + else if (error == -EBUSY && pm_wakeup_pending()) + error = 0; - dpm_noirq_resume_devices(PMSG_RESUME); - if (error && (error != -EBUSY || !pm_wakeup_pending())) { - dpm_noirq_end(); - break; - } - - if (s2idle_ops && s2idle_ops->wake) + if (!error && s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); + if (error) + break; + if (s2idle_ops && s2idle_ops->sync) s2idle_ops->sync(); -- GitLab From bca73f595a566f0262967535bb5b2ea9c4271d9a Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Thu, 28 Sep 2017 22:37:35 -0500 Subject: [PATCH 0628/1507] powerpc: Fix workaround for spurious MCE on POWER9 In the recent commit d8bd9f3f0925 ("powerpc: Handle MCE on POWER9 with only DSISR bit 30 set") I screwed up the bit number. It should be bit 25 (IBM bit 38). Fixes: d8bd9f3f0925 ("powerpc: Handle MCE on POWER9 with only DSISR bit 30 set") Signed-off-by: Michael Neuling Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/mce_power.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index f523125b9d343..72f153c6f3fac 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -626,7 +626,7 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs) { /* * On POWER9 DD2.1 and below, it's possible to get a machine check - * caused by a paste instruction where only DSISR bit 30 is set. This + * caused by a paste instruction where only DSISR bit 25 is set. This * will result in the MCE handler seeing an unknown event and the kernel * crashing. An MCE that occurs like this is spurious, so we don't need * to do anything in terms of servicing it. If there is something that @@ -634,7 +634,7 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs) * correct DSISR so that it can be serviced properly. So detect this * case and mark it as handled. */ - if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x40000000) + if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000) return 1; return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table); -- GitLab From 4fc0870d7e462fe3b86e0f938ae75ce884728c7d Mon Sep 17 00:00:00 2001 From: Christophe Lombard Date: Tue, 26 Sep 2017 10:15:21 +0200 Subject: [PATCH 0629/1507] cxl: Fix memory page not handled The in-kernel 'library' API can be called by drivers to help interaction with an IBM XSL on a POWER9 system. The cxllib_handle_fault() API is used to handle memory fault. All memory pages of the specified buffer have to be handled but under certain conditions,the last page may not be touched, and the address the adapter is trying to access is never sent to the kernel for resolution. This patch reworks start address of the loop with an address aligned on the page size. In this context, the last page is not missed. Signed-off-by: Christophe Lombard Acked-by: Frederic Barrat Acked-by: Andrew Donnellan Fixes: 3ced8d730063 ("cxl: Export library to support IBM XSL"); Signed-off-by: Michael Ellerman --- drivers/misc/cxl/cxllib.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c index 5dba23ca2e5fe..dc9bc1807fdfa 100644 --- a/drivers/misc/cxl/cxllib.c +++ b/drivers/misc/cxl/cxllib.c @@ -219,8 +219,17 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags) down_read(&mm->mmap_sem); - for (dar = addr; dar < addr + size; dar += page_size) { - if (!vma || dar < vma->vm_start || dar > vma->vm_end) { + vma = find_vma(mm, addr); + if (!vma) { + pr_err("Can't find vma for addr %016llx\n", addr); + rc = -EFAULT; + goto out; + } + /* get the size of the pages allocated */ + page_size = vma_kernel_pagesize(vma); + + for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) { + if (dar < vma->vm_start || dar >= vma->vm_end) { vma = find_vma(mm, addr); if (!vma) { pr_err("Can't find vma for addr %016llx\n", addr); -- GitLab From 5af48b59f35cf712793badabe1a574a0d0ce3bd3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 27 Sep 2017 16:12:44 +0300 Subject: [PATCH 0630/1507] net: bridge: add per-port group_fwd_mask with less restrictions We need to be able to transparently forward most link-local frames via tunnels (e.g. vxlan, qinq). Currently the bridge's group_fwd_mask has a mask which restricts the forwarding of STP and LACP, but we need to be able to forward these over tunnels and control that forwarding on a per-port basis thus add a new per-port group_fwd_mask option which only disallows mac pause frames to be forwarded (they're always dropped anyway). The patch does not change the current default situation - all of the others are still restricted unless configured for forwarding. We have successfully tested this patch with LACP and STP forwarding over VxLAN and qinq tunnels. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_input.c | 1 + net/bridge/br_netlink.c | 14 +++++++++++++- net/bridge/br_private.h | 10 +++++++++- net/bridge/br_sysfs_if.c | 18 ++++++++++++++++++ 5 files changed, 42 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8d062c58d5cbc..ea87bd708ee9e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -325,6 +325,7 @@ enum { IFLA_BRPORT_MCAST_TO_UCAST, IFLA_BRPORT_VLAN_TUNNEL, IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7637f58c12263..7cb613776b318 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -289,6 +289,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) * * Others reserved for future standardization */ + fwd_mask |= p->group_fwd_mask; switch (dest[5]) { case 0x00: /* Bridge Group Address */ /* If STP is turned off, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3bc890716c89c..dea88a255d263 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -152,6 +152,7 @@ static inline size_t br_port_info_size(void) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + 0; } @@ -208,7 +209,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & - BR_VLAN_TUNNEL))) + BR_VLAN_TUNNEL)) || + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask)) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -637,6 +639,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, }; /* Change the state of the port and notify spanning tree */ @@ -773,6 +776,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } #endif + + if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { + u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); + + if (fwd_mask & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = fwd_mask; + } + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e870cfc85b147..020c709a017f0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -36,7 +36,14 @@ /* Control of forwarding link local multicast */ #define BR_GROUPFWD_DEFAULT 0 /* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */ -#define BR_GROUPFWD_RESTRICTED 0x0007u +enum { + BR_GROUPFWD_STP = BIT(0), + BR_GROUPFWD_MACPAUSE = BIT(1), + BR_GROUPFWD_LACP = BIT(2), +}; + +#define BR_GROUPFWD_RESTRICTED (BR_GROUPFWD_STP | BR_GROUPFWD_MACPAUSE | \ + BR_GROUPFWD_LACP) /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ #define BR_GROUPFWD_8021AD 0xB801u @@ -268,6 +275,7 @@ struct net_bridge_port { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + u16 group_fwd_mask; }; #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 5d5d413a6cf8a..9110d5e56085c 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -165,6 +165,23 @@ static int store_flush(struct net_bridge_port *p, unsigned long v) } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); +static ssize_t show_group_fwd_mask(struct net_bridge_port *p, char *buf) +{ + return sprintf(buf, "%#x\n", p->group_fwd_mask); +} + +static int store_group_fwd_mask(struct net_bridge_port *p, + unsigned long v) +{ + if (v & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = v; + + return 0; +} +static BRPORT_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask, + store_group_fwd_mask); + BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); @@ -223,6 +240,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_proxyarp_wifi, &brport_attr_multicast_flood, &brport_attr_broadcast_flood, + &brport_attr_group_fwd_mask, NULL }; -- GitLab From cf5d74b85ef40c202c76d90959db4d850f301b95 Mon Sep 17 00:00:00 2001 From: Hoang Tran Date: Wed, 27 Sep 2017 18:30:58 +0200 Subject: [PATCH 0631/1507] tcp: fix under-evaluated ssthresh in TCP Vegas With the commit 76174004a0f19785 (tcp: do not slow start when cwnd equals ssthresh), the comparison to the reduced cwnd in tcp_vegas_ssthresh() would under-evaluate the ssthresh. Signed-off-by: Hoang Tran Signed-off-by: David S. Miller --- net/ipv4/tcp_vegas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 218cfcc776500..ee113ff15fd02 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -158,7 +158,7 @@ EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event); static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp) { - return min(tp->snd_ssthresh, tp->snd_cwnd-1); + return min(tp->snd_ssthresh, tp->snd_cwnd); } static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) -- GitLab From cb4d2b3f03d8eed90be3a194e5b54b734ec4bbe9 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:52 -0700 Subject: [PATCH 0632/1507] bpf: Add name, load_time, uid and map_ids to bpf_prog_info The patch adds name and load_time to struct bpf_prog_aux. They are also exported to bpf_prog_info. The bpf_prog's name is passed by userspace during BPF_PROG_LOAD. The kernel only stores the first (BPF_PROG_NAME_LEN - 1) bytes and the name stored in the kernel is always \0 terminated. The kernel will reject name that contains characters other than isalnum() and '_'. It will also reject name that is not null terminated. The existing 'user->uid' of the bpf_prog_aux is also exported to the bpf_prog_info as created_by_uid. The existing 'used_maps' of the bpf_prog_aux is exported to the newly added members 'nr_map_ids' and 'map_ids' of the bpf_prog_info. On the input, nr_map_ids tells how big the userspace's map_ids buffer is. On the output, nr_map_ids tells the exact user_map_cnt and it will only copy up to the userspace's map_ids buffer is allowed. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 8 +++++++ kernel/bpf/syscall.c | 51 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2b672c50f160e..33ccc474fb043 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -187,6 +187,8 @@ struct bpf_prog_aux { struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; + u64 load_time; /* ns since boottime */ + u8 name[BPF_OBJ_NAME_LEN]; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e43491ac48237..bd6348269bf54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -175,6 +175,8 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -210,6 +212,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; + __u8 prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -812,6 +815,11 @@ struct bpf_prog_info { __u32 xlated_prog_len; __aligned_u64 jited_prog_insns; __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 25d074920a009..45970df3f8204 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,9 @@ #include #include #include +#include +#include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -312,6 +315,30 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL +/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. + * Return 0 on success and < 0 on error. + */ +static int bpf_obj_name_cpy(char *dst, const char *src) +{ + const char *end = src + BPF_OBJ_NAME_LEN; + + /* Copy all isalnum() and '_' char */ + while (src < end && *src) { + if (!isalnum(*src) && *src != '_') + return -EINVAL; + *dst++ = *src++; + } + + /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ + if (src == end) + return -EINVAL; + + /* '\0' terminates dst */ + *dst = 0; + + return 0; +} + #define BPF_MAP_CREATE_LAST_FIELD numa_node /* called via syscall */ static int map_create(union bpf_attr *attr) @@ -973,7 +1000,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_flags +#define BPF_PROG_LOAD_LAST_FIELD prog_name static int bpf_prog_load(union bpf_attr *attr) { @@ -1037,6 +1064,11 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_prog; + prog->aux->load_time = ktime_get_boot_ns(); + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); + if (err) + goto free_prog; + /* run eBPF verifier */ err = bpf_check(&prog, attr); if (err < 0) @@ -1358,8 +1390,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.type = prog->type; info.id = prog->aux->id; + info.load_time = prog->aux->load_time; + info.created_by_uid = from_kuid_munged(current_user_ns(), + prog->aux->user->uid); memcpy(info.tag, prog->tag, sizeof(prog->tag)); + memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + + ulen = info.nr_map_ids; + info.nr_map_ids = prog->aux->used_map_cnt; + ulen = min_t(u32, info.nr_map_ids, ulen); + if (ulen) { + u32 *user_map_ids = (u32 *)info.map_ids; + u32 i; + + for (i = 0; i < ulen; i++) + if (put_user(prog->aux->used_maps[i]->id, + &user_map_ids[i])) + return -EFAULT; + } if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; -- GitLab From ad5b177bd73f5107d97c36f56395c4281fb6f089 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:53 -0700 Subject: [PATCH 0633/1507] bpf: Add map_name to bpf_map_info This patch allows userspace to specify a name for a map during BPF_MAP_CREATE. The map's name can later be exported to user space via BPF_OBJ_GET_INFO_BY_FD. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 7 ++++++- 3 files changed, 9 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33ccc474fb043..252f4bc9eb258 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,6 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; + u8 name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd6348269bf54..6d2137b4cf380 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -190,6 +190,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ + __u8 map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -829,6 +830,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45970df3f8204..11a7f82a55d19 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -339,7 +339,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD numa_node +#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -361,6 +361,10 @@ static int map_create(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + err = bpf_obj_name_cpy(map->name, attr->map_name); + if (err) + goto free_map_nouncharge; + atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); @@ -1462,6 +1466,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + memcpy(info.name, map->name, sizeof(map->name)); if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- GitLab From 88cda1c9da02c8aa31e1d5dcf22e8a35cc8c19f2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:54 -0700 Subject: [PATCH 0634/1507] bpf: libbpf: Provide basic API support to specify BPF obj name This patch extends the libbpf to provide API support to allow specifying BPF object name. In tools/lib/bpf/libbpf, the C symbol of the function and the map is used. Regarding section name, all maps are under the same section named "maps". Hence, section name is not a good choice for map's name. To be consistent with map, bpf_prog also follows and uses its function symbol as the prog's name. This patch adds logic to collect function's symbols in libbpf. There is existing codes to collect the map's symbols and no change is needed. The bpf_load_program_name() and bpf_map_create_name() are added to take the name argument. For the other bpf_map_create_xxx() variants, a name argument is directly added to them. In samples/bpf, bpf_load.c in particular, the symbol is also used as the map's name and the map symbols has already been collected in the existing code. For bpf_prog, bpf_load.c does not collect the function symbol name. We can consider to collect them later if there is a need to continue supporting the bpf_load.c. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/bpf_load.c | 2 + samples/bpf/map_perf_test_user.c | 1 + tools/include/uapi/linux/bpf.h | 10 ++ tools/lib/bpf/bpf.c | 57 +++++++--- tools/lib/bpf/bpf.h | 23 +++-- tools/lib/bpf/libbpf.c | 109 +++++++++++++++----- tools/testing/selftests/bpf/test_verifier.c | 2 +- 7 files changed, 157 insertions(+), 47 deletions(-) diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 6aa50098dfb8e..18b1c8dd03917 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -221,6 +221,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps, int inner_map_fd = map_fd[maps[i].def.inner_map_idx]; map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type, + maps[i].name, maps[i].def.key_size, inner_map_fd, maps[i].def.max_entries, @@ -228,6 +229,7 @@ static int load_maps(struct bpf_map_data *maps, int nr_maps, numa_node); } else { map_fd[i] = bpf_create_map_node(maps[i].def.type, + maps[i].name, maps[i].def.key_size, maps[i].def.value_size, maps[i].def.max_entries, diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index a0310fc700576..519d9af4b04a1 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -137,6 +137,7 @@ static void do_test_lru(enum test_type test, int cpu) inner_lru_map_fds[cpu] = bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH, + test_map_names[INNER_LRU_HASH_PREALLOC], sizeof(uint32_t), sizeof(long), inner_lru_hash_size, 0, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e43491ac48237..6d2137b4cf380 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -175,6 +175,8 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -188,6 +190,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ + __u8 map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -210,6 +213,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; + __u8 prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -812,6 +816,11 @@ struct bpf_prog_info { __u32 xlated_prog_len; __aligned_u64 jited_prog_insns; __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -821,6 +830,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 1d6907d379c99..daf624e4c720e 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -46,6 +46,8 @@ # endif #endif +#define min(x, y) ((x) < (y) ? (x) : (y)) + static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -57,10 +59,11 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map_node(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags, - int node) +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) { + __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -70,6 +73,8 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size, attr.value_size = value_size; attr.max_entries = max_entries; attr.map_flags = map_flags; + memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; attr.numa_node = node; @@ -81,14 +86,23 @@ int bpf_create_map_node(enum bpf_map_type map_type, int key_size, int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, key_size, value_size, + return bpf_create_map_node(map_type, NULL, key_size, value_size, max_entries, map_flags, -1); } -int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags) +{ + return bpf_create_map_node(map_type, name, key_size, value_size, + max_entries, map_flags, -1); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { + __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -99,6 +113,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; + memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; attr.numa_node = node; @@ -107,19 +123,24 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags) +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags) { - return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd, - max_entries, map_flags, -1); + return bpf_create_map_in_map_node(map_type, name, key_size, + inner_map_fd, max_entries, map_flags, + -1); } -int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, const char *license, - __u32 kern_version, char *log_buf, size_t log_buf_sz) +int bpf_load_program_name(enum bpf_prog_type type, const char *name, + const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) { int fd; union bpf_attr attr; + __u32 name_len = name ? strlen(name) : 0; bzero(&attr, sizeof(attr)); attr.prog_type = type; @@ -130,6 +151,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.log_size = 0; attr.log_level = 0; attr.kern_version = kern_version; + memcpy(attr.prog_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); fd = sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); if (fd >= 0 || !log_buf || !log_buf_sz) @@ -143,6 +165,15 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) +{ + return bpf_load_program_name(type, NULL, insns, insns_cnt, license, + kern_version, log_buf, log_buf_sz); +} + int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, int strict_alignment, const char *license, __u32 kern_version, diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index b8ea5843c39ee..118d00535a0d4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,19 +24,28 @@ #include #include -int bpf_create_map_node(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags, - int node); +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node); +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags); int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); -int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node); -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags); +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags); /* Recommend log buffer size */ #define BPF_LOG_BUF_SIZE 65536 +int bpf_load_program_name(enum bpf_prog_type type, const char *name, + const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz); int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 35f6dfcdc5651..4f402dcdf3729 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -171,6 +171,7 @@ int libbpf_strerror(int err, char *buf, size_t size) struct bpf_program { /* Index in elf obj file, for relocation use. */ int idx; + char *name; char *section_name; struct bpf_insn *insns; size_t insns_cnt; @@ -283,6 +284,7 @@ static void bpf_program__exit(struct bpf_program *prog) prog->clear_priv = NULL; bpf_program__unload(prog); + zfree(&prog->name); zfree(&prog->section_name); zfree(&prog->insns); zfree(&prog->reloc_desc); @@ -293,26 +295,27 @@ static void bpf_program__exit(struct bpf_program *prog) } static int -bpf_program__init(void *data, size_t size, char *name, int idx, - struct bpf_program *prog) +bpf_program__init(void *data, size_t size, char *section_name, int idx, + struct bpf_program *prog) { if (size < sizeof(struct bpf_insn)) { - pr_warning("corrupted section '%s'\n", name); + pr_warning("corrupted section '%s'\n", section_name); return -EINVAL; } bzero(prog, sizeof(*prog)); - prog->section_name = strdup(name); + prog->section_name = strdup(section_name); if (!prog->section_name) { - pr_warning("failed to alloc name for prog %s\n", - name); + pr_warning("failed to alloc name for prog under section %s\n", + section_name); goto errout; } prog->insns = malloc(size); if (!prog->insns) { - pr_warning("failed to alloc insns for %s\n", name); + pr_warning("failed to alloc insns for prog under section %s\n", + section_name); goto errout; } prog->insns_cnt = size / sizeof(struct bpf_insn); @@ -331,12 +334,12 @@ bpf_program__init(void *data, size_t size, char *name, int idx, static int bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, - char *name, int idx) + char *section_name, int idx) { struct bpf_program prog, *progs; int nr_progs, err; - err = bpf_program__init(data, size, name, idx, &prog); + err = bpf_program__init(data, size, section_name, idx, &prog); if (err) return err; @@ -350,8 +353,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, * is still valid, so don't need special treat for * bpf_close_object(). */ - pr_warning("failed to alloc a new program '%s'\n", - name); + pr_warning("failed to alloc a new program under section '%s'\n", + section_name); bpf_program__exit(&prog); return -ENOMEM; } @@ -364,6 +367,54 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, return 0; } +static int +bpf_object__init_prog_names(struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + struct bpf_program *prog; + size_t pi, si; + + for (pi = 0; pi < obj->nr_programs; pi++) { + char *name = NULL; + + prog = &obj->programs[pi]; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; + si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (sym.st_shndx != prog->idx) + continue; + + name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + if (!name) { + pr_warning("failed to get sym name string for prog %s\n", + prog->section_name); + return -LIBBPF_ERRNO__LIBELF; + } + } + + if (!name) { + pr_warning("failed to find sym for prog %s\n", + prog->section_name); + return -EINVAL; + } + + prog->name = strdup(name); + if (!prog->name) { + pr_warning("failed to allocate memory for prog sym %s\n", + name); + return -ENOMEM; + } + } + + return 0; +} + static struct bpf_object *bpf_object__new(const char *path, void *obj_buf, size_t obj_buf_sz) @@ -766,8 +817,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj) pr_warning("Corrupted ELF file: index of strtab invalid\n"); return LIBBPF_ERRNO__FORMAT; } - if (obj->efile.maps_shndx >= 0) + if (obj->efile.maps_shndx >= 0) { err = bpf_object__init_maps(obj); + if (err) + goto out; + } + err = bpf_object__init_prog_names(obj); out: return err; } @@ -870,11 +925,12 @@ bpf_object__create_maps(struct bpf_object *obj) struct bpf_map_def *def = &obj->maps[i].def; int *pfd = &obj->maps[i].fd; - *pfd = bpf_create_map(def->type, - def->key_size, - def->value_size, - def->max_entries, - 0); + *pfd = bpf_create_map_name(def->type, + obj->maps[i].name, + def->key_size, + def->value_size, + def->max_entries, + 0); if (*pfd < 0) { size_t j; int err = *pfd; @@ -982,7 +1038,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) } static int -load_program(enum bpf_prog_type type, struct bpf_insn *insns, +load_program(enum bpf_prog_type type, const char *name, struct bpf_insn *insns, int insns_cnt, char *license, u32 kern_version, int *pfd) { int ret; @@ -995,8 +1051,8 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns, if (!log_buf) pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program(type, insns, insns_cnt, license, - kern_version, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_name(type, name, insns, insns_cnt, license, + kern_version, log_buf, BPF_LOG_BUF_SIZE); if (ret >= 0) { *pfd = ret; @@ -1021,9 +1077,9 @@ load_program(enum bpf_prog_type type, struct bpf_insn *insns, if (type != BPF_PROG_TYPE_KPROBE) { int fd; - fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, - insns_cnt, license, kern_version, - NULL, 0); + fd = bpf_load_program_name(BPF_PROG_TYPE_KPROBE, name, + insns, insns_cnt, license, + kern_version, NULL, 0); if (fd >= 0) { close(fd); ret = -LIBBPF_ERRNO__PROGTYPE; @@ -1067,8 +1123,8 @@ bpf_program__load(struct bpf_program *prog, pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", prog->section_name, prog->instances.nr); } - err = load_program(prog->type, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + err = load_program(prog->type, prog->name, prog->insns, + prog->insns_cnt, license, kern_version, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -1096,7 +1152,8 @@ bpf_program__load(struct bpf_program *prog, continue; } - err = load_program(prog->type, result.new_insn_ptr, + err = load_program(prog->type, prog->name, + result.new_insn_ptr, result.new_insn_cnt, license, kern_version, &fd); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index a0426147523d9..290d5056c1650 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6939,7 +6939,7 @@ static int create_map_in_map(void) return inner_map_fd; } - outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, sizeof(int), inner_map_fd, 1, 0); if (outer_map_fd < 0) printf("Failed to create array of maps '%s'!\n", -- GitLab From 6e525d06674a21468b4e728ef880770a0ca5c60d Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:55 -0700 Subject: [PATCH 0635/1507] bpf: Swap the order of checking prog_info and map_info This patch swaps the checking order. It now checks the map_info first and then prog_info. It is a prep work for adding test to the newly added fields (the map_ids of prog_info field in particular). Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/test_progs.c | 58 ++++++++++++------------ 1 file changed, 30 insertions(+), 28 deletions(-) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 11ee25cea227b..31ae27dc8d047 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -316,6 +316,36 @@ static void test_bpf_obj_id(void) error_cnt++; assert(!err); + /* Insert a magic value to the map */ + map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); + assert(map_fds[i] >= 0); + err = bpf_map_update_elem(map_fds[i], &array_key, + &array_magic_value, 0); + assert(!err); + + /* Check getting map info */ + info_len = sizeof(struct bpf_map_info) * 2; + bzero(&map_infos[i], info_len); + err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], + &info_len); + if (CHECK(err || + map_infos[i].type != BPF_MAP_TYPE_ARRAY || + map_infos[i].key_size != sizeof(__u32) || + map_infos[i].value_size != sizeof(__u64) || + map_infos[i].max_entries != 1 || + map_infos[i].map_flags != 0 || + info_len != sizeof(struct bpf_map_info), + "get-map-info(fd)", + "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n", + err, errno, + map_infos[i].type, BPF_MAP_TYPE_ARRAY, + info_len, sizeof(struct bpf_map_info), + map_infos[i].key_size, + map_infos[i].value_size, + map_infos[i].max_entries, + map_infos[i].map_flags)) + goto done; + /* Check getting prog info */ info_len = sizeof(struct bpf_prog_info) * 2; bzero(&prog_infos[i], info_len); @@ -347,34 +377,6 @@ static void test_bpf_obj_id(void) !!memcmp(xlated_insns, zeros, sizeof(zeros)))) goto done; - map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); - assert(map_fds[i] >= 0); - err = bpf_map_update_elem(map_fds[i], &array_key, - &array_magic_value, 0); - assert(!err); - - /* Check getting map info */ - info_len = sizeof(struct bpf_map_info) * 2; - bzero(&map_infos[i], info_len); - err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i], - &info_len); - if (CHECK(err || - map_infos[i].type != BPF_MAP_TYPE_ARRAY || - map_infos[i].key_size != sizeof(__u32) || - map_infos[i].value_size != sizeof(__u64) || - map_infos[i].max_entries != 1 || - map_infos[i].map_flags != 0 || - info_len != sizeof(struct bpf_map_info), - "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n", - err, errno, - map_infos[i].type, BPF_MAP_TYPE_ARRAY, - info_len, sizeof(struct bpf_map_info), - map_infos[i].key_size, - map_infos[i].value_size, - map_infos[i].max_entries, - map_infos[i].map_flags)) - goto done; } /* Check bpf_prog_get_next_id() */ -- GitLab From 3a8ad560a9674235d1dd2e174434f540924e249f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:56 -0700 Subject: [PATCH 0636/1507] bpf: Test new fields in bpf_attr and bpf_{prog, map}_info This patch tests newly added fields of the bpf_attr, bpf_prog_info and bpf_map_info. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/test_progs.c | 143 +++++++++++++++++++++-- 1 file changed, 132 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 31ae27dc8d047..69427531408dd 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -10,6 +10,7 @@ #include #include #include +#include #include typedef __u16 __sum16; @@ -19,6 +20,8 @@ typedef __u16 __sum16; #include #include #include +#include +#include #include #include @@ -273,16 +276,26 @@ static void test_bpf_obj_id(void) const int nr_iters = 2; const char *file = "./test_obj_id.o"; const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + const char *expected_prog_name = "test_obj_id"; + const char *expected_map_name = "test_map_id"; + const __u64 nsec_per_sec = 1000000000; struct bpf_object *objs[nr_iters]; int prog_fds[nr_iters], map_fds[nr_iters]; /* +1 to test for the info_len returned by kernel */ struct bpf_prog_info prog_infos[nr_iters + 1]; struct bpf_map_info map_infos[nr_iters + 1]; + /* Each prog only uses one map. +1 to test nr_map_ids + * returned by kernel. + */ + __u32 map_ids[nr_iters + 1]; char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; + struct timespec real_time_ts, boot_time_ts; int sysctl_fd, jit_enabled = 0, err = 0; __u64 array_value; + uid_t my_uid = getuid(); + time_t now, load_time; sysctl_fd = open(jit_sysctl, 0, O_RDONLY); if (sysctl_fd != -1) { @@ -307,6 +320,7 @@ static void test_bpf_obj_id(void) /* Check bpf_obj_get_info_by_fd() */ bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { + now = time(NULL); err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail @@ -334,16 +348,18 @@ static void test_bpf_obj_id(void) map_infos[i].value_size != sizeof(__u64) || map_infos[i].max_entries != 1 || map_infos[i].map_flags != 0 || - info_len != sizeof(struct bpf_map_info), + info_len != sizeof(struct bpf_map_info) || + strcmp((char *)map_infos[i].name, expected_map_name), "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X\n", + "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", err, errno, map_infos[i].type, BPF_MAP_TYPE_ARRAY, info_len, sizeof(struct bpf_map_info), map_infos[i].key_size, map_infos[i].value_size, map_infos[i].max_entries, - map_infos[i].map_flags)) + map_infos[i].map_flags, + map_infos[i].name, expected_map_name)) goto done; /* Check getting prog info */ @@ -355,8 +371,16 @@ static void test_bpf_obj_id(void) prog_infos[i].jited_prog_len = sizeof(jited_insns); prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns); prog_infos[i].xlated_prog_len = sizeof(xlated_insns); + prog_infos[i].map_ids = ptr_to_u64(map_ids + i); + prog_infos[i].nr_map_ids = 2; + err = clock_gettime(CLOCK_REALTIME, &real_time_ts); + assert(!err); + err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts); + assert(!err); err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i], &info_len); + load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + + (prog_infos[i].load_time / nsec_per_sec); if (CHECK(err || prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || @@ -364,9 +388,14 @@ static void test_bpf_obj_id(void) (jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))) || !prog_infos[i].xlated_prog_len || - !memcmp(xlated_insns, zeros, sizeof(zeros)), + !memcmp(xlated_insns, zeros, sizeof(zeros)) || + load_time < now - 60 || load_time > now + 60 || + prog_infos[i].created_by_uid != my_uid || + prog_infos[i].nr_map_ids != 1 || + *(int *)prog_infos[i].map_ids != map_infos[i].id || + strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n", + "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -374,9 +403,13 @@ static void test_bpf_obj_id(void) prog_infos[i].jited_prog_len, prog_infos[i].xlated_prog_len, !!memcmp(jited_insns, zeros, sizeof(zeros)), - !!memcmp(xlated_insns, zeros, sizeof(zeros)))) + !!memcmp(xlated_insns, zeros, sizeof(zeros)), + load_time, now, + prog_infos[i].created_by_uid, my_uid, + prog_infos[i].nr_map_ids, 1, + *(int *)prog_infos[i].map_ids, map_infos[i].id, + prog_infos[i].name, expected_prog_name)) goto done; - } /* Check bpf_prog_get_next_id() */ @@ -384,6 +417,7 @@ static void test_bpf_obj_id(void) next_id = 0; while (!bpf_prog_get_next_id(next_id, &next_id)) { struct bpf_prog_info prog_info = {}; + __u32 saved_map_id; int prog_fd; info_len = sizeof(prog_info); @@ -406,16 +440,33 @@ static void test_bpf_obj_id(void) nr_id_found++; + /* Negative test: + * prog_info.nr_map_ids = 1 + * prog_info.map_ids = NULL + */ + prog_info.nr_map_ids = 1; + err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); + if (CHECK(!err || errno != EFAULT, + "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)", + err, errno, EFAULT)) + break; + bzero(&prog_info, sizeof(prog_info)); + info_len = sizeof(prog_info); + + saved_map_id = *(int *)(prog_infos[i].map_ids); + prog_info.map_ids = prog_infos[i].map_ids; + prog_info.nr_map_ids = 2; err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len); prog_infos[i].jited_prog_insns = 0; prog_infos[i].xlated_prog_insns = 0; CHECK(err || info_len != sizeof(struct bpf_prog_info) || - memcmp(&prog_info, &prog_infos[i], info_len), + memcmp(&prog_info, &prog_infos[i], info_len) || + *(int *)prog_info.map_ids != saved_map_id, "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d\n", + "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n", err, errno, info_len, sizeof(struct bpf_prog_info), - memcmp(&prog_info, &prog_infos[i], info_len)); - + memcmp(&prog_info, &prog_infos[i], info_len), + *(int *)prog_info.map_ids, saved_map_id); close(prog_fd); } CHECK(nr_id_found != nr_iters, @@ -497,6 +548,75 @@ static void test_pkt_md_access(void) bpf_object__close(obj); } +static void test_obj_name(void) +{ + struct { + const char *name; + int success; + int expected_errno; + } tests[] = { + { "", 1, 0 }, + { "_123456789ABCDE", 1, 0 }, + { "_123456789ABCDEF", 0, EINVAL }, + { "_123456789ABCD\n", 0, EINVAL }, + }; + struct bpf_insn prog[] = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + __u32 duration = 0; + int i; + + for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + size_t name_len = strlen(tests[i].name) + 1; + union bpf_attr attr; + size_t ncopy; + int fd; + + /* test different attr.prog_name during BPF_PROG_LOAD */ + ncopy = name_len < sizeof(attr.prog_name) ? + name_len : sizeof(attr.prog_name); + bzero(&attr, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SCHED_CLS; + attr.insn_cnt = 2; + attr.insns = ptr_to_u64(prog); + attr.license = ptr_to_u64(""); + memcpy(attr.prog_name, tests[i].name, ncopy); + + fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + CHECK((tests[i].success && fd < 0) || + (!tests[i].success && fd != -1) || + (!tests[i].success && errno != tests[i].expected_errno), + "check-bpf-prog-name", + "fd %d(%d) errno %d(%d)\n", + fd, tests[i].success, errno, tests[i].expected_errno); + + if (fd != -1) + close(fd); + + /* test different attr.map_name during BPF_MAP_CREATE */ + ncopy = name_len < sizeof(attr.map_name) ? + name_len : sizeof(attr.map_name); + bzero(&attr, sizeof(attr)); + attr.map_type = BPF_MAP_TYPE_ARRAY; + attr.key_size = 4; + attr.value_size = 4; + attr.max_entries = 1; + attr.map_flags = 0; + memcpy(attr.map_name, tests[i].name, ncopy); + fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); + CHECK((tests[i].success && fd < 0) || + (!tests[i].success && fd != -1) || + (!tests[i].success && errno != tests[i].expected_errno), + "check-bpf-map-name", + "fd %d(%d) errno %d(%d)\n", + fd, tests[i].success, errno, tests[i].expected_errno); + + if (fd != -1) + close(fd); + } +} + int main(void) { struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; @@ -509,6 +629,7 @@ int main(void) test_tcp_estats(); test_bpf_obj_id(); test_pkt_md_access(); + test_obj_name(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; -- GitLab From c7c3e5913bf18eda3cf38932bebdce48351baac9 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 27 Sep 2017 19:08:00 -0700 Subject: [PATCH 0637/1507] net: ipv4: remove fib_weight fib_weight in fib_info is set but not used. Remove it and the helpers for setting it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 --- net/ipv4/fib_semantics.c | 9 --------- 2 files changed, 12 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 1a7f7e4243202..f80524396c062 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -122,9 +122,6 @@ struct fib_info { #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; -#ifdef CONFIG_IP_ROUTE_MULTIPATH - int fib_weight; -#endif struct rcu_head rcu; struct fib_nh fib_nh[0]; #define fib_dev fib_nh[0].nh_dev diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 57a5d48acee84..be0874620ecc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -601,17 +601,9 @@ static void fib_rebalance(struct fib_info *fi) atomic_set(&nexthop_nh->nh_upper_bound, upper_bound); } endfor_nexthops(fi); } - -static inline void fib_add_weight(struct fib_info *fi, - const struct fib_nh *nh) -{ - fi->fib_weight += nh->nh_weight; -} - #else /* CONFIG_IP_ROUTE_MULTIPATH */ #define fib_rebalance(fi) do { } while (0) -#define fib_add_weight(fi, nh) do { } while (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -1275,7 +1267,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg, change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); - fib_add_weight(fi, nexthop_nh); } endfor_nexthops(fi) fib_rebalance(fi); -- GitLab From fa8fefaa678ea390b873195d19c09930da84a4bb Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 27 Sep 2017 20:41:59 -0700 Subject: [PATCH 0638/1507] net: ipv4: remove fib_info arg to fib_check_nh fib_check_nh does not use the fib_info arg; remove t. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index be0874620ecc1..467b3c15395f1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -766,8 +766,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) * | * |-> {local prefix} (terminal node) */ -static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh, struct netlink_ext_ack *extack) +static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, + struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -1250,7 +1250,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh, extack); + err = fib_check_nh(cfg, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) -- GitLab From 441430eb54a00586f95f1aefc48e0801bbd6a923 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Wed, 6 Sep 2017 19:08:11 +0300 Subject: [PATCH 0639/1507] perf/aux: Only update ->aux_wakeup in non-overwrite mode The following commit: d9a50b0256 ("perf/aux: Ensure aux_wakeup represents most recent wakeup index") changed the AUX wakeup position calculation to rounddown(), which causes a division-by-zero in AUX overwrite mode (aka "snapshot mode"). The zero denominator results from the fact that perf record doesn't set aux_watermark to anything, in which case the kernel will set it to half the AUX buffer size, but only for non-overwrite mode. In the overwrite mode aux_watermark stays zero. The good news is that, AUX overwrite mode, wakeups don't happen and related bookkeeping is not relevant, so we can simply forego the whole wakeup updates. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/20170906160811.16510-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e12eea..f684d8e5fa2be 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } -- GitLab From 69b73e95982649a1f2dc63b8f08f2113d28f7fed Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Sep 2017 10:07:44 +0200 Subject: [PATCH 0640/1507] um/time: Fixup namespace collision The new timer_setup() function for struct timer_list collides with a private um function. Rename it. Fixes: 686fef928bba ("timer: Prepare to change timer callback argument type") Signed-off-by: Thomas Gleixner Cc: Richard Weinberger Cc: Jeff Dike Cc: user-mode-linux-devel@lists.sourceforge.net Cc: Kees Cook --- arch/um/kernel/time.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 0b034ebbda2a1..7f69d17de3540 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -98,7 +98,7 @@ static struct clocksource timer_clocksource = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -static void __init timer_setup(void) +static void __init um_timer_setup(void) { int err; @@ -132,5 +132,5 @@ void read_persistent_clock(struct timespec *ts) void __init time_init(void) { timer_set_signal_handler(); - late_time_init = timer_setup; + late_time_init = um_timer_setup; } -- GitLab From 1593baab910da72480d651ea7bf2ce6e3a25a484 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:09:26 +0200 Subject: [PATCH 0641/1507] sched/debug: Implement consistent task-state printing Currently get_task_state() and task_state_to_char() report different states, create a number of common helpers and unify the reported state space. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/proc/array.c | 15 ++------------- include/linux/sched.h | 26 +++++++++++++++++++------- 2 files changed, 21 insertions(+), 20 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index 525157ca25cbe..01196d3ad4525 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -130,19 +130,8 @@ static const char * const task_state_array[] = { static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - - /* - * Parked tasks do not run; they sit in __kthread_parkme(). - * Without this check, we would report them as running, which is - * clearly wrong, so we report them as sleeping instead. - */ - if (tsk->state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - - return task_state_array[fls(state)]; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array) - 1); + return task_state_array[__get_task_state(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) diff --git a/include/linux/sched.h b/include/linux/sched.h index 92fb8dd5a9e48..163a0b7389081 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1243,17 +1243,29 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } -static inline char task_state_to_char(struct task_struct *task) +static inline unsigned int __get_task_state(struct task_struct *tsk) { - const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - unsigned long state = task->state; + unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; - state = state ? __ffs(state) + 1 : 0; + if (tsk_state == TASK_PARKED) + state = TASK_INTERRUPTIBLE; - /* Make sure the string lines up properly with the number of task states: */ - BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + return fls(state); +} + +static inline char __task_state_to_char(unsigned int state) +{ + static const char state_char[] = "RSDTtXZ"; + + BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != sizeof(state_char) - 2); - return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; + return state_char[state]; +} + +static inline char task_state_to_char(struct task_struct *tsk) +{ + return __task_state_to_char(__get_task_state(tsk)); } /** -- GitLab From 92c4bc9f9cd92a8581e36bc5105f03b569f37e36 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:13:36 +0200 Subject: [PATCH 0642/1507] sched/debug: Convert TASK_state to hex Bit patterns are easier in hex. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 163a0b7389081..69bed5339ffad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -65,23 +65,23 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0 -#define TASK_INTERRUPTIBLE 1 -#define TASK_UNINTERRUPTIBLE 2 -#define __TASK_STOPPED 4 -#define __TASK_TRACED 8 +#define TASK_RUNNING 0x0000 +#define TASK_INTERRUPTIBLE 0x0001 +#define TASK_UNINTERRUPTIBLE 0x0002 +#define __TASK_STOPPED 0x0004 +#define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 16 -#define EXIT_ZOMBIE 32 +#define EXIT_DEAD 0x0010 +#define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 64 -#define TASK_WAKEKILL 128 -#define TASK_WAKING 256 -#define TASK_PARKED 512 -#define TASK_NOLOAD 1024 -#define TASK_NEW 2048 -#define TASK_STATE_MAX 4096 +#define TASK_DEAD 0x0040 +#define TASK_WAKEKILL 0x0080 +#define TASK_WAKING 0x0100 +#define TASK_PARKED 0x0200 +#define TASK_NOLOAD 0x0400 +#define TASK_NEW 0x0800 +#define TASK_STATE_MAX 0x1000 #define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" -- GitLab From 65d5dc47fe8530e17e318722fb4df676536c2bfc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:14:08 +0200 Subject: [PATCH 0643/1507] sched/debug: Remove unused variable Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb5a5de9..2f93e4a2d9f62 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { -- GitLab From efb40f588b4370ffaeffafbd50f6ff213d954254 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:19:53 +0200 Subject: [PATCH 0644/1507] sched/tracing: Fix trace_sched_switch task-state printing Convert trace_sched_switch to use the common task-state helpers and fix the "X" and "Z" order, possibly they ended up in the wrong order because TASK_REPORT has them in the wrong order too. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- include/trace/events/sched.h | 18 +++++++++++------- 2 files changed, 12 insertions(+), 8 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 69bed5339ffad..a2fe636b68256 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -99,7 +99,7 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index ae1409ffe99a0..c63e20c9ef24d 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -114,7 +114,10 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * Preemption ignores task state, therefore preempted tasks are always * RUNNING (we will not have dequeued if state != RUNNING). */ - return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state; + if (preempt) + return TASK_STATE_MAX; + + return __get_task_state(p); } #endif /* CREATE_TRACE_POINTS */ @@ -152,12 +155,13 @@ TRACE_EVENT(sched_switch, TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - __entry->prev_state & (TASK_STATE_MAX-1) ? - __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|", - { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, - { 16, "Z" }, { 32, "X" }, { 64, "x" }, - { 128, "K" }, { 256, "W" }, { 512, "P" }, - { 1024, "N" }) : "R", + + (__entry->prev_state & TASK_REPORT) ? + __print_flags(__entry->prev_state & TASK_REPORT, "|", + { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, + { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }) : + "R", + __entry->prev_state & TASK_STATE_MAX ? "+" : "", __entry->next_comm, __entry->next_pid, __entry->next_prio) ); -- GitLab From 9c29c31830a4eca724e137a9339137204bbb31be Mon Sep 17 00:00:00 2001 From: Prateek Sood Date: Thu, 7 Sep 2017 20:00:58 +0530 Subject: [PATCH 0645/1507] locking/rwsem-xadd: Fix missed wakeup due to reordering of load If a spinner is present, there is a chance that the load of rwsem_has_spinner() in rwsem_wake() can be reordered with respect to decrement of rwsem count in __up_write() leading to wakeup being missed: spinning writer up_write caller --------------- ----------------------- [S] osq_unlock() [L] osq spin_lock(wait_lock) sem->count=0xFFFFFFFF00000001 +0xFFFFFFFF00000000 count=sem->count MB sem->count=0xFFFFFFFE00000001 -0xFFFFFFFF00000001 spin_trylock(wait_lock) return rwsem_try_write_lock(count) spin_unlock(wait_lock) schedule() Reordering of atomic_long_sub_return_release() in __up_write() and rwsem_has_spinner() in rwsem_wake() can cause missing of wakeup in up_write() context. In spinning writer, sem->count and local variable count is 0XFFFFFFFE00000001. It would result in rwsem_try_write_lock() failing to acquire rwsem and spinning writer going to sleep in rwsem_down_write_failed(). The smp_rmb() will make sure that the spinner state is consulted after sem->count is updated in up_write context. Signed-off-by: Prateek Sood Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dave@stgolabs.net Cc: longman@redhat.com Cc: parri.andrea@gmail.com Cc: sramana@codeaurora.org Link: http://lkml.kernel.org/r/1504794658-15397-1-git-send-email-prsood@codeaurora.org Signed-off-by: Ingo Molnar --- kernel/locking/rwsem-xadd.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f660666ab89..1fefe6dcafd74 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -612,6 +612,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) unsigned long flags; DEFINE_WAKE_Q(wake_q); + /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize -- GitLab From 5f6ad26ea353fdf3dad2328052cbee49e0b9c5b4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:23:31 +0200 Subject: [PATCH 0646/1507] sched/tracing: Use common task-state helpers Remove yet another task-state char instance. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- kernel/trace/trace_output.c | 21 ++++++--------------- kernel/trace/trace_sched_wakeup.c | 8 ++++---- 3 files changed, 10 insertions(+), 21 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index a2fe636b68256..bc78079334155 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -83,8 +83,6 @@ struct task_group; #define TASK_NEW 0x0800 #define TASK_STATE_MAX 0x1000 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" - /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629af22857..c738e764e2a55 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b676461..0c331978b1a63 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) -- GitLab From 06eb61844d841d0032a9950ce7f8e783ee49c0d0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:30:40 +0200 Subject: [PATCH 0647/1507] sched/debug: Add explicit TASK_IDLE printing Markus reported that kthreads that idle using TASK_IDLE instead of TASK_INTERRUPTIBLE are reported in as TASK_UNINTERRUPTIBLE and things like htop mark those red. This is undesirable, so add an explicit state for TASK_IDLE. Reported-by: Markus Trippelsdorf Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/proc/array.c | 21 +++++++++++++-------- include/linux/sched.h | 12 ++++++++++-- include/trace/events/sched.h | 7 ++++--- 3 files changed, 27 insertions(+), 13 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index 01196d3ad4525..a120a4549d484 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -119,18 +119,23 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) * simple bit tests. */ static const char * const task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "t (tracing stop)", /* 8 */ - "X (dead)", /* 16 */ - "Z (zombie)", /* 32 */ + + /* states in TASK_REPORT: */ + "R (running)", /* 0x00 */ + "S (sleeping)", /* 0x01 */ + "D (disk sleep)", /* 0x02 */ + "T (stopped)", /* 0x04 */ + "t (tracing stop)", /* 0x08 */ + "X (dead)", /* 0x10 */ + "Z (zombie)", /* 0x20 */ + + /* states beyond TASK_REPORT: */ + "I (idle)", /* 0x40 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array) - 1); + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); return task_state_array[__get_task_state(tsk)]; } diff --git a/include/linux/sched.h b/include/linux/sched.h index bc78079334155..286fc1117046b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1241,22 +1241,30 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } +#define TASK_REPORT_IDLE (TASK_REPORT + 1) +#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) + static inline unsigned int __get_task_state(struct task_struct *tsk) { unsigned int tsk_state = READ_ONCE(tsk->state); unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); + if (tsk_state == TASK_PARKED) state = TASK_INTERRUPTIBLE; + if (tsk_state == TASK_IDLE) + state = TASK_REPORT_IDLE; + return fls(state); } static inline char __task_state_to_char(unsigned int state) { - static const char state_char[] = "RSDTtXZ"; + static const char state_char[] = "RSDTtXZI"; - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != sizeof(state_char) - 2); + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); return state_char[state]; } diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index c63e20c9ef24d..b371ef8206e14 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -156,10 +156,11 @@ TRACE_EVENT(sched_switch, TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", __entry->prev_comm, __entry->prev_pid, __entry->prev_prio, - (__entry->prev_state & TASK_REPORT) ? - __print_flags(__entry->prev_state & TASK_REPORT, "|", + (__entry->prev_state & (TASK_REPORT_MAX - 1)) ? + __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, - { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }) : + { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }, + { 0x40, "I" }) : "R", __entry->prev_state & TASK_STATE_MAX ? "+" : "", -- GitLab From 5d68cc95fb24b2f58060cc5340dd7402a11f054e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:32:41 +0200 Subject: [PATCH 0648/1507] sched/debug: Ignore TASK_IDLE for SysRq-W Markus reported that tasks in TASK_IDLE state are reported by SysRq-W, which results in undesirable clutter. Reported-by: Markus Trippelsdorf Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966567daf..d17c5da523a0b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } -- GitLab From 8ef9925b02c23e3838d5e593c5cf37984141150f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Sep 2017 18:37:28 +0200 Subject: [PATCH 0649/1507] sched/debug: Add explicit TASK_PARKED printing Currently TASK_PARKED is masqueraded as TASK_INTERRUPTIBLE, give it its own print state because it will not in fact get woken by regular wakeups and is a long-term state. This requires moving TASK_PARKED into the TASK_REPORT mask, and since that latter needs to be a contiguous bitmask, we need to shuffle the bits around a bit. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/proc/array.c | 3 ++- include/linux/sched.h | 16 +++++++--------- include/trace/events/sched.h | 2 +- 3 files changed, 10 insertions(+), 11 deletions(-) diff --git a/fs/proc/array.c b/fs/proc/array.c index a120a4549d484..77a8eacbe032f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -128,9 +128,10 @@ static const char * const task_state_array[] = { "t (tracing stop)", /* 0x08 */ "X (dead)", /* 0x10 */ "Z (zombie)", /* 0x20 */ + "P (parked)", /* 0x40 */ /* states beyond TASK_REPORT: */ - "I (idle)", /* 0x40 */ + "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) diff --git a/include/linux/sched.h b/include/linux/sched.h index 286fc1117046b..26a7df4e558c2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -75,10 +75,10 @@ struct task_group; #define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_DEAD 0x0040 -#define TASK_WAKEKILL 0x0080 -#define TASK_WAKING 0x0100 -#define TASK_PARKED 0x0200 +#define TASK_PARKED 0x0040 +#define TASK_DEAD 0x0080 +#define TASK_WAKEKILL 0x0100 +#define TASK_WAKING 0x0200 #define TASK_NOLOAD 0x0400 #define TASK_NEW 0x0800 #define TASK_STATE_MAX 0x1000 @@ -97,7 +97,8 @@ struct task_group; /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE) + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) #define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) @@ -1251,9 +1252,6 @@ static inline unsigned int __get_task_state(struct task_struct *tsk) BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); - if (tsk_state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; @@ -1262,7 +1260,7 @@ static inline unsigned int __get_task_state(struct task_struct *tsk) static inline char __task_state_to_char(unsigned int state) { - static const char state_char[] = "RSDTtXZI"; + static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index b371ef8206e14..3c8b7f6256701 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -160,7 +160,7 @@ TRACE_EVENT(sched_switch, __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|", { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" }, { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" }, - { 0x40, "I" }) : + { 0x40, "P" }, { 0x80, "I" }) : "R", __entry->prev_state & TASK_STATE_MAX ? "+" : "", -- GitLab From e5173418ac597cebe9f7a39adf10be470000b518 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Wed, 27 Sep 2017 10:06:27 +0100 Subject: [PATCH 0650/1507] netfilter: ipset: Fix race between dump and swap Fix a race between ip_set_dump_start() and ip_set_swap(). The race is as follows: * Without holding the ref lock, ip_set_swap() checks ref_netlink of the set and it is 0. * ip_set_dump_start() takes a reference on the set. * ip_set_swap() does the swap (even though it now has a non-zero reference count). * ip_set_dump_start() gets the set from ip_set_list again which is now a different set since it has been swapped. * ip_set_dump_start() calls __ip_set_put_netlink() and hits a BUG_ON due to the reference count being 0. Fix this race by extending the critical region in which the ref lock is held to include checking the ref counts. The race can be reproduced with the following script: while :; do ipset destroy hash_ip1 ipset destroy hash_ip2 ipset create hash_ip1 hash:ip family inet hashsize 1024 \ maxelem 500000 ipset create hash_ip2 hash:ip family inet hashsize 300000 \ maxelem 500000 ipset create hash_ip3 hash:ip family inet hashsize 1024 \ maxelem 500000 ipset save & ipset swap hash_ip3 hash_ip2 ipset destroy hash_ip3 wait done Signed-off-by: Ross Lagerwall Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index a7f049ff3049a..cf84f7b37cd9d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1191,14 +1191,17 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, from->family == to->family)) return -IPSET_ERR_TYPE_MISMATCH; - if (from->ref_netlink || to->ref_netlink) + write_lock_bh(&ip_set_ref_lock); + + if (from->ref_netlink || to->ref_netlink) { + write_unlock_bh(&ip_set_ref_lock); return -EBUSY; + } strncpy(from_name, from->name, IPSET_MAXNAMELEN); strncpy(from->name, to->name, IPSET_MAXNAMELEN); strncpy(to->name, from_name, IPSET_MAXNAMELEN); - write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); ip_set(inst, from_id) = to; ip_set(inst, to_id) = from; -- GitLab From 520a13c530aeb5f63e011d668c42db1af19ed349 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 28 Sep 2017 16:58:26 -0500 Subject: [PATCH 0651/1507] x86/asm: Fix inline asm call constraints for GCC 4.4 The kernel test bot (run by Xiaolong Ye) reported that the following commit: f5caf621ee35 ("x86/asm: Fix inline asm call constraints for Clang") is causing double faults in a kernel compiled with GCC 4.4. Linus subsequently diagnosed the crash pattern and the buggy commit and found that the issue is with this code: register unsigned int __asm_call_sp asm("esp"); #define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp) Even on a 64-bit kernel, it's using ESP instead of RSP. That causes GCC to produce the following bogus code: ffffffff8147461d: 89 e0 mov %esp,%eax ffffffff8147461f: 4c 89 f7 mov %r14,%rdi ffffffff81474622: 4c 89 fe mov %r15,%rsi ffffffff81474625: ba 20 00 00 00 mov $0x20,%edx ffffffff8147462a: 89 c4 mov %eax,%esp ffffffff8147462c: e8 bf 52 05 00 callq ffffffff814c98f0 Despite the absurdity of it backing up and restoring the stack pointer for no reason, the bug is actually the fact that it's only backing up and restoring the lower 32 bits of the stack pointer. The upper 32 bits are getting cleared out, corrupting the stack pointer. So change the '__asm_call_sp' register variable to be associated with the actual full-size stack pointer. This also requires changing the __ASM_SEL() macro to be based on the actual compiled arch size, rather than the CONFIG value, because CONFIG_X86_64 compiles some files with '-m32' (e.g., realmode and vdso). Otherwise Clang fails to build the kernel because it complains about the use of a 64-bit register (RSP) in a 32-bit file. Reported-and-Bisected-and-Tested-by: kernel test robot Diagnosed-by: Linus Torvalds Signed-off-by: Josh Poimboeuf Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Dmitriy Vyukov Cc: LKP Cc: Linus Torvalds Cc: Matthias Kaehlcke Cc: Miguel Bernal Marin Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: f5caf621ee35 ("x86/asm: Fix inline asm call constraints for Clang") Link: http://lkml.kernel.org/r/20170928215826.6sdpmwtkiydiytim@treble Signed-off-by: Ingo Molnar --- arch/x86/include/asm/asm.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c1eadbaf1115a..30c3c9ac784a6 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -11,10 +11,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif @@ -139,7 +141,7 @@ * gets set up by the containing function. If you forget to do this, objtool * may print a "call without frame pointer save/setup" warning. */ -register unsigned int __asm_call_sp asm("esp"); +register unsigned long __asm_call_sp asm(_ASM_SP); #define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp) #endif -- GitLab From 5ccba44ba118a5000cccc50076b0344632459779 Mon Sep 17 00:00:00 2001 From: Ethan Zhao Date: Mon, 4 Sep 2017 13:59:34 +0800 Subject: [PATCH 0652/1507] sched/sysctl: Check user input value of sysctl_sched_time_avg System will hang if user set sysctl_sched_time_avg to 0: [root@XXX ~]# sysctl kernel.sched_time_avg_ms=0 Stack traceback for pid 0 0xffff883f6406c600 0 0 1 3 R 0xffff883f6406cf50 *swapper/3 ffff883f7ccc3ae8 0000000000000018 ffffffff810c4dd0 0000000000000000 0000000000017800 ffff883f7ccc3d78 0000000000000003 ffff883f7ccc3bf8 ffffffff810c4fc9 ffff883f7ccc3c08 00000000810c5043 ffff883f7ccc3c08 Call Trace: [] ? update_group_capacity+0x110/0x200 [] ? update_sd_lb_stats+0x109/0x600 [] ? find_busiest_group+0x47/0x530 [] ? load_balance+0x194/0x900 [] ? update_rq_clock.part.83+0x1a/0xe0 [] ? rebalance_domains+0x152/0x290 [] ? run_rebalance_domains+0xdc/0x1d0 [] ? __do_softirq+0xfb/0x320 [] ? irq_exit+0x125/0x130 [] ? scheduler_ipi+0x97/0x160 [] ? smp_reschedule_interrupt+0x29/0x30 [] ? reschedule_interrupt+0x6e/0x80 [] ? cpuidle_enter_state+0xcc/0x230 [] ? cpuidle_enter_state+0x9c/0x230 [] ? cpuidle_enter+0x17/0x20 [] ? cpu_startup_entry+0x38c/0x420 [] ? start_secondary+0x173/0x1e0 Because divide-by-zero error happens in function: update_group_capacity() update_cpu_capacity() scale_rt_capacity() { ... total = sched_avg_period() + delta; used = div_u64(avg, total); ... } To fix this issue, check user input value of sysctl_sched_time_avg, keep it unchanged when hitting invalid input, and set the minimum limit of sysctl_sched_time_avg to 1 ms. Reported-by: James Puthukattukaran Signed-off-by: Ethan Zhao Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: ethan.kernel@gmail.com Cc: keescook@chromium.org Cc: mcgrof@kernel.org Cc: Link: http://lkml.kernel.org/r/1504504774-18253-1-git-send-email-ethan.zhao@oracle.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157f..423554ad36102 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { -- GitLab From 0d18779be13766b33c69cbc26df38383598da373 Mon Sep 17 00:00:00 2001 From: JingPiao Chen Date: Sat, 23 Sep 2017 17:10:44 +0800 Subject: [PATCH 0653/1507] netfilter: nf_tables: fix update chain error # nft add table filter # nft add chain filter c1 # nft rename chain filter c1 c2 Error: Could not process rule: No such file or directory rename chain filter c1 c2 ^^^^^^^^^^^^^^^^^^^^^^^^^^ # nft add chain filter c2 # nft rename chain filter c1 c2 # nft list table filter table ip filter { chain c2 { } chain c2 { } } Fixes: 664b0f8cd8 ("netfilter: nf_tables: add generation mask to chains") Signed-off-by: JingPiao Chen Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 929927171426a..f98ca8c6aa59d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1487,8 +1487,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); - if (IS_ERR(chain2)) - return PTR_ERR(chain2); + if (!IS_ERR(chain2)) + return -EEXIST; } if (nla[NFTA_CHAIN_COUNTERS]) { -- GitLab From e6b72ee88a56bcfe63f72e9c30766484c45bec72 Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Tue, 26 Sep 2017 18:35:45 +0200 Subject: [PATCH 0654/1507] netfilter: ebtables: fix race condition in frame_filter_net_init() It is possible for ebt_in_hook to be triggered before ebt_table is assigned resulting in a NULL-pointer dereference. Make sure hooks are registered as the last step. Fixes: aee12a0a3727 ("ebtables: remove nf_hook_register usage") Signed-off-by: Artem Savkov Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 7 ++++--- net/bridge/netfilter/ebtable_broute.c | 4 ++-- net/bridge/netfilter/ebtable_filter.c | 4 ++-- net/bridge/netfilter/ebtable_nat.c | 4 ++-- net/bridge/netfilter/ebtables.c | 17 +++++++++-------- 5 files changed, 19 insertions(+), 17 deletions(-) diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b0df9..528b24c78308e 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 2585b100ebbbc..276b60262981c 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -65,8 +65,8 @@ static int ebt_broute(struct sk_buff *skb) static int __net_init broute_net_init(struct net *net) { - net->xt.broute_table = ebt_register_table(net, &broute_table, NULL); - return PTR_ERR_OR_ZERO(net->xt.broute_table); + return ebt_register_table(net, &broute_table, NULL, + &net->xt.broute_table); } static void __net_exit broute_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 45a00dbdbcad6..c41da5fac84f4 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_filter[] = { static int __net_init frame_filter_net_init(struct net *net) { - net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter); - return PTR_ERR_OR_ZERO(net->xt.frame_filter); + return ebt_register_table(net, &frame_filter, ebt_ops_filter, + &net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 57cd5bb154e70..08df7406ecb38 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_nat[] = { static int __net_init frame_nat_net_init(struct net *net) { - net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat); - return PTR_ERR_OR_ZERO(net->xt.frame_nat); + return ebt_register_table(net, &frame_nat, ebt_ops_nat, + &net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 83951f978445e..3b3dcf719e078 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1169,9 +1169,8 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) kfree(table); } -struct ebt_table * -ebt_register_table(struct net *net, const struct ebt_table *input_table, - const struct nf_hook_ops *ops) +int ebt_register_table(struct net *net, const struct ebt_table *input_table, + const struct nf_hook_ops *ops, struct ebt_table **res) { struct ebt_table_info *newinfo; struct ebt_table *t, *table; @@ -1183,7 +1182,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, repl->entries == NULL || repl->entries_size == 0 || repl->counters != NULL || input_table->private != NULL) { BUGPRINT("Bad table data for ebt_register_table!!!\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } /* Don't add one table to multiple lists. */ @@ -1252,16 +1251,18 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]); mutex_unlock(&ebt_mutex); + WRITE_ONCE(*res, table); + if (!ops) - return table; + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret) { __ebt_unregister_table(net, table); - return ERR_PTR(ret); + *res = NULL; } - return table; + return ret; free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: @@ -1276,7 +1277,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table, free_table: kfree(table); out: - return ERR_PTR(ret); + return ret; } void ebt_unregister_table(struct net *net, struct ebt_table *table, -- GitLab From 305d0ab4764d36a02c8e7cddb67099aca65351ce Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 28 Sep 2017 18:16:44 -0700 Subject: [PATCH 0655/1507] KVM: nVMX: Fix nested #PF intends to break L1's vmlauch/vmresume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ------------[ cut here ]------------ WARNING: CPU: 4 PID: 5280 at /home/kernel/linux/arch/x86/kvm//vmx.c:11394 nested_vmx_vmexit+0xc2b/0xd70 [kvm_intel] CPU: 4 PID: 5280 Comm: qemu-system-x86 Tainted: G W OE 4.13.0+ #17 RIP: 0010:nested_vmx_vmexit+0xc2b/0xd70 [kvm_intel] Call Trace: ? emulator_read_emulated+0x15/0x20 [kvm] ? segmented_read+0xae/0xf0 [kvm] vmx_inject_page_fault_nested+0x60/0x70 [kvm_intel] ? vmx_inject_page_fault_nested+0x60/0x70 [kvm_intel] x86_emulate_instruction+0x733/0x810 [kvm] vmx_handle_exit+0x2f4/0xda0 [kvm_intel] ? kvm_arch_vcpu_ioctl_run+0xd2f/0x1c60 [kvm] kvm_arch_vcpu_ioctl_run+0xdab/0x1c60 [kvm] ? kvm_arch_vcpu_load+0x62/0x230 [kvm] kvm_vcpu_ioctl+0x340/0x700 [kvm] ? kvm_vcpu_ioctl+0x340/0x700 [kvm] ? __fget+0xfc/0x210 do_vfs_ioctl+0xa4/0x6a0 ? __fget+0x11d/0x210 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x23/0xc2 A nested #PF is triggered during L0 emulating instruction for L2. However, it doesn't consider we should not break L1's vmlauch/vmresme. This patch fixes it by queuing the #PF exception instead ,requesting an immediate VM exit from L2 and keeping the exception for L1 pending for a subsequent nested VM exit. This should actually work all the time, making vmx_inject_page_fault_nested totally unnecessary. However, that's not working yet, so this patch can work around the issue in the meanwhile. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7f62c94196d1b..5bfa353f63548 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -9845,7 +9845,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | -- GitLab From b862789aa5186d5ea3a024b7cfe0f80c3a38b980 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Fri, 29 Sep 2017 19:01:45 +0800 Subject: [PATCH 0656/1507] kvm/x86: Handle async PF in RCU read-side critical sections Sasha Levin reported a WARNING: | WARNING: CPU: 0 PID: 6974 at kernel/rcu/tree_plugin.h:329 | rcu_preempt_note_context_switch kernel/rcu/tree_plugin.h:329 [inline] | WARNING: CPU: 0 PID: 6974 at kernel/rcu/tree_plugin.h:329 | rcu_note_context_switch+0x16c/0x2210 kernel/rcu/tree.c:458 ... | CPU: 0 PID: 6974 Comm: syz-fuzzer Not tainted 4.13.0-next-20170908+ #246 | Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS | 1.10.1-1ubuntu1 04/01/2014 | Call Trace: ... | RIP: 0010:rcu_preempt_note_context_switch kernel/rcu/tree_plugin.h:329 [inline] | RIP: 0010:rcu_note_context_switch+0x16c/0x2210 kernel/rcu/tree.c:458 | RSP: 0018:ffff88003b2debc8 EFLAGS: 00010002 | RAX: 0000000000000001 RBX: 1ffff1000765bd85 RCX: 0000000000000000 | RDX: 1ffff100075d7882 RSI: ffffffffb5c7da20 RDI: ffff88003aebc410 | RBP: ffff88003b2def30 R08: dffffc0000000000 R09: 0000000000000001 | R10: 0000000000000000 R11: 0000000000000000 R12: ffff88003b2def08 | R13: 0000000000000000 R14: ffff88003aebc040 R15: ffff88003aebc040 | __schedule+0x201/0x2240 kernel/sched/core.c:3292 | schedule+0x113/0x460 kernel/sched/core.c:3421 | kvm_async_pf_task_wait+0x43f/0x940 arch/x86/kernel/kvm.c:158 | do_async_page_fault+0x72/0x90 arch/x86/kernel/kvm.c:271 | async_page_fault+0x22/0x30 arch/x86/entry/entry_64.S:1069 | RIP: 0010:format_decode+0x240/0x830 lib/vsprintf.c:1996 | RSP: 0018:ffff88003b2df520 EFLAGS: 00010283 | RAX: 000000000000003f RBX: ffffffffb5d1e141 RCX: ffff88003b2df670 | RDX: 0000000000000001 RSI: dffffc0000000000 RDI: ffffffffb5d1e140 | RBP: ffff88003b2df560 R08: dffffc0000000000 R09: 0000000000000000 | R10: ffff88003b2df718 R11: 0000000000000000 R12: ffff88003b2df5d8 | R13: 0000000000000064 R14: ffffffffb5d1e140 R15: 0000000000000000 | vsnprintf+0x173/0x1700 lib/vsprintf.c:2136 | sprintf+0xbe/0xf0 lib/vsprintf.c:2386 | proc_self_get_link+0xfb/0x1c0 fs/proc/self.c:23 | get_link fs/namei.c:1047 [inline] | link_path_walk+0x1041/0x1490 fs/namei.c:2127 ... This happened when the host hit a page fault, and delivered it as in an async page fault, while the guest was in an RCU read-side critical section. The guest then tries to reschedule in kvm_async_pf_task_wait(), but rcu_preempt_note_context_switch() would treat the reschedule as a sleep in RCU read-side critical section, which is not allowed (even in preemptible RCU). Thus the WARN. To cure this, make kvm_async_pf_task_wait() go to the halt path if the PF happens in a RCU read-side critical section. Reported-by: Sasha Levin Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: stable@vger.kernel.org Signed-off-by: Boqun Feng Signed-off-by: Paolo Bonzini --- arch/x86/kernel/kvm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa60a08b65b10..e675704fa6f7d 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -140,7 +140,8 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || preempt_count() > 1 || + rcu_preempt_depth(); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); -- GitLab From 04eae427406ef6af9b05bd631e235f4a509666b1 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Fri, 29 Sep 2017 08:25:01 -0500 Subject: [PATCH 0657/1507] RDMA/iwpm: Properly mark end of NL messages Commit 1a1c116f3dcf removes nlmsg_len calculation in ibnl_put_attr causing netlink messages to be rejected due to incorrect length. Add nlmsg_end after all attributes are appended to calculate the nlmsg_len. Fixes: 1a1c116f3dcf ("RDMA/netlink: Simplify the put_msg and put_attr") Signed-off-by: Shiraz Saleem Signed-off-by: Tatyana Nikolova Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/core/iwpm_msg.c | 8 ++++++++ drivers/infiniband/core/iwpm_util.c | 5 +++++ 2 files changed, 13 insertions(+) diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c index 30825bb9b8e92..8861c052155ab 100644 --- a/drivers/infiniband/core/iwpm_msg.c +++ b/drivers/infiniband/core/iwpm_msg.c @@ -100,6 +100,8 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) if (ret) goto pid_query_error; + nlmsg_end(skb, nlh); + pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n", __func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name); @@ -170,6 +172,8 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) &pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto add_mapping_error; + + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); @@ -246,6 +250,8 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) &pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR); if (ret) goto query_mapping_error; + + nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); @@ -308,6 +314,8 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) if (ret) goto remove_mapping_error; + nlmsg_end(skb, nlh); + ret = rdma_nl_unicast_wait(skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c index c81c559426262..3c4faadb8cddd 100644 --- a/drivers/infiniband/core/iwpm_util.c +++ b/drivers/infiniband/core/iwpm_util.c @@ -597,6 +597,9 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid) &mapping_num, IWPM_NLA_MAPINFO_SEND_NUM); if (ret) goto mapinfo_num_error; + + nlmsg_end(skb, nlh); + ret = rdma_nl_unicast(skb, iwpm_pid); if (ret) { skb = NULL; @@ -678,6 +681,8 @@ int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid) if (ret) goto send_mapping_info_unlock; + nlmsg_end(skb, nlh); + iwpm_print_sockaddr(&map_info->local_sockaddr, "send_mapping_info: Local sockaddr:"); iwpm_print_sockaddr(&map_info->mapped_sockaddr, -- GitLab From f069faba688701c4d56b6c3452a130f97bf02e95 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 29 Sep 2017 11:29:55 +0100 Subject: [PATCH 0658/1507] arm64: mm: Use READ_ONCE when dereferencing pointer to pte table On kernels built with support for transparent huge pages, different CPUs can access the PMD concurrently due to e.g. fast GUP or page_vma_mapped_walk and they must take care to use READ_ONCE to avoid value tearing or caching of stale values by the compiler. Unfortunately, these functions call into our pgtable macros, which don't use READ_ONCE, and compiler caching has been observed to cause the following crash during ext4 writeback: PC is at check_pte+0x20/0x170 LR is at page_vma_mapped_walk+0x2e0/0x540 [...] Process doio (pid: 2463, stack limit = 0xffff00000f2e8000) Call trace: [] check_pte+0x20/0x170 [] page_vma_mapped_walk+0x2e0/0x540 [] page_mkclean_one+0xac/0x278 [] rmap_walk_file+0xf0/0x238 [] rmap_walk+0x64/0xa0 [] page_mkclean+0x90/0xa8 [] clear_page_dirty_for_io+0x84/0x2a8 [] mpage_submit_page+0x34/0x98 [] mpage_process_page_bufs+0x164/0x170 [] mpage_prepare_extent_to_map+0x134/0x2b8 [] ext4_writepages+0x484/0xe30 [] do_writepages+0x44/0xe8 [] __filemap_fdatawrite_range+0xbc/0x110 [] file_write_and_wait_range+0x48/0xd8 [] ext4_sync_file+0x80/0x4b8 [] vfs_fsync_range+0x64/0xc0 [] SyS_msync+0x194/0x1e8 This is because page_vma_mapped_walk loads the PMD twice before calling pte_offset_map: the first time without READ_ONCE (where it gets all zeroes due to a concurrent pmdp_invalidate) and the second time with READ_ONCE (where it sees a valid table pointer due to a concurrent pmd_populate). However, the compiler inlines everything and caches the first value in a register, which is subsequently used in pte_offset_phys which returns a junk pointer that is later dereferenced when attempting to access the relevant pte. This patch fixes the issue by using READ_ONCE in pte_offset_phys to ensure that a stale value is not used. Whilst this is a point fix for a known failure (and simple to backport), a full fix moving all of our page table accessors over to {READ,WRITE}_ONCE and consistently using READ_ONCE in page_vma_mapped_walk is in the works for a future kernel release. Cc: Jon Masters Cc: Timur Tabi Cc: Fixes: f27176cfc363 ("mm: convert page_mkclean_one() to use page_vma_mapped_walk()") Tested-by: Richard Ruigrok Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index bc4e92337d169..b46e54c2399b5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -401,7 +401,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd) /* Find an entry in the third-level page table. */ #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t)) +#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr)))) #define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr)) -- GitLab From 760bfb47c36a07741a089bf6a28e854ffbee7dc9 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 29 Sep 2017 12:27:41 +0100 Subject: [PATCH 0659/1507] arm64: fault: Route pte translation faults via do_translation_fault We currently route pte translation faults via do_page_fault, which elides the address check against TASK_SIZE before invoking the mm fault handling code. However, this can cause issues with the path walking code in conjunction with our word-at-a-time implementation because load_unaligned_zeropad can end up faulting in kernel space if it reads across a page boundary and runs into a page fault (e.g. by attempting to read from a guard region). In the case of such a fault, load_unaligned_zeropad has registered a fixup to shift the valid data and pad with zeroes, however the abort is reported as a level 3 translation fault and we dispatch it straight to do_page_fault, despite it being a kernel address. This results in calling a sleeping function from atomic context: BUG: sleeping function called from invalid context at arch/arm64/mm/fault.c:313 in_atomic(): 0, irqs_disabled(): 0, pid: 10290 Internal error: Oops - BUG: 0 [#1] PREEMPT SMP [...] [] ___might_sleep+0x134/0x144 [] __might_sleep+0x7c/0x8c [] do_page_fault+0x140/0x330 [] do_mem_abort+0x54/0xb0 Exception stack(0xfffffffb20247a70 to 0xfffffffb20247ba0) [...] [] el1_da+0x18/0x78 [] path_parentat+0x44/0x88 [] filename_parentat+0x5c/0xd8 [] filename_create+0x4c/0x128 [] SyS_mkdirat+0x50/0xc8 [] el0_svc_naked+0x24/0x28 Code: 36380080 d5384100 f9400800 9402566d (d4210000) ---[ end trace 2d01889f2bca9b9f ]--- Fix this by dispatching all translation faults to do_translation_faults, which avoids invoking the page fault logic for faults on kernel addresses. Cc: Reported-by: Ankit Jain Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 89993c4be1bef..2069e9bc0fca6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -651,7 +651,7 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, - { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, -- GitLab From bc829ee36e0ec92383c9d9b88fe08f00d4d592f8 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Fri, 29 Sep 2017 11:24:19 -0500 Subject: [PATCH 0660/1507] x86/mm: Disable branch profiling in mem_encrypt.c Some routines in mem_encrypt.c are called very early in the boot process, e.g. sme_encrypt_kernel(). When CONFIG_TRACE_BRANCH_PROFILING=y is defined the resulting branch profiling associated with the check to see if SME is active results in a kernel crash. Disable branch profiling for mem_encrypt.c by defining DISABLE_BRANCH_PROFILING before including any header files. Reported-by: kernel test robot Signed-off-by: Tom Lendacky Acked-by: Borislav Petkov Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170929162419.6016.53390.stgit@tlendack-t1.amdoffice.net Signed-off-by: Ingo Molnar --- arch/x86/mm/mem_encrypt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 3fcc8e01683be..16c5f37933a2a 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -10,6 +10,8 @@ * published by the Free Software Foundation. */ +#define DISABLE_BRANCH_PROFILING + #include #include #include -- GitLab From 196bd485ee4f03ce4c690bfcf38138abfcd0a4bc Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 29 Sep 2017 17:15:36 +0300 Subject: [PATCH 0661/1507] x86/asm: Use register variable to get stack pointer value Currently we use current_stack_pointer() function to get the value of the stack pointer register. Since commit: f5caf621ee35 ("x86/asm: Fix inline asm call constraints for Clang") ... we have a stack register variable declared. It can be used instead of current_stack_pointer() function which allows to optimize away some excessive "mov %rsp, %" instructions: -mov %rsp,%rdx -sub %rdx,%rax -cmp $0x3fff,%rax -ja ffffffff810722fd +sub %rsp,%rax +cmp $0x3fff,%rax +ja ffffffff810722fa Remove current_stack_pointer(), rename __asm_call_sp to current_stack_pointer and use it instead of the removed function. Signed-off-by: Andrey Ryabinin Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170929141537.29167-1-aryabinin@virtuozzo.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/asm.h | 4 ++-- arch/x86/include/asm/thread_info.h | 11 ----------- arch/x86/kernel/irq_32.c | 6 +++--- arch/x86/kernel/traps.c | 2 +- arch/x86/mm/tlb.c | 2 +- 5 files changed, 7 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 30c3c9ac784a6..b0dc91f4bedc6 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -141,8 +141,8 @@ * gets set up by the containing function. If you forget to do this, objtool * may print a "call without frame pointer save/setup" warning. */ -register unsigned long __asm_call_sp asm(_ASM_SP); -#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp) +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 5161da1a0fa0a..89e7eeb5cec1d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -158,17 +158,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9dea..d4eb450144fdb 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -64,7 +64,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,7 +88,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -139,7 +139,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 34ea3651362ef..67db4f43309ec 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -142,7 +142,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE); preempt_enable_no_resched(); } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 93fe97cce5819..49d9778376d77 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -191,7 +191,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer()); + unsigned int index = pgd_index(current_stack_pointer); pgd_t *pgd = next->pgd + index; if (unlikely(pgd_none(*pgd))) -- GitLab From 6c85501f2fabcfc4fc6ed976543d252c4eaf4be9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Sep 2017 13:43:15 -0400 Subject: [PATCH 0662/1507] fix infoleak in waitid(2) kernel_waitid() can return a PID, an error or 0. rusage is filled in the first case and waitid(2) rusage should've been copied out exactly in that case, *not* whenever kernel_waitid() has not returned an error. Compat variant shares that braino; none of kernel_wait4() callers do, so the below ought to fix it. Reported-and-tested-by: Alexander Potapenko Fixes: ce72a16fa705 ("wait4(2)/waitid(2): separate copying rusage to userland") Cc: stable@vger.kernel.org # v4.13 Signed-off-by: Al Viro --- kernel/exit.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 3481ababd06aa..f2cd53e92147c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) -- GitLab From 2b634bb0686e43a6338fe779fbabd72b6b928fdc Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:10:14 -0400 Subject: [PATCH 0663/1507] i40e/i40evf: rename bytes_per_int to bytes_per_usec This value is not calculating bytes_per_int, which would actually just be bytes/ITR_COUNTDOWN_START, but rather it's calculating bytes/usecs. Rename the variable for clarity so that future developers understand what the value is actually calculating. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 12 ++++++------ drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 12 ++++++------ 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f426762bd83a5..d9fdf69bbc6e8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -960,14 +960,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; u32 new_itr = rc->itr; - int bytes_per_int; + int bytes_per_usec; unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; + bytes_per_usec = rc->total_bytes / usecs; /* The calculations in this algorithm depend on interrupts actually * firing at the ITR rate. This may not happen if the packet rate is @@ -993,18 +993,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) */ switch (new_latency_range) { case I40E_LOWEST_LATENCY: - if (bytes_per_int > 10) + if (bytes_per_usec > 10) new_latency_range = I40E_LOW_LATENCY; break; case I40E_LOW_LATENCY: - if (bytes_per_int > 20) + if (bytes_per_usec > 20) new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_int <= 10) + else if (bytes_per_usec <= 10) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: default: - if (bytes_per_int <= 20) + if (bytes_per_usec <= 20) new_latency_range = I40E_LOW_LATENCY; break; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index c32c62462c844..37e1de886d480 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -358,14 +358,14 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; u32 new_itr = rc->itr; - int bytes_per_int; + int bytes_per_usec; unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; + bytes_per_usec = rc->total_bytes / usecs; /* The calculations in this algorithm depend on interrupts actually * firing at the ITR rate. This may not happen if the packet rate is @@ -391,18 +391,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) */ switch (new_latency_range) { case I40E_LOWEST_LATENCY: - if (bytes_per_int > 10) + if (bytes_per_usec > 10) new_latency_range = I40E_LOW_LATENCY; break; case I40E_LOW_LATENCY: - if (bytes_per_int > 20) + if (bytes_per_usec > 20) new_latency_range = I40E_BULK_LATENCY; - else if (bytes_per_int <= 10) + else if (bytes_per_usec <= 10) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: default: - if (bytes_per_int <= 20) + if (bytes_per_usec <= 20) new_latency_range = I40E_LOW_LATENCY; break; } -- GitLab From 16badf758b25bd00528246ab9af938296b9d368d Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Fri, 14 Jul 2017 09:10:15 -0400 Subject: [PATCH 0664/1507] i40e: Fix unqualified module message while bringing link up In current driver, when ifconfig ethx up is done, the link state doesn't transition to UP inside i40e_open(). It changes after AQ command response is handled in i40e_handle_link_event(). When pf->hw.phy.link_info.link_info is DOWN inside i40e_open(), The state is transient and invalid. So log message gets printed based on incorrect info (i.e link_info and an_info). This commit removes check for unqualified module inside i40e_up_complete(). The existing check in i40e_handle_link_event() logs the error message based on correct link state information. Signed-off-by: Sudheer Mogilappagari Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6498da8806cbf..b235a27232a80 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5470,15 +5470,6 @@ static int i40e_up_complete(struct i40e_vsi *vsi) i40e_print_link_message(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - } else if (vsi->netdev) { - i40e_print_link_message(vsi, false); - /* need to check for qualified module here*/ - if ((pf->hw.phy.link_info.link_info & - I40E_AQ_MEDIA_AVAILABLE) && - (!(pf->hw.phy.link_info.an_info & - I40E_AQ_QUALIFIED_MODULE))) - netdev_err(vsi->netdev, - "the driver failed to link because an unqualified module was detected."); } /* replay FDIR SB filters */ -- GitLab From 9a03449d3ea0f6b497ff3a3bf6203a5e72c7e6be Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Fri, 14 Jul 2017 09:10:16 -0400 Subject: [PATCH 0665/1507] i40e: Fix link down message when interface is brought up i40e_print_link_message() is intended to compare new link state with current link state and print log message only if the new state is different from current state. However in current driver the new state does not get updated when link is going down because of the if condition. When an interface is brought down, vsi->state is set to I40E_VSI_DOWN in i40e_vsi_close() and later i40e_print_link_message() does not get invoked in i40e_link_event due to if condition. Hence link down message doesn't appear when link is going down. The down state is seen later during i40e_open() and old state gets printed. The actual link state doesn't get updated in i40e_close() or i40e_open() but when i40e_handle_link_event is called inside i40e_clean_adminq_subtask. This change allows i40e_print_link_message() to be called when interface is going down and keeps the state information updated. Signed-off-by: Sudheer Mogilappagari Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b235a27232a80..2e8fe6186b38e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6420,8 +6420,7 @@ static void i40e_link_event(struct i40e_pf *pf) new_link == netif_carrier_ok(vsi->netdev))) return; - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - i40e_print_link_message(vsi, new_link); + i40e_print_link_message(vsi, new_link); /* Notify the base of the switch tree connected to * the link. Floating VEBs are not notified. -- GitLab From 3fded4663b07f8fa99b9424ca3d5c46b79f6b27e Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Fri, 14 Jul 2017 09:10:18 -0400 Subject: [PATCH 0666/1507] i40e: simplify member variable accesses This commit replaces usage of vsi->back in i40e_print_link_message() (which is actually a PF pointer) with temp variable. Signed-off-by: Sudheer Mogilappagari Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2e8fe6186b38e..3c650917b54f5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5346,13 +5346,14 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) { enum i40e_aq_link_speed new_speed; + struct i40e_pf *pf = vsi->back; char *speed = "Unknown"; char *fc = "Unknown"; char *fec = ""; char *req_fec = ""; char *an = ""; - new_speed = vsi->back->hw.phy.link_info.link_speed; + new_speed = pf->hw.phy.link_info.link_speed; if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed)) return; @@ -5366,13 +5367,13 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) /* Warn user if link speed on NPAR enabled partition is not at * least 10GB */ - if (vsi->back->hw.func_caps.npar_enable && - (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB || - vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB)) + if (pf->hw.func_caps.npar_enable && + (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB || + pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB)) netdev_warn(vsi->netdev, "The partition detected link speed that is less than 10Gbps\n"); - switch (vsi->back->hw.phy.link_info.link_speed) { + switch (pf->hw.phy.link_info.link_speed) { case I40E_LINK_SPEED_40GB: speed = "40 G"; break; @@ -5395,7 +5396,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) break; } - switch (vsi->back->hw.fc.current_mode) { + switch (pf->hw.fc.current_mode) { case I40E_FC_FULL: fc = "RX/TX"; break; @@ -5410,18 +5411,18 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) break; } - if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { + if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { req_fec = ", Requested FEC: None"; fec = ", FEC: None"; an = ", Autoneg: False"; - if (vsi->back->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) + if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) an = ", Autoneg: True"; - if (vsi->back->hw.phy.link_info.fec_info & + if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA) fec = ", FEC: CL74 FC-FEC/BASE-R"; - else if (vsi->back->hw.phy.link_info.fec_info & + else if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA) fec = ", FEC: CL108 RS-FEC"; -- GitLab From e04ea00217904fc3f6fddac0b74e74e5ac488fda Mon Sep 17 00:00:00 2001 From: Mariusz Stachura Date: Fri, 14 Jul 2017 09:10:19 -0400 Subject: [PATCH 0667/1507] i40e: relax warning message in case of version mismatch Fortville and Fort Park devices are often on different firmware release schedules. This change relaxes the minor version warning message, so it is only displayed for older FW warning version for old firmware Fortville 3 or earlier. Signed-off-by: Mariusz Stachura Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3c650917b54f5..a887087d08cd8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11374,8 +11374,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR) dev_info(&pdev->dev, "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); - else if (hw->aq.api_maj_ver < I40E_FW_API_VERSION_MAJOR || - hw->aq.api_min_ver < (I40E_FW_API_VERSION_MINOR - 1)) + else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4) dev_info(&pdev->dev, "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); -- GitLab From 0dc8692e914ac49931d69b5217d5fe0171fc026e Mon Sep 17 00:00:00 2001 From: Mariusz Stachura Date: Fri, 14 Jul 2017 09:27:00 -0400 Subject: [PATCH 0668/1507] i40e: fix for flow director counters not wrapping as expected An errata with GLQF_PCNT causes it to not wrap as expected. This can cause an error in flow director statistics. This patch resets affected counters just after reading. Signed-off-by: Mariusz Stachura Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 35 ++++++++++++++------- 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a887087d08cd8..638f5bad0bd7a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -599,6 +599,20 @@ static void i40e_stat_update32(struct i40e_hw *hw, u32 reg, *stat = (u32)((new_data + BIT_ULL(32)) - *offset); } +/** + * i40e_stat_update_and_clear32 - read and clear hw reg, update a 32 bit stat + * @hw: ptr to the hardware info + * @reg: the hw reg to read and clear + * @stat: ptr to the stat + **/ +static void i40e_stat_update_and_clear32(struct i40e_hw *hw, u32 reg, u64 *stat) +{ + u32 new_data = rd32(hw, reg); + + wr32(hw, reg, 1); /* must write a nonzero value to clear register */ + *stat += new_data; +} + /** * i40e_update_eth_stats - Update VSI-specific ethernet statistics counters. * @vsi: the VSI to be updated @@ -1040,18 +1054,15 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_jabber, &nsd->rx_jabber); /* FDIR stats */ - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_atr_match, &nsd->fd_atr_match); - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_sb_match, &nsd->fd_sb_match); - i40e_stat_update32(hw, - I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)), - pf->stat_offsets_loaded, - &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(hw->pf_id)), + &nsd->fd_atr_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(hw->pf_id)), + &nsd->fd_sb_match); + i40e_stat_update_and_clear32(hw, + I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(hw->pf_id)), + &nsd->fd_atr_tunnel_match); val = rd32(hw, I40E_PRTPM_EEE_STAT); nsd->tx_lpi_status = -- GitLab From 905770fa3e6f30b393829ba1c238554e7f238aee Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Fri, 14 Jul 2017 09:27:01 -0400 Subject: [PATCH 0669/1507] i40evf: lower message level We see this message regularly on VF reset or unload (which invokes a reset). It's essentially meaningless unless it's happening constantly. To prevent consternation, lower the log level to debug so it's not seen under normal circumstance. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 85876f4fb1fb2..2bb0fe00361f2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -52,7 +52,7 @@ static int i40evf_send_pf_msg(struct i40evf_adapter *adapter, err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); if (err) - dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", + dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", op, i40evf_stat_str(hw, err), i40evf_aq_str(hw, hw->aq.asq_last_status)); return err; -- GitLab From c17401a1dd210a5f22ab1ec7c7366037c158a14c Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:27:02 -0400 Subject: [PATCH 0670/1507] i40e: use separate state bit for miscellaneous IRQ setup We currently (mis)use the __I40E_RECOVERY_PENDING bit to determine when we should actually request a new IRQ in i40e_setup_misc_vector(). This led to a design mistake where we open-coded the re-setup of the miscellaneous vector in i40e_resume() instead of using the function provided. If we did not open-code this and instead tried to use the i40e_setup_misc_vector() function, it would lead to never reallocating the IRQ. This would lead to a second i40e_suspend() call failing to free the vector due to a NULL pointer dereference. A future patch is going to re-work how the i40e_suspend() and i40e_resume() flows work to clear all IRQ vectors, which would require us to use i40e_setup_misc_vector() directly. Since during this time the __I40E_RECOVERY_PENDING bit is set, we'll never re-allocate the vector. Rather than leaving the open-coded setup in i40e_resume() lets just fix the problem properly in i40e_setup_misc_vector(). Introduce a new state bit which indicates when the IRQ has been assigned, which will be set when i40e_setup_misc_vector is first called. This ultimately resolves the issue of re-requesting the vector, without overloading the __I40E_RECOVERY_PENDING state. This ensures that the suspend/resume cycle can use the setup function instead of open-coding the re-request during resume. Additionally, since the only callers of i40e_stop_misc_vector also want to free it, move this code directly into the function to avoid duplication. Due to the new functionality, rename it to i40e_free_misc_vector(). This lets us drop the extra calls to free and re-enable the vector during i40e_suspend() and i40e_resume(). We don't need to call i40e_setup_misc_Vector() in i40e_resume() because it gets called by the i40e_rebuild() call. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 39 ++++++++------------- 2 files changed, 15 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d0c1bf5441d84..b7a539cdca00c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -136,6 +136,7 @@ enum i40e_state_t { __I40E_MDD_EVENT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, + __I40E_MISC_IRQ_REQUESTED, __I40E_RESET_INTR_RECEIVED, __I40E_REINIT_REQUESTED, __I40E_PF_RESET_REQUESTED, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 638f5bad0bd7a..3ea4f8b942c34 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3604,14 +3604,20 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi) } /** - * i40e_stop_misc_vector - Stop the vector that handles non-queue events + * i40e_free_misc_vector - Free the vector that handles non-queue events * @pf: board private structure **/ -static void i40e_stop_misc_vector(struct i40e_pf *pf) +static void i40e_free_misc_vector(struct i40e_pf *pf) { /* Disable ICR 0 */ wr32(&pf->hw, I40E_PFINT_ICR0_ENA, 0); i40e_flush(&pf->hw); + + if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) { + synchronize_irq(pf->msix_entries[0].vector); + free_irq(pf->msix_entries[0].vector, pf); + clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state); + } } /** @@ -4466,11 +4472,7 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf) { int i; - i40e_stop_misc_vector(pf); - if (pf->flags & I40E_FLAG_MSIX_ENABLED && pf->msix_entries) { - synchronize_irq(pf->msix_entries[0].vector); - free_irq(pf->msix_entries[0].vector, pf); - } + i40e_free_misc_vector(pf); i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector, I40E_IWARP_IRQ_PILE_ID); @@ -8365,13 +8367,12 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) struct i40e_hw *hw = &pf->hw; int err = 0; - /* Only request the irq if this is the first time through, and - * not when we're rebuilding after a Reset - */ - if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) { + /* Only request the IRQ once, the first time through. */ + if (!test_and_set_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) { err = request_irq(pf->msix_entries[0].vector, i40e_intr, 0, pf->int_name, pf); if (err) { + clear_bit(__I40E_MISC_IRQ_REQUESTED, pf->state); dev_info(&pf->pdev->dev, "request_irq for %s failed: %d\n", pf->int_name, err); @@ -12069,11 +12070,8 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - i40e_stop_misc_vector(pf); - if (pf->msix_entries) { - synchronize_irq(pf->msix_entries[0].vector); - free_irq(pf->msix_entries[0].vector, pf); - } + i40e_free_misc_vector(pf); + retval = pci_save_state(pdev); if (retval) return retval; @@ -12113,15 +12111,6 @@ static int i40e_resume(struct pci_dev *pdev) /* handling the reset will rebuild the device state */ if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { clear_bit(__I40E_DOWN, pf->state); - if (pf->msix_entries) { - err = request_irq(pf->msix_entries[0].vector, - i40e_intr, 0, pf->int_name, pf); - if (err) { - dev_err(&pf->pdev->dev, - "request_irq for %s failed: %d\n", - pf->int_name, err); - } - } i40e_reset_and_rebuild(pf, false, false); } -- GitLab From 0e5d3da400558b7d30586a2cc1afe02276445636 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:27:03 -0400 Subject: [PATCH 0671/1507] i40e: use newer generic PM support instead of legacy PM callbacks Stop using the old legacy PM support, since we now have stable support for the newer generic PM callbacks. This has several advantages. First, we no longer have to manage our own pci_save_state() and power changes, as it's preferred to have the PCI stack do this. Second, these routines get called for both hibernate and suspend to ram, so we can have the driver properly handle all the suspend/resume flows that it needs to. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 54 +++++++-------------- 1 file changed, 17 insertions(+), 37 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3ea4f8b942c34..c823604370246 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12050,14 +12050,14 @@ static void i40e_shutdown(struct pci_dev *pdev) #ifdef CONFIG_PM /** - * i40e_suspend - PCI callback for moving to D3 - * @pdev: PCI device information struct + * i40e_suspend - PM callback for moving to D3 + * @dev: generic device information structure **/ -static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) +static int i40e_suspend(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); struct i40e_hw *hw = &pf->hw; - int retval = 0; set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); @@ -12072,41 +12072,17 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) i40e_free_misc_vector(pf); - retval = pci_save_state(pdev); - if (retval) - return retval; - - pci_wake_from_d3(pdev, pf->wol_en); - pci_set_power_state(pdev, PCI_D3hot); - - return retval; + return 0; } /** - * i40e_resume - PCI callback for waking up from D3 - * @pdev: PCI device information struct + * i40e_resume - PM callback for waking up from D3 + * @dev: generic device information structure **/ -static int i40e_resume(struct pci_dev *pdev) +static int i40e_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); - u32 err; - - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* pci_restore_state() clears dev->state_saves, so - * call pci_save_state() again to restore it. - */ - pci_save_state(pdev); - - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; - } - pci_set_master(pdev); - - /* no wakeup events while running */ - pci_wake_from_d3(pdev, false); /* handling the reset will rebuild the device state */ if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { @@ -12117,22 +12093,26 @@ static int i40e_resume(struct pci_dev *pdev) return 0; } -#endif +#endif /* CONFIG_PM */ + static const struct pci_error_handlers i40e_err_handler = { .error_detected = i40e_pci_error_detected, .slot_reset = i40e_pci_error_slot_reset, .resume = i40e_pci_error_resume, }; +static SIMPLE_DEV_PM_OPS(i40e_pm_ops, i40e_suspend, i40e_resume); + static struct pci_driver i40e_driver = { .name = i40e_driver_name, .id_table = i40e_pci_tbl, .probe = i40e_probe, .remove = i40e_remove, #ifdef CONFIG_PM - .suspend = i40e_suspend, - .resume = i40e_resume, -#endif + .driver = { + .pm = &i40e_pm_ops, + }, +#endif /* CONFIG_PM */ .shutdown = i40e_shutdown, .err_handler = &i40e_err_handler, .sriov_configure = i40e_pci_sriov_configure, -- GitLab From 401586c2b9bb16147f3dcc64d3596013625e2c44 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:27:04 -0400 Subject: [PATCH 0672/1507] i40e: don't clear suspended state until we finish resuming When handling suspend and resume callbacks we want to make sure that (a) we don't suspend again if we're already suspended and (b) we don't resume again if we're already resuming. Lets make sure we test_and_set the __I40E_SUSPENDED bit in i40e_suspend which ensures that a suspend call when already suspended will exit early. Additionally, if __I40E_SUSPENDED is not set when we begin resuming, exit early as well. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c823604370246..494cafde6b269 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12059,7 +12059,10 @@ static int i40e_suspend(struct device *dev) struct i40e_pf *pf = pci_get_drvdata(pdev); struct i40e_hw *hw = &pf->hw; - set_bit(__I40E_SUSPENDED, pf->state); + /* If we're already suspended, then there is nothing to do */ + if (test_and_set_bit(__I40E_SUSPENDED, pf->state)) + return 0; + set_bit(__I40E_DOWN, pf->state); if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) @@ -12084,11 +12087,15 @@ static int i40e_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); - /* handling the reset will rebuild the device state */ - if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { - clear_bit(__I40E_DOWN, pf->state); - i40e_reset_and_rebuild(pf, false, false); - } + /* If we're not suspended, then there is nothing to do */ + if (!test_bit(__I40E_SUSPENDED, pf->state)) + return 0; + + clear_bit(__I40E_DOWN, pf->state); + i40e_reset_and_rebuild(pf, false, false); + + /* Clear suspended state last after everything is recovered */ + clear_bit(__I40E_SUSPENDED, pf->state); return 0; } -- GitLab From 5c499228803a77bd4e878c7119fbd40a1dc6d773 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:27:05 -0400 Subject: [PATCH 0673/1507] i40e: prevent service task from running while we're suspended Although the service task does check the suspended status before running, it might already be part way through running when we go to suspend. Lets ensure that the service task is stopped and will not be restarted again until we finish resuming. This ensures that service task code does not cause strange interactions with the suspend/resume handlers. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 494cafde6b269..368373459ad5d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12065,6 +12065,10 @@ static int i40e_suspend(struct device *dev) set_bit(__I40E_DOWN, pf->state); + /* Ensure service task will not be running */ + del_timer_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); + if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); @@ -12097,6 +12101,10 @@ static int i40e_resume(struct device *dev) /* Clear suspended state last after everything is recovered */ clear_bit(__I40E_SUSPENDED, pf->state); + /* Restart the service task */ + mod_timer(&pf->service_timer, + round_jiffies(jiffies + pf->service_timer_period)); + return 0; } -- GitLab From b980c0634fe56928a45cc3c0f688d96e36705403 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 14 Jul 2017 09:27:06 -0400 Subject: [PATCH 0674/1507] i40e: shutdown all IRQs and disable MSI-X when suspended On some platforms with a large number of CPUs, we will allocate many IRQ vectors. When hibernating, the system will attempt to migrate all of the vectors back to CPU0 when shutting down all the other CPUs. It is possible that we have so many vectors that it cannot re-assign them to CPU0. This is even more likely if we have many devices installed in one platform. The end result is failure to hibernate, as it is not possible to shutdown the CPUs. We can avoid this by disabling MSI-X and clearing our interrupt scheme when the device is suspended. A more ideal solution would be some method for the stack to properly handle this for all drivers, rather than on a case-by-case basis for each driver to fix itself. However, until this more ideal solution exists, we can do our part and shutdown our IRQs during suspend, which should allow systems with a large number of CPUs to safely suspend or hibernate. It may be worth investigating if we should shut down even further when we suspend as it may make the path cleaner, but this was the minimum fix for the hibernation issue mentioned here. Testing-hints: This affects systems with a large number of CPUs, and with multiple devices enabled. Without this change, those platforms are unable to hibernate at all. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 68 ++++++++++++++++++- .../net/ethernet/intel/i40evf/i40evf_main.c | 2 +- 2 files changed, 68 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 368373459ad5d..8a44793d5390d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8354,6 +8354,57 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) return 0; } +#ifdef CONFIG_PM +/** + * i40e_restore_interrupt_scheme - Restore the interrupt scheme + * @pf: private board data structure + * + * Restore the interrupt scheme that was cleared when we suspended the + * device. This should be called during resume to re-allocate the q_vectors + * and reacquire IRQs. + */ +static int i40e_restore_interrupt_scheme(struct i40e_pf *pf) +{ + int err, i; + + /* We cleared the MSI and MSI-X flags when disabling the old interrupt + * scheme. We need to re-enabled them here in order to attempt to + * re-acquire the MSI or MSI-X vectors + */ + pf->flags |= (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED); + + err = i40e_init_interrupt_scheme(pf); + if (err) + return err; + + /* Now that we've re-acquired IRQs, we need to remap the vectors and + * rings together again. + */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (pf->vsi[i]) { + err = i40e_vsi_alloc_q_vectors(pf->vsi[i]); + if (err) + goto err_unwind; + i40e_vsi_map_rings_to_vectors(pf->vsi[i]); + } + } + + err = i40e_setup_misc_vector(pf); + if (err) + goto err_unwind; + + return 0; + +err_unwind: + while (i--) { + if (pf->vsi[i]) + i40e_vsi_free_q_vectors(pf->vsi[i]); + } + + return err; +} +#endif /* CONFIG_PM */ + /** * i40e_setup_misc_vector - Setup the misc vector to handle non queue events * @pf: board private structure @@ -12077,7 +12128,12 @@ static int i40e_suspend(struct device *dev) wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - i40e_free_misc_vector(pf); + /* Clear the interrupt scheme and release our IRQs so that the system + * can safely hibernate even when there are a large number of CPUs. + * Otherwise hibernation might fail when mapping all the vectors back + * to CPU0. + */ + i40e_clear_interrupt_scheme(pf); return 0; } @@ -12090,11 +12146,21 @@ static int i40e_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct i40e_pf *pf = pci_get_drvdata(pdev); + int err; /* If we're not suspended, then there is nothing to do */ if (!test_bit(__I40E_SUSPENDED, pf->state)) return 0; + /* We cleared the interrupt scheme when we suspended, so we need to + * restore it now to resume device functionality. + */ + err = i40e_restore_interrupt_scheme(pf); + if (err) { + dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n", + err); + } + clear_bit(__I40E_DOWN, pf->state); i40e_reset_and_rebuild(pf, false, false); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index c243f9da95ae0..80ade65102797 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -46,7 +46,7 @@ static const char i40evf_driver_string[] = #define DRV_VERSION_MAJOR 3 #define DRV_VERSION_MINOR 0 -#define DRV_VERSION_BUILD 0 +#define DRV_VERSION_BUILD 1 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ -- GitLab From c97fc9b6a798f4253c176231ba0aceda6b59b058 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Fri, 14 Jul 2017 09:27:07 -0400 Subject: [PATCH 0675/1507] i40evf: fix ring to vector mapping The current implementation for mapping queues to vectors is broken because it attempts to map each Tx and Rx ring to its own vector, however we use combined queues so we should actually be mapping the Tx/Rx rings together on one vector. Also in the current implementation, in the case where we have more queues than vectors, we attempt to group the queues together into 'chunks' and map each 'chunk' of queues to a vector. Chunking them together would be more ideal if, and only if, we only had RSS because of the way the hashing algorithm works but in the case of a future patch that enables VF ADq, round robin assignment is better and still works with RSS. This patch resolves both those issues and simplifies the code needed to accomplish this. Instead of treating the case where we have more queues than vectors as special, if we notice our vector index is greater than vectors, reset the vector index to zero and continue mapping. This should ensure that in both cases, whether we have enough vectors for each queue or not, the queues get appropriately mapped. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40evf/i40evf_main.c | 48 ++++--------------- 1 file changed, 10 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 80ade65102797..69ef6c1d5364f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -432,52 +432,24 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) **/ static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) { + int rings_remaining = adapter->num_active_queues; + int ridx = 0, vidx = 0; int q_vectors; - int v_start = 0; - int rxr_idx = 0, txr_idx = 0; - int rxr_remaining = adapter->num_active_queues; - int txr_remaining = adapter->num_active_queues; - int i, j; - int rqpv, tqpv; int err = 0; q_vectors = adapter->num_msix_vectors - NONQ_VECS; - /* The ideal configuration... - * We have enough vectors to map one per queue. - */ - if (q_vectors >= (rxr_remaining * 2)) { - for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) - i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx); + for (; ridx < rings_remaining; ridx++) { + i40evf_map_vector_to_rxq(adapter, vidx, ridx); + i40evf_map_vector_to_txq(adapter, vidx, ridx); - for (; txr_idx < txr_remaining; v_start++, txr_idx++) - i40evf_map_vector_to_txq(adapter, v_start, txr_idx); - goto out; - } - - /* If we don't have enough vectors for a 1-to-1 - * mapping, we'll have to group them so there are - * multiple queues per vector. - * Re-adjusting *qpv takes care of the remainder. - */ - for (i = v_start; i < q_vectors; i++) { - rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i); - for (j = 0; j < rqpv; j++) { - i40evf_map_vector_to_rxq(adapter, i, rxr_idx); - rxr_idx++; - rxr_remaining--; - } - } - for (i = v_start; i < q_vectors; i++) { - tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i); - for (j = 0; j < tqpv; j++) { - i40evf_map_vector_to_txq(adapter, i, txr_idx); - txr_idx++; - txr_remaining--; - } + /* In the case where we have more queues than vectors, continue + * round-robin on vectors until all queues are mapped. + */ + if (++vidx >= q_vectors) + vidx = 0; } -out: adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; return err; -- GitLab From a3f5aa907340b5d7b54223ddbaa90410f168864d Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Fri, 14 Jul 2017 09:27:08 -0400 Subject: [PATCH 0676/1507] i40e: Enable VF to negotiate number of allocated queues Currently the PF allocates a default number of queues for each VF and cannot be changed. This patch enables the VF to request a different number of queues allocated to it. This patch also adds a new virtchnl op and capability flag to facilitate this negotiation. After the PF receives a request message, it will set a requested number of queues for that VF. Then when the VF resets, its VSI will get a new number of queues allocated to it. This is a best effort request and since we only allocate a guaranteed default number, if the VF tries to ask for more than the guaranteed number, there may not be enough in HW to accommodate it unless other queues for other VFs are freed. It should also be noted decreasing the number queues allocated to a VF to below the default will NOT enable the allocation of more than 32 VFs per PF and will not free queues guaranteed to each VF by default. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 75 +++++++++++++++++++ .../ethernet/intel/i40e/i40e_virtchnl_pf.h | 1 + include/linux/avf/virtchnl.h | 20 +++++ 4 files changed, 97 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index b7a539cdca00c..439c63cb2a0cf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -77,6 +77,7 @@ #define i40e_default_queues_per_vmdq(pf) \ (((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1) #define I40E_DEFAULT_QUEUES_PER_VF 4 +#define I40E_MAX_VF_QUEUES 16 #define I40E_DEFAULT_QUEUES_PER_TC 1 /* should be a power of 2 */ #define i40e_pf_get_max_q_per_tc(pf) \ (((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4d1e670f490ed..a75396c157d95 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -815,6 +815,14 @@ static void i40e_free_vf_res(struct i40e_vf *vf) */ clear_bit(I40E_VF_STATE_INIT, &vf->vf_states); + /* It's possible the VF had requeuested more queues than the default so + * do the accounting here when we're about to free them. + */ + if (vf->num_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) { + pf->queues_left += vf->num_queue_pairs - + I40E_DEFAULT_QUEUES_PER_VF; + } + /* free vsi & disconnect it from the parent uplink */ if (vf->lan_vsi_idx) { i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]); @@ -868,12 +876,27 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) int total_queue_pairs = 0; int ret; + if (vf->num_req_queues && + vf->num_req_queues <= pf->queues_left + I40E_DEFAULT_QUEUES_PER_VF) + pf->num_vf_qps = vf->num_req_queues; + else + pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; + /* allocate hw vsi context & associated resources */ ret = i40e_alloc_vsi_res(vf, I40E_VSI_SRIOV); if (ret) goto error_alloc; total_queue_pairs += pf->vsi[vf->lan_vsi_idx]->alloc_queue_pairs; + /* We account for each VF to get a default number of queue pairs. If + * the VF has now requested more, we need to account for that to make + * certain we never request more queues than we actually have left in + * HW. + */ + if (total_queue_pairs > I40E_DEFAULT_QUEUES_PER_VF) + pf->queues_left -= + total_queue_pairs - I40E_DEFAULT_QUEUES_PER_VF; + if (vf->trusted) set_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); else @@ -1579,6 +1602,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; } + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_REQ_QUEUES) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; + vfres->num_vsis = num_vsis; vfres->num_queue_pairs = vf->num_queue_pairs; vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; @@ -1986,6 +2012,52 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) aq_ret); } +/** + * i40e_vc_request_queues_msg + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * VFs get a default number of queues but can use this message to request a + * different number. Will respond with either the number requested or the + * maximum we can support. + **/ +static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) +{ + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + int req_pairs = vfres->num_queue_pairs; + int cur_pairs = vf->num_queue_pairs; + struct i40e_pf *pf = vf->pf; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) + return -EINVAL; + + if (req_pairs <= 0) { + dev_err(&pf->pdev->dev, + "VF %d tried to request %d queues. Ignoring.\n", + vf->vf_id, req_pairs); + } else if (req_pairs > I40E_MAX_VF_QUEUES) { + dev_err(&pf->pdev->dev, + "VF %d tried to request more than %d queues.\n", + vf->vf_id, + I40E_MAX_VF_QUEUES); + vfres->num_queue_pairs = I40E_MAX_VF_QUEUES; + } else if (req_pairs - cur_pairs > pf->queues_left) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but only %d left.\n", + vf->vf_id, + req_pairs - cur_pairs, + pf->queues_left); + vfres->num_queue_pairs = pf->queues_left + cur_pairs; + } else { + vf->num_req_queues = req_pairs; + } + + return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0, + (u8 *)vfres, sizeof(vfres)); +} + /** * i40e_vc_get_stats_msg * @vf: pointer to the VF info @@ -2708,6 +2780,9 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen); break; + case VIRTCHNL_OP_REQUEST_QUEUES: + ret = i40e_vc_request_queues_msg(vf, msg, msglen); + break; case VIRTCHNL_OP_UNKNOWN: default: diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 1f4b0c504368f..5111d05d5f2f0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -97,6 +97,7 @@ struct i40e_vf { u16 lan_vsi_id; /* ID as used by firmware */ u8 num_queue_pairs; /* num of qps assigned to VF vsis */ + u8 num_req_queues; /* num of requested qps */ u64 num_mdd_events; /* num of mdd events detected */ /* num of continuous malformed or invalid msgs detected */ u64 num_invalid_msgs; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2b038442c352a..60e5d90cb18ac 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -135,6 +135,7 @@ enum virtchnl_ops { VIRTCHNL_OP_SET_RSS_HENA = 26, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, + VIRTCHNL_OP_REQUEST_QUEUES = 29, }; /* This macro is used to generate a compilation error if a structure @@ -235,6 +236,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 +#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040 #define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 @@ -325,6 +327,21 @@ struct virtchnl_vsi_queue_config_info { struct virtchnl_queue_pair_info qpair[1]; }; +/* VIRTCHNL_OP_REQUEST_QUEUES + * VF sends this message to request the PF to allocate additional queues to + * this VF. Each VF gets a guaranteed number of queues on init but asking for + * additional queues must be negotiated. This is a best effort request as it + * is possible the PF does not have enough queues left to support the request. + * If the PF cannot support the number requested it will respond with the + * maximum number it is able to support; otherwise it will respond with the + * number requested. + */ + +/* VF resource request */ +struct virtchnl_vf_res_request { + u16 num_queue_pairs; +}; + VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info); /* VIRTCHNL_OP_CONFIG_IRQ_MAP @@ -691,6 +708,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: break; + case VIRTCHNL_OP_REQUEST_QUEUES: + valid_len = sizeof(struct virtchnl_vf_res_request); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: -- GitLab From 22b96551f213d7e7d743442c923c266a10306b9b Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Fri, 14 Jul 2017 09:27:09 -0400 Subject: [PATCH 0677/1507] i40e: refactor FW version checking The i40e driver now supports two different devices with two different firmware versions. So be smart about how we handle these. Move the FW version macros to the appropriate header file, and add a convenience macro that checks the version based on the device. Then use this macro to check whether or not the driver can use the new link info API. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 10 +++++++++- drivers/net/ethernet/intel/i40e/i40e_common.c | 6 ++++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 10 +++++++++- 4 files changed, 23 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 5d5f422cbae55..e2a9ec80a6237 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -34,7 +34,15 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0005 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 struct i40e_aq_desc { __le16 flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 111426ba5fbce..7346d8850c8e8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1593,8 +1593,10 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, status = I40E_ERR_UNKNOWN_PHY; if (report_init) { - hw->phy.phy_types = le32_to_cpu(abilities->phy_type); - hw->phy.phy_types |= ((u64)abilities->phy_type_ext << 32); + if (hw->mac.type == I40E_MAC_XL710 && + hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && + hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) + status = i40e_aq_get_link_info(hw, true, NULL, NULL); } return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8a44793d5390d..47f71d7c3ae0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11434,7 +11434,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_nvm_version_str(hw)); if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && - hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR) + hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) dev_info(&pdev->dev, "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 83e63e55c4b4e..f9f48d1900b0a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -34,7 +34,15 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0005 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 struct i40e_aq_desc { __le16 flags; -- GitLab From 9792bf5ad5e30b207274ccbb459a89eab6033b46 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 22 Sep 2017 22:00:29 -0700 Subject: [PATCH 0678/1507] clk: Export clk_bulk_prepare() Allow clk_bulk_prepare() to be referenced by kernel modules by adding the missing EXPORT_SYMBOL_GPL(). Fixes: 266e4e9d9150 ("clk: add clk_bulk_get accessories") Reported-by: Ulf Hansson Signed-off-by: Bjorn Andersson Reviewed-by: Ulf Hansson Signed-off-by: Stephen Boyd --- drivers/clk/clk-bulk.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c index c834f5abfc497..4c10456f8a329 100644 --- a/drivers/clk/clk-bulk.c +++ b/drivers/clk/clk-bulk.c @@ -105,6 +105,7 @@ int __must_check clk_bulk_prepare(int num_clks, return ret; } +EXPORT_SYMBOL_GPL(clk_bulk_prepare); #endif /* CONFIG_HAVE_CLK_PREPARE */ -- GitLab From 1f372c7bfb23286d2bf4ce0423ab488e86b74bb2 Mon Sep 17 00:00:00 2001 From: Mike Manning Date: Mon, 25 Sep 2017 22:01:36 +0100 Subject: [PATCH 0679/1507] net: ipv6: send NS for DAD when link operationally up The NS for DAD are sent on admin up as long as a valid qdisc is found. A race condition exists by which these packets will not egress the interface if the operational state of the lower device is not yet up. The solution is to delay DAD until the link is operationally up according to RFC2863. Rather than only doing this, follow the existing code checks by deferring IPv6 device initialization altogether. The fix allows DAD on devices like tunnels that are controlled by userspace control plane. The fix has no impact on regular deployments, but means that there is no IPv6 connectivity until the port has been opened in the case of port-based network access control, which should be desirable. Signed-off-by: Mike Manning Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 13c3b697f8c04..f553f72d0bee7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -303,10 +303,10 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .disable_policy = 0, }; -/* Check if a valid qdisc is available */ -static inline bool addrconf_qdisc_ok(const struct net_device *dev) +/* Check if link is ready: is it up and is a valid qdisc available */ +static inline bool addrconf_link_ready(const struct net_device *dev) { - return !qdisc_tx_is_noop(dev); + return netif_oper_up(dev) && !qdisc_tx_is_noop(dev); } static void addrconf_del_rs_timer(struct inet6_dev *idev) @@ -451,7 +451,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) ndev->token = in6addr_any; - if (netif_running(dev) && addrconf_qdisc_ok(dev)) + if (netif_running(dev) && addrconf_link_ready(dev)) ndev->if_flags |= IF_READY; ipv6_mc_init_dev(ndev); @@ -3403,7 +3403,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, /* restore routes for permanent addresses */ addrconf_permanent_addr(dev); - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); @@ -3418,7 +3418,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } } else if (event == NETDEV_CHANGE) { - if (!addrconf_qdisc_ok(dev)) { + if (!addrconf_link_ready(dev)) { /* device is still not ready. */ break; } -- GitLab From 84e14fe353de7624872e582887712079ba0b2d56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 26 Sep 2017 21:32:42 -0700 Subject: [PATCH 0680/1507] net-ipv6: add support for sockopt(SOL_IPV6, IPV6_FREEBIND) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far we've been relying on sockopt(SOL_IP, IP_FREEBIND) being usable even on IPv6 sockets. However, it turns out it is perfectly reasonable to want to set freebind on an AF_INET6 SOCK_RAW socket - but there is no way to set any SOL_IP socket option on such a socket (they're all blindly errored out). One use case for this is to allow spoofing src ip on a raw socket via sendmsg cmsg. Tested: built, and booted # python >>> import socket >>> SOL_IP = socket.SOL_IP >>> SOL_IPV6 = socket.IPPROTO_IPV6 >>> IP_FREEBIND = 15 >>> IPV6_FREEBIND = 78 >>> s = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM, 0) >>> s.getsockopt(SOL_IP, IP_FREEBIND) 0 >>> s.getsockopt(SOL_IPV6, IPV6_FREEBIND) 0 >>> s.setsockopt(SOL_IPV6, IPV6_FREEBIND, 1) >>> s.getsockopt(SOL_IP, IP_FREEBIND) 1 >>> s.getsockopt(SOL_IPV6, IPV6_FREEBIND) 1 Signed-off-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/uapi/linux/in6.h | 1 + net/ipv6/ipv6_sockglue.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 46444f8fbee4e..4f8f3eb0699f2 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -284,6 +284,7 @@ struct in6_flowlabel_req { #define IPV6_TRANSPARENT 75 #define IPV6_UNICAST_IF 76 #define IPV6_RECVFRAGSIZE 77 +#define IPV6_FREEBIND 78 /* * Multicast Routing: diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a5e466d4e0931..b9404feabd785 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -377,6 +377,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_FREEBIND: + if (optlen < sizeof(int)) + goto e_inval; + /* we also don't have a separate freebind bit for IPV6 */ + inet_sk(sk)->freebind = valbool; + retv = 0; + break; + case IPV6_RECVORIGDSTADDR: if (optlen < sizeof(int)) goto e_inval; @@ -1214,6 +1222,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = inet_sk(sk)->transparent; break; + case IPV6_FREEBIND: + val = inet_sk(sk)->freebind; + break; + case IPV6_RECVORIGDSTADDR: val = np->rxopt.bits.rxorigdstaddr; break; -- GitLab From 45c1fd61d5cead2ae23880e0677b8660ab9006a4 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 27 Sep 2017 22:45:13 +0100 Subject: [PATCH 0681/1507] mkiss: remove redundant check on len being zero The check on len is redundant as it is always greater than 1, so just remove it and make the printk less complex. Detected by CoverityScan, CID#1226729 ("Logically dead code") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/hamradio/mkiss.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index aec6c26563cff..54bf8e6e4a090 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -477,7 +477,8 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len) cmd = 0; } ax->crcauto = (cmd ? 0 : 1); - printk(KERN_INFO "mkiss: %s: crc mode %s %d\n", ax->dev->name, (len) ? "set to" : "is", cmd); + printk(KERN_INFO "mkiss: %s: crc mode set to %d\n", + ax->dev->name, cmd); } spin_unlock_bh(&ax->buflock); netif_start_queue(dev); -- GitLab From 706cc9f51d9a22528af18d4b3ffbd17b30a1d3b0 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 30 Sep 2017 09:24:28 +0200 Subject: [PATCH 0682/1507] batman-adv: Add argument names for function ptr definitions checkpatch started to report unnamed arguments in function pointer definitions. Add the corresponding names to these definitions to avoid this warning. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 033819aefc390..4daed7ad46f21 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -73,8 +73,8 @@ * list traversals just rcu-locked */ struct list_head batadv_hardif_list; -static int (*batadv_rx_handler[256])(struct sk_buff *, - struct batadv_hard_iface *); +static int (*batadv_rx_handler[256])(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); unsigned char batadv_broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; @@ -540,8 +540,8 @@ batadv_recv_handler_register(u8 packet_type, int (*recv_handler)(struct sk_buff *, struct batadv_hard_iface *)) { - int (*curr)(struct sk_buff *, - struct batadv_hard_iface *); + int (*curr)(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); curr = batadv_rx_handler[packet_type]; if (curr != batadv_recv_unhandled_packet && -- GitLab From fef0035c0f31322d417d1954bba5ab959bf91183 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 28 Sep 2017 00:41:44 +0200 Subject: [PATCH 0683/1507] netlink: do not proceed if dump's start() errs Drivers that use the start method for netlink dumping rely on dumpit not being called if start fails. For example, ila_xlat.c allocates memory and assigns it to cb->args[0] in its start() function. It might fail to do that and return -ENOMEM instead. However, even when returning an error, dumpit will be called, which, in the example above, quickly dereferences the memory in cb->args[0], which will OOPS the kernel. This is but one example of how this goes wrong. Since start() has always been a function with an int return type, it therefore makes sense to use it properly, rather than ignoring it. This patch thus returns early and does not call dumpit() when start() fails. Signed-off-by: Jason A. Donenfeld Cc: Johannes Berg Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 327807731b441..94c11cf0459d3 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2270,10 +2270,13 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, mutex_unlock(nlk->cb_mutex); + ret = 0; if (cb->start) - cb->start(cb); + ret = cb->start(cb); + + if (!ret) + ret = netlink_dump(sk); - ret = netlink_dump(sk); sock_put(sk); if (ret) -- GitLab From d51711c0557d6dbd26c63144aef32c7b3ec264b9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Sep 2017 13:23:31 +0800 Subject: [PATCH 0684/1507] ip_gre: ipgre_tap device should keep dst Without keeping dst, the tunnel will not update any mtu/pmtu info, since it does not have a dst on the skb. Reproducer: client(ipgre_tap1 - eth1) <-----> (eth1 - ipgre_tap1)server After reducing eth1's mtu on client, then perforamnce became 0. This patch is to netif_keep_dst in gre_tap_init, as ipgre does. Reported-by: Jianlin Shi Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0162fb955b33a..8b837f6f55320 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1223,6 +1223,7 @@ static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } -- GitLab From 2d40557cc702ed8e5edd9bd422233f86652d932e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Sep 2017 13:23:50 +0800 Subject: [PATCH 0685/1507] ip6_gre: ip6gre_tap device should keep dst The patch 'ip_gre: ipgre_tap device should keep dst' fixed a issue that ipgre_tap mtu couldn't be updated in tx path. The same fix is needed for ip6gre_tap as well. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 20f66f4c94605..1602b491b2811 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1311,6 +1311,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); } static bool ip6gre_netlink_encap_parms(struct nlattr *data[], -- GitLab From d41bb33ba33b8f8debe54ed36be6925eb496e354 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 28 Sep 2017 13:24:07 +0800 Subject: [PATCH 0686/1507] ip6_tunnel: update mtu properly for ARPHRD_ETHER tunnel device in tx path Now when updating mtu in tx path, it doesn't consider ARPHRD_ETHER tunnel device, like ip6gre_tap tunnel, for which it should also subtract ether header to get the correct mtu. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f2f21c24915f1..a1c24443cd9e0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1043,6 +1043,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int mtu; + unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; bool use_cache = false; @@ -1124,7 +1125,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, t->parms.name); goto tx_err_dst_release; } - mtu = dst_mtu(dst) - psh_hlen - t->tun_hlen; + mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; @@ -1133,7 +1134,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, mtu = IPV6_MIN_MTU; if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); - if (skb->len - t->tun_hlen > mtu && !skb_is_gso(skb)) { + if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; -- GitLab From 7487449c86c65202b3b725c4524cb48dd65e4e6f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 28 Sep 2017 15:51:36 +0200 Subject: [PATCH 0687/1507] IPv4: early demux can return an error code Currently no error is emitted, but this infrastructure will used by the next patch to allow source address validation for mcast sockets. Since early demux can do a route lookup and an ipv4 route lookup can return an error code this is consistent with the current ipv4 route infrastructure. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/protocol.h | 4 ++-- include/net/tcp.h | 2 +- include/net/udp.h | 2 +- net/ipv4/ip_input.c | 25 +++++++++++++++---------- net/ipv4/tcp_ipv4.c | 9 +++++---- net/ipv4/udp.c | 11 ++++++----- 6 files changed, 30 insertions(+), 23 deletions(-) diff --git a/include/net/protocol.h b/include/net/protocol.h index 65ba335b0e7e6..4fc75f7ae23be 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -39,8 +39,8 @@ /* This is used to register protocols. */ struct net_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); + int (*early_demux)(struct sk_buff *skb); + int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, diff --git a/include/net/tcp.h b/include/net/tcp.h index 3bc910a9bfc6f..89974c5286d8a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -345,7 +345,7 @@ void tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); -void tcp_v4_early_demux(struct sk_buff *skb); +int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); diff --git a/include/net/udp.h b/include/net/udp.h index 12dfbfe2e2d78..6c759c8594e25 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -259,7 +259,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); } -void udp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fa2dc8f692c63..57fc13c6ab2b7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -311,9 +311,10 @@ static inline bool ip_rcv_options(struct sk_buff *skb) static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); - struct rtable *rt; + int (*edemux)(struct sk_buff *skb); struct net_device *dev = skb->dev; - void (*edemux)(struct sk_buff *skb); + struct rtable *rt; + int err; /* if ingress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -331,7 +332,9 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - edemux(skb); + err = edemux(skb); + if (unlikely(err)) + goto drop_error; /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } @@ -342,13 +345,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { - int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, dev); - if (unlikely(err)) { - if (err == -EXDEV) - __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); - goto drop; - } + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, dev); + if (unlikely(err)) + goto drop_error; } #ifdef CONFIG_IP_ROUTE_CLASSID @@ -399,6 +399,11 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) drop: kfree_skb(skb); return NET_RX_DROP; + +drop_error: + if (err == -EXDEV) + __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + goto drop; } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5162bc1..85164d4d3e537 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1503,23 +1503,23 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(tcp_v4_do_rcv); -void tcp_v4_early_demux(struct sk_buff *skb) +int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) - return; + return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) - return; + return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) - return; + return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, @@ -1538,6 +1538,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb_dst_set_noref(skb, dst); } } + return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ef29df8648e4d..9b30f821fe96b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2221,7 +2221,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, return NULL; } -void udp_v4_early_demux(struct sk_buff *skb) +int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct iphdr *iph; @@ -2234,7 +2234,7 @@ void udp_v4_early_demux(struct sk_buff *skb) /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) - return; + return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); @@ -2244,14 +2244,14 @@ void udp_v4_early_demux(struct sk_buff *skb) struct in_device *in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) - return; + return 0; /* we are supposed to accept bcast packets */ if (skb->pkt_type == PACKET_MULTICAST) { ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, iph->protocol); if (!ours) - return; + return 0; } sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, @@ -2263,7 +2263,7 @@ void udp_v4_early_demux(struct sk_buff *skb) } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) - return; + return 0; skb->sk = sk; skb->destructor = sock_efree; @@ -2278,6 +2278,7 @@ void udp_v4_early_demux(struct sk_buff *skb) */ skb_dst_set_noref(skb, dst); } + return 0; } int udp_rcv(struct sk_buff *skb) -- GitLab From bc044e8db7962e727a75b591b9851ff2ac5cf846 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 28 Sep 2017 15:51:37 +0200 Subject: [PATCH 0688/1507] udp: perform source validation for mcast early demux The UDP early demux can leverate the rx dst cache even for multicast unconnected sockets. In such scenario the ipv4 source address is validated only on the first packet in the given flow. After that, when we fetch the dst entry from the socket rx cache, we stop enforcing the rp_filter and we even start accepting any kind of martian addresses. Disabling the dst cache for unconnected multicast socket will cause large performace regression, nearly reducing by half the max ingress tput. Instead we factor out a route helper to completely validate an skb source address for multicast packets and we call it from the UDP early demux for mcast packets landing on unconnected sockets, after successful fetching the related cached dst entry. This still gives a measurable, but limited performance regression: rp_filter = 0 rp_filter = 1 edmux disabled: 1182 Kpps 1127 Kpps edmux before: 2238 Kpps 2238 Kpps edmux after: 2037 Kpps 2019 Kpps The above figures are on top of current net tree. Applying the net-next commit 6e617de84e87 ("net: avoid a full fib lookup when rp_filter is disabled.") the delta with rp_filter == 0 will decrease even more. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/route.h | 4 +++- net/ipv4/route.c | 46 +++++++++++++++++++++++++-------------------- net/ipv4/udp.c | 13 ++++++++++++- 3 files changed, 41 insertions(+), 22 deletions(-) diff --git a/include/net/route.h b/include/net/route.h index 57dfc6850d378..d538e6db1afef 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -175,7 +175,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } - +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 94d4cd2d5ea4f..ac6fde5d45f14 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1520,43 +1520,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev, EXPORT_SYMBOL(rt_dst_alloc); /* called in rcu_read_lock() section */ -static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev, int our) +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + struct in_device *in_dev, u32 *itag) { - struct rtable *rth; - struct in_device *in_dev = __in_dev_get_rcu(dev); - unsigned int flags = RTCF_MULTICAST; - u32 itag = 0; int err; /* Primary sanity checks. */ - if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) - goto e_inval; + return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) - goto e_inval; + return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) - goto e_inval; + return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, - in_dev, &itag); + in_dev, itag); if (err < 0) - goto e_err; + return err; } + return 0; +} + +/* called in rcu_read_lock() section */ +static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, int our) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; + struct rtable *rth; + u32 itag = 0; + int err; + + err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); + if (err) + return err; + if (our) flags |= RTCF_LOCAL; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) - goto e_nobufs; + return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; @@ -1572,13 +1585,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb_dst_set(skb, &rth->dst); return 0; - -e_nobufs: - return -ENOBUFS; -e_inval: - return -EINVAL; -e_err: - return err; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9b30f821fe96b..5676237d2b0f8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2224,6 +2224,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; @@ -2241,7 +2242,7 @@ int udp_v4_early_demux(struct sk_buff *skb) if (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; @@ -2272,11 +2273,21 @@ int udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { + u32 itag = 0; + /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); + + /* for unconnected multicast sockets we need to validate + * the source on each packet + */ + if (!inet_sk(sk)->inet_daddr && in_dev) + return ip_mc_validate_source(skb, iph->daddr, + iph->saddr, iph->tos, + skb->dev, in_dev, &itag); } return 0; } -- GitLab From 5a59a3a0ef0e546626a762d49dc06feaa204bab3 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 28 Sep 2017 17:57:58 +0200 Subject: [PATCH 0689/1507] ppp: fix __percpu annotation Move sparse annotation right after pointer type. Fixes sparse warning: drivers/net/ppp/ppp_generic.c:1422:13: warning: incorrect type in initializer (different address spaces) drivers/net/ppp/ppp_generic.c:1422:13: expected void const [noderef] *__vpp_verify drivers/net/ppp/ppp_generic.c:1422:13: got int * ... Fixes: e5dadc65f9e0 ("ppp: Fix false xmit recursion detect with two ppp devices") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index a404552555d48..c3f77e3b7819c 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -120,7 +120,7 @@ struct ppp { int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ - int *xmit_recursion __percpu; /* xmit recursion detect */ + int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ -- GitLab From 21a2774ef5d4fde772fbcb9d0eabb76f585e5af5 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 28 Sep 2017 11:19:06 -0700 Subject: [PATCH 0690/1507] Revert "net: dsa: bcm_sf2: Defer port enabling to calling port_enable" This reverts commit e85ec74ace29 ("net: dsa: bcm_sf2: Defer port enabling to calling port_enable") because this now makes an unbind followed by a bind to fail connecting to the ingrated PHY. What this patch missed is that we need the PHY to be enabled with bcm_sf2_gphy_enable_set() before probing it on the MDIO bus. This is correctly done in the ops->setup() function, but by the time ops->port_enable() runs, this is too late. Upon unbind we would power down the PHY, and so when we would bind again, the PHY would be left powered off. Fixes: e85ec74ace29 ("net: dsa: bcm_sf2: Defer port enabling to calling port_enable") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 898d5642b516b..7aecc98d0a189 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -754,11 +754,14 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds) struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); unsigned int port; - /* Disable unused ports and configure IMP port */ + /* Enable all valid ports and disable those unused */ for (port = 0; port < priv->hw_params.num_ports; port++) { - if (dsa_is_cpu_port(ds, port)) + /* IMP port receives special treatment */ + if ((1 << port) & ds->enabled_port_mask) + bcm_sf2_port_setup(ds, port, NULL); + else if (dsa_is_cpu_port(ds, port)) bcm_sf2_imp_setup(ds, port); - else if (!((1 << port) & ds->enabled_port_mask)) + else bcm_sf2_port_disable(ds, port, NULL); } -- GitLab From e876a8a7e9dd89dc88c12ca2e81beb478dbe9897 Mon Sep 17 00:00:00 2001 From: Mick Tarsel Date: Thu, 28 Sep 2017 13:53:18 -0700 Subject: [PATCH 0691/1507] ibmvnic: Set state UP State is initially reported as UNKNOWN. Before register call netif_carrier_off(). Once the device is opened, call netif_carrier_on() in order to set the state to UP. Signed-off-by: Mick Tarsel Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index cb8182f4fdfa1..4bc14a9015711 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -927,6 +927,7 @@ static int ibmvnic_open(struct net_device *netdev) } rc = __ibmvnic_open(netdev); + netif_carrier_on(netdev); mutex_unlock(&adapter->reset_lock); return rc; @@ -3899,6 +3900,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) if (rc) goto ibmvnic_init_fail; + netif_carrier_off(netdev); rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); -- GitLab From aad06212d36cf34859428a0a279e5c14ee5c9e26 Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Fri, 29 Sep 2017 10:02:54 +0200 Subject: [PATCH 0692/1507] tipc: use only positive error codes in messages In commit e3a77561e7d32 ("tipc: split up function tipc_msg_eval()"), we have updated the function tipc_msg_lookup_dest() to set the error codes to negative values at destination lookup failures. Thus when the function sets the error code to -TIPC_ERR_NO_NAME, its inserted into the 4 bit error field of the message header as 0xf instead of TIPC_ERR_NO_NAME (1). The value 0xf is an unknown error code. In this commit, we set only positive error code. Fixes: e3a77561e7d32 ("tipc: split up function tipc_msg_eval()") Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- net/tipc/msg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 6ef379f004ac6..121e59a1d0e72 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -551,7 +551,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) return false; if (msg_errcode(msg)) return false; - *err = -TIPC_ERR_NO_NAME; + *err = TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; msg = buf_msg(skb); -- GitLab From ef739d8aabaa26dd99f5661e38a86f4d85d8dfed Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 29 Sep 2017 14:34:22 +0100 Subject: [PATCH 0693/1507] net: ipmr: make function ipmr_notifier_init static The function ipmr_notifier_init is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: warning: symbol 'ipmr_notifier_init' was not declared. Should it be static? Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 292a8e80bdfaa..a844738b38bd4 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -3224,7 +3224,7 @@ static const struct fib_notifier_ops ipmr_notifier_ops_template = { .owner = THIS_MODULE, }; -int __net_init ipmr_notifier_init(struct net *net) +static int __net_init ipmr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; -- GitLab From b1c49d14200dae47544f7ea6ee9040ded01f8425 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 29 Sep 2017 15:01:16 +0100 Subject: [PATCH 0694/1507] net_sched: remove redundant assignment to ret The assignment of -EINVAL to variable ret is redundant as it is being overwritten on the following error exit paths or to the return value from the following call to basic_set_parms. Fix this up by removing it. Cleans up clang warning message: net/sched/cls_basic.c:185:2: warning: Value stored to 'err' is never read Fixes: 1d8134fea2eb ("net_sched: use idr to allocate basic filter handles") Signed-off-by: Colin Ian King Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_basic.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index cfeb6f1585669..700b345b07f9f 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -182,7 +182,6 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - err = -EINVAL; if (handle) { fnew->handle = handle; if (!fold) { -- GitLab From 721e08dad17e226ef68819d0a23dc53c25fe8ea5 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 29 Sep 2017 10:52:17 -0700 Subject: [PATCH 0695/1507] bpf: Fix compiler warning on info.map_ids for 32bit platform This patch uses u64_to_user_ptr() to cast info.map_ids to a userspace ptr. It also tags the user_map_ids with '__user' for sparse check. Fixes: cb4d2b3f03d8 ("bpf: Add name, load_time, uid and map_ids to bpf_prog_info") Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 11a7f82a55d19..b927da66f653f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1405,7 +1405,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { - u32 *user_map_ids = (u32 *)info.map_ids; + u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) -- GitLab From 09af87d18f6ba05588e6316c47fdacf06e28cce8 Mon Sep 17 00:00:00 2001 From: Simon Xiao Date: Fri, 29 Sep 2017 11:39:46 -0700 Subject: [PATCH 0696/1507] hv_netvsc: report stop_queue and wake_queue Report the numbers of events for stop_queue and wake_queue in ethtool stats. Example: ethtool -S eth0 NIC statistics: ... stop_queue: 7 wake_queue: 7 ... Signed-off-by: Simon Xiao Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 2 ++ drivers/net/hyperv/netvsc.c | 12 ++++++++++-- drivers/net/hyperv/netvsc_drv.c | 2 ++ 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 5176be76ca7d5..6f550e15a41cc 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -686,6 +686,8 @@ struct netvsc_ethtool_stats { unsigned long tx_busy; unsigned long tx_send_full; unsigned long rx_comp_busy; + unsigned long stop_queue; + unsigned long wake_queue; }; struct netvsc_vf_pcpu_stats { diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index b0d323e249781..6e5194916bbee 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -609,6 +609,7 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, { struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id; struct net_device *ndev = hv_get_drvdata(device); + struct net_device_context *ndev_ctx = netdev_priv(ndev); struct vmbus_channel *channel = device->channel; u16 q_idx = 0; int queue_sends; @@ -643,8 +644,10 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) && (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || - queue_sends < 1)) + queue_sends < 1)) { netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx)); + ndev_ctx->eth_stats.wake_queue++; + } } static void netvsc_send_completion(struct netvsc_device *net_device, @@ -749,6 +752,7 @@ static inline int netvsc_send_pkt( &net_device->chan_table[packet->q_idx]; struct vmbus_channel *out_channel = nvchan->channel; struct net_device *ndev = hv_get_drvdata(device); + struct net_device_context *ndev_ctx = netdev_priv(ndev); struct netdev_queue *txq = netdev_get_tx_queue(ndev, packet->q_idx); u64 req_id; int ret; @@ -789,12 +793,16 @@ static inline int netvsc_send_pkt( if (ret == 0) { atomic_inc_return(&nvchan->queue_sends); - if (ring_avail < RING_AVAIL_PERCENT_LOWATER) + if (ring_avail < RING_AVAIL_PERCENT_LOWATER) { netif_tx_stop_queue(txq); + ndev_ctx->eth_stats.stop_queue++; + } } else if (ret == -EAGAIN) { netif_tx_stop_queue(txq); + ndev_ctx->eth_stats.stop_queue++; if (atomic_read(&nvchan->queue_sends) < 1) { netif_tx_wake_queue(txq); + ndev_ctx->eth_stats.wake_queue++; ret = -ENOSPC; } } else { diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index e9d54c9ee78cf..f300ae61c6c6c 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1126,6 +1126,8 @@ static const struct { { "tx_busy", offsetof(struct netvsc_ethtool_stats, tx_busy) }, { "tx_send_full", offsetof(struct netvsc_ethtool_stats, tx_send_full) }, { "rx_comp_busy", offsetof(struct netvsc_ethtool_stats, rx_comp_busy) }, + { "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) }, + { "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) }, }, vf_stats[] = { { "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) }, { "vf_rx_bytes", offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) }, -- GitLab From 075cfdd659cb1e86f948f11ba577f27706f0756e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 29 Sep 2017 20:51:23 +0100 Subject: [PATCH 0697/1507] net: hns3: fix null pointer dereference before null check pointer ndev is being dereferenced with the call to netif_running before it is being null checked. Re-order the code to only dereference ndev after it has been null checked. Detected by CoverityScan, CID#1457206 ("Dereference before null check") Fixes: 9df8f79a4d29 ("net: hns3: Add DCB support when interacting with network stack") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index 4a0890f98b706..c31506514e5da 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -2865,7 +2865,7 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; struct net_device *ndev = kinfo->netdev; - bool if_running = netif_running(ndev); + bool if_running; int ret; u8 i; @@ -2875,6 +2875,8 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc) if (!ndev) return -ENODEV; + if_running = netif_running(ndev); + ret = netdev_set_num_tc(ndev, tc); if (ret) return ret; -- GitLab From 3775b1b7f0c330e59c434d1852d7762ae0a9c164 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:15 -0400 Subject: [PATCH 0698/1507] net: dsa: add master helper to look up slaves The DSA tagging code does not need to know about the DSA architecture, it only needs to return the slave device corresponding to the source port index (and eventually the source device index for cascade-capable switches) parsed from the frame received on the master device. For this purpose, provide an inline dsa_master_get_slave helper which validates the device and port indexes and look up the slave device. This makes the tagging rcv functions more concise and robust, and also makes dsa_get_cpu_port obsolete. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 24 +++++++++++++++++++----- net/dsa/tag_brcm.c | 9 ++------- net/dsa/tag_dsa.c | 18 ++---------------- net/dsa/tag_edsa.c | 18 ++---------------- net/dsa/tag_ksz.c | 9 +++------ net/dsa/tag_lan9303.c | 20 ++------------------ net/dsa/tag_mtk.c | 16 +++------------- net/dsa/tag_qca.c | 17 +++-------------- net/dsa/tag_trailer.c | 9 +++------ 9 files changed, 39 insertions(+), 101 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index eccc627762837..d429505dc4e71 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -113,6 +113,25 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], int dsa_master_ethtool_setup(struct net_device *dev); void dsa_master_ethtool_restore(struct net_device *dev); +static inline struct net_device *dsa_master_get_slave(struct net_device *dev, + int device, int port) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_switch *ds; + + if (device < 0 || device >= DSA_MAX_SWITCHES) + return NULL; + + ds = dst->ds[device]; + if (!ds) + return NULL; + + if (port < 0 || port >= ds->num_ports) + return NULL; + + return ds->ports[port].netdev; +} + /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, struct switchdev_trans *trans); @@ -182,9 +201,4 @@ static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) return p->dp->cpu_dp->netdev; } -static inline struct dsa_port *dsa_get_cpu_port(struct dsa_switch_tree *dst) -{ - return dst->cpu_dp; -} - #endif diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index dbb016434ace8..8e4bdb9d9ae36 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -92,9 +92,6 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; int source_port; u8 *brcm_tag; @@ -117,8 +114,8 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - /* Validate port against switch setup, either the port is totally */ - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + skb->dev = dsa_master_get_slave(dev, 0, source_port); + if (!skb->dev) return NULL; /* Remove Broadcom tag and update checksum */ @@ -129,8 +126,6 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb->data - ETH_HLEN - BRCM_TAG_LEN, 2 * ETH_ALEN); - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index fbf9ca954773d..c77218f173d1b 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -67,8 +67,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; u8 *dsa_header; int source_device; int source_port; @@ -93,18 +91,8 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - /* - * Check that the source device exists and that the source - * port is a registered DSA port. - */ - if (source_device >= DSA_MAX_SWITCHES) - return NULL; - - ds = dst->ds[source_device]; - if (!ds) - return NULL; - - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + skb->dev = dsa_master_get_slave(dev, source_device, source_port); + if (!skb->dev) return NULL; /* @@ -153,8 +141,6 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 76367ba1b2e24..0b83cbe0c9e8a 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -80,8 +80,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; u8 *edsa_header; int source_device; int source_port; @@ -106,18 +104,8 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = edsa_header[0] & 0x1f; source_port = (edsa_header[1] >> 3) & 0x1f; - /* - * Check that the source device exists and that the source - * port is a registered DSA port. - */ - if (source_device >= DSA_MAX_SWITCHES) - return NULL; - - ds = dst->ds[source_device]; - if (!ds) - return NULL; - - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + skb->dev = dsa_master_get_slave(dev, source_device, source_port); + if (!skb->dev) return NULL; /* @@ -172,8 +160,6 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 010ca0a336c46..b241c990cde08 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -80,22 +80,19 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; u8 *tag; int source_port; tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; source_port = tag[0] & 7; - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + + skb->dev = dsa_master_get_slave(dev, 0, source_port); + if (!skb->dev) return NULL; pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 0b9826105e421..4f211e56c81fe 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -71,17 +71,8 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { u16 *lan9303_tag; - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; unsigned int source_port; - ds = dst->ds[0]; - - if (unlikely(!ds)) { - dev_warn_ratelimited(&dev->dev, "Dropping packet, due to missing DSA switch device\n"); - return NULL; - } - if (unlikely(!pskb_may_pull(skb, LAN9303_TAG_LEN))) { dev_warn_ratelimited(&dev->dev, "Dropping packet, cannot pull\n"); @@ -103,16 +94,12 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, source_port = ntohs(lan9303_tag[1]) & 0x3; - if (source_port >= ds->num_ports) { + skb->dev = dsa_master_get_slave(dev, 0, source_port); + if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; } - if (!ds->ports[source_port].netdev) { - dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid netdev or device\n"); - return NULL; - } - /* remove the special VLAN tag between the MAC addresses * and the current ethertype field. */ @@ -120,9 +107,6 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN), 2 * ETH_ALEN); - /* forward the packet to the dedicated interface */ - skb->dev = ds->ports[source_port].netdev; - return skb; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index ec8ee5f43255e..968586c5d40e8 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -46,8 +46,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds; int port; __be16 *phdr, hdr; @@ -68,20 +66,12 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb->data - ETH_HLEN - MTK_HDR_LEN, 2 * ETH_ALEN); - /* This protocol doesn't support cascading multiple - * switches so it's safe to assume the switch is first - * in the tree. - */ - ds = dst->ds[0]; - if (!ds) - return NULL; - /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - if (!ds->ports[port].netdev) - return NULL; - skb->dev = ds->ports[port].netdev; + skb->dev = dsa_master_get_slave(dev, 0, port); + if (!skb->dev) + return NULL; return skb; } diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1d4c70711c0f4..8d33d9ebf910d 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -65,9 +65,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds; u8 ver; int port; __be16 *phdr, hdr; @@ -92,20 +89,12 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN, ETH_HLEN - QCA_HDR_LEN); - /* This protocol doesn't support cascading multiple switches so it's - * safe to assume the switch is first in the tree - */ - ds = cpu_dp->ds; - if (!ds) - return NULL; - /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); - if (!ds->ports[port].netdev) - return NULL; - /* Update skb & forward the frame accordingly */ - skb->dev = ds->ports[port].netdev; + skb->dev = dsa_master_get_slave(dev, 0, port); + if (!skb->dev) + return NULL; return skb; } diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d2fd4923aa3eb..61668be267f5d 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -58,9 +58,6 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; u8 *trailer; int source_port; @@ -73,13 +70,13 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; source_port = trailer[1] & 7; - if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + + skb->dev = dsa_master_get_slave(dev, 0, source_port); + if (!skb->dev) return NULL; pskb_trim_rcsum(skb, skb->len - 4); - skb->dev = ds->ports[source_port].netdev; - return skb; } -- GitLab From 7ec764eef934409c4e15539440c31bca0b8de005 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:16 -0400 Subject: [PATCH 0699/1507] net: dsa: use cpu_dp in master code Make it clear that the master device is linked to a CPU port by using "cpu_dp" for the dsa_port variable in master.c instead of "port", then use a "port" variable to describe the port index, as usually seen in other places of DSA core. This will make the future patch touching dsa_ptr more readable. There is no functional changes. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/master.c | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) diff --git a/net/dsa/master.c b/net/dsa/master.c index 5e5147ec5a444..ef15d35f1574b 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -17,9 +17,10 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, uint64_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *port = dst->cpu_dp; - struct dsa_switch *ds = port->ds; - const struct ethtool_ops *ops = port->orig_ethtool_ops; + struct dsa_port *cpu_dp = dst->cpu_dp; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; int count = 0; if (ops && ops->get_sset_count && ops->get_ethtool_stats) { @@ -28,15 +29,15 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, } if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, port->index, data + count); + ds->ops->get_ethtool_stats(ds, port, data + count); } static int dsa_master_get_sset_count(struct net_device *dev, int sset) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *port = dst->cpu_dp; - struct dsa_switch *ds = port->ds; - const struct ethtool_ops *ops = port->orig_ethtool_ops; + struct dsa_port *cpu_dp = dst->cpu_dp; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; int count = 0; if (ops && ops->get_sset_count) @@ -52,16 +53,17 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *port = dst->cpu_dp; - struct dsa_switch *ds = port->ds; - const struct ethtool_ops *ops = port->orig_ethtool_ops; + struct dsa_port *cpu_dp = dst->cpu_dp; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; int len = ETH_GSTRING_LEN; int mcount = 0, count; unsigned int i; uint8_t pfx[4]; uint8_t *ndata; - snprintf(pfx, sizeof(pfx), "p%.2d", port->index); + snprintf(pfx, sizeof(pfx), "p%.2d", port); /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; @@ -76,7 +78,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, * the output after to prepend our CPU port prefix we * constructed earlier */ - ds->ops->get_strings(ds, port->index, ndata); + ds->ops->get_strings(ds, port, ndata); count = ds->ops->get_sset_count(ds); for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), @@ -89,17 +91,17 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, int dsa_master_ethtool_setup(struct net_device *dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *port = dst->cpu_dp; - struct dsa_switch *ds = port->ds; + struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_switch *ds = cpu_dp->ds; struct ethtool_ops *ops; ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); if (!ops) return -ENOMEM; - port->orig_ethtool_ops = dev->ethtool_ops; - if (port->orig_ethtool_ops) - memcpy(ops, port->orig_ethtool_ops, sizeof(*ops)); + cpu_dp->orig_ethtool_ops = dev->ethtool_ops; + if (cpu_dp->orig_ethtool_ops) + memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; @@ -113,8 +115,8 @@ int dsa_master_ethtool_setup(struct net_device *dev) void dsa_master_ethtool_restore(struct net_device *dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *port = dst->cpu_dp; + struct dsa_port *cpu_dp = dst->cpu_dp; - dev->ethtool_ops = port->orig_ethtool_ops; - port->orig_ethtool_ops = NULL; + dev->ethtool_ops = cpu_dp->orig_ethtool_ops; + cpu_dp->orig_ethtool_ops = NULL; } -- GitLab From 62fc95876298987c35e9fb10badd467f4787aae7 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:17 -0400 Subject: [PATCH 0700/1507] net: dsa: use temporary dsa_device_ops variable When resolving the DSA tagging protocol used by a CPU switch, use a temporary "tag_ops" variable to store the dsa_device_ops instead of using directly dst->tag_ops. This will make the future patches moving this pointer around easier to read. There is no functional changes. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 8 +++++--- net/dsa/legacy.c | 8 +++++--- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index dcccaebde7086..6a10c5c1639f2 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -485,6 +485,7 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, struct dsa_switch_tree *dst, struct dsa_switch *ds) { + const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; struct net_device *ethernet_dev; struct device_node *ethernet; @@ -514,13 +515,14 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, ds->cpu_port_mask |= BIT(index); tag_protocol = ds->ops->get_tag_protocol(ds); - dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); - if (IS_ERR(dst->tag_ops)) { + tag_ops = dsa_resolve_tag_protocol(tag_protocol); + if (IS_ERR(tag_ops)) { dev_warn(ds->dev, "No tagger for this switch\n"); ds->cpu_port_mask &= ~BIT(index); - return PTR_ERR(dst->tag_ops); + return PTR_ERR(tag_ops); } + dst->tag_ops = tag_ops; dst->rcv = dst->tag_ops->rcv; return 0; diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index ae505d8e4417b..8e849013f69d9 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -144,13 +144,15 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, * switch. */ if (dst->cpu_dp->ds == ds) { + const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; tag_protocol = ops->get_tag_protocol(ds); - dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); - if (IS_ERR(dst->tag_ops)) - return PTR_ERR(dst->tag_ops); + tag_ops = dsa_resolve_tag_protocol(tag_protocol); + if (IS_ERR(tag_ops)) + return PTR_ERR(tag_ops); + dst->tag_ops = tag_ops; dst->rcv = dst->tag_ops->rcv; } -- GitLab From 152402483ed75b167d5628d414e876ffa7a6d4c4 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:18 -0400 Subject: [PATCH 0701/1507] net: dsa: add tagging ops to port The DSA tagging protocol operations are specific to each CPU port, thus the dsa_device_ops pointer belongs to the dsa_port structure. >From now on assign a slave's xmit copy from its CPU port tagging operations. This will ease the future support for multiple CPU ports. Also keep the tag_ops at the beginning of the dsa_port structure so that we ensure copies for hot path are in cacheline 1. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 3 +++ net/dsa/dsa2.c | 1 + net/dsa/dsa_priv.h | 2 +- net/dsa/legacy.c | 1 + net/dsa/slave.c | 3 +-- 5 files changed, 7 insertions(+), 3 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index 8dee216a5a9b1..4d1df2f086e89 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -175,6 +175,9 @@ struct dsa_mall_tc_entry { struct dsa_port { + /* CPU port tagging operations used by master or slave devices */ + const struct dsa_device_ops *tag_ops; + struct dsa_switch *ds; unsigned int index; const char *name; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 6a10c5c1639f2..9eac4726dc0c8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -522,6 +522,7 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, return PTR_ERR(tag_ops); } + dst->cpu_dp->tag_ops = tag_ops; dst->tag_ops = tag_ops; dst->rcv = dst->tag_ops->rcv; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index d429505dc4e71..9397291bb3aae 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -66,7 +66,7 @@ struct dsa_notifier_vlan_info { }; struct dsa_slave_priv { - /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ + /* Copy of CPU port xmit for faster access in slave transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 8e849013f69d9..4d374541815ac 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -152,6 +152,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, if (IS_ERR(tag_ops)) return PTR_ERR(tag_ops); + dst->cpu_dp->tag_ops = tag_ops; dst->tag_ops = tag_ops; dst->rcv = dst->tag_ops->rcv; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index bf8800de13c17..4b634db05cee4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1117,7 +1117,6 @@ int dsa_slave_resume(struct net_device *slave_dev) int dsa_slave_create(struct dsa_port *port, const char *name) { struct dsa_switch *ds = port->ds; - struct dsa_switch_tree *dst = ds->dst; struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; @@ -1162,7 +1161,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) } p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = dst->tag_ops->xmit; + p->xmit = cpu_dp->tag_ops->xmit; p->old_pause = -1; p->old_link = -1; -- GitLab From 3e41f93b358a8800194b87995ad076fc50919719 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:19 -0400 Subject: [PATCH 0702/1507] net: dsa: prepare master receive hot path In preparation to make DSA master devices point to their corresponding CPU port instead of the whole tree, add copies of dst and rcv in the dsa_port structure so that we keep fast access in the receive hot path. Also keep the copies at the beginning of the dsa_port structure in order to ensure they are available in cacheline 1. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ net/dsa/dsa2.c | 4 ++++ net/dsa/legacy.c | 4 ++++ 3 files changed, 13 insertions(+) diff --git a/include/net/dsa.h b/include/net/dsa.h index 4d1df2f086e89..6bda01fa57477 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -178,6 +178,11 @@ struct dsa_port { /* CPU port tagging operations used by master or slave devices */ const struct dsa_device_ops *tag_ops; + /* Copies for faster access in master receive hot path */ + struct dsa_switch_tree *dst; + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt); + struct dsa_switch *ds; unsigned int index; const char *name; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9eac4726dc0c8..b71e3bb478e43 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -524,7 +524,11 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, dst->cpu_dp->tag_ops = tag_ops; dst->tag_ops = tag_ops; + + /* Make a few copies for faster access in master receive hot path */ + dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv; dst->rcv = dst->tag_ops->rcv; + dst->cpu_dp->dst = dst; return 0; } diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 4d374541815ac..96c7e3f8b8bb8 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -154,7 +154,11 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, dst->cpu_dp->tag_ops = tag_ops; dst->tag_ops = tag_ops; + + /* Few copies for faster access in master receive hot path */ + dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv; dst->rcv = dst->tag_ops->rcv; + dst->cpu_dp->dst = dst; } memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable)); -- GitLab From 2f657a600409f1961d67642fe384a9d4be71d36a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:20 -0400 Subject: [PATCH 0703/1507] net: dsa: change dsa_ptr for a dsa_port With DSA, a master net device (CPU facing interface) has a dsa_ptr pointer to which hangs a dsa_switch_tree. This is not correct because a master interface is wired to a dedicated switch port, and because we can theoretically have several master interfaces pointing to several CPU ports of the same switch fabric. Change the master interface's dsa_ptr for the CPU dsa_port pointer. This is a step towards supporting multiple CPU ports. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- net/dsa/dsa.c | 6 +++--- net/dsa/dsa2.c | 2 +- net/dsa/dsa_priv.h | 3 ++- net/dsa/legacy.c | 2 +- net/dsa/master.c | 15 +++++---------- 6 files changed, 14 insertions(+), 18 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f535779d9dc1d..e1d6ef130611d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -55,7 +55,7 @@ struct netpoll_info; struct device; struct phy_device; -struct dsa_switch_tree; +struct dsa_port; /* 802.11 specific */ struct wireless_dev; @@ -1752,7 +1752,7 @@ struct net_device { struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) - struct dsa_switch_tree *dsa_ptr; + struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 81c852e328217..51ca2a524a27b 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -160,12 +160,12 @@ EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { - struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; struct pcpu_sw_netstats *s; struct dsa_slave_priv *p; - if (unlikely(dst == NULL)) { + if (unlikely(!cpu_dp)) { kfree_skb(skb); return 0; } @@ -174,7 +174,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; - nskb = dst->rcv(skb, dev, pt); + nskb = cpu_dp->rcv(skb, dev, pt); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b71e3bb478e43..62302558f38c0 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -438,7 +438,7 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) * sent to the tag format's receive function. */ wmb(); - dst->cpu_dp->netdev->dsa_ptr = dst; + dst->cpu_dp->netdev->dsa_ptr = dst->cpu_dp; err = dsa_master_ethtool_setup(dst->cpu_dp->netdev); if (err) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 9397291bb3aae..2850077cc9ccb 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -116,7 +116,8 @@ void dsa_master_ethtool_restore(struct net_device *dev); static inline struct net_device *dsa_master_get_slave(struct net_device *dev, int device, int port) { - struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_switch *ds; if (device < 0 || device >= DSA_MAX_SWITCHES) diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 96c7e3f8b8bb8..71917505a5ccf 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -607,7 +607,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, * sent to the tag format's receive function. */ wmb(); - dev->dsa_ptr = dst; + dev->dsa_ptr = dst->cpu_dp; return dsa_master_ethtool_setup(dst->cpu_dp->netdev); } diff --git a/net/dsa/master.c b/net/dsa/master.c index ef15d35f1574b..5f3f57e372e02 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -16,8 +16,7 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; @@ -34,8 +33,7 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, static int dsa_master_get_sset_count(struct net_device *dev, int sset) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; struct dsa_switch *ds = cpu_dp->ds; int count = 0; @@ -52,8 +50,7 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; @@ -90,8 +87,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, int dsa_master_ethtool_setup(struct net_device *dev) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch *ds = cpu_dp->ds; struct ethtool_ops *ops; @@ -114,8 +110,7 @@ int dsa_master_ethtool_setup(struct net_device *dev) void dsa_master_ethtool_restore(struct net_device *dev) { - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dst->cpu_dp; + struct dsa_port *cpu_dp = dev->dsa_ptr; dev->ethtool_ops = cpu_dp->orig_ethtool_ops; cpu_dp->orig_ethtool_ops = NULL; -- GitLab From aa193d9b1d7ea6893ce24a9d141f676950563987 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 29 Sep 2017 17:19:21 -0400 Subject: [PATCH 0704/1507] net: dsa: remove tag ops from the switch tree Now that the dsa_ptr is a dsa_port instance, there is no need to keep the tag operations in the dsa_switch_tree structure. Remove it. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 11 ----------- net/dsa/dsa2.c | 2 -- net/dsa/legacy.c | 2 -- 3 files changed, 15 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index 6bda01fa57477..10dceccd9ce86 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -130,11 +130,6 @@ struct dsa_switch_tree { */ struct dsa_platform_data *pd; - /* Copy of tag_ops->rcv for faster access in hot path */ - struct sk_buff * (*rcv)(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt); - /* * The switch port to which the CPU is attached. */ @@ -144,12 +139,6 @@ struct dsa_switch_tree { * Data for the individual switch chips. */ struct dsa_switch *ds[DSA_MAX_SWITCHES]; - - /* - * Tagging protocol operations for adding and removing an - * encapsulation tag. - */ - const struct dsa_device_ops *tag_ops; }; /* TC matchall action types, only mirroring for now */ diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 62302558f38c0..54ed054777bd7 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -523,11 +523,9 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, } dst->cpu_dp->tag_ops = tag_ops; - dst->tag_ops = tag_ops; /* Make a few copies for faster access in master receive hot path */ dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv; - dst->rcv = dst->tag_ops->rcv; dst->cpu_dp->dst = dst; return 0; diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 71917505a5ccf..19ff6e0a21dc5 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -153,11 +153,9 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, return PTR_ERR(tag_ops); dst->cpu_dp->tag_ops = tag_ops; - dst->tag_ops = tag_ops; /* Few copies for faster access in master receive hot path */ dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv; - dst->rcv = dst->tag_ops->rcv; dst->cpu_dp->dst = dst; } -- GitLab From 007a61ae2f35c7fcf767313285c4924e81f11983 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Thu, 28 Sep 2017 21:33:23 +0200 Subject: [PATCH 0705/1507] nvme: fix visibility of "uuid" ns attribute "uuid" must be invisible if both ns->uuid and ns->nguid are unset, not if either one is. Fixes: d934f9848a77 "nvme: provide UUID value to userspace" Signed-off-by: Martin Wilck Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index bb2aad0786373..5a14cc7f28ee7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2136,7 +2136,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj, struct nvme_ns *ns = nvme_get_ns_from_dev(dev); if (a == &dev_attr_uuid.attr) { - if (uuid_is_null(&ns->uuid) || + if (uuid_is_null(&ns->uuid) && !memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) return 0; } -- GitLab From 74007ae6316ebe40260e44f8ab558f9b1ccc04e5 Mon Sep 17 00:00:00 2001 From: Christophe Jaillet Date: Sat, 23 Sep 2017 08:44:15 +0200 Subject: [PATCH 0706/1507] hwmon: (xgene) Fix up error handling path mixup in 'xgene_hwmon_probe()' Commit 2ca492e22cb7 has moved the call to 'kfifo_alloc()' from after the main 'if' statement to before it. But it has not updated the error handling paths accordingly. Fix all that: - if 'kfifo_alloc()' fails we can return directly - direct returns after 'kfifo_alloc()' must now go to 'out_mbox_free' - 'goto out_mbox_free' must be replaced by 'goto out', otherwise the '[pcc_]mbox_free_channel()' call will be missed. Fixes: 2ca492e22cb7 ("hwmon: (xgene) Fix crash when alarm occurs before driver probe") Signed-off-by: Christophe JAILLET Signed-off-by: Guenter Roeck --- drivers/hwmon/xgene-hwmon.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index 9c0dbb8191ad4..e1be61095532f 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -630,7 +630,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev) sizeof(struct slimpro_resp_msg) * ASYNC_MSG_FIFO_SIZE, GFP_KERNEL); if (rc) - goto out_mbox_free; + return -ENOMEM; INIT_WORK(&ctx->workq, xgene_hwmon_evt_work); @@ -646,7 +646,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "SLIMpro mailbox channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } } else { struct acpi_pcct_hw_reduced *cppc_ss; @@ -654,7 +655,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (device_property_read_u32(&pdev->dev, "pcc-channel", &ctx->mbox_idx)) { dev_err(&pdev->dev, "no pcc-channel property\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } cl->rx_callback = xgene_hwmon_pcc_rx_cb; @@ -662,7 +664,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (IS_ERR(ctx->mbox_chan)) { dev_err(&pdev->dev, "PPC channel request failed\n"); - return -ENODEV; + rc = -ENODEV; + goto out_mbox_free; } /* @@ -675,13 +678,13 @@ static int xgene_hwmon_probe(struct platform_device *pdev) if (!cppc_ss) { dev_err(&pdev->dev, "PPC subspace not found\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->mbox_chan->mbox->txdone_irq) { dev_err(&pdev->dev, "PCC IRQ not supported\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } /* @@ -696,14 +699,14 @@ static int xgene_hwmon_probe(struct platform_device *pdev) } else { dev_err(&pdev->dev, "Failed to get PCC comm region\n"); rc = -ENODEV; - goto out_mbox_free; + goto out; } if (!ctx->pcc_comm_addr) { dev_err(&pdev->dev, "Failed to ioremap PCC comm region\n"); rc = -ENOMEM; - goto out_mbox_free; + goto out; } /* -- GitLab From 9e66317d3c92ddaab330c125dfe9d06eee268aff Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 1 Oct 2017 14:54:54 -0700 Subject: [PATCH 0707/1507] Linux 4.14-rc3 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index f0c5b21fadb2c..cf007a31d575d 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Fearless Coyote # *DOCUMENTATION* -- GitLab From 35c036ef4a722e953e17884f4f4325f78eeab475 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 20 Sep 2017 12:42:13 -0400 Subject: [PATCH 0708/1507] nfs: RPC_MAX_AUTH_SIZE is in bytes The units of RPC_MAX_AUTH_SIZE is bytes, not 4-byte words. This causes the client to request a larger-than-necessary session replay slot size. Signed-off-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 37c8af0032758..14ed9791ec9cf 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1842,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr, * Assumes OPEN is the biggest non-idempotent compound. * 2 is the verifier. */ - max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + - RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; + max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2) + * XDR_UNIT + RPC_MAX_AUTH_SIZE; encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); -- GitLab From cdb2e53fd6dc715c5b45d0967fcb6dc574cb28f8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 21 Sep 2017 00:53:46 +0300 Subject: [PATCH 0709/1507] NFS: Cleanup error handling in nfs_idmap_request_key() nfs_idmap_get_desc() can't actually return zero. But if it did then we would return ERR_PTR(0) which is NULL and the caller, nfs_idmap_get_key(), doesn't expect that so it leads to a NULL pointer dereference. I've cleaned this up by changing the "<=" to "<" so it's more clear that we don't return ERR_PTR(0). Signed-off-by: Dan Carpenter Signed-off-by: Trond Myklebust --- fs/nfs/nfs4idmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index dd5d27da8c0cc..30426c1a1bbda 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); - if (ret <= 0) + if (ret < 0) return ERR_PTR(ret); rkey = request_key(&key_type_id_resolver, desc, ""); -- GitLab From 68ebf8fe3bce8c167cf83fbd681c1eb1ed419c6c Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Fri, 22 Sep 2017 07:57:10 -0400 Subject: [PATCH 0710/1507] NFS: Fix uninitialized rpc_wait_queue Michael Sterrett reports a NULL pointer dereference on NFSv3 mounts when CONFIG_NFS_V4 is not set because the NFS UOC rpc_wait_queue has not been initialized. Move the initialization of the queue out of the CONFIG_NFS_V4 conditional setion. Fixes: 7d6ddf88c4db ("NFS: Add an iocounter wait function for async RPC tasks") Cc: stable@vger.kernel.org # 4.11+ Signed-off-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index efebe6cf4378e..22880ef6d8dd7 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) static void pnfs_init_server(struct nfs_server *server) { rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); - rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); } #else @@ -888,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void) ida_init(&server->openowner_id); ida_init(&server->lockowner_id); pnfs_init_server(server); + rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); return server; } -- GitLab From d099b8af46f5e1e37182eff988f9373dcc2b0128 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 18 Sep 2017 12:21:14 +0100 Subject: [PATCH 0711/1507] sunrpc: remove redundant initialization of sock sock is being initialized and then being almost immediately updated hence the initialized value is not being used and is redundant. Remove the initialization. Cleans up clang warning: warning: Value stored to 'sock' during its initialization is never read Signed-off-by: Colin Ian King Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9b5de31aa4293..c1841f234a717 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2203,7 +2203,7 @@ static void xs_udp_setup_socket(struct work_struct *work) struct sock_xprt *transport = container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; - struct socket *sock = transport->sock; + struct socket *sock; int status = -EIO; sock = xs_create_sock(xprt, transport, -- GitLab From 0a47df11bfc31e1ceae7f91cea84d3bff500475d Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Fri, 29 Sep 2017 09:36:43 -0400 Subject: [PATCH 0712/1507] nfs/filelayout: fix oops when freeing filelayout segment Check for a NULL dsaddr in filelayout_free_lseg() before calling nfs4_fl_put_deviceid(). This fixes the following oops: [ 1967.645207] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030 [ 1967.646010] IP: [] nfs4_put_deviceid_node+0xa/0x90 [nfsv4] [ 1967.646010] PGD c08bc067 PUD 915d3067 PMD 0 [ 1967.753036] Oops: 0000 [#1] SMP [ 1967.753036] Modules linked in: nfs_layout_nfsv41_files ext4 mbcache jbd2 loop rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache amd64_edac_mod ipmi_ssif edac_mce_amd edac_core kvm_amd sg kvm ipmi_si ipmi_devintf irqbypass pcspkr k8temp ipmi_msghandler i2c_piix4 shpchp nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic crct10dif_common amdkfd amd_iommu_v2 radeon i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops mptsas ttm scsi_transport_sas mptscsih drm mptbase serio_raw i2c_core bnx2 dm_mirror dm_region_hash dm_log dm_mod [ 1967.790031] CPU: 2 PID: 1370 Comm: ls Not tainted 3.10.0-709.el7.test.bz1463784.x86_64 #1 [ 1967.790031] Hardware name: IBM BladeCenter LS21 -[7971AC1]-/Server Blade, BIOS -[BAE155AUS-1.10]- 06/03/2009 [ 1967.790031] task: ffff8800c42a3f40 ti: ffff8800c4064000 task.ti: ffff8800c4064000 [ 1967.790031] RIP: 0010:[] [] nfs4_put_deviceid_node+0xa/0x90 [nfsv4] [ 1967.790031] RSP: 0000:ffff8800c4067978 EFLAGS: 00010246 [ 1967.790031] RAX: ffffffffc062f000 RBX: ffff8801d468a540 RCX: dead000000000200 [ 1967.790031] RDX: ffff8800c40679f8 RSI: ffff8800c4067a0c RDI: 0000000000000000 [ 1967.790031] RBP: ffff8800c4067980 R08: ffff8801d468a540 R09: 0000000000000000 [ 1967.790031] R10: 0000000000000000 R11: ffffffffffffffff R12: ffff8801d468a540 [ 1967.790031] R13: ffff8800c40679f8 R14: ffff8801d5645300 R15: ffff880126f15ff0 [ 1967.790031] FS: 00007f11053c9800(0000) GS:ffff88012bd00000(0000) knlGS:0000000000000000 [ 1967.790031] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 1967.790031] CR2: 0000000000000030 CR3: 0000000094b55000 CR4: 00000000000007e0 [ 1967.790031] Stack: [ 1967.790031] ffff8801d468a540 ffff8800c4067990 ffffffffc062d2fe ffff8800c40679b0 [ 1967.790031] ffffffffc062b5b4 ffff8800c40679f8 ffff8801d468a540 ffff8800c40679d8 [ 1967.790031] ffffffffc06d39af ffff8800c40679f8 ffff880126f16078 0000000000000001 [ 1967.790031] Call Trace: [ 1967.790031] [] nfs4_fl_put_deviceid+0xe/0x10 [nfs_layout_nfsv41_files] [ 1967.790031] [] filelayout_free_lseg+0x24/0x90 [nfs_layout_nfsv41_files] [ 1967.790031] [] pnfs_free_lseg_list+0x5f/0x80 [nfsv4] [ 1967.790031] [] _pnfs_return_layout+0x157/0x270 [nfsv4] [ 1967.790031] [] nfs4_evict_inode+0x4d/0x70 [nfsv4] [ 1967.790031] [] evict+0xa9/0x180 [ 1967.790031] [] iput+0xf9/0x190 [ 1967.790031] [] nfs_dentry_iput+0x3a/0x50 [nfs] [ 1967.790031] [] shrink_dentry_list+0x20f/0x490 [ 1967.790031] [] d_invalidate+0xd8/0x150 [ 1967.790031] [] nfs_readdir_page_filler+0x40b/0x600 [nfs] [ 1967.790031] [] nfs_readdir_xdr_to_array+0x20d/0x3b0 [nfs] [ 1967.790031] [] ? __mem_cgroup_commit_charge+0xe2/0x2f0 [ 1967.790031] [] ? __add_to_page_cache_locked+0x48/0x170 [ 1967.790031] [] ? nfs_readdir_xdr_to_array+0x3b0/0x3b0 [nfs] [ 1967.790031] [] nfs_readdir_filler+0x22/0x90 [nfs] [ 1967.790031] [] do_read_cache_page+0x7f/0x190 [ 1967.790031] [] ? fillonedir+0xe0/0xe0 [ 1967.790031] [] read_cache_page+0x1c/0x30 [ 1967.790031] [] nfs_readdir+0x1ab/0x6b0 [nfs] [ 1967.790031] [] ? nfs4_xdr_dec_layoutget+0x270/0x270 [nfsv4] [ 1967.790031] [] ? fillonedir+0xe0/0xe0 [ 1967.790031] [] vfs_readdir+0xb0/0xe0 [ 1967.790031] [] SyS_getdents+0x95/0x120 [ 1967.790031] [] system_call_fastpath+0x16/0x1b [ 1967.790031] Code: 90 31 d2 48 89 d0 5d c3 85 f6 74 f5 8d 4e 01 89 f0 f0 0f b1 0f 39 f0 74 e2 89 c6 eb eb 0f 1f 40 00 66 66 66 66 90 55 48 89 e5 53 <48> 8b 47 30 48 89 fb a8 04 74 3b 8b 57 60 83 fa 02 74 19 8d 4a [ 1967.790031] RIP [] nfs4_put_deviceid_node+0xa/0x90 [nfsv4] [ 1967.790031] RSP [ 1967.790031] CR2: 0000000000000030 Signed-off-by: Scott Mayhew Fixes: 1ebf98012792 ("NFS/filelayout: Fix racy setting of fl->dsaddr...") Cc: stable@vger.kernel.org # v4.13+ Signed-off-by: Trond Myklebust --- fs/nfs/filelayout/filelayout.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 44c638b7876cf..508126eb49f95 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -745,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); dprintk("--> %s\n", __func__); - nfs4_fl_put_deviceid(fl->dsaddr); + if (fl->dsaddr != NULL) + nfs4_fl_put_deviceid(fl->dsaddr); /* This assumes a single RW lseg */ if (lseg->pls_range.iomode == IOMODE_RW) { struct nfs4_filelayout *flo; -- GitLab From e1cfcbe82b4534bd0f99fef92a6d33843fd85e0e Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 27 Sep 2017 11:35:40 +0800 Subject: [PATCH 0713/1507] ipv4: Namespaceify tcp_fastopen knob Different namespace application might require enable TCP Fast Open feature independently of the host. This patch series continues making more of the TCP Fast Open related sysctl knobs be per net-namespace. Reported-by: Luca BRUNO Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/af_inet.c | 7 ++++--- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_fastopen.c | 11 +++++------ net/ipv4/tcp_ipv4.c | 2 ++ 7 files changed, 21 insertions(+), 19 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index abc84d986da49..16420ccaef155 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -128,6 +128,7 @@ struct netns_ipv4 { int sysctl_tcp_timestamps; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; + int sysctl_tcp_fastopen; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; diff --git a/include/net/tcp.h b/include/net/tcp.h index 770b608c84395..9e414a99034fd 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* sysctl variables for tcp */ -extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; extern int sysctl_tcp_rfc1337; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e31108e5ef79c..ddd126d120acf 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; - int err; + int err, tcp_fastopen; lock_sock(sk); @@ -217,8 +217,9 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && - (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && + (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(true); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d3c038d7b045..e31e853cf486e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -400,13 +400,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_fastopen", - .data = &sysctl_tcp_fastopen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "tcp_fastopen_key", .mode = 0600, @@ -1085,6 +1078,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_fastopen", + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5091402720abc..dac56c4ad357d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1126,7 +1126,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -2759,7 +2759,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3c33220c4181..31b08ec38cb8a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -9,8 +9,6 @@ #include #include -int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE; - struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); @@ -279,21 +277,22 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc) { - struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); - if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } - if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ @@ -347,7 +346,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, return false; } - if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { + if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { cookie->len = -1; return true; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5162bc1..88409b13c9d22 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2472,6 +2472,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; + net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + return 0; fail: tcp_sk_exit(net); -- GitLab From dd000598a39b6937fcefdf143720ec9fb5250e72 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 27 Sep 2017 11:35:41 +0800 Subject: [PATCH 0714/1507] ipv4: Remove the 'publish' logic in tcp_fastopen_init_key_once MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The 'publish' logic is not necessary after commit dfea2aa65424 ("tcp: Do not call tcp_fastopen_reset_cipher from interrupt context"), because in tcp_fastopen_cookie_gen，it wouldn't call tcp_fastopen_init_key_once. Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/af_inet.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 5 ----- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_fastopen.c | 4 ++-- 5 files changed, 5 insertions(+), 10 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 9e414a99034fd..d9376e2458e98 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1555,7 +1555,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc); -void tcp_fastopen_init_key_once(bool publish); +void tcp_fastopen_init_key_once(void); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ddd126d120acf..e73ce79d71767 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -222,7 +222,7 @@ int inet_listen(struct socket *sock, int backlog) (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(); } err = inet_csk_listen_start(sk, backlog); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index e31e853cf486e..f6324ead0e19a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -282,11 +282,6 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, ret = -EINVAL; goto bad_key; } - /* Generate a dummy secret but don't publish it. This - * is needed so we don't regenerate a new key on the - * first invocation of tcp_fastopen_cookie_gen - */ - tcp_fastopen_init_key_once(false); tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dac56c4ad357d..4e395452d69fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2749,7 +2749,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - tcp_fastopen_init_key_once(true); + tcp_fastopen_init_key_once(); fastopen_queue_tune(sk, val); } else { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 31b08ec38cb8a..8c8f0f0af59dd 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -13,7 +13,7 @@ struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); -void tcp_fastopen_init_key_once(bool publish) +void tcp_fastopen_init_key_once(void) { static u8 key[TCP_FASTOPEN_KEY_LENGTH]; @@ -23,7 +23,7 @@ void tcp_fastopen_init_key_once(bool publish) * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ - if (net_get_random_once(key, sizeof(key)) && publish) + if (net_get_random_once(key, sizeof(key))) tcp_fastopen_reset_cipher(key, sizeof(key)); } -- GitLab From 437138485656c41e32b8c63c0987cfa0348be0e6 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 27 Sep 2017 11:35:42 +0800 Subject: [PATCH 0715/1507] ipv4: Namespaceify tcp_fastopen_key knob Different namespace application might require different tcp_fastopen_key independently of the host. David Miller pointed out there is a leak without releasing the context of tcp_fastopen_key during netns teardown. So add the release action in exit_batch path. Tested: 1. Container namespace: # cat /proc/sys/net/ipv4/tcp_fastopen_key: 2817fff2-f803cf97-eadfd1f3-78c0992b cookie key in tcp syn packets: Fast Open Cookie Kind: TCP Fast Open Cookie (34) Length: 10 Fast Open Cookie: 1e5dd82a8c492ca9 2. Host: # cat /proc/sys/net/ipv4/tcp_fastopen_key: 107d7c5f-68eb2ac7-02fb06e6-ed341702 cookie key in tcp syn packets: Fast Open Cookie Kind: TCP Fast Open Cookie (34) Length: 10 Fast Open Cookie: e213c02bf0afbc8a Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 4 +++ include/net/tcp.h | 6 ++-- net/ipv4/af_inet.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 21 +++++++------ net/ipv4/tcp.c | 2 +- net/ipv4/tcp_fastopen.c | 64 +++++++++++++++++++++++++------------- net/ipv4/tcp_ipv4.c | 6 ++++ 7 files changed, 70 insertions(+), 35 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 16420ccaef155..7bb9603ff66c1 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -36,6 +36,8 @@ struct inet_timewait_death_row { int sysctl_max_tw_buckets; }; +struct tcp_fastopen_context; + struct netns_ipv4 { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; @@ -129,6 +131,8 @@ struct netns_ipv4 { struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; int sysctl_tcp_fastopen; + struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; + spinlock_t tcp_fastopen_ctx_lock; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; diff --git a/include/net/tcp.h b/include/net/tcp.h index d9376e2458e98..6d25d83050543 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1549,13 +1549,13 @@ struct tcp_fastopen_request { }; void tcp_free_fastopen_req(struct tcp_sock *tp); -extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; -int tcp_fastopen_reset_cipher(void *key, unsigned int len); +void tcp_fastopen_ctx_destroy(struct net *net); +int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc); -void tcp_fastopen_init_key_once(void); +void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e73ce79d71767..43a1bbed7a427 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -222,7 +222,7 @@ int inet_listen(struct socket *sock, int backlog) (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); - tcp_fastopen_init_key_once(); + tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk, backlog); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index f6324ead0e19a..20e19fe78dbdb 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -251,10 +251,12 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl, return ret; } -static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, +static int proc_tcp_fastopen_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; int ret; @@ -265,7 +267,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, return -ENOMEM; rcu_read_lock(); - ctxt = rcu_dereference(tcp_fastopen_ctx); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else @@ -282,7 +284,7 @@ static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: @@ -395,12 +397,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_fastopen_key", - .mode = 0600, - .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), - .proc_handler = proc_tcp_fastopen_key, - }, { .procname = "tcp_fastopen_blackhole_timeout_sec", .data = &sysctl_tcp_fastopen_blackhole_timeout, @@ -1080,6 +1076,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "tcp_fastopen_key", + .mode = 0600, + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + .proc_handler = proc_tcp_fastopen_key, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4e395452d69fd..23225c98d287b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2749,7 +2749,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - tcp_fastopen_init_key_once(); + tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 8c8f0f0af59dd..4eae44ac3cb04 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -9,13 +9,18 @@ #include #include -struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; - -static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); - -void tcp_fastopen_init_key_once(void) +void tcp_fastopen_init_key_once(struct net *net) { - static u8 key[TCP_FASTOPEN_KEY_LENGTH]; + u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctxt; + + rcu_read_lock(); + ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + if (ctxt) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. @@ -23,8 +28,8 @@ void tcp_fastopen_init_key_once(void) * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ - if (net_get_random_once(key, sizeof(key))) - tcp_fastopen_reset_cipher(key, sizeof(key)); + get_random_bytes(key, sizeof(key)); + tcp_fastopen_reset_cipher(net, key, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) @@ -35,7 +40,22 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head) kfree(ctx); } -int tcp_fastopen_reset_cipher(void *key, unsigned int len) +void tcp_fastopen_ctx_destroy(struct net *net) +{ + struct tcp_fastopen_context *ctxt; + + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + + ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + + if (ctxt) + call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); +} + +int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len) { int err; struct tcp_fastopen_context *ctx, *octx; @@ -59,26 +79,27 @@ error: kfree(ctx); } memcpy(ctx->key, key, len); - spin_lock(&tcp_fastopen_ctx_lock); + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); - octx = rcu_dereference_protected(tcp_fastopen_ctx, - lockdep_is_held(&tcp_fastopen_ctx_lock)); - rcu_assign_pointer(tcp_fastopen_ctx, ctx); - spin_unlock(&tcp_fastopen_ctx_lock); + octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); return err; } -static bool __tcp_fastopen_cookie_gen(const void *path, +static bool __tcp_fastopen_cookie_gen(struct net *net, + const void *path, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; bool ok = false; rcu_read_lock(); - ctx = rcu_dereference(tcp_fastopen_ctx); + ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctx) { crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; @@ -94,7 +115,8 @@ static bool __tcp_fastopen_cookie_gen(const void *path, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct request_sock *req, +static bool tcp_fastopen_cookie_gen(struct net *net, + struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { @@ -102,7 +124,7 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct iphdr *iph = ip_hdr(syn); __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(path, foc); + return __tcp_fastopen_cookie_gen(net, path, foc); } #if IS_ENABLED(CONFIG_IPV6) @@ -110,13 +132,13 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, const struct ipv6hdr *ip6h = ipv6_hdr(syn); struct tcp_fastopen_cookie tmp; - if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) { + if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) { struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(buf, foc); + return __tcp_fastopen_cookie_gen(net, buf, foc); } } #endif @@ -296,7 +318,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(req, skb, &valid_foc) && + tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) && foc->len == TCP_FASTOPEN_COOKIE_SIZE && foc->len == valid_foc.len && !memcmp(foc->val, valid_foc.val, foc->len)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 88409b13c9d22..49c74c0d0d210 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2473,6 +2473,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_timestamps = 1; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); return 0; fail: @@ -2483,7 +2484,12 @@ static int __net_init tcp_sk_init(struct net *net) static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { + struct net *net; + inet_twsk_purge(&tcp_hashinfo, AF_INET); + + list_for_each_entry(net, net_exit_list, exit_list) + tcp_fastopen_ctx_destroy(net); } static struct pernet_operations __net_initdata tcp_sk_ops = { -- GitLab From 3733be14a32bae288b61ed28341e593baba983af Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Wed, 27 Sep 2017 11:35:43 +0800 Subject: [PATCH 0716/1507] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob Different namespace application might require different time period in second to disable Fastopen on active TCP sockets. Tested: Simulate following similar situation that the server's data gets dropped after 3WHS. C ---- syn-data ---> S C <--- syn/ack ----- S C ---- ack --------> S S (accept & write) C? X <- data ------ S [retry and timeout] And then print netstat of TCPFastOpenBlackhole, the counter increased as expected when the firewall blackhole issue is detected and active TFO is disabled. # cat /proc/net/netstat | awk '{print $91}' TCPFastOpenBlackhole 1 Signed-off-by: Haishuang Yan Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 3 +++ net/ipv4/sysctl_net_ipv4.c | 20 +++++++++++--------- net/ipv4/tcp_fastopen.c | 30 +++++++++++------------------- net/ipv4/tcp_ipv4.c | 2 ++ 4 files changed, 27 insertions(+), 28 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 7bb9603ff66c1..2c4222a5d1025 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -133,6 +133,9 @@ struct netns_ipv4 { int sysctl_tcp_fastopen; struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; spinlock_t tcp_fastopen_ctx_lock; + unsigned int sysctl_tcp_fastopen_blackhole_timeout; + atomic_t tfo_active_disable_times; + unsigned long tfo_active_disable_stamp; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 20e19fe78dbdb..cac8dd309f390 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -355,11 +355,13 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_tcp_fastopen_blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) - tcp_fastopen_active_timeout_reset(); + atomic_set(&net->ipv4.tfo_active_disable_times, 0); return ret; } @@ -397,14 +399,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_fastopen_blackhole_timeout_sec", - .data = &sysctl_tcp_fastopen_blackhole_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_tfo_blackhole_detect_timeout, - .extra1 = &zero, - }, { .procname = "tcp_abort_on_overflow", .data = &sysctl_tcp_abort_on_overflow, @@ -1083,6 +1077,14 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), .proc_handler = proc_tcp_fastopen_key, }, + { + .procname = "tcp_fastopen_blackhole_timeout_sec", + .data = &init_net.ipv4.sysctl_tcp_fastopen_blackhole_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_tfo_blackhole_detect_timeout, + .extra1 = &zero, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4eae44ac3cb04..de470e7e586f4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -422,25 +422,16 @@ EXPORT_SYMBOL(tcp_fastopen_defer_connect); * TFO connection with data exchanges. */ -/* Default to 1hr */ -unsigned int sysctl_tcp_fastopen_blackhole_timeout __read_mostly = 60 * 60; -static atomic_t tfo_active_disable_times __read_mostly = ATOMIC_INIT(0); -static unsigned long tfo_active_disable_stamp __read_mostly; - /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { - atomic_inc(&tfo_active_disable_times); - tfo_active_disable_stamp = jiffies; - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENBLACKHOLE); -} + struct net *net = sock_net(sk); -/* Reset tfo_active_disable_times to 0 */ -void tcp_fastopen_active_timeout_reset(void) -{ - atomic_set(&tfo_active_disable_times, 0); + atomic_inc(&net->ipv4.tfo_active_disable_times); + net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable @@ -449,17 +440,18 @@ void tcp_fastopen_active_timeout_reset(void) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - int tfo_da_times = atomic_read(&tfo_active_disable_times); - int multiplier; + unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; + int multiplier; if (!tfo_da_times) return false; /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * sysctl_tcp_fastopen_blackhole_timeout * HZ; - if (time_before(jiffies, tfo_active_disable_stamp + timeout)) + timeout = multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) return true; /* Mark check bit so we can check for successful active TFO @@ -495,10 +487,10 @@ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) } } } else if (tp->syn_fastopen_ch && - atomic_read(&tfo_active_disable_times)) { + atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) - tcp_fastopen_active_timeout_reset(); + atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 49c74c0d0d210..ad3b5bbaf942d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2474,6 +2474,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); + net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; + atomic_set(&net->ipv4.tfo_active_disable_times, 0); return 0; fail: -- GitLab From b80ccfe9bbcac70e66fdfaef73f0988a27f9a68c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Tue, 26 Sep 2017 20:37:22 -0700 Subject: [PATCH 0717/1507] net-ipv6: remove unused IP6_ECN_clear() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is unused, and furthermore it is buggy since it suffers from the same issue that requires IP6_ECN_set_ce() to take a pointer to the skb so that it may (in case of CHECKSUM_COMPLETE) update skb->csum Instead of fixing it, let's just outright remove it. Tested: builds, and 'git grep IP6_ECN_clear' comes up empty Signed-off-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/net/inet_ecn.h | 5 ----- 1 file changed, 5 deletions(-) diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index dce2d586d9cec..f5ff16d72fe63 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -133,11 +133,6 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) return 1; } -static inline void IP6_ECN_clear(struct ipv6hdr *iph) -{ - *(__be32*)iph &= ~htonl(INET_ECN_MASK << 20); -} - static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; -- GitLab From 935a9749a36828af0e8be224a5cd4bc758112c34 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2017 22:00:53 +0800 Subject: [PATCH 0718/1507] ip_gre: get key from session_id correctly in erspan_rcv erspan only uses the first 10 bits of session_id as the key to look up the tunnel. But in erspan_rcv, it missed 'session_id & ID_MASK' when getting the key from session_id. If any other flag is also set in session_id in a packet, it would fail to find the tunnel due to incorrect key in erspan_rcv. This patch is to add 'session_id & ID_MASK' there and also remove the unnecessary variable session_id. Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8b837f6f55320..b25b1e5112d0d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel *tunnel; struct erspanhdr *ershdr; const struct iphdr *iph; - __be32 session_id; __be32 index; int len; @@ -275,8 +274,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, /* The original GRE header does not have key field, * Use ERSPAN 10-bit session ID as key. */ - session_id = cpu_to_be32(ntohs(ershdr->session_id)); - tpi->key = session_id; + tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK); index = ershdr->md.index; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, -- GitLab From 5513d08d29511c263c00933c00dd7a82fffda3c9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2017 22:00:54 +0800 Subject: [PATCH 0719/1507] ip_gre: check packet length and mtu correctly in erspan_xmit As a ARPHRD_ETHER device, skb->len in erspan_xmit is the length of the whole ether packet. So before checking if a packet size exceeds the mtu, skb->len should subtract dev->hard_header_len. Otherwise, all packets with max size according to mtu would be trimmed to be truncated packet. Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b25b1e5112d0d..2a4ef9dc48ffb 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -731,7 +731,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len > dev->mtu) { + if (skb->len - dev->hard_header_len > dev->mtu) { pskb_trim(skb, dev->mtu); truncate = true; } -- GitLab From c122fda271717f4fc618e0a31e833941fd5f1efd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2017 22:00:55 +0800 Subject: [PATCH 0720/1507] ip_gre: set tunnel hlen properly in erspan_tunnel_init According to __gre_tunnel_init, tunnel->hlen should be set as the headers' length between inner packet and outer iphdr. It would be used especially to calculate a proper mtu when updating mtu in tnl_update_pmtu. Now without setting it, a bigger mtu value than expected would be updated, which hurts performance a lot. This patch is to fix it by setting tunnel->hlen with: tunnel->tun_hlen + tunnel->encap_hlen + sizeof(struct erspanhdr) Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2a4ef9dc48ffb..fad0bb1e3e9af 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1245,7 +1245,9 @@ static int erspan_tunnel_init(struct net_device *dev) tunnel->tun_hlen = 8; tunnel->parms.iph.protocol = IPPROTO_GRE; - t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr); + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + + sizeof(struct erspanhdr); + t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; dev->mtu = ETH_DATA_LEN - t_hlen - 4; -- GitLab From c84bed440e4e11a973e8c0254d0dfaccfca41fb0 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 1 Oct 2017 22:00:56 +0800 Subject: [PATCH 0721/1507] ip_gre: erspan device should keep dst The patch 'ip_gre: ipgre_tap device should keep dst' fixed the issue ipgre_tap dev mtu couldn't be updated in tx path. The same fix is needed for erspan as well. Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index fad0bb1e3e9af..467e44d7587dc 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1254,6 +1254,7 @@ static int erspan_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_keep_dst(dev); return ip_tunnel_init(dev); } -- GitLab From 9f775ead5e570e7e19015b9e4e2f3dd6e71a5935 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 28 Sep 2017 15:44:38 +0200 Subject: [PATCH 0722/1507] l2tp: fix l2tp_eth module loading The l2tp_eth module crashes if its netlink callbacks are run when the pernet data aren't initialised. We should normally register_pernet_device() before the genl callbacks. However, the pernet data only maintain a list of l2tpeth interfaces, and this list is never used. So let's just drop pernet handling instead. Fixes: d9e31d17ceba ("l2tp: Add L2TP ethernet pseudowire support") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_eth.c | 51 ++------------------------------------------- 1 file changed, 2 insertions(+), 49 deletions(-) diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 87da9ef618608..014a7bc2a8725 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -44,7 +44,6 @@ struct l2tp_eth { struct net_device *dev; struct sock *tunnel_sock; struct l2tp_session *session; - struct list_head list; atomic_long_t tx_bytes; atomic_long_t tx_packets; atomic_long_t tx_dropped; @@ -58,17 +57,6 @@ struct l2tp_eth_sess { struct net_device *dev; }; -/* per-net private data for this module */ -static unsigned int l2tp_eth_net_id; -struct l2tp_eth_net { - struct list_head l2tp_eth_dev_list; - spinlock_t l2tp_eth_lock; -}; - -static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net) -{ - return net_generic(net, l2tp_eth_net_id); -} static int l2tp_eth_dev_init(struct net_device *dev) { @@ -84,12 +72,6 @@ static int l2tp_eth_dev_init(struct net_device *dev) static void l2tp_eth_dev_uninit(struct net_device *dev) { - struct l2tp_eth *priv = netdev_priv(dev); - struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev)); - - spin_lock(&pn->l2tp_eth_lock); - list_del_init(&priv->list); - spin_unlock(&pn->l2tp_eth_lock); dev_put(dev); } @@ -273,7 +255,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, struct l2tp_eth *priv; struct l2tp_eth_sess *spriv; int rc; - struct l2tp_eth_net *pn; if (cfg->ifname) { strlcpy(name, cfg->ifname, IFNAMSIZ); @@ -305,7 +286,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, priv = netdev_priv(dev); priv->dev = dev; priv->session = session; - INIT_LIST_HEAD(&priv->list); priv->tunnel_sock = tunnel->sock; session->recv_skb = l2tp_eth_dev_recv; @@ -326,10 +306,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, strlcpy(session->ifname, dev->name, IFNAMSIZ); dev_hold(dev); - pn = l2tp_eth_pernet(dev_net(dev)); - spin_lock(&pn->l2tp_eth_lock); - list_add(&priv->list, &pn->l2tp_eth_dev_list); - spin_unlock(&pn->l2tp_eth_lock); return 0; @@ -342,22 +318,6 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, return rc; } -static __net_init int l2tp_eth_init_net(struct net *net) -{ - struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id); - - INIT_LIST_HEAD(&pn->l2tp_eth_dev_list); - spin_lock_init(&pn->l2tp_eth_lock); - - return 0; -} - -static struct pernet_operations l2tp_eth_net_ops = { - .init = l2tp_eth_init_net, - .id = &l2tp_eth_net_id, - .size = sizeof(struct l2tp_eth_net), -}; - static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = { .session_create = l2tp_eth_create, @@ -371,25 +331,18 @@ static int __init l2tp_eth_init(void) err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops); if (err) - goto out; - - err = register_pernet_device(&l2tp_eth_net_ops); - if (err) - goto out_unreg; + goto err; pr_info("L2TP ethernet pseudowire support (L2TPv3)\n"); return 0; -out_unreg: - l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH); -out: +err: return err; } static void __exit l2tp_eth_exit(void) { - unregister_pernet_device(&l2tp_eth_net_ops); l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH); } -- GitLab From 90841047a01b452cc8c3f9b990698b264143334a Mon Sep 17 00:00:00 2001 From: Grant Grundler Date: Thu, 28 Sep 2017 11:35:00 -0700 Subject: [PATCH 0723/1507] r8152: add Linksys USB3GIGV1 id This linksys dongle by default comes up in cdc_ether mode. This patch allows r8152 to claim the device: Bus 002 Device 002: ID 13b1:0041 Linksys Signed-off-by: Grant Grundler Reviewed-by: Douglas Anderson Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ether.c | 10 ++++++++++ drivers/net/usb/r8152.c | 2 ++ 2 files changed, 12 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 8ab281b478f23..677a85360db15 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -547,6 +547,7 @@ static const struct driver_info wwan_info = { #define REALTEK_VENDOR_ID 0x0bda #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef +#define LINKSYS_VENDOR_ID 0x13b1 #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e @@ -737,6 +738,15 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +#if IS_ENABLED(CONFIG_USB_RTL8152) +/* Linksys USB3GIGV1 Ethernet Adapter */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, +#endif + /* ThinkPad USB-C Dock (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x3062, USB_CLASS_COMM, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index ceb78e2ea4f08..941ece08ba785 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -613,6 +613,7 @@ enum rtl8152_flags { #define VENDOR_ID_MICROSOFT 0x045e #define VENDOR_ID_SAMSUNG 0x04e8 #define VENDOR_ID_LENOVO 0x17ef +#define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 #define MCU_TYPE_PLA 0x0100 @@ -5316,6 +5317,7 @@ static const struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x720c)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)}, {REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)}, {} }; -- GitLab From 4792ea04bcd03b8ccfd1ae336c5deba52dd9edc9 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Fri, 29 Sep 2017 14:27:39 +0200 Subject: [PATCH 0724/1507] net: mvpp2: Fix clock resource by adding an optional bus clock On Armada 7K/8K we need to explicitly enable the bus clock. The bus clock is optional because not all the SoCs need them but at least for Armada 7K/8K it is actually mandatory. The binding documentation is updating accordingly. Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- .../devicetree/bindings/net/marvell-pp2.txt | 10 ++++++---- drivers/net/ethernet/marvell/mvpp2.c | 15 +++++++++++++++ 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index 7e2dad08a12e9..1814fa13f6ab8 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -21,8 +21,9 @@ Required properties: - main controller clock (for both armada-375-pp2 and armada-7k-pp2) - GOP clock (for both armada-375-pp2 and armada-7k-pp2) - MG clock (only for armada-7k-pp2) -- clock-names: names of used clocks, must be "pp_clk", "gop_clk" and - "mg_clk" (the latter only for armada-7k-pp2). + - AXI clock (only for armada-7k-pp2) +- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk" + and "axi_clk" (the 2 latter only for armada-7k-pp2). The ethernet ports are represented by subnodes. At least one port is required. @@ -78,8 +79,9 @@ Example for marvell,armada-7k-pp2: cpm_ethernet: ethernet@0 { compatible = "marvell,armada-7k-pp22"; reg = <0x0 0x100000>, <0x129000 0xb000>; - clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, <&cpm_syscon0 1 5>; - clock-names = "pp_clk", "gop_clk", "gp_clk"; + clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, + <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>; + clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk"; eth0: eth0 { interrupts = , diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 1610555647201..9c86cb7cb988a 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -793,6 +793,7 @@ struct mvpp2 { struct clk *pp_clk; struct clk *gop_clk; struct clk *mg_clk; + struct clk *axi_clk; /* List of pointers to port structures */ struct mvpp2_port **port_list; @@ -7970,6 +7971,18 @@ static int mvpp2_probe(struct platform_device *pdev) err = clk_prepare_enable(priv->mg_clk); if (err < 0) goto err_gop_clk; + + priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk"); + if (IS_ERR(priv->axi_clk)) { + err = PTR_ERR(priv->axi_clk); + if (err == -EPROBE_DEFER) + goto err_gop_clk; + priv->axi_clk = NULL; + } else { + err = clk_prepare_enable(priv->axi_clk); + if (err < 0) + goto err_gop_clk; + } } /* Get system's tclk rate */ @@ -8024,6 +8037,7 @@ static int mvpp2_probe(struct platform_device *pdev) return 0; err_mg_clk: + clk_disable_unprepare(priv->axi_clk); if (priv->hw_version == MVPP22) clk_disable_unprepare(priv->mg_clk); err_gop_clk: @@ -8061,6 +8075,7 @@ static int mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(priv->mg_clk); clk_disable_unprepare(priv->pp_clk); clk_disable_unprepare(priv->gop_clk); -- GitLab From 81359617f1b783a01e6e22b46cbb046e9513b9c6 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 30 Sep 2017 07:34:34 +0200 Subject: [PATCH 0725/1507] net: hns3: Fix an error handling path in 'hclge_rss_init_hw()' If this sanity check fails, we must free 'rss_indir'. Otherwise there is a memory leak. 'goto err' as done in the other error handling paths to fix it. Fixes: 46a3df9f9718 ("net: hns3: Fix for setting rss_size incorrectly") Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e0685e630afec..c1cdbfd83bdba 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2652,7 +2652,8 @@ static int hclge_rss_init_hw(struct hclge_dev *hdev) dev_err(&hdev->pdev->dev, "Configure rss tc size failed, invalid TC_SIZE = %d\n", rss_size); - return -EINVAL; + ret = -EINVAL; + goto err; } roundup_size = roundup_pow_of_two(rss_size); -- GitLab From 9c86b846ce02f7e35d7234cf090b80553eba5389 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:15 +0200 Subject: [PATCH 0726/1507] bcm63xx_enet: correct clock usage Check the return code of prepare_enable and change one last instance of enable only to prepare_enable. Also properly disable and release the clock in error paths and on remove for enetsw. Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 31 +++++++++++++++----- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index c6221f04a7486..a45ec97b5b1e8 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1773,7 +1773,9 @@ static int bcm_enet_probe(struct platform_device *pdev) ret = PTR_ERR(priv->mac_clk); goto out; } - clk_prepare_enable(priv->mac_clk); + ret = clk_prepare_enable(priv->mac_clk); + if (ret) + goto out_put_clk_mac; /* initialize default and fetch platform data */ priv->rx_ring_size = BCMENET_DEF_RX_DESC; @@ -1805,9 +1807,11 @@ static int bcm_enet_probe(struct platform_device *pdev) if (IS_ERR(priv->phy_clk)) { ret = PTR_ERR(priv->phy_clk); priv->phy_clk = NULL; - goto out_put_clk_mac; + goto out_disable_clk_mac; } - clk_prepare_enable(priv->phy_clk); + ret = clk_prepare_enable(priv->phy_clk); + if (ret) + goto out_put_clk_phy; } /* do minimal hardware init to be able to probe mii bus */ @@ -1900,13 +1904,16 @@ static int bcm_enet_probe(struct platform_device *pdev) out_uninit_hw: /* turn off mdc clock */ enet_writel(priv, 0, ENET_MIISC_REG); - if (priv->phy_clk) { + if (priv->phy_clk) clk_disable_unprepare(priv->phy_clk); + +out_put_clk_phy: + if (priv->phy_clk) clk_put(priv->phy_clk); - } -out_put_clk_mac: +out_disable_clk_mac: clk_disable_unprepare(priv->mac_clk); +out_put_clk_mac: clk_put(priv->mac_clk); out: free_netdev(dev); @@ -2748,7 +2755,9 @@ static int bcm_enetsw_probe(struct platform_device *pdev) ret = PTR_ERR(priv->mac_clk); goto out_unmap; } - clk_enable(priv->mac_clk); + ret = clk_prepare_enable(priv->mac_clk); + if (ret) + goto out_put_clk; priv->rx_chan = 0; priv->tx_chan = 1; @@ -2769,7 +2778,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev) ret = register_netdev(dev); if (ret) - goto out_put_clk; + goto out_disable_clk; netif_carrier_off(dev); platform_set_drvdata(pdev, dev); @@ -2778,6 +2787,9 @@ static int bcm_enetsw_probe(struct platform_device *pdev) return 0; +out_disable_clk: + clk_disable_unprepare(priv->mac_clk); + out_put_clk: clk_put(priv->mac_clk); @@ -2809,6 +2821,9 @@ static int bcm_enetsw_remove(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); + clk_disable_unprepare(priv->mac_clk); + clk_put(priv->mac_clk); + free_netdev(dev); return 0; } -- GitLab From d6213c1f2ad54a964b77471690264ed685718928 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:16 +0200 Subject: [PATCH 0727/1507] bcm63xx_enet: do not write to random DMA channel on BCM6345 The DMA controller regs actually point to DMA channel 0, so the write to ENETDMA_CFG_REG will actually modify a random DMA channel. Since DMA controller registers do not exist on BCM6345, guard the write with the usual check for dma_has_sram. Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a45ec97b5b1e8..a1e1e12e187a5 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1062,7 +1062,8 @@ static int bcm_enet_open(struct net_device *dev) val = enet_readl(priv, ENET_CTL_REG); val |= ENET_CTL_ENABLE_MASK; enet_writel(priv, val, ENET_CTL_REG); - enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG); + if (priv->dma_has_sram) + enet_dma_writel(priv, ENETDMA_CFG_EN_MASK, ENETDMA_CFG_REG); enet_dmac_writel(priv, priv->dma_chan_en_mask, ENETDMAC_CHANCFG, priv->rx_chan); -- GitLab From 527a48713b01057d94aeec8f4383b1e20c82522c Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:17 +0200 Subject: [PATCH 0728/1507] bcm63xx_enet: do not rely on probe order Do not rely on the shared device being probed before the enet(sw) devices. This makes it easier to eventually move out the shared device as a dma controller driver (what it should be). Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a1e1e12e187a5..8caf6abab3a6c 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1722,10 +1722,8 @@ static int bcm_enet_probe(struct platform_device *pdev) const char *clk_name; int i, ret; - /* stop if shared driver failed, assume driver->probe will be - * called in the same order we register devices (correct ?) */ if (!bcm_enet_shared_base[0]) - return -ENODEV; + return -EPROBE_DEFER; res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); res_irq_rx = platform_get_resource(pdev, IORESOURCE_IRQ, 1); @@ -2696,11 +2694,8 @@ static int bcm_enetsw_probe(struct platform_device *pdev) struct resource *res_mem; int ret, irq_rx, irq_tx; - /* stop if shared driver failed, assume driver->probe will be - * called in the same order we register devices (correct ?) - */ if (!bcm_enet_shared_base[0]) - return -ENODEV; + return -EPROBE_DEFER; res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); irq_rx = platform_get_irq(pdev, 0); -- GitLab From 7e697ce99ceb09538cdc1dfa9ebb3db60236b0a7 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:18 +0200 Subject: [PATCH 0729/1507] bcm63xx_enet: use managed functions for clock/ioremap Use managed functions where possible to reduce the amount of resource handling on error and remove paths. Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 54 +++++--------------- 1 file changed, 12 insertions(+), 42 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 8caf6abab3a6c..059ef4f1d1378 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1767,14 +1767,14 @@ static int bcm_enet_probe(struct platform_device *pdev) clk_name = "enet1"; } - priv->mac_clk = clk_get(&pdev->dev, clk_name); + priv->mac_clk = devm_clk_get(&pdev->dev, clk_name); if (IS_ERR(priv->mac_clk)) { ret = PTR_ERR(priv->mac_clk); goto out; } ret = clk_prepare_enable(priv->mac_clk); if (ret) - goto out_put_clk_mac; + goto out; /* initialize default and fetch platform data */ priv->rx_ring_size = BCMENET_DEF_RX_DESC; @@ -1802,7 +1802,7 @@ static int bcm_enet_probe(struct platform_device *pdev) if (priv->mac_id == 0 && priv->has_phy && !priv->use_external_mii) { /* using internal PHY, enable clock */ - priv->phy_clk = clk_get(&pdev->dev, "ephy"); + priv->phy_clk = devm_clk_get(&pdev->dev, "ephy"); if (IS_ERR(priv->phy_clk)) { ret = PTR_ERR(priv->phy_clk); priv->phy_clk = NULL; @@ -1810,7 +1810,7 @@ static int bcm_enet_probe(struct platform_device *pdev) } ret = clk_prepare_enable(priv->phy_clk); if (ret) - goto out_put_clk_phy; + goto out_disable_clk_mac; } /* do minimal hardware init to be able to probe mii bus */ @@ -1906,14 +1906,8 @@ static int bcm_enet_probe(struct platform_device *pdev) if (priv->phy_clk) clk_disable_unprepare(priv->phy_clk); -out_put_clk_phy: - if (priv->phy_clk) - clk_put(priv->phy_clk); - out_disable_clk_mac: clk_disable_unprepare(priv->mac_clk); -out_put_clk_mac: - clk_put(priv->mac_clk); out: free_netdev(dev); return ret; @@ -1949,12 +1943,10 @@ static int bcm_enet_remove(struct platform_device *pdev) } /* disable hw block clocks */ - if (priv->phy_clk) { + if (priv->phy_clk) clk_disable_unprepare(priv->phy_clk); - clk_put(priv->phy_clk); - } + clk_disable_unprepare(priv->mac_clk); - clk_put(priv->mac_clk); free_netdev(dev); return 0; @@ -2734,26 +2726,20 @@ static int bcm_enetsw_probe(struct platform_device *pdev) if (ret) goto out; - if (!request_mem_region(res_mem->start, resource_size(res_mem), - "bcm63xx_enetsw")) { - ret = -EBUSY; + priv->base = devm_ioremap_resource(&pdev->dev, res_mem); + if (IS_ERR(priv->base)) { + ret = PTR_ERR(priv->base); goto out; } - priv->base = ioremap(res_mem->start, resource_size(res_mem)); - if (priv->base == NULL) { - ret = -ENOMEM; - goto out_release_mem; - } - - priv->mac_clk = clk_get(&pdev->dev, "enetsw"); + priv->mac_clk = devm_clk_get(&pdev->dev, "enetsw"); if (IS_ERR(priv->mac_clk)) { ret = PTR_ERR(priv->mac_clk); - goto out_unmap; + goto out; } ret = clk_prepare_enable(priv->mac_clk); if (ret) - goto out_put_clk; + goto out; priv->rx_chan = 0; priv->tx_chan = 1; @@ -2785,15 +2771,6 @@ static int bcm_enetsw_probe(struct platform_device *pdev) out_disable_clk: clk_disable_unprepare(priv->mac_clk); - -out_put_clk: - clk_put(priv->mac_clk); - -out_unmap: - iounmap(priv->base); - -out_release_mem: - release_mem_region(res_mem->start, resource_size(res_mem)); out: free_netdev(dev); return ret; @@ -2805,20 +2782,13 @@ static int bcm_enetsw_remove(struct platform_device *pdev) { struct bcm_enet_priv *priv; struct net_device *dev; - struct resource *res; /* stop netdevice */ dev = platform_get_drvdata(pdev); priv = netdev_priv(dev); unregister_netdev(dev); - /* release device resources */ - iounmap(priv->base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - clk_disable_unprepare(priv->mac_clk); - clk_put(priv->mac_clk); free_netdev(dev); return 0; -- GitLab From 4e78e5c5d881bf2d6267545a554c1baf245257b7 Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:19 +0200 Subject: [PATCH 0730/1507] bcm63xx_enet: drop unneeded NULL phy_clk check clk_disable and clk_unprepare are NULL-safe, so need to duplicate the NULL check of the functions. Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 059ef4f1d1378..f6bc13fe8a997 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1903,8 +1903,7 @@ static int bcm_enet_probe(struct platform_device *pdev) out_uninit_hw: /* turn off mdc clock */ enet_writel(priv, 0, ENET_MIISC_REG); - if (priv->phy_clk) - clk_disable_unprepare(priv->phy_clk); + clk_disable_unprepare(priv->phy_clk); out_disable_clk_mac: clk_disable_unprepare(priv->mac_clk); @@ -1943,9 +1942,7 @@ static int bcm_enet_remove(struct platform_device *pdev) } /* disable hw block clocks */ - if (priv->phy_clk) - clk_disable_unprepare(priv->phy_clk); - + clk_disable_unprepare(priv->phy_clk); clk_disable_unprepare(priv->mac_clk); free_netdev(dev); -- GitLab From 840f922317fb5c20841d6d7f3853ead506546ade Mon Sep 17 00:00:00 2001 From: Jonas Gorski Date: Sun, 1 Oct 2017 13:02:20 +0200 Subject: [PATCH 0731/1507] bcm63xx_enet: remove unneeded include We don't use anyhing from that file, so drop it. Signed-off-by: Jonas Gorski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.h b/drivers/net/ethernet/broadcom/bcm63xx_enet.h index 0a1b7b2e55bde..dd6ae3077433e 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.h +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.h @@ -8,7 +8,6 @@ #include #include -#include #include #include -- GitLab From 45bfbc013b4294cadafbef821d377d3a99c7ab1e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 1 Oct 2017 17:27:35 +0100 Subject: [PATCH 0732/1507] mlxsw: spectrum: fix uninitialized value in err In the unlikely event that mfc->mfc_un.res.ttls[i] is 255 for all values of i from 0 to MAXIVS-1, the err is not set at all and hence has a garbage value on the error return at the end of the function, so initialize it to 0. Also, the error return check on err and goto to err: inside the for loop makes it impossible for err to be zero at the end of the for loop, so we can remove the redundant err check at the end of the loop. Detected by CoverityScan CID#1457207 ("Unitialized scalar value") Fixes: c011ec1bbfd6 ("mlxsw: spectrum: Add the multicast routing offloading logic") Signed-off-by: Colin Ian King Reviewed-by: Yotam Gigi Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 09120259a45df..4aaf6ca1be7cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -349,7 +349,7 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table, { struct mlxsw_sp_mr_route_vif_entry *rve, *tmp; struct mlxsw_sp_mr_route *mr_route; - int err; + int err = 0; int i; /* Allocate and init a new route and fill it with parameters */ @@ -376,8 +376,6 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table, } } mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]); - if (err) - goto err; mr_route->route_action = mlxsw_sp_mr_route_action(mr_route); return mr_route; -- GitLab From 0929567a7a2dab8455a7313956973ff0d339709a Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 1 Oct 2017 14:07:34 -0700 Subject: [PATCH 0733/1507] samples/bpf: fix warnings in xdp_monitor_user MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make local functions static to fix HOSTCC samples/bpf/xdp_monitor_user.o samples/bpf/xdp_monitor_user.c:64:7: warning: no previous prototype for ‘gettime’ [-Wmissing-prototypes] __u64 gettime(void) ^~~~~~~ samples/bpf/xdp_monitor_user.c:209:6: warning: no previous prototype for ‘print_bpf_prog_info’ [-Wmissing-prototypes] void print_bpf_prog_info(void) ^~~~~~~~~~~~~~~~~~~ Fixes: 3ffab5460264 ("samples/bpf: xdp_monitor tool based on tracepoints") Signed-off-by: Stephen Hemminger Acked-by: Alexei Starovoitov Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- samples/bpf/xdp_monitor_user.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index b51b4f5e32575..c5ab8b776973a 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -61,7 +61,7 @@ static void usage(char *argv[]) } #define NANOSEC_PER_SEC 1000000000 /* 10^9 */ -__u64 gettime(void) +static __u64 gettime(void) { struct timespec t; int res; @@ -206,7 +206,7 @@ static void stats_poll(int interval, bool err_only) } } -void print_bpf_prog_info(void) +static void print_bpf_prog_info(void) { int i; -- GitLab From fb458864d9a78cc433fec7979acbe4078c82d7a8 Mon Sep 17 00:00:00 2001 From: Chanho Min Date: Tue, 26 Sep 2017 09:03:40 +0900 Subject: [PATCH 0734/1507] mmc: core: add driver strength selection when selecting hs400es The driver strength selection is missed and required when selecting hs400es. So, It is added here. Fixes: 81ac2af65793ecf ("mmc: core: implement enhanced strobe support") Cc: stable@vger.kernel.org Signed-off-by: Hankyung Yu Signed-off-by: Chanho Min Reviewed-by: Adrian Hunter Reviewed-by: Shawn Lin Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index a7eb623f8daa3..36217ad5e9b1f 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1286,6 +1286,23 @@ int mmc_hs400_to_hs200(struct mmc_card *card) return err; } +static void mmc_select_driver_type(struct mmc_card *card) +{ + int card_drv_type, drive_strength, drv_type; + + card_drv_type = card->ext_csd.raw_driver_strength | + mmc_driver_type_mask(0); + + drive_strength = mmc_select_drive_strength(card, + card->ext_csd.hs200_max_dtr, + card_drv_type, &drv_type); + + card->drive_strength = drive_strength; + + if (drv_type) + mmc_set_driver_type(card->host, drv_type); +} + static int mmc_select_hs400es(struct mmc_card *card) { struct mmc_host *host = card->host; @@ -1341,6 +1358,8 @@ static int mmc_select_hs400es(struct mmc_card *card) goto out_err; } + mmc_select_driver_type(card); + /* Switch card to HS400 */ val = EXT_CSD_TIMING_HS400 | card->drive_strength << EXT_CSD_DRV_STR_SHIFT; @@ -1374,23 +1393,6 @@ static int mmc_select_hs400es(struct mmc_card *card) return err; } -static void mmc_select_driver_type(struct mmc_card *card) -{ - int card_drv_type, drive_strength, drv_type; - - card_drv_type = card->ext_csd.raw_driver_strength | - mmc_driver_type_mask(0); - - drive_strength = mmc_select_drive_strength(card, - card->ext_csd.hs200_max_dtr, - card_drv_type, &drv_type); - - card->drive_strength = drive_strength; - - if (drv_type) - mmc_set_driver_type(card->host, drv_type); -} - /* * For device supporting HS200 mode, the following sequence * should be done before executing the tuning process. -- GitLab From 2a5e597c6bb1b873e473e5f57147e9e5d2755430 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 18 Sep 2017 09:27:42 -0700 Subject: [PATCH 0735/1507] HID: wacom: Always increment hdev refcount within wacom_get_hdev_data The wacom_get_hdev_data function is used to find and return a reference to the "other half" of a Wacom device (i.e., the touch device associated with a pen, or vice-versa). To ensure these references are properly accounted for, the function is supposed to automatically increment the refcount before returning. This was not done, however, for devices which have pen & touch on different interfaces of the same USB device. This can lead to a WARNING ("refcount_t: underflow; use-after-free") when removing the module or device as we call kref_put() more times than kref_get(). Triggering an "actual" use- after-free would be difficult since both devices will disappear nearly- simultaneously. To silence this warning and prevent the potential error, we need to increment the refcount for all cases within wacom_get_hdev_data. Fixes: 41372d5d40 ("HID: wacom: Augment 'oVid' and 'oPid' with heuristics for HID_GENERIC") Cc: # v4.9+ Signed-off-by: Jason Gerecke Reviewed-by: Ping Cheng Signed-off-by: Jiri Kosina --- drivers/hid/wacom_sys.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 735bfbbcaa827..906e654fb0ba4 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -668,8 +668,10 @@ static struct wacom_hdev_data *wacom_get_hdev_data(struct hid_device *hdev) /* Try to find an already-probed interface from the same device */ list_for_each_entry(data, &wacom_udev_list, list) { - if (compare_device_paths(hdev, data->dev, '/')) + if (compare_device_paths(hdev, data->dev, '/')) { + kref_get(&data->kref); return data; + } } /* Fallback to finding devices that appear to be "siblings" */ -- GitLab From 814b6d17487fd970f293ee674c90ba267f82415d Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 19 Sep 2017 18:37:46 -0700 Subject: [PATCH 0736/1507] HID: hidraw: fix power sequence when closing device We should not try to bring HID device out of full power state before calling hid_hw_close(), so that transport driver operates on powered up device (making this inverse of the opening sequence). Signed-off-by: Dmitry Torokhov Reviewed-by: Guenter Roeck Reviewed-by: Benson Leung Signed-off-by: Jiri Kosina --- drivers/hid/hidraw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index ec530454e6f68..5fbe0f81ab2eb 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -337,8 +337,8 @@ static void drop_ref(struct hidraw *hidraw, int exists_bit) kfree(hidraw); } else { /* close device for last reader */ - hid_hw_power(hidraw->hid, PM_HINT_NORMAL); hid_hw_close(hidraw->hid); + hid_hw_power(hidraw->hid, PM_HINT_NORMAL); } } } -- GitLab From 66dcdafe8e251a3edc5d84cf725835567bd3dd35 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Mon, 2 Oct 2017 15:50:34 +0800 Subject: [PATCH 0737/1507] Revert "HID: multitouch: Support ALPS PTP stick with pid 0x120A" This reverts commit fcaa4a07d2a4b541e91da7a55d8b3331f96d1865. As noted by Masaki [1], 0x120A + trackpoint will not be used in mass production machines, so remove the ID accordingly. [1] http://www.spinics.net/lists/linux-input/msg53222.html Signed-off-by: Kai-Heng Feng Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-ids.h | 1 - drivers/hid/hid-multitouch.c | 4 ---- 2 files changed, 5 deletions(-) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 832897d4a849d..a989191998587 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -75,7 +75,6 @@ #define USB_VENDOR_ID_ALPS_JP 0x044E #define HID_DEVICE_ID_ALPS_U1_DUAL 0x120B -#define HID_DEVICE_ID_ALPS_U1_PTP_2 0x120A #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP 0x121F #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index c78625dceced9..9e8c4d2ba11d2 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1419,10 +1419,6 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) }, - { .driver_data = MT_CLS_WIN_8_DUAL, - HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, - USB_VENDOR_ID_ALPS_JP, - HID_DEVICE_ID_ALPS_U1_PTP_2) }, /* Lenovo X1 TAB Gen 2 */ { .driver_data = MT_CLS_WIN_8_DUAL, -- GitLab From 504871e602d9a9ea2321d47ca506887417f54e75 Mon Sep 17 00:00:00 2001 From: Manikanta Pubbisetty Date: Tue, 26 Sep 2017 00:39:15 +0530 Subject: [PATCH 0738/1507] mac80211: fix bandwidth computation for TDLS peers Section 11.23.1 of 80211-2016 specification allows TDLS peers to operate on wider bandwidths though they are connected to a BSS which do not support wider bandwidth operations, provided both the peers advertise wider bandwidth capabilities. The existing logic considers the minimum of station's and AP's capability for bandwidth computation. The same logic applies for TDLS peers as well, this restricts operating on wider bandwidths over a TDLS link when the peers are connected to legacy APs. As an example, if 80Mhz VHT capable peers are connected to a 20Mhz 5 GHz AP, then as per the existing logic TDLS operation will be restricted to 20Mhz. Address this problem by not considering BSS capability in bandwidth computation if the participating TDLS peers have wider bandwidth capability. Signed-off-by: Manikanta Pubbisetty [lots of wording/typo fixes] Signed-off-by: Johannes Berg --- net/mac80211/vht.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 19ec2189d3acb..b9276ac849fa4 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -386,6 +386,16 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) bw = ieee80211_sta_cap_rx_bw(sta); bw = min(bw, sta->cur_max_bandwidth); + + /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of + * IEEE80211-2016 specification makes higher bandwidth operation + * possible on the TDLS link if the peers have wider bandwidth + * capability. + */ + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && + test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) + return bw; + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; -- GitLab From 8f797c288e3a788e9578dd4db08b624a6d4b6a9b Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 26 Sep 2017 13:48:05 +0200 Subject: [PATCH 0739/1507] mac80211: fix STA_SLOW_THRESHOLD htmldocs failure Patch fixes htmldocs build problem: Error(.//net/mac80211/sta_info.h:416): cannot understand prototype: 'STA_SLOW_THRESHOLD 6000 ' Signed-off-by: Stanislaw Gruszka Signed-off-by: Johannes Berg --- net/mac80211/sta_info.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 3acbdfa9f649f..a35c964f6217a 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -398,7 +398,7 @@ struct ieee80211_sta_rx_stats { u64 msdu[IEEE80211_NUM_TIDS + 1]; }; -/** +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being -- GitLab From 66b1bedf662518e9b6367990a87e9601b35a94c1 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 29 Sep 2017 14:21:14 +0300 Subject: [PATCH 0740/1507] ieee80211: Add WFA TPC report element OUI type Add Transmit Power Control OUI type definition for WLAN_OUI_MICROSOFT. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 55a604ad459f6..ee6657a0ed696 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2445,6 +2445,7 @@ enum ieee80211_sa_query_action { #define WLAN_OUI_TYPE_MICROSOFT_WPA 1 #define WLAN_OUI_TYPE_MICROSOFT_WMM 2 #define WLAN_OUI_TYPE_MICROSOFT_WPS 4 +#define WLAN_OUI_TYPE_MICROSOFT_TPC 8 /* * WMM/802.11e Tspec Element -- GitLab From 503c1fb98ba3859c13863957c7c65c92371a9e50 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 29 Sep 2017 14:21:49 +0200 Subject: [PATCH 0741/1507] cfg80211/nl80211: add a port authorized event Add an event that indicates that a connection is authorized (i.e. the 4 way handshake was performed by the driver). This event should be sent by the driver after sending a connect/roamed event. This is useful for networks that require 802.1X authentication. In cases that the driver supports 4 way handshake offload, but the 802.1X authentication is managed by user space, the driver needs to inform user space right after the 802.11 association was completed so user space can initialize its 802.1X state machine etc. However, it is also possible that the AP will choose to skip the 802.1X authentication (e.g. when PMKSA caching is used) and proceed with the 4 way handshake immediately. In this case the driver needs to inform user space that 802.1X authentication is no longer required (e.g. to prevent user space from disconnecting since it did not get any EAPOLs from the AP). This is also useful for roaming, in which case it is possible that the driver used the Fast Transition protocol so 802.1X is not required. Since there will now be a dedicated notification indicating that the connection is authorized, the authorized flag can be removed from the roamed event. Drivers can send the new port authorized event right after sending the roamed event to indicate the new AP is already authorized. This therefore reserves the old PORT_AUTHORIZED attribute. Signed-off-by: Avraham Stern Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 21 +++++++++++++---- include/uapi/linux/nl80211.h | 28 +++++++++++++--------- net/wireless/core.h | 5 ++++ net/wireless/nl80211.c | 34 ++++++++++++++++++++++++--- net/wireless/nl80211.h | 2 ++ net/wireless/sme.c | 45 +++++++++++++++++++++++++++++++++++- net/wireless/util.c | 3 +++ 7 files changed, 119 insertions(+), 19 deletions(-) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cc1996081463c..8b8118a7fadbc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5428,9 +5428,6 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length - * @authorized: true if the 802.1X authentication was done by the driver or is - * not needed (e.g., when Fast Transition protocol was used), false - * otherwise. Ignored for networks that don't use 802.1X authentication. */ struct cfg80211_roam_info { struct ieee80211_channel *channel; @@ -5440,7 +5437,6 @@ struct cfg80211_roam_info { size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; - bool authorized; }; /** @@ -5464,6 +5460,23 @@ struct cfg80211_roam_info { void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp); +/** + * cfg80211_port_authorized - notify cfg80211 of successful security association + * + * @dev: network device + * @bssid: the BSSID of the AP + * @gfp: allocation flags + * + * This function should be called by a driver that supports 4 way handshake + * offload after a security association was successfully established (i.e., + * the 4 way handshake was completed successfully). The call to this function + * should be preceded with a call to cfg80211_connect_result(), + * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to + * indicate the 802.11 association. + */ +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp); + /** * cfg80211_disconnected - notify cfg80211 that connection was dropped * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 59ba6ca66a0d0..95832ce03a440 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -569,13 +569,14 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * @NL80211_CMD_ROAM: notifcation indicating the card/driver roamed by itself. - * When the driver roamed in a network that requires 802.1X authentication, - * %NL80211_ATTR_PORT_AUTHORIZED should be set if the 802.1X authentication - * was done by the driver or if roaming was done using Fast Transition - * protocol (in which case 802.1X authentication is not needed). If - * %NL80211_ATTR_PORT_AUTHORIZED is not set, user space is responsible for - * the 802.1X authentication. + * When establishing a security association, drivers that support 4 way + * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when + * the 4 way handshake is completed successfully. + * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. + * When a security association was established with the new AP (e.g. if + * the FT protocol was used for roaming or the driver completed the 4 way + * handshake), this event should be followed by an + * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other * reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and @@ -982,6 +983,12 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * &NL80211_ATTR_MAC. + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way + * handshake was completed successfully by the driver. The BSSID is + * specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake + * offload should send this event after indicating 802.11 association with + * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed + * &NL80211_CMD_DISCONNECT should be indicated instead. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1185,6 +1192,8 @@ enum nl80211_commands { NL80211_CMD_SET_PMK, NL80211_CMD_DEL_PMK, + NL80211_CMD_PORT_AUTHORIZED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2138,10 +2147,7 @@ enum nl80211_commands { * in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it * wants to use the supported offload of the 4-way handshake. * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. - * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED - * notification indicating that that 802.1X authentication was done by - * the driver or is not needed (because roaming used the Fast Transition - * protocol). + * @NL80211_ATTR_PORT_AUTHORIZED: (reserved) * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined diff --git a/net/wireless/core.h b/net/wireless/core.h index 6e809325af3bf..35165f42c2a8d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -216,6 +216,7 @@ enum cfg80211_event_type { EVENT_DISCONNECTED, EVENT_IBSS_JOINED, EVENT_STOPPED, + EVENT_PORT_AUTHORIZED, }; struct cfg80211_event { @@ -235,6 +236,9 @@ struct cfg80211_event { u8 bssid[ETH_ALEN]; struct ieee80211_channel *channel; } ij; + struct { + u8 bssid[ETH_ALEN]; + } pa; }; }; @@ -385,6 +389,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1e39ba3cfd060..90e212db68893 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13830,9 +13830,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie)) || - (info->authorized && - nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) + info->resp_ie))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -13846,6 +13844,36 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PORT_AUTHORIZED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index b96933322077c..bf9e772a30b90 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -58,6 +58,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0a49b88070d0b..f38ed490e42b8 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -960,7 +960,6 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; - ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); @@ -969,6 +968,50 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, } EXPORT_SYMBOL(cfg80211_roamed); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +{ + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (WARN_ON(!wdev->current_bss) || + WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + return; + + nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, + bssid); +} + +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + if (WARN_ON(!bssid)) + return; + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_PORT_AUTHORIZED; + memcpy(ev->pa.bssid, bssid, ETH_ALEN); + + /* + * Use the wdev event list so that if there are pending + * connected/roamed events, they will be reported first. + */ + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + queue_work(cfg80211_wq, &rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_port_authorized); + void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { diff --git a/net/wireless/util.c b/net/wireless/util.c index 7a1fcc6ee0606..ff21c314a6094 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -846,6 +846,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_STOPPED: __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; + case EVENT_PORT_AUTHORIZED: + __cfg80211_port_authorized(wdev, ev->pa.bssid); + break; } wdev_unlock(wdev); -- GitLab From 51db452df07bb4c5754b73789253ba21681d9dc2 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 26 Sep 2017 09:11:49 +0900 Subject: [PATCH 0742/1507] Revert "ALSA: echoaudio: purge contradictions between dimension matrix members and total number of members" This reverts commit 275353bb684e to fix a regression which can abort 'alsactl' program in alsa-utils due to assertion in alsa-lib. alsactl: control.c:2513: snd_ctl_elem_value_get_integer: Assertion `idx < sizeof(obj->value.integer.value) / sizeof(obj->value.integer.value[0])' failed. alsactl: control.c:2976: snd_ctl_elem_value_get_integer: Assertion `idx < ARRAY_SIZE(obj->value.integer.value)' failed. This commit is a band-aid. In a point of usage of ALSA control interface, the drivers still bring an issue that they prevent userspace applications to have a consistent way to parse each levels of the dimension information via ALSA control interface. Let me investigate this issue. Current implementation of the drivers have three control element sets with dimension information: * 'Monitor Mixer Volume' (type: integer) * 'VMixer Volume' (type: integer) * 'VU-meters' (type: boolean) Although the number of elements named as 'Monitor Mixer Volume' differs depending on drivers in this group, it can be calculated by macros defined by each driver (= (BX_NUM - BX_ANALOG_IN) * BX_ANALOG_IN). Each of the elements has one member for value and has dimension information with 2 levels (= BX_ANALOG_IN * (BX_NUM - BX_ANALOG_IN)). For these elements, userspace applications are expected to handle the dimension information so that all of the elements construct a matrix where the number of rows and columns are represented by the dimension information. The same way is applied to elements named as 'VMixer Volume'. The number of these elements can also be calculated by macros defined by each drivers (= PX_ANALOG_IN * BX_ANALOG_IN). Each of the element has one member for value and has dimension information with 2 levels (= BX_ANALOG_IN * PX_ANALOG_IN). All of the elements construct a matrix with the dimension information. An element named as 'VU-meters' gets a different way in a point of dimension information. The element includes 96 members for value. The element has dimension information with 3 levels (= 3 or 2 * 16 * 2). For this element, userspace applications are expected to handle the dimension information so that all of the members for value construct a matrix where the number of rows and columns are represented by the dimension information. This is different from the way for the former. As a summary, the drivers were not designed to produce a consistent way to parse the dimension information. This makes it hard for general userspace applications such as amixer to parse the information by a consistent way, and actually no userspace applications except for 'echomixer' utilize the dimension information. Additionally, no drivers excluding this group use the information. The reverted commit was written based on the latter way. A commit 860c1994a70a ('ALSA: control: add dimension validator for userspace elements') is written based on the latter way, too. The patch should be reconsider too in the same time to re-define a consistent way to parse the dimension information. Reported-by: Mark Hills Reported-by: S. Christian Collins Fixes: 275353bb684e ('ALSA: echoaudio: purge contradictions between dimension matrix members and total number of members') Cc: # v4.8+ Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- sound/pci/echoaudio/echoaudio.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index 7326695bca337..d68f99e076a87 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -1272,11 +1272,11 @@ static int snd_echo_mixer_info(struct snd_kcontrol *kcontrol, chip = snd_kcontrol_chip(kcontrol); uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = ECHOGAIN_MAXOUT; uinfo->dimen.d[0] = num_busses_out(chip); uinfo->dimen.d[1] = num_busses_in(chip); - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1]; return 0; } @@ -1344,11 +1344,11 @@ static int snd_echo_vmixer_info(struct snd_kcontrol *kcontrol, chip = snd_kcontrol_chip(kcontrol); uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 1; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = ECHOGAIN_MAXOUT; uinfo->dimen.d[0] = num_busses_out(chip); uinfo->dimen.d[1] = num_pipes_out(chip); - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1]; return 0; } @@ -1728,6 +1728,7 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; + uinfo->count = 96; uinfo->value.integer.min = ECHOGAIN_MINOUT; uinfo->value.integer.max = 0; #ifdef ECHOCARD_HAS_VMIXER @@ -1737,7 +1738,6 @@ static int snd_echo_vumeters_info(struct snd_kcontrol *kcontrol, #endif uinfo->dimen.d[1] = 16; /* 16 channels */ uinfo->dimen.d[2] = 2; /* 0=level, 1=peak */ - uinfo->count = uinfo->dimen.d[0] * uinfo->dimen.d[1] * uinfo->dimen.d[2]; return 0; } -- GitLab From 0a6de8b8668a2cfc0912a1d7df21107e1a075a3a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 2 Oct 2017 12:42:00 +0100 Subject: [PATCH 0743/1507] arm64: fix misleading data abort decoding Currently data_abort_decode() dumps the ISS field as a decimal value with a '0x' prefix, which is somewhat misleading. Fix it to print as hexadecimal, as was intended. Fixes: 1f9b8936f36f4a8e ("arm64: Decode information from ESR upon mem faults") Reviewed-by: Dave Martin Reviewed-by: Julien Thierry Acked-by: Will Deacon Signed-off-by: Mark Rutland Signed-off-by: Catalin Marinas --- arch/arm64/mm/fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2069e9bc0fca6..b64958b23a7fa 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -97,7 +97,7 @@ static void data_abort_decode(unsigned int esr) (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { - pr_alert(" ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK); + pr_alert(" ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK); } pr_alert(" CM = %lu, WnR = %lu\n", -- GitLab From 9f4057fc937f200f000dbc378c5c3e37d45e31dc Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 22 Sep 2017 09:26:57 +0800 Subject: [PATCH 0744/1507] ceph: properly queue cap snap for newly created snap realm commit 3ae0bebc "ceph: queue cap snap only when snap realm's context changes" introduced a regression: we may not call queue_realm_cap_snaps() for newly created snap realm. This regression allows unflushed snapshot data to be overwritten. Link: http://tracker.ceph.com/issues/21483 Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/snap.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 1ffc8b426c1c4..7fc0b850c3527 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -374,12 +374,10 @@ static int build_snap_context(struct ceph_snap_realm *realm, realm->ino, realm, snapc, snapc->seq, (unsigned int) snapc->num_snaps); - if (realm->cached_context) { - ceph_put_snap_context(realm->cached_context); - /* queue realm for cap_snap creation */ - list_add_tail(&realm->dirty_item, dirty_realms); - } + ceph_put_snap_context(realm->cached_context); realm->cached_context = snapc; + /* queue realm for cap_snap creation */ + list_add_tail(&realm->dirty_item, dirty_realms); return 0; fail: -- GitLab From 38f340ccdf9ed5f1350505b46c5689d015967057 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 22 Sep 2017 11:41:06 +0800 Subject: [PATCH 0745/1507] ceph: fix __choose_mds() for LSSNAP request previous commit 5d37ca14 "ceph: send LSSNAP request to auth mds of directory inode" is buggy. It makes __choose_mds() choose mds base on hash of '.snap' dentry. Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 84edfc60d87a8..f23c820daaedc 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -734,12 +734,13 @@ static int __choose_mds(struct ceph_mds_client *mdsc, inode = req->r_inode; ihold(inode); } else { - /* req->r_dentry is non-null for LSSNAP request. - * fall-thru */ - WARN_ON_ONCE(!req->r_dentry); + /* req->r_dentry is non-null for LSSNAP request */ + rcu_read_lock(); + inode = get_nonsnap_parent(req->r_dentry); + rcu_read_unlock(); + dout("__choose_mds using snapdir's parent %p\n", inode); } - } - if (!inode && req->r_dentry) { + } else if (req->r_dentry) { /* ignore race with rename; old or new d_parent is okay */ struct dentry *parent; struct inode *dir; -- GitLab From 17a91809942ca32c70026d2d5ba3348a2c4fdf8f Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 2 Oct 2017 07:17:50 -0700 Subject: [PATCH 0746/1507] fm10k: ensure we process SM mbx when processing VF mbx When we process VF mailboxes, the driver is likely going to also queue up messages to the switch manager. This process merely queues up the FIFO, but doesn't actually begin the transmission process. Because we hold the mailbox lock during this VF processing, the PF<->SM mailbox is not getting processed at this time. Ensure that we actually process the PF<->SM mailbox in between each PF<->VF mailbox. This should ensure prompt transmission of the messages queued up after each VF message is received and handled. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 5f4dac0d36ef1..2ec49116fe910 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -126,6 +126,9 @@ s32 fm10k_iov_mbx(struct fm10k_intfc *interface) struct fm10k_mbx_info *mbx = &vf_info->mbx; u16 glort = vf_info->glort; + /* process the SM mailbox first to drain outgoing messages */ + hw->mbx.ops.process(hw, &hw->mbx); + /* verify port mapping is valid, if not reset port */ if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) hw->iov.ops.reset_lport(hw, vf_info); -- GitLab From b52b7f7059f2df8eb3258a25bc69e12dc21ebcd7 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 8 Mar 2017 15:55:43 -0800 Subject: [PATCH 0747/1507] fm10k: reschedule service event if we stall the PF<->SM mailbox When we are handling PF<->VF mailbox messages, it is possible that the VF will send us so many messages that the PF<->SM FIFO will fill up. In this case, we stop the loop and wait until the service event is rescheduled. Normally this should happen due to an interrupt. But it is possible that we don't get another interrupt for a while and it isn't until the service timer actually reschedules us. Instead, simply reschedule immediately which will cause the service event to be run again as soon as we exit. This ensures that we promptly handle all of the PF<->VF messages with minimal delay, while still giving time for the SM mailbox to drain. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 2ec49116fe910..d8356c494f065 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -143,6 +143,10 @@ s32 fm10k_iov_mbx(struct fm10k_intfc *interface) if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) { /* keep track of how many times this occurs */ interface->hw_sm_mbx_full++; + + /* make sure we try again momentarily */ + fm10k_service_event_schedule(interface); + break; } -- GitLab From 95f49d4bdee34dd0f68446bb260ab537f62ed9b3 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Mon, 8 May 2017 18:18:09 +0200 Subject: [PATCH 0748/1507] fm10k: Use seq_putc() in fm10k_dbg_desc_break() Two single characters should be put into a sequence. Thus use the corresponding function "seq_putc". This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 5116fd0436309..14df09e2d964f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -52,9 +52,9 @@ static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s, static void fm10k_dbg_desc_break(struct seq_file *s, int i) { while (i--) - seq_puts(s, "-"); + seq_putc(s, '-'); - seq_puts(s, "\n"); + seq_putc(s, '\n'); } static int fm10k_dbg_tx_desc_seq_show(struct seq_file *s, void *v) -- GitLab From 5c66d1251d67714e9f6e6b0af18ca989109b876f Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:04 -0700 Subject: [PATCH 0749/1507] fm10k: stop spurious link down messages when Tx FIFO is full In fm10k_get_host_state_generic, we check the mailbox tx_read() function to ensure that the mailbox is still open. This function also checks to make sure we have space to transmit another message. Unfortunately, if we just recently sent a bunch of messages (such as enabling hundreds of VLANs on a VF) this can result in a race where the watchdog task thinks the link went down just because we haven't had time to process all these messages yet. Instead, lets just check whether the mailbox is still open. This ensures that we don't race with the Tx FIFO, and we only link down once the mailbox is not open. This is safe, because if the FIFO fills up and we're unable to send a message for too long, we'll end up triggering the timeout detection which results in a reset. Additionally, since we still check to ensure the mailbox state is OPEN, we'll transition to link down whenever the mailbox closes as well. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_common.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index 62a6ad9b3eeda..736a9f087bc9f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -517,8 +517,8 @@ s32 fm10k_get_host_state_generic(struct fm10k_hw *hw, bool *host_ready) goto out; } - /* verify Mailbox is still valid */ - if (!mbx->ops.tx_ready(mbx, FM10K_VFMBX_MSG_MTU)) + /* verify Mailbox is still open */ + if (mbx->state != FM10K_STATE_OPEN) goto out; /* interface cannot receive traffic without logical ports */ -- GitLab From 375ce90eab7ee1c87eefa2cd312b0be9ac961082 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:05 -0700 Subject: [PATCH 0750/1507] fm10k: fix typos on fall through comments Newer versions of GCC since version 7 now warn when a case statement may fall through without an explicit comment. "Fallthough" does not count as it is misspelled. Fix the typos for these comments to appease the new warnings. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_mbx.c | 4 ++-- drivers/net/ethernet/intel/fm10k/fm10k_pf.c | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 334088a101c3d..244d3ad58ca72 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1586,7 +1586,7 @@ s32 fm10k_pfvf_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, mbx->mbmem_reg = FM10K_MBMEM_VF(id, 0); break; } - /* fallthough */ + /* fall through */ default: return FM10K_MBX_ERR_NO_MBX; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 40ee0242a80ae..9e4fb3a443763 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -1334,19 +1334,19 @@ static u8 fm10k_iov_supported_xcast_mode_pf(struct fm10k_vf_info *vf_info, case FM10K_XCAST_MODE_PROMISC: if (vf_flags & FM10K_VF_FLAG_PROMISC_CAPABLE) return FM10K_XCAST_MODE_PROMISC; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_ALLMULTI: if (vf_flags & FM10K_VF_FLAG_ALLMULTI_CAPABLE) return FM10K_XCAST_MODE_ALLMULTI; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_MULTI: if (vf_flags & FM10K_VF_FLAG_MULTI_CAPABLE) return FM10K_XCAST_MODE_MULTI; - /* fallthough */ + /* fall through */ case FM10K_XCAST_MODE_NONE: if (vf_flags & FM10K_VF_FLAG_NONE_CAPABLE) return FM10K_XCAST_MODE_NONE; - /* fallthough */ + /* fall through */ default: break; } -- GitLab From b94dd008c401fc73a8d843e3219356255f40c1ed Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:06 -0700 Subject: [PATCH 0751/1507] fm10k: avoid possible truncation of q_vector->name New versions of GCC since version 7 began warning about possible truncation of calls to snprintf. We can fix this and avoid false positives. First, we should pass the full buffer size to snprintf, because it guarantees a NULL character as part of its passed length, so passing len-1 is simply wasting a byte of possible storage. Second, if we make the ri and ti variables unsigned, the compiler is able to correctly reason that the value never gets larger than 256, so it doesn't need to warn about the full space required to print a signed integer. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 63784576ae8b3..9212b3fa3b62e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1544,7 +1544,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) struct net_device *dev = interface->netdev; struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - int ri = 0, ti = 0; + unsigned int ri = 0, ti = 0; int vector, err; entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; @@ -1554,15 +1554,15 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) /* name the vector */ if (q_vector->tx.count && q_vector->rx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-TxRx-%d", dev->name, ri++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-TxRx-%u", dev->name, ri++); ti++; } else if (q_vector->rx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-rx-%d", dev->name, ri++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-rx-%u", dev->name, ri++); } else if (q_vector->tx.count) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "%s-tx-%d", dev->name, ti++); + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-tx-%u", dev->name, ti++); } else { /* skip this unused q_vector */ continue; -- GitLab From 523a0b558db4ca205522976077911e5efe235781 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:07 -0700 Subject: [PATCH 0752/1507] fm10k: add missing fall through comment Newer versions of GCC starting with 7 now additionally warn when a case statement may fall through without an explicit comment mentioning it. Add such a comment to silence the warning, as this is expected. Unfortunately the comment must come directly before the next case statement, so we put it outside the #ifdef. Otherwise, the compiler cannot properly detect it and thus the warning is displayed regardless. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9dffaba85ae6b..189d52a8a6053 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -876,6 +876,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring, case IPPROTO_GRE: if (skb->encapsulation) break; + /* fall through */ default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, -- GitLab From 8bac58be1700dab3cac8cb53ed0651da40777024 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:08 -0700 Subject: [PATCH 0753/1507] fm10k: avoid needless delay when loading driver When we load the driver, we set the last_reset to be in the future, which delays the initial driver reset. Additionally, the service task isn't scheduled to run automatically until the timer runs out. This causes a needless delay of the first reset to begin talking to the switch manager. We can avoid this by simply not setting last_reset and immediately scheduling the service task while in probe. This allows the device to wake up faster, and avoids this delay. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9212b3fa3b62e..6c2c4bffaedfb 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1800,9 +1800,6 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, netdev->vlan_features |= NETIF_F_HIGHDMA; } - /* delay any future reset requests */ - interface->last_reset = jiffies + (10 * HZ); - /* reset and initialize the hardware so it is in a known state */ err = hw->mac.ops.reset_hw(hw); if (err) { @@ -2079,8 +2076,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* enable SR-IOV after registering netdev to enforce PF/VF ordering */ fm10k_iov_configure(pdev, 0); - /* clear the service task disable bit to allow service task to start */ + /* clear the service task disable bit and kick off service task */ clear_bit(__FM10K_SERVICE_DISABLE, interface->state); + fm10k_service_event_schedule(interface); return 0; -- GitLab From 4abf01b43b62525e4f1a20dd1a2bc4a1967d8928 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:09 -0700 Subject: [PATCH 0754/1507] fm10k: simplify reading PFVFLRE register We're doing a really convoluted bitshift and read for the PFVFLRE register. Just reading the PFVFLRE(1), shifting it by 32, then reading PFVFLRE(0) should be sufficient. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index d8356c494f065..dfc88a4637353 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -67,10 +67,8 @@ s32 fm10k_iov_event(struct fm10k_intfc *interface) /* read VFLRE to determine if any VFs have been reset */ do { - vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(0)); + vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1)); vflre <<= 32; - vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(1)); - vflre = (vflre << 32) | (vflre >> 32); vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0)); i = iov_data->num_vfs; -- GitLab From d876c1583bb1b7f7264880265b824e88b791aa5d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:10 -0700 Subject: [PATCH 0755/1507] fm10k: don't loop while resetting VFs due to VFLR event We've always had a really weird looping construction for resetting VFs. We read the VFLRE register and reset the VF if the corresponding bit is set, which makes sense. However we loop continuously until we no longer have any bits left unset. At first this makes sense, as a sort of "keep trying until we succeed" concept. Unfortunately this causes a problem if we happen to surprise remove while this code is executing, because in this case we'll always read all 1s for the VFLRE register. This results in a hard lockup on the CPU because the loop will never terminate. Because our own reset function will clear the VFLR event register always, (except when we've lost PCIe link obviously) there is no real reason to loop. In practice, we'll loop over once and find that no VFs are pending anymore. Lets just check once. Since we're clear the notification when we reset there's no benefit to the loop. Additionally, there shouldn't be a race as future VLFRE events should trigger an interrupt. Additionally, we didn't warn or do anything in the looped case anyways. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 24 +++++++++----------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index dfc88a4637353..03897720bf0b5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -66,23 +66,21 @@ s32 fm10k_iov_event(struct fm10k_intfc *interface) goto read_unlock; /* read VFLRE to determine if any VFs have been reset */ - do { - vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1)); - vflre <<= 32; - vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0)); + vflre = fm10k_read_reg(hw, FM10K_PFVFLRE(1)); + vflre <<= 32; + vflre |= fm10k_read_reg(hw, FM10K_PFVFLRE(0)); - i = iov_data->num_vfs; + i = iov_data->num_vfs; - for (vflre <<= 64 - i; vflre && i--; vflre += vflre) { - struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; + for (vflre <<= 64 - i; vflre && i--; vflre += vflre) { + struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; - if (vflre >= 0) - continue; + if (vflre >= 0) + continue; - hw->iov.ops.reset_resources(hw, vf_info); - vf_info->mbx.ops.connect(hw, &vf_info->mbx); - } - } while (i != iov_data->num_vfs); + hw->iov.ops.reset_resources(hw, vf_info); + vf_info->mbx.ops.connect(hw, &vf_info->mbx); + } read_unlock: rcu_read_unlock(); -- GitLab From dd5eede2b711350f684e8510300cb3762a821ae6 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:11 -0700 Subject: [PATCH 0756/1507] fm10k: avoid divide by zero in rare cases when device is resetting It is possible that under rare circumstances the device is undergoing a reset, such as when a PFLR occurs, and the device may be transmitting simultaneously. In this case, we might attempt to divide by zero when finding the proper r_idx. Instead, lets read the num_tx_queues once, and make sure it's non-zero. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index e69d49d91d67d..77d495fedced0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -643,9 +643,13 @@ int fm10k_close(struct net_device *netdev) static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) { struct fm10k_intfc *interface = netdev_priv(dev); + int num_tx_queues = READ_ONCE(interface->num_tx_queues); unsigned int r_idx = skb->queue_mapping; int err; + if (!num_tx_queues) + return NETDEV_TX_BUSY; + if ((skb->protocol == htons(ETH_P_8021Q)) && !skb_vlan_tag_present(skb)) { /* FM10K only supports hardware tagging, any tags in frame @@ -698,8 +702,8 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) __skb_put(skb, pad_len); } - if (r_idx >= interface->num_tx_queues) - r_idx %= interface->num_tx_queues; + if (r_idx >= num_tx_queues) + r_idx %= num_tx_queues; err = fm10k_xmit_frame_ring(skb, interface->tx_ring[r_idx]); -- GitLab From 65b0a469e9e6d025ce9cc46f6cc94d28abf5561c Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:12 -0700 Subject: [PATCH 0757/1507] fm10k: move fm10k_prepare_for_reset and fm10k_handle_reset A future patch needs these functions defined earlier in the file. Move them closer to above where they will be called. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 58 ++++++++++---------- 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 6c2c4bffaedfb..41335154d6b1b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -132,35 +132,6 @@ static void fm10k_service_timer(unsigned long data) fm10k_service_event_schedule(interface); } -static void fm10k_detach_subtask(struct fm10k_intfc *interface) -{ - struct net_device *netdev = interface->netdev; - u32 __iomem *hw_addr; - u32 value; - - /* do nothing if device is still present or hw_addr is set */ - if (netif_device_present(netdev) || interface->hw.hw_addr) - return; - - /* check the real address space to see if we've recovered */ - hw_addr = READ_ONCE(interface->uc_addr); - value = readl(hw_addr); - if (~value) { - interface->hw.hw_addr = interface->uc_addr; - netif_device_attach(netdev); - set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); - netdev_warn(netdev, "PCIe link restored, device now attached\n"); - return; - } - - rtnl_lock(); - - if (netif_running(netdev)) - dev_close(netdev); - - rtnl_unlock(); -} - static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; @@ -270,6 +241,35 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) return err; } +static void fm10k_detach_subtask(struct fm10k_intfc *interface) +{ + struct net_device *netdev = interface->netdev; + u32 __iomem *hw_addr; + u32 value; + + /* do nothing if device is still present or hw_addr is set */ + if (netif_device_present(netdev) || interface->hw.hw_addr) + return; + + /* check the real address space to see if we've recovered */ + hw_addr = READ_ONCE(interface->uc_addr); + value = readl(hw_addr); + if (~value) { + interface->hw.hw_addr = interface->uc_addr; + netif_device_attach(netdev); + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); + netdev_warn(netdev, "PCIe link restored, device now attached\n"); + return; + } + + rtnl_lock(); + + if (netif_running(netdev)) + dev_close(netdev); + + rtnl_unlock(); +} + static void fm10k_reinit(struct fm10k_intfc *interface) { int err; -- GitLab From 04914390f5a197da1e042f585e1263ad8ebff632 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:13 -0700 Subject: [PATCH 0758/1507] fm10k: prevent race condition of __FM10K_SERVICE_SCHED Although very unlikely, it is possible that cancel_work_sync() may stop the service_task before it actually started. In this case, the __FM10K_SERVICE_SCHED bit will never be cleared. This results in the service task being unable to reschedule in the future. Add a helper function which sets the service disable bit, waits for the service task to stop and clears the schedule bit, thus avoiding the race condition. We know the schedule bit is safe to clear because the cancel_work_sync() guarantees the service task is not running. Add a helper function also to restart the service task, for symmetry. This is not strictly needed but helps the mental model of how to stop and start the service task. This race could only happen in fm10k_suspend/fm10k_resume as this is the only place where the service task is actually restarted. Thus, suspend/resume testing would be ideal. However, note that the chance of this happening is very slim as the service event is scheduled for immediate execution, and you would have to trigger a suspend at almost the exact same time as the service task was scheduled. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 32 +++++++++++++++----- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 41335154d6b1b..9575f7c1862d5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -118,6 +118,27 @@ static void fm10k_service_event_complete(struct fm10k_intfc *interface) fm10k_service_event_schedule(interface); } +static void fm10k_stop_service_event(struct fm10k_intfc *interface) +{ + set_bit(__FM10K_SERVICE_DISABLE, interface->state); + cancel_work_sync(&interface->service_task); + + /* It's possible that cancel_work_sync stopped the service task from + * running before it could actually start. In this case the + * __FM10K_SERVICE_SCHED bit will never be cleared. Since we know that + * the service task cannot be running at this point, we need to clear + * the scheduled bit, as otherwise the service task may never be + * restarted. + */ + clear_bit(__FM10K_SERVICE_SCHED, interface->state); +} + +static void fm10k_start_service_event(struct fm10k_intfc *interface) +{ + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); + fm10k_service_event_schedule(interface); +} + /** * fm10k_service_timer - Timer Call-back * @data: pointer to interface cast into an unsigned long @@ -2116,8 +2137,7 @@ static void fm10k_remove(struct pci_dev *pdev) del_timer_sync(&interface->service_timer); - set_bit(__FM10K_SERVICE_DISABLE, interface->state); - cancel_work_sync(&interface->service_task); + fm10k_stop_service_event(interface); /* free netdev, this may bounce the interrupts due to setup_tc */ if (netdev->reg_state == NETREG_REGISTERED) @@ -2155,8 +2175,7 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) * stopped. We stop the watchdog task until after we resume software * activity. */ - set_bit(__FM10K_SERVICE_DISABLE, interface->state); - cancel_work_sync(&interface->service_task); + fm10k_stop_service_event(interface); fm10k_prepare_for_reset(interface); } @@ -2183,9 +2202,8 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) interface->link_down_event = jiffies + (HZ); set_bit(__FM10K_LINK_DOWN, interface->state); - /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, interface->state); - fm10k_service_event_schedule(interface); + /* restart the service task */ + fm10k_start_service_event(interface); return err; } -- GitLab From 7682e399485fe19622b6fd82510b1f4551e48a25 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 2 Oct 2017 14:06:43 +0200 Subject: [PATCH 0759/1507] ALSA: usx2y: Suppress kernel warning at page allocation failures The usx2y driver allocates the stream read/write buffers in continuous pages depending on the stream setup, and this may spew the kernel warning messages with a stack trace like: WARNING: CPU: 1 PID: 1846 at mm/page_alloc.c:3883 __alloc_pages_slowpath+0x1ef2/0x2d70 Modules linked in: CPU: 1 PID: 1846 Comm: kworker/1:2 Not tainted .... It may confuse user as if it were any serious error, although this is no fatal error and the driver handles the error case gracefully. Since the driver has already some sanity check of the given size (128 and 256 pages), it can't pass any crazy value. So it's merely page fragmentation. This patch adds __GFP_NOWARN to each caller for suppressing such kernel warnings. The original issue was spotted by syzkaller. Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: Signed-off-by: Takashi Iwai --- sound/usb/usx2y/usb_stream.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/sound/usb/usx2y/usb_stream.c b/sound/usb/usx2y/usb_stream.c index 4dab490807009..e229abd216526 100644 --- a/sound/usb/usx2y/usb_stream.c +++ b/sound/usb/usx2y/usb_stream.c @@ -191,7 +191,8 @@ struct usb_stream *usb_stream_new(struct usb_stream_kernel *sk, } pg = get_order(read_size); - sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg); + sk->s = (void *) __get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO| + __GFP_NOWARN, pg); if (!sk->s) { snd_printk(KERN_WARNING "couldn't __get_free_pages()\n"); goto out; @@ -211,7 +212,8 @@ struct usb_stream *usb_stream_new(struct usb_stream_kernel *sk, pg = get_order(write_size); sk->write_page = - (void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO, pg); + (void *)__get_free_pages(GFP_KERNEL|__GFP_COMP|__GFP_ZERO| + __GFP_NOWARN, pg); if (!sk->write_page) { snd_printk(KERN_WARNING "couldn't __get_free_pages()\n"); usb_stream_free(sk); -- GitLab From 32f16369e59fcc505c5ed93a6a8cad3d5636b463 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 2 Oct 2017 10:41:15 +0200 Subject: [PATCH 0760/1507] net/dst: Make skb parameter of skb{metadata_dst, tunnel_info}() const Make the skb parameter of skb_metadata_dst() and skb_tunnel_info() const as they are not modified. This is in preparation for using them in call-sites where skb is const. Signed-off-by: Simon Horman Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index a803129a4849f..9fba2ebf6ddaa 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -24,7 +24,7 @@ struct metadata_dst { } u; }; -static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb) +static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb) { struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); @@ -34,7 +34,8 @@ static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb) return NULL; } -static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb) +static inline struct ip_tunnel_info * +skb_tunnel_info(const struct sk_buff *skb) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; -- GitLab From a38402bc50709aac76796a955a15152a76e3fd4e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 2 Oct 2017 10:41:16 +0200 Subject: [PATCH 0761/1507] flow_dissector: dissect tunnel info Move dissection of tunnel info from the flower classifier to the flow dissector where all other dissection occurs. This should not have any behavioural affect on other users of the flow dissector. Signed-off-by: Simon Horman Reviewed-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 100 ++++++++++++++++++++++++++++++++++++++ net/sched/cls_flower.c | 25 ---------- 2 files changed, 100 insertions(+), 25 deletions(-) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0a977373d0033..1f5caafb44920 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -115,6 +116,102 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +static void +skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct flow_dissector_key_control *ctrl; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) + return; + + ctrl = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + target_container); + ctrl->addr_type = type; +} + +static void +__skb_flow_dissect_tunnel_info(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct ip_tunnel_info *info; + struct ip_tunnel_key *key; + + /* A quick check to see if there might be something to do. */ + if (!dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL) && + !dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS)) + return; + + info = skb_tunnel_info(skb); + if (!info) + return; + + key = &info->key; + + switch (ip_tunnel_info_af(info)) { + case AF_INET: + skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, + flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_dissector_key_ipv4_addrs *ipv4; + + ipv4 = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + target_container); + ipv4->src = key->u.ipv4.src; + ipv4->dst = key->u.ipv4.dst; + } + break; + case AF_INET6: + skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, + flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { + struct flow_dissector_key_ipv6_addrs *ipv6; + + ipv6 = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, + target_container); + ipv6->src = key->u.ipv6.src; + ipv6->dst = key->u.ipv6.dst; + } + break; + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *keyid; + + keyid = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + target_container); + keyid->keyid = tunnel_id_to_key32(key->tun_id); + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + struct flow_dissector_key_ports *tp; + + tp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + target_container); + tp->src = key->tp_src; + tp->dst = key->tp_dst; + } +} + static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -478,6 +575,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); + __skb_flow_dissect_tunnel_info(skb, flow_dissector, + target_container); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d230cb4c80945..db831ac708f60 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -152,37 +152,12 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; - struct ip_tunnel_info *info; if (!atomic_read(&head->ht.nelems)) return -1; fl_clear_masked_range(&skb_key, &head->mask); - info = skb_tunnel_info(skb); - if (info) { - struct ip_tunnel_key *key = &info->key; - - switch (ip_tunnel_info_af(info)) { - case AF_INET: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV4_ADDRS; - skb_key.enc_ipv4.src = key->u.ipv4.src; - skb_key.enc_ipv4.dst = key->u.ipv4.dst; - break; - case AF_INET6: - skb_key.enc_control.addr_type = - FLOW_DISSECTOR_KEY_IPV6_ADDRS; - skb_key.enc_ipv6.src = key->u.ipv6.src; - skb_key.enc_ipv6.dst = key->u.ipv6.dst; - break; - } - - skb_key.enc_key_id.keyid = tunnel_id_to_key32(key->tun_id); - skb_key.enc_tp.src = key->tp_src; - skb_key.enc_tp.dst = key->tp_dst; - } - skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, * so do it rather here. -- GitLab From 6227efc1a20b24a21ce8e9122c0569696d644aff Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 2 Oct 2017 12:05:29 +0200 Subject: [PATCH 0762/1507] selftests: rtnetlink.sh: add vxlan and fou test cases fou test lifted from ip-fou man page. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 96 ++++++++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a048f7a5f94c6..62c87da927708 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -332,6 +332,101 @@ kci_test_vrf() echo "PASS: vrf" } +kci_test_encap_vxlan() +{ + ret=0 + vxlan="test-vxlan0" + vlan="test-vlan0" + testns="$1" + + ip netns exec "$testns" ip link add "$vxlan" type vxlan id 42 group 239.1.1.1 \ + dev "$devdummy" dstport 4789 2>/dev/null + if [ $? -ne 0 ]; then + echo "FAIL: can't add vxlan interface, skipping test" + return 0 + fi + check_err $? + + ip netns exec "$testns" ip addr add 10.2.11.49/24 dev "$vxlan" + check_err $? + + ip netns exec "$testns" ip link set up dev "$vxlan" + check_err $? + + ip netns exec "$testns" ip link add link "$vxlan" name "$vlan" type vlan id 1 + check_err $? + + ip netns exec "$testns" ip link del "$vxlan" + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: vxlan" + return 1 + fi + echo "PASS: vxlan" +} + +kci_test_encap_fou() +{ + ret=0 + name="test-fou" + testns="$1" + + ip fou help 2>&1 |grep -q 'Usage: ip fou' + if [ $? -ne 0 ];then + echo "SKIP: fou: iproute2 too old" + return 1 + fi + + ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null + if [ $? -ne 0 ];then + echo "FAIL: can't add fou port 7777, skipping test" + return 1 + fi + + ip netns exec "$testns" ip fou add port 8888 ipproto 4 + check_err $? + + ip netns exec "$testns" ip fou del port 9999 2>/dev/null + check_fail $? + + ip netns exec "$testns" ip fou del port 7777 + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: fou" + return 1 + fi + + echo "PASS: fou" +} + +# test various encap methods, use netns to avoid unwanted interference +kci_test_encap() +{ + testns="testns" + ret=0 + + ip netns add "$testns" + if [ $? -ne 0 ]; then + echo "SKIP encap tests: cannot add net namespace $testns" + return 1 + fi + + ip netns exec "$testns" ip link set lo up + check_err $? + + ip netns exec "$testns" ip link add name "$devdummy" type dummy + check_err $? + ip netns exec "$testns" ip link set "$devdummy" up + check_err $? + + kci_test_encap_vxlan "$testns" + kci_test_encap_fou "$testns" + + ip netns del "$testns" +} + kci_test_rtnl() { kci_add_dummy @@ -348,6 +443,7 @@ kci_test_rtnl() kci_test_addrlabel kci_test_ifalias kci_test_vrf + kci_test_encap kci_del_dummy } -- GitLab From 28a04c7b7bbecaab642fcb6a2d7354eb70ea7fbe Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 2 Oct 2017 12:14:56 +0200 Subject: [PATCH 0763/1507] mlxsw: spectrum_router: Move VRF refcounting When creating a new RIF, bumping RIF count of the containing VR is the last thing to be done. Symmetrically, when destroying a RIF, RIF count is first dropped and only then the rest of the cleanup proceeds. That's a problem for loopback RIFs. Those hold two VR references: one for overlay and one for underlay. mlxsw_sp_rif_destroy() releases the overlay one, and the deconfigure() callback the underlay one. But if both overlay and underlay are the same, and if there are no other artifacts holding the VR alive, this put actually destroys the VR. Later on, when mlxsw_sp_rif_destroy() calls mlxsw_sp_vr_put() for the same VR, the VR will already have been released and the kernel crashes with NULL pointer dereference. The underlying problem is that the RIF under destruction ends up referencing the overlay VR much longer than it claims: all the way until the call to mlxsw_sp_vr_put(). So line up the reference counting properly to reflect this. Make corresponding changes in mlxsw_sp_rif_create() as well for symmetry. Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs") Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2cfb3f5d092db..3917b4dd4202f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5068,6 +5068,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN); if (IS_ERR(vr)) return ERR_CAST(vr); + vr->rif_count++; err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index); if (err) @@ -5099,7 +5100,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_counters_alloc(rif); mlxsw_sp->router->rifs[rif_index] = rif; - vr->rif_count++; return rif; @@ -5110,6 +5110,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, kfree(rif); err_rif_alloc: err_rif_index_alloc: + vr->rif_count--; mlxsw_sp_vr_put(vr); return ERR_PTR(err); } @@ -5124,7 +5125,6 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif); vr = &mlxsw_sp->router->vrs[rif->vr_id]; - vr->rif_count--; mlxsw_sp->router->rifs[rif->rif_index] = NULL; mlxsw_sp_rif_counters_free(rif); ops->deconfigure(rif); @@ -5132,6 +5132,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) /* Loopback RIFs are not associated with a FID. */ mlxsw_sp_fid_put(fid); kfree(rif); + vr->rif_count--; mlxsw_sp_vr_put(vr); } -- GitLab From de0f43c01a4b5d408a5c087c8a92ac1739938f8b Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 2 Oct 2017 12:14:57 +0200 Subject: [PATCH 0764/1507] mlxsw: spectrum_router: Track RIF of IPIP next hops When considering whether to set RTNH_F_OFFLOAD flag on an IPv6 route, mlxsw_sp_fib6_entry_offload_set() looks up the mlxsw_sp_nexthop corresponding to a given route, and decides based on whether the next hop's offloaded flag was set. When looking for the matching next hop, it also takes into account the device of the route, which must match next hop's RIF. IPIP next hops however hitherto didn't set the RIF. As a result, IPv6 routes forwarding traffic to IP-in-IP netdevices are never marked as offloaded, even when they actually are. Thus track RIF of IPIP next hops the same way as that of ETHERNET next hops. Fixes: 8f28a3097645 ("mlxsw: spectrum_router: Support IPv6 overlay encap") Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 3917b4dd4202f..032089efc1a0f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2723,6 +2723,7 @@ static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop_rif_fini(nh); break; case MLXSW_SP_NEXTHOP_TYPE_IPIP: + mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh); break; } @@ -2742,7 +2743,11 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV4)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + if (err) + return err; + mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); + return 0; } nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; @@ -4009,7 +4014,11 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV6)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + if (err) + return err; + mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); + return 0; } nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; -- GitLab From 7ff176f81dd4675d08951d2395c7ddb1d9974da6 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 2 Oct 2017 12:21:57 +0200 Subject: [PATCH 0765/1507] mlxsw: spectrum_router: Fix a typo Signed-off-by: Petr Machata Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index ef4b86b3aa9b2..75078a3fbee80 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1680,7 +1680,7 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd), rauhtd_pl); if (err) { - dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n"); + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour table\n"); break; } num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl); -- GitLab From 85f44a15b1920babc2d28c11f514f5b217a29968 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 2 Oct 2017 12:21:58 +0200 Subject: [PATCH 0766/1507] mlxsw: spectrum_router: Drop a redundant condition Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 75078a3fbee80..58bc04cbbef45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3251,7 +3251,7 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry, return; if (mlxsw_sp_fib_entry_should_offload(fib_entry)) mlxsw_sp_fib_entry_offload_set(fib_entry); - else if (!mlxsw_sp_fib_entry_should_offload(fib_entry)) + else mlxsw_sp_fib_entry_offload_unset(fib_entry); return; default: -- GitLab From f2f2efb807d339513199b1bb771806c90cce83ae Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:28 +0300 Subject: [PATCH 0767/1507] byteorder: Move {cpu_to_be32, be32_to_cpu}_array() from Thunderbolt to core We will be using these when communicating XDomain discovery protocol over Thunderbolt link but they might be useful for other drivers as well. Make them available through byteorder/generic.h. Suggested-by: Andy Shevchenko Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/ctl.c | 14 -------------- include/linux/byteorder/generic.h | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 14 deletions(-) diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index fb40dd0588b9a..e6a4c9458c763 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -289,20 +289,6 @@ static void tb_cfg_print_error(struct tb_ctl *ctl, } } -static void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) -{ - int i; - for (i = 0; i < len; i++) - dst[i] = cpu_to_be32(src[i]); -} - -static void be32_to_cpu_array(u32 *dst, __be32 *src, size_t len) -{ - int i; - for (i = 0; i < len; i++) - dst[i] = be32_to_cpu(src[i]); -} - static __be32 tb_crc(const void *data, size_t len) { return cpu_to_be32(~__crc32c_le(~0, data, len)); diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 89f67c1c31606..805d166544597 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -170,4 +170,20 @@ static inline void be64_add_cpu(__be64 *var, u64 val) *var = cpu_to_be64(be64_to_cpu(*var) + val); } +static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = cpu_to_be32(src[i]); +} + +static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) +{ + int i; + + for (i = 0; i < len; i++) + dst[i] = be32_to_cpu(src[i]); +} + #endif /* _LINUX_BYTEORDER_GENERIC_H */ -- GitLab From 806717081ab6088957c4857d42941159a07cc571 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:29 +0300 Subject: [PATCH 0768/1507] thunderbolt: Remove __packed from ICM message structures These messages are all 32-bit aligned and they should be packed without the __packed attribute just fine. It also allows compiler to generate better code on some architectures. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/tb_msgs.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h index de6441e4a0602..f3adf58a40ce8 100644 --- a/drivers/thunderbolt/tb_msgs.h +++ b/drivers/thunderbolt/tb_msgs.h @@ -130,7 +130,7 @@ struct icm_pkg_header { u8 flags; u8 packet_id; u8 total_packets; -} __packed; +}; #define ICM_FLAGS_ERROR BIT(0) #define ICM_FLAGS_NO_KEY BIT(1) @@ -139,20 +139,20 @@ struct icm_pkg_header { struct icm_pkg_driver_ready { struct icm_pkg_header hdr; -} __packed; +}; struct icm_pkg_driver_ready_response { struct icm_pkg_header hdr; u8 romver; u8 ramver; u16 security_level; -} __packed; +}; /* Falcon Ridge & Alpine Ridge common messages */ struct icm_fr_pkg_get_topology { struct icm_pkg_header hdr; -} __packed; +}; #define ICM_GET_TOPOLOGY_PACKETS 14 @@ -167,7 +167,7 @@ struct icm_fr_pkg_get_topology_response { u32 reserved[2]; u32 ports[16]; u32 port_hop_info[16]; -} __packed; +}; #define ICM_SWITCH_USED BIT(0) #define ICM_SWITCH_UPSTREAM_PORT_MASK GENMASK(7, 1) @@ -184,7 +184,7 @@ struct icm_fr_event_device_connected { u8 connection_id; u16 link_info; u32 ep_name[55]; -} __packed; +}; #define ICM_LINK_INFO_LINK_MASK 0x7 #define ICM_LINK_INFO_DEPTH_SHIFT 4 @@ -197,13 +197,13 @@ struct icm_fr_pkg_approve_device { u8 connection_key; u8 connection_id; u16 reserved; -} __packed; +}; struct icm_fr_event_device_disconnected { struct icm_pkg_header hdr; u16 reserved; u16 link_info; -} __packed; +}; struct icm_fr_pkg_add_device_key { struct icm_pkg_header hdr; @@ -212,7 +212,7 @@ struct icm_fr_pkg_add_device_key { u8 connection_id; u16 reserved; u32 key[8]; -} __packed; +}; struct icm_fr_pkg_add_device_key_response { struct icm_pkg_header hdr; @@ -220,7 +220,7 @@ struct icm_fr_pkg_add_device_key_response { u8 connection_key; u8 connection_id; u16 reserved; -} __packed; +}; struct icm_fr_pkg_challenge_device { struct icm_pkg_header hdr; @@ -229,7 +229,7 @@ struct icm_fr_pkg_challenge_device { u8 connection_id; u16 reserved; u32 challenge[8]; -} __packed; +}; struct icm_fr_pkg_challenge_device_response { struct icm_pkg_header hdr; @@ -239,7 +239,7 @@ struct icm_fr_pkg_challenge_device_response { u16 reserved; u32 challenge[8]; u32 response[8]; -} __packed; +}; /* Alpine Ridge only messages */ @@ -247,7 +247,7 @@ struct icm_ar_pkg_get_route { struct icm_pkg_header hdr; u16 reserved; u16 link_info; -} __packed; +}; struct icm_ar_pkg_get_route_response { struct icm_pkg_header hdr; @@ -255,6 +255,6 @@ struct icm_ar_pkg_get_route_response { u16 link_info; u32 route_hi; u32 route_lo; -} __packed; +}; #endif -- GitLab From cdae7c07e3e3509eaabc18c1640a55dc5b99c179 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:30 +0300 Subject: [PATCH 0769/1507] thunderbolt: Add support for XDomain properties Thunderbolt XDomain discovery protocol uses directories which contain properties and other directories to exchange information about what capabilities the remote host supports. This also includes identification information like device ID and name. This adds support for parsing and formatting these properties and establishes an API drivers can use in addition to the core Thunderbolt driver. This API is exposed in a new header: include/linux/thunderbolt.h. This code is based on the work done by Amir Levy and Michael Jamet. Signed-off-by: Michael Jamet Signed-off-by: Mika Westerberg Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/Makefile | 2 +- drivers/thunderbolt/property.c | 670 +++++++++++++++++++++++++++++++++ include/linux/thunderbolt.h | 89 +++++ 3 files changed, 760 insertions(+), 1 deletion(-) create mode 100644 drivers/thunderbolt/property.c create mode 100644 include/linux/thunderbolt.h diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile index 4900febc6c8ab..7afd21f5383a0 100644 --- a/drivers/thunderbolt/Makefile +++ b/drivers/thunderbolt/Makefile @@ -1,3 +1,3 @@ obj-${CONFIG_THUNDERBOLT} := thunderbolt.o thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel_pci.o eeprom.o -thunderbolt-objs += domain.o dma_port.o icm.o +thunderbolt-objs += domain.o dma_port.o icm.o property.o diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c new file mode 100644 index 0000000000000..8fe913a95b4ad --- /dev/null +++ b/drivers/thunderbolt/property.c @@ -0,0 +1,670 @@ +/* + * Thunderbolt XDomain property support + * + * Copyright (C) 2017, Intel Corporation + * Authors: Michael Jamet + * Mika Westerberg + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +struct tb_property_entry { + u32 key_hi; + u32 key_lo; + u16 length; + u8 reserved; + u8 type; + u32 value; +}; + +struct tb_property_rootdir_entry { + u32 magic; + u32 length; + struct tb_property_entry entries[]; +}; + +struct tb_property_dir_entry { + u32 uuid[4]; + struct tb_property_entry entries[]; +}; + +#define TB_PROPERTY_ROOTDIR_MAGIC 0x55584401 + +static struct tb_property_dir *__tb_property_parse_dir(const u32 *block, + size_t block_len, unsigned int dir_offset, size_t dir_len, + bool is_root); + +static inline void parse_dwdata(void *dst, const void *src, size_t dwords) +{ + be32_to_cpu_array(dst, src, dwords); +} + +static inline void format_dwdata(void *dst, const void *src, size_t dwords) +{ + cpu_to_be32_array(dst, src, dwords); +} + +static bool tb_property_entry_valid(const struct tb_property_entry *entry, + size_t block_len) +{ + switch (entry->type) { + case TB_PROPERTY_TYPE_DIRECTORY: + case TB_PROPERTY_TYPE_DATA: + case TB_PROPERTY_TYPE_TEXT: + if (entry->length > block_len) + return false; + if (entry->value + entry->length > block_len) + return false; + break; + + case TB_PROPERTY_TYPE_VALUE: + if (entry->length != 1) + return false; + break; + } + + return true; +} + +static bool tb_property_key_valid(const char *key) +{ + return key && strlen(key) <= TB_PROPERTY_KEY_SIZE; +} + +static struct tb_property * +tb_property_alloc(const char *key, enum tb_property_type type) +{ + struct tb_property *property; + + property = kzalloc(sizeof(*property), GFP_KERNEL); + if (!property) + return NULL; + + strcpy(property->key, key); + property->type = type; + INIT_LIST_HEAD(&property->list); + + return property; +} + +static struct tb_property *tb_property_parse(const u32 *block, size_t block_len, + const struct tb_property_entry *entry) +{ + char key[TB_PROPERTY_KEY_SIZE + 1]; + struct tb_property *property; + struct tb_property_dir *dir; + + if (!tb_property_entry_valid(entry, block_len)) + return NULL; + + parse_dwdata(key, entry, 2); + key[TB_PROPERTY_KEY_SIZE] = '\0'; + + property = tb_property_alloc(key, entry->type); + if (!property) + return NULL; + + property->length = entry->length; + + switch (property->type) { + case TB_PROPERTY_TYPE_DIRECTORY: + dir = __tb_property_parse_dir(block, block_len, entry->value, + entry->length, false); + if (!dir) { + kfree(property); + return NULL; + } + property->value.dir = dir; + break; + + case TB_PROPERTY_TYPE_DATA: + property->value.data = kcalloc(property->length, sizeof(u32), + GFP_KERNEL); + if (!property->value.data) { + kfree(property); + return NULL; + } + parse_dwdata(property->value.data, block + entry->value, + entry->length); + break; + + case TB_PROPERTY_TYPE_TEXT: + property->value.text = kcalloc(property->length, sizeof(u32), + GFP_KERNEL); + if (!property->value.text) { + kfree(property); + return NULL; + } + parse_dwdata(property->value.text, block + entry->value, + entry->length); + /* Force null termination */ + property->value.text[property->length * 4 - 1] = '\0'; + break; + + case TB_PROPERTY_TYPE_VALUE: + property->value.immediate = entry->value; + break; + + default: + property->type = TB_PROPERTY_TYPE_UNKNOWN; + break; + } + + return property; +} + +static struct tb_property_dir *__tb_property_parse_dir(const u32 *block, + size_t block_len, unsigned int dir_offset, size_t dir_len, bool is_root) +{ + const struct tb_property_entry *entries; + size_t i, content_len, nentries; + unsigned int content_offset; + struct tb_property_dir *dir; + + dir = kzalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + return NULL; + + if (is_root) { + content_offset = dir_offset + 2; + content_len = dir_len; + } else { + dir->uuid = kmemdup(&block[dir_offset], sizeof(*dir->uuid), + GFP_KERNEL); + content_offset = dir_offset + 4; + content_len = dir_len - 4; /* Length includes UUID */ + } + + entries = (const struct tb_property_entry *)&block[content_offset]; + nentries = content_len / (sizeof(*entries) / 4); + + INIT_LIST_HEAD(&dir->properties); + + for (i = 0; i < nentries; i++) { + struct tb_property *property; + + property = tb_property_parse(block, block_len, &entries[i]); + if (!property) { + tb_property_free_dir(dir); + return NULL; + } + + list_add_tail(&property->list, &dir->properties); + } + + return dir; +} + +/** + * tb_property_parse_dir() - Parses properties from given property block + * @block: Property block to parse + * @block_len: Number of dword elements in the property block + * + * This function parses the XDomain properties data block into format that + * can be traversed using the helper functions provided by this module. + * Upon success returns the parsed directory. In case of error returns + * %NULL. The resulting &struct tb_property_dir needs to be released by + * calling tb_property_free_dir() when not needed anymore. + * + * The @block is expected to be root directory. + */ +struct tb_property_dir *tb_property_parse_dir(const u32 *block, + size_t block_len) +{ + const struct tb_property_rootdir_entry *rootdir = + (const struct tb_property_rootdir_entry *)block; + + if (rootdir->magic != TB_PROPERTY_ROOTDIR_MAGIC) + return NULL; + if (rootdir->length > block_len) + return NULL; + + return __tb_property_parse_dir(block, block_len, 0, rootdir->length, + true); +} + +/** + * tb_property_create_dir() - Creates new property directory + * @uuid: UUID used to identify the particular directory + * + * Creates new, empty property directory. If @uuid is %NULL then the + * directory is assumed to be root directory. + */ +struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid) +{ + struct tb_property_dir *dir; + + dir = kzalloc(sizeof(*dir), GFP_KERNEL); + if (!dir) + return NULL; + + INIT_LIST_HEAD(&dir->properties); + if (uuid) { + dir->uuid = kmemdup(uuid, sizeof(*dir->uuid), GFP_KERNEL); + if (!dir->uuid) { + kfree(dir); + return NULL; + } + } + + return dir; +} +EXPORT_SYMBOL_GPL(tb_property_create_dir); + +static void tb_property_free(struct tb_property *property) +{ + switch (property->type) { + case TB_PROPERTY_TYPE_DIRECTORY: + tb_property_free_dir(property->value.dir); + break; + + case TB_PROPERTY_TYPE_DATA: + kfree(property->value.data); + break; + + case TB_PROPERTY_TYPE_TEXT: + kfree(property->value.text); + break; + + default: + break; + } + + kfree(property); +} + +/** + * tb_property_free_dir() - Release memory allocated for property directory + * @dir: Directory to release + * + * This will release all the memory the directory occupies including all + * descendants. It is OK to pass %NULL @dir, then the function does + * nothing. + */ +void tb_property_free_dir(struct tb_property_dir *dir) +{ + struct tb_property *property, *tmp; + + if (!dir) + return; + + list_for_each_entry_safe(property, tmp, &dir->properties, list) { + list_del(&property->list); + tb_property_free(property); + } + kfree(dir->uuid); + kfree(dir); +} +EXPORT_SYMBOL_GPL(tb_property_free_dir); + +static size_t tb_property_dir_length(const struct tb_property_dir *dir, + bool recurse, size_t *data_len) +{ + const struct tb_property *property; + size_t len = 0; + + if (dir->uuid) + len += sizeof(*dir->uuid) / 4; + else + len += sizeof(struct tb_property_rootdir_entry) / 4; + + list_for_each_entry(property, &dir->properties, list) { + len += sizeof(struct tb_property_entry) / 4; + + switch (property->type) { + case TB_PROPERTY_TYPE_DIRECTORY: + if (recurse) { + len += tb_property_dir_length( + property->value.dir, recurse, data_len); + } + /* Reserve dword padding after each directory */ + if (data_len) + *data_len += 1; + break; + + case TB_PROPERTY_TYPE_DATA: + case TB_PROPERTY_TYPE_TEXT: + if (data_len) + *data_len += property->length; + break; + + default: + break; + } + } + + return len; +} + +static ssize_t __tb_property_format_dir(const struct tb_property_dir *dir, + u32 *block, unsigned int start_offset, size_t block_len) +{ + unsigned int data_offset, dir_end; + const struct tb_property *property; + struct tb_property_entry *entry; + size_t dir_len, data_len = 0; + int ret; + + /* + * The structure of property block looks like following. Leaf + * data/text is included right after the directory and each + * directory follows each other (even nested ones). + * + * +----------+ <-- start_offset + * | header | <-- root directory header + * +----------+ --- + * | entry 0 | -^--------------------. + * +----------+ | | + * | entry 1 | -|--------------------|--. + * +----------+ | | | + * | entry 2 | -|-----------------. | | + * +----------+ | | | | + * : : | dir_len | | | + * . . | | | | + * : : | | | | + * +----------+ | | | | + * | entry n | v | | | + * +----------+ <-- data_offset | | | + * | data 0 | <------------------|--' | + * +----------+ | | + * | data 1 | <------------------|-----' + * +----------+ | + * | 00000000 | padding | + * +----------+ <-- dir_end <------' + * | UUID | <-- directory UUID (child directory) + * +----------+ + * | entry 0 | + * +----------+ + * | entry 1 | + * +----------+ + * : : + * . . + * : : + * +----------+ + * | entry n | + * +----------+ + * | data 0 | + * +----------+ + * + * We use dir_end to hold pointer to the end of the directory. It + * will increase as we add directories and each directory should be + * added starting from previous dir_end. + */ + dir_len = tb_property_dir_length(dir, false, &data_len); + data_offset = start_offset + dir_len; + dir_end = start_offset + data_len + dir_len; + + if (data_offset > dir_end) + return -EINVAL; + if (dir_end > block_len) + return -EINVAL; + + /* Write headers first */ + if (dir->uuid) { + struct tb_property_dir_entry *pe; + + pe = (struct tb_property_dir_entry *)&block[start_offset]; + memcpy(pe->uuid, dir->uuid, sizeof(pe->uuid)); + entry = pe->entries; + } else { + struct tb_property_rootdir_entry *re; + + re = (struct tb_property_rootdir_entry *)&block[start_offset]; + re->magic = TB_PROPERTY_ROOTDIR_MAGIC; + re->length = dir_len - sizeof(*re) / 4; + entry = re->entries; + } + + list_for_each_entry(property, &dir->properties, list) { + const struct tb_property_dir *child; + + format_dwdata(entry, property->key, 2); + entry->type = property->type; + + switch (property->type) { + case TB_PROPERTY_TYPE_DIRECTORY: + child = property->value.dir; + ret = __tb_property_format_dir(child, block, dir_end, + block_len); + if (ret < 0) + return ret; + entry->length = tb_property_dir_length(child, false, + NULL); + entry->value = dir_end; + dir_end = ret; + break; + + case TB_PROPERTY_TYPE_DATA: + format_dwdata(&block[data_offset], property->value.data, + property->length); + entry->length = property->length; + entry->value = data_offset; + data_offset += entry->length; + break; + + case TB_PROPERTY_TYPE_TEXT: + format_dwdata(&block[data_offset], property->value.text, + property->length); + entry->length = property->length; + entry->value = data_offset; + data_offset += entry->length; + break; + + case TB_PROPERTY_TYPE_VALUE: + entry->length = property->length; + entry->value = property->value.immediate; + break; + + default: + break; + } + + entry++; + } + + return dir_end; +} + +/** + * tb_property_format_dir() - Formats directory to the packed XDomain format + * @dir: Directory to format + * @block: Property block where the packed data is placed + * @block_len: Length of the property block + * + * This function formats the directory to the packed format that can be + * then send over the thunderbolt fabric to receiving host. Returns %0 in + * case of success and negative errno on faulure. Passing %NULL in @block + * returns number of entries the block takes. + */ +ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block, + size_t block_len) +{ + ssize_t ret; + + if (!block) { + size_t dir_len, data_len = 0; + + dir_len = tb_property_dir_length(dir, true, &data_len); + return dir_len + data_len; + } + + ret = __tb_property_format_dir(dir, block, 0, block_len); + return ret < 0 ? ret : 0; +} + +/** + * tb_property_add_immediate() - Add immediate property to directory + * @parent: Directory to add the property + * @key: Key for the property + * @value: Immediate value to store with the property + */ +int tb_property_add_immediate(struct tb_property_dir *parent, const char *key, + u32 value) +{ + struct tb_property *property; + + if (!tb_property_key_valid(key)) + return -EINVAL; + + property = tb_property_alloc(key, TB_PROPERTY_TYPE_VALUE); + if (!property) + return -ENOMEM; + + property->length = 1; + property->value.immediate = value; + + list_add_tail(&property->list, &parent->properties); + return 0; +} +EXPORT_SYMBOL_GPL(tb_property_add_immediate); + +/** + * tb_property_add_data() - Adds arbitrary data property to directory + * @parent: Directory to add the property + * @key: Key for the property + * @buf: Data buffer to add + * @buflen: Number of bytes in the data buffer + * + * Function takes a copy of @buf and adds it to the directory. + */ +int tb_property_add_data(struct tb_property_dir *parent, const char *key, + const void *buf, size_t buflen) +{ + /* Need to pad to dword boundary */ + size_t size = round_up(buflen, 4); + struct tb_property *property; + + if (!tb_property_key_valid(key)) + return -EINVAL; + + property = tb_property_alloc(key, TB_PROPERTY_TYPE_DATA); + if (!property) + return -ENOMEM; + + property->length = size / 4; + property->value.data = kzalloc(size, GFP_KERNEL); + memcpy(property->value.data, buf, buflen); + + list_add_tail(&property->list, &parent->properties); + return 0; +} +EXPORT_SYMBOL_GPL(tb_property_add_data); + +/** + * tb_property_add_text() - Adds string property to directory + * @parent: Directory to add the property + * @key: Key for the property + * @text: String to add + * + * Function takes a copy of @text and adds it to the directory. + */ +int tb_property_add_text(struct tb_property_dir *parent, const char *key, + const char *text) +{ + /* Need to pad to dword boundary */ + size_t size = round_up(strlen(text) + 1, 4); + struct tb_property *property; + + if (!tb_property_key_valid(key)) + return -EINVAL; + + property = tb_property_alloc(key, TB_PROPERTY_TYPE_TEXT); + if (!property) + return -ENOMEM; + + property->length = size / 4; + property->value.data = kzalloc(size, GFP_KERNEL); + strcpy(property->value.text, text); + + list_add_tail(&property->list, &parent->properties); + return 0; +} +EXPORT_SYMBOL_GPL(tb_property_add_text); + +/** + * tb_property_add_dir() - Adds a directory to the parent directory + * @parent: Directory to add the property + * @key: Key for the property + * @dir: Directory to add + */ +int tb_property_add_dir(struct tb_property_dir *parent, const char *key, + struct tb_property_dir *dir) +{ + struct tb_property *property; + + if (!tb_property_key_valid(key)) + return -EINVAL; + + property = tb_property_alloc(key, TB_PROPERTY_TYPE_DIRECTORY); + if (!property) + return -ENOMEM; + + property->value.dir = dir; + + list_add_tail(&property->list, &parent->properties); + return 0; +} +EXPORT_SYMBOL_GPL(tb_property_add_dir); + +/** + * tb_property_remove() - Removes property from a parent directory + * @property: Property to remove + * + * Note memory for @property is released as well so it is not allowed to + * touch the object after call to this function. + */ +void tb_property_remove(struct tb_property *property) +{ + list_del(&property->list); + kfree(property); +} +EXPORT_SYMBOL_GPL(tb_property_remove); + +/** + * tb_property_find() - Find a property from a directory + * @dir: Directory where the property is searched + * @key: Key to look for + * @type: Type of the property + * + * Finds and returns property from the given directory. Does not recurse + * into sub-directories. Returns %NULL if the property was not found. + */ +struct tb_property *tb_property_find(struct tb_property_dir *dir, + const char *key, enum tb_property_type type) +{ + struct tb_property *property; + + list_for_each_entry(property, &dir->properties, list) { + if (property->type == type && !strcmp(property->key, key)) + return property; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(tb_property_find); + +/** + * tb_property_get_next() - Get next property from directory + * @dir: Directory holding properties + * @prev: Previous property in the directory (%NULL returns the first) + */ +struct tb_property *tb_property_get_next(struct tb_property_dir *dir, + struct tb_property *prev) +{ + if (prev) { + if (list_is_last(&prev->list, &dir->properties)) + return NULL; + return list_next_entry(prev, list); + } + return list_first_entry_or_null(&dir->properties, struct tb_property, + list); +} +EXPORT_SYMBOL_GPL(tb_property_get_next); diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h new file mode 100644 index 0000000000000..96561c1265ae8 --- /dev/null +++ b/include/linux/thunderbolt.h @@ -0,0 +1,89 @@ +/* + * Thunderbolt service API + * + * Copyright (C) 2017, Intel Corporation + * Authors: Michael Jamet + * Mika Westerberg + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef THUNDERBOLT_H_ +#define THUNDERBOLT_H_ + +#include +#include + +/** + * struct tb_property_dir - XDomain property directory + * @uuid: Directory UUID or %NULL if root directory + * @properties: List of properties in this directory + * + * User needs to provide serialization if needed. + */ +struct tb_property_dir { + const uuid_t *uuid; + struct list_head properties; +}; + +enum tb_property_type { + TB_PROPERTY_TYPE_UNKNOWN = 0x00, + TB_PROPERTY_TYPE_DIRECTORY = 0x44, + TB_PROPERTY_TYPE_DATA = 0x64, + TB_PROPERTY_TYPE_TEXT = 0x74, + TB_PROPERTY_TYPE_VALUE = 0x76, +}; + +#define TB_PROPERTY_KEY_SIZE 8 + +/** + * struct tb_property - XDomain property + * @list: Used to link properties together in a directory + * @key: Key for the property (always terminated). + * @type: Type of the property + * @length: Length of the property data in dwords + * @value: Property value + * + * Users use @type to determine which field in @value is filled. + */ +struct tb_property { + struct list_head list; + char key[TB_PROPERTY_KEY_SIZE + 1]; + enum tb_property_type type; + size_t length; + union { + struct tb_property_dir *dir; + u8 *data; + char *text; + u32 immediate; + } value; +}; + +struct tb_property_dir *tb_property_parse_dir(const u32 *block, + size_t block_len); +ssize_t tb_property_format_dir(const struct tb_property_dir *dir, u32 *block, + size_t block_len); +struct tb_property_dir *tb_property_create_dir(const uuid_t *uuid); +void tb_property_free_dir(struct tb_property_dir *dir); +int tb_property_add_immediate(struct tb_property_dir *parent, const char *key, + u32 value); +int tb_property_add_data(struct tb_property_dir *parent, const char *key, + const void *buf, size_t buflen); +int tb_property_add_text(struct tb_property_dir *parent, const char *key, + const char *text); +int tb_property_add_dir(struct tb_property_dir *parent, const char *key, + struct tb_property_dir *dir); +void tb_property_remove(struct tb_property *tb_property); +struct tb_property *tb_property_find(struct tb_property_dir *dir, + const char *key, enum tb_property_type type); +struct tb_property *tb_property_get_next(struct tb_property_dir *dir, + struct tb_property *prev); + +#define tb_property_for_each(dir, property) \ + for (property = tb_property_get_next(dir, NULL); \ + property; \ + property = tb_property_get_next(dir, property)) + +#endif /* THUNDERBOLT_H_ */ -- GitLab From eaf8ff35a345449207ad116e2574c19780ec9a98 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:31 +0300 Subject: [PATCH 0770/1507] thunderbolt: Move enum tb_cfg_pkg_type to thunderbolt.h These will be needed by Thunderbolt services when sending and receiving XDomain control messages. While there change TB_CFG_PKG_PREPARE_TO_SLEEP value to be decimal in order to be consistent with other members. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/ctl.h | 1 + drivers/thunderbolt/tb_msgs.h | 17 ----------------- include/linux/thunderbolt.h | 17 +++++++++++++++++ 3 files changed, 18 insertions(+), 17 deletions(-) diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h index 36fd28b1c1c57..d0f21e1e0b8b8 100644 --- a/drivers/thunderbolt/ctl.h +++ b/drivers/thunderbolt/ctl.h @@ -8,6 +8,7 @@ #define _TB_CFG #include +#include #include "nhi.h" #include "tb_msgs.h" diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h index f3adf58a40ce8..f2b2550cd97c5 100644 --- a/drivers/thunderbolt/tb_msgs.h +++ b/drivers/thunderbolt/tb_msgs.h @@ -15,23 +15,6 @@ #include #include -enum tb_cfg_pkg_type { - TB_CFG_PKG_READ = 1, - TB_CFG_PKG_WRITE = 2, - TB_CFG_PKG_ERROR = 3, - TB_CFG_PKG_NOTIFY_ACK = 4, - TB_CFG_PKG_EVENT = 5, - TB_CFG_PKG_XDOMAIN_REQ = 6, - TB_CFG_PKG_XDOMAIN_RESP = 7, - TB_CFG_PKG_OVERRIDE = 8, - TB_CFG_PKG_RESET = 9, - TB_CFG_PKG_ICM_EVENT = 10, - TB_CFG_PKG_ICM_CMD = 11, - TB_CFG_PKG_ICM_RESP = 12, - TB_CFG_PKG_PREPARE_TO_SLEEP = 0xd, - -}; - enum tb_cfg_space { TB_CFG_HOPS = 0, TB_CFG_PORT = 1, diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 96561c1265ae8..b512b1e2b4f29 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -1,6 +1,7 @@ /* * Thunderbolt service API * + * Copyright (C) 2014 Andreas Noever * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg @@ -16,6 +17,22 @@ #include #include +enum tb_cfg_pkg_type { + TB_CFG_PKG_READ = 1, + TB_CFG_PKG_WRITE = 2, + TB_CFG_PKG_ERROR = 3, + TB_CFG_PKG_NOTIFY_ACK = 4, + TB_CFG_PKG_EVENT = 5, + TB_CFG_PKG_XDOMAIN_REQ = 6, + TB_CFG_PKG_XDOMAIN_RESP = 7, + TB_CFG_PKG_OVERRIDE = 8, + TB_CFG_PKG_RESET = 9, + TB_CFG_PKG_ICM_EVENT = 10, + TB_CFG_PKG_ICM_CMD = 11, + TB_CFG_PKG_ICM_RESP = 12, + TB_CFG_PKG_PREPARE_TO_SLEEP = 13, +}; + /** * struct tb_property_dir - XDomain property directory * @uuid: Directory UUID or %NULL if root directory -- GitLab From 9e99b9f4d5c36340dabda6d14053195b2a43796b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:32 +0300 Subject: [PATCH 0771/1507] thunderbolt: Move thunderbolt domain structure to thunderbolt.h These are needed by Thunderbolt services so move them to thunderbolt.h to make sure they are available outside of drivers/thunderbolt. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/tb.h | 42 ---------------------------------- include/linux/thunderbolt.h | 45 +++++++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+), 42 deletions(-) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index e0deee4f1eb09..2fefe76621ca3 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -39,20 +39,6 @@ struct tb_switch_nvm { bool authenticating; }; -/** - * enum tb_security_level - Thunderbolt security level - * @TB_SECURITY_NONE: No security, legacy mode - * @TB_SECURITY_USER: User approval required at minimum - * @TB_SECURITY_SECURE: One time saved key required at minimum - * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB) - */ -enum tb_security_level { - TB_SECURITY_NONE, - TB_SECURITY_USER, - TB_SECURITY_SECURE, - TB_SECURITY_DPONLY, -}; - #define TB_SWITCH_KEY_SIZE 32 /* Each physical port contains 2 links on modern controllers */ #define TB_SWITCH_LINKS_PER_PHY_PORT 2 @@ -223,33 +209,6 @@ struct tb_cm_ops { int (*disconnect_pcie_paths)(struct tb *tb); }; -/** - * struct tb - main thunderbolt bus structure - * @dev: Domain device - * @lock: Big lock. Must be held when accessing any struct - * tb_switch / struct tb_port. - * @nhi: Pointer to the NHI structure - * @ctl: Control channel for this domain - * @wq: Ordered workqueue for all domain specific work - * @root_switch: Root switch of this domain - * @cm_ops: Connection manager specific operations vector - * @index: Linux assigned domain number - * @security_level: Current security level - * @privdata: Private connection manager specific data - */ -struct tb { - struct device dev; - struct mutex lock; - struct tb_nhi *nhi; - struct tb_ctl *ctl; - struct workqueue_struct *wq; - struct tb_switch *root_switch; - const struct tb_cm_ops *cm_ops; - int index; - enum tb_security_level security_level; - unsigned long privdata[0]; -}; - static inline void *tb_priv(struct tb *tb) { return (void *)tb->privdata; @@ -368,7 +327,6 @@ static inline int tb_port_write(struct tb_port *port, const void *buffer, struct tb *icm_probe(struct tb_nhi *nhi); struct tb *tb_probe(struct tb_nhi *nhi); -extern struct bus_type tb_bus_type; extern struct device_type tb_domain_type; extern struct device_type tb_switch_type; diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index b512b1e2b4f29..910b1bf92112e 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -14,7 +14,9 @@ #ifndef THUNDERBOLT_H_ #define THUNDERBOLT_H_ +#include #include +#include #include enum tb_cfg_pkg_type { @@ -33,6 +35,49 @@ enum tb_cfg_pkg_type { TB_CFG_PKG_PREPARE_TO_SLEEP = 13, }; +/** + * enum tb_security_level - Thunderbolt security level + * @TB_SECURITY_NONE: No security, legacy mode + * @TB_SECURITY_USER: User approval required at minimum + * @TB_SECURITY_SECURE: One time saved key required at minimum + * @TB_SECURITY_DPONLY: Only tunnel Display port (and USB) + */ +enum tb_security_level { + TB_SECURITY_NONE, + TB_SECURITY_USER, + TB_SECURITY_SECURE, + TB_SECURITY_DPONLY, +}; + +/** + * struct tb - main thunderbolt bus structure + * @dev: Domain device + * @lock: Big lock. Must be held when accessing any struct + * tb_switch / struct tb_port. + * @nhi: Pointer to the NHI structure + * @ctl: Control channel for this domain + * @wq: Ordered workqueue for all domain specific work + * @root_switch: Root switch of this domain + * @cm_ops: Connection manager specific operations vector + * @index: Linux assigned domain number + * @security_level: Current security level + * @privdata: Private connection manager specific data + */ +struct tb { + struct device dev; + struct mutex lock; + struct tb_nhi *nhi; + struct tb_ctl *ctl; + struct workqueue_struct *wq; + struct tb_switch *root_switch; + const struct tb_cm_ops *cm_ops; + int index; + enum tb_security_level security_level; + unsigned long privdata[0]; +}; + +extern struct bus_type tb_bus_type; + /** * struct tb_property_dir - XDomain property directory * @uuid: Directory UUID or %NULL if root directory -- GitLab From e69b71f8458b78a2ef44e3d07374a8f46e45123d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:33 +0300 Subject: [PATCH 0772/1507] thunderbolt: Move tb_switch_phy_port_from_link() to thunderbolt.h A Thunderbolt service might need to find the physical port from a link the cable is connected to. For instance networking driver uses this information to generate MAC address according the Apple ThunderboltIP protocol. Move this function to thunderbolt.h and rename it to tb_phy_port_from_link() to reflect the fact that it does not take switch as parameter. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/icm.c | 2 +- drivers/thunderbolt/tb.h | 7 ------- include/linux/thunderbolt.h | 7 +++++++ 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 53250fc057e1f..8c22b91ed0405 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -89,7 +89,7 @@ static inline struct tb *icm_to_tb(struct icm *icm) static inline u8 phy_port_from_route(u64 route, u8 depth) { - return tb_switch_phy_port_from_link(route >> ((depth - 1) * 8)); + return tb_phy_port_from_link(route >> ((depth - 1) * 8)); } static inline u8 dual_link_from_link(u8 link) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 2fefe76621ca3..ea21d927bd094 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -40,8 +40,6 @@ struct tb_switch_nvm { }; #define TB_SWITCH_KEY_SIZE 32 -/* Each physical port contains 2 links on modern controllers */ -#define TB_SWITCH_LINKS_PER_PHY_PORT 2 /** * struct tb_switch - a thunderbolt switch @@ -367,11 +365,6 @@ struct tb_switch *tb_switch_find_by_link_depth(struct tb *tb, u8 link, u8 depth); struct tb_switch *tb_switch_find_by_uuid(struct tb *tb, const uuid_t *uuid); -static inline unsigned int tb_switch_phy_port_from_link(unsigned int link) -{ - return (link - 1) / TB_SWITCH_LINKS_PER_PHY_PORT; -} - static inline void tb_switch_put(struct tb_switch *sw) { put_device(&sw->dev); diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 910b1bf92112e..43b8d1e093411 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -78,6 +78,13 @@ struct tb { extern struct bus_type tb_bus_type; +#define TB_LINKS_PER_PHY_PORT 2 + +static inline unsigned int tb_phy_port_from_link(unsigned int link) +{ + return (link - 1) / TB_LINKS_PER_PHY_PORT; +} + /** * struct tb_property_dir - XDomain property directory * @uuid: Directory UUID or %NULL if root directory -- GitLab From d1ff70241a275133e1a0258b7c23588b122276c8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:34 +0300 Subject: [PATCH 0773/1507] thunderbolt: Add support for XDomain discovery protocol When two hosts are connected over a Thunderbolt cable, there is a protocol they can use to communicate capabilities supported by the host. The discovery protocol uses automatically configured control channel (ring 0) and is build on top of request/response transactions using special XDomain primitives provided by the Thunderbolt base protocol. The capabilities consists of a root directory block of basic properties used for identification of the host, and then there can be zero or more directories each describing a Thunderbolt service and its capabilities. Once both sides have discovered what is supported the two hosts can setup high-speed DMA paths and transfer data to the other side using whatever protocol was agreed based on the properties. The software protocol used to communicate which DMA paths to enable is service specific. This patch adds support for the XDomain discovery protocol to the Thunderbolt bus. We model each remote host connection as a Linux XDomain device. For each Thunderbolt service found supported on the XDomain device, we create Linux Thunderbolt service device which Thunderbolt service drivers can then bind to based on the protocol identification information retrieved from the property directory describing the service. This code is based on the work done by Amir Levy and Michael Jamet. Signed-off-by: Michael Jamet Signed-off-by: Mika Westerberg Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- .../ABI/testing/sysfs-bus-thunderbolt | 48 + drivers/thunderbolt/Makefile | 2 +- drivers/thunderbolt/ctl.c | 11 +- drivers/thunderbolt/ctl.h | 2 +- drivers/thunderbolt/domain.c | 197 ++- drivers/thunderbolt/icm.c | 218 ++- drivers/thunderbolt/nhi.h | 2 + drivers/thunderbolt/switch.c | 7 +- drivers/thunderbolt/tb.h | 39 +- drivers/thunderbolt/tb_msgs.h | 123 ++ drivers/thunderbolt/xdomain.c | 1576 +++++++++++++++++ include/linux/mod_devicetable.h | 26 + include/linux/thunderbolt.h | 242 +++ scripts/mod/devicetable-offsets.c | 7 + scripts/mod/file2alias.c | 25 + 15 files changed, 2507 insertions(+), 18 deletions(-) create mode 100644 drivers/thunderbolt/xdomain.c diff --git a/Documentation/ABI/testing/sysfs-bus-thunderbolt b/Documentation/ABI/testing/sysfs-bus-thunderbolt index 392bef5bd3996..93798c02e28b2 100644 --- a/Documentation/ABI/testing/sysfs-bus-thunderbolt +++ b/Documentation/ABI/testing/sysfs-bus-thunderbolt @@ -110,3 +110,51 @@ Description: When new NVM image is written to the non-active NVM is directly the status value from the DMA configuration based mailbox before the device is power cycled. Writing 0 here clears the status. + +What: /sys/bus/thunderbolt/devices/./key +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: This contains name of the property directory the XDomain + service exposes. This entry describes the protocol in + question. Following directories are already reserved by + the Apple XDomain specification: + + network: IP/ethernet over Thunderbolt + targetdm: Target disk mode protocol over Thunderbolt + extdisp: External display mode protocol over Thunderbolt + +What: /sys/bus/thunderbolt/devices/./modalias +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: Stores the same MODALIAS value emitted by uevent for + the XDomain service. Format: tbtsvc:kSpNvNrN + +What: /sys/bus/thunderbolt/devices/./prtcid +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: This contains XDomain protocol identifier the XDomain + service supports. + +What: /sys/bus/thunderbolt/devices/./prtcvers +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: This contains XDomain protocol version the XDomain + service supports. + +What: /sys/bus/thunderbolt/devices/./prtcrevs +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: This contains XDomain software version the XDomain + service supports. + +What: /sys/bus/thunderbolt/devices/./prtcstns +Date: Jan 2018 +KernelVersion: 4.15 +Contact: thunderbolt-software@lists.01.org +Description: This contains XDomain service specific settings as + bitmask. Format: %x diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile index 7afd21f5383a0..f2f0de27252b1 100644 --- a/drivers/thunderbolt/Makefile +++ b/drivers/thunderbolt/Makefile @@ -1,3 +1,3 @@ obj-${CONFIG_THUNDERBOLT} := thunderbolt.o thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel_pci.o eeprom.o -thunderbolt-objs += domain.o dma_port.o icm.o property.o +thunderbolt-objs += domain.o dma_port.o icm.o property.o xdomain.o diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index e6a4c9458c763..46e393c5fd1d1 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -368,10 +368,10 @@ static int tb_ctl_tx(struct tb_ctl *ctl, const void *data, size_t len, /** * tb_ctl_handle_event() - acknowledge a plug event, invoke ctl->callback */ -static void tb_ctl_handle_event(struct tb_ctl *ctl, enum tb_cfg_pkg_type type, +static bool tb_ctl_handle_event(struct tb_ctl *ctl, enum tb_cfg_pkg_type type, struct ctl_pkg *pkg, size_t size) { - ctl->callback(ctl->callback_data, type, pkg->buffer, size); + return ctl->callback(ctl->callback_data, type, pkg->buffer, size); } static void tb_ctl_rx_submit(struct ctl_pkg *pkg) @@ -444,6 +444,8 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame, break; case TB_CFG_PKG_EVENT: + case TB_CFG_PKG_XDOMAIN_RESP: + case TB_CFG_PKG_XDOMAIN_REQ: if (*(__be32 *)(pkg->buffer + frame->size) != crc32) { tb_ctl_err(pkg->ctl, "RX: checksum mismatch, dropping packet\n"); @@ -451,8 +453,9 @@ static void tb_ctl_rx_callback(struct tb_ring *ring, struct ring_frame *frame, } /* Fall through */ case TB_CFG_PKG_ICM_EVENT: - tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size); - goto rx; + if (tb_ctl_handle_event(pkg->ctl, frame->eof, pkg, frame->size)) + goto rx; + break; default: break; diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h index d0f21e1e0b8b8..85c49dd301eab 100644 --- a/drivers/thunderbolt/ctl.h +++ b/drivers/thunderbolt/ctl.h @@ -16,7 +16,7 @@ /* control channel */ struct tb_ctl; -typedef void (*event_cb)(void *data, enum tb_cfg_pkg_type type, +typedef bool (*event_cb)(void *data, enum tb_cfg_pkg_type type, const void *buf, size_t size); struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data); diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index 9f2dcd48974d6..9b90115319ce8 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -20,6 +20,98 @@ static DEFINE_IDA(tb_domain_ida); +static bool match_service_id(const struct tb_service_id *id, + const struct tb_service *svc) +{ + if (id->match_flags & TBSVC_MATCH_PROTOCOL_KEY) { + if (strcmp(id->protocol_key, svc->key)) + return false; + } + + if (id->match_flags & TBSVC_MATCH_PROTOCOL_ID) { + if (id->protocol_id != svc->prtcid) + return false; + } + + if (id->match_flags & TBSVC_MATCH_PROTOCOL_VERSION) { + if (id->protocol_version != svc->prtcvers) + return false; + } + + if (id->match_flags & TBSVC_MATCH_PROTOCOL_VERSION) { + if (id->protocol_revision != svc->prtcrevs) + return false; + } + + return true; +} + +static const struct tb_service_id *__tb_service_match(struct device *dev, + struct device_driver *drv) +{ + struct tb_service_driver *driver; + const struct tb_service_id *ids; + struct tb_service *svc; + + svc = tb_to_service(dev); + if (!svc) + return NULL; + + driver = container_of(drv, struct tb_service_driver, driver); + if (!driver->id_table) + return NULL; + + for (ids = driver->id_table; ids->match_flags != 0; ids++) { + if (match_service_id(ids, svc)) + return ids; + } + + return NULL; +} + +static int tb_service_match(struct device *dev, struct device_driver *drv) +{ + return !!__tb_service_match(dev, drv); +} + +static int tb_service_probe(struct device *dev) +{ + struct tb_service *svc = tb_to_service(dev); + struct tb_service_driver *driver; + const struct tb_service_id *id; + + driver = container_of(dev->driver, struct tb_service_driver, driver); + id = __tb_service_match(dev, &driver->driver); + + return driver->probe(svc, id); +} + +static int tb_service_remove(struct device *dev) +{ + struct tb_service *svc = tb_to_service(dev); + struct tb_service_driver *driver; + + driver = container_of(dev->driver, struct tb_service_driver, driver); + if (driver->remove) + driver->remove(svc); + + return 0; +} + +static void tb_service_shutdown(struct device *dev) +{ + struct tb_service_driver *driver; + struct tb_service *svc; + + svc = tb_to_service(dev); + if (!svc || !dev->driver) + return; + + driver = container_of(dev->driver, struct tb_service_driver, driver); + if (driver->shutdown) + driver->shutdown(svc); +} + static const char * const tb_security_names[] = { [TB_SECURITY_NONE] = "none", [TB_SECURITY_USER] = "user", @@ -52,6 +144,10 @@ static const struct attribute_group *domain_attr_groups[] = { struct bus_type tb_bus_type = { .name = "thunderbolt", + .match = tb_service_match, + .probe = tb_service_probe, + .remove = tb_service_remove, + .shutdown = tb_service_shutdown, }; static void tb_domain_release(struct device *dev) @@ -128,17 +224,26 @@ struct tb *tb_domain_alloc(struct tb_nhi *nhi, size_t privsize) return NULL; } -static void tb_domain_event_cb(void *data, enum tb_cfg_pkg_type type, +static bool tb_domain_event_cb(void *data, enum tb_cfg_pkg_type type, const void *buf, size_t size) { struct tb *tb = data; if (!tb->cm_ops->handle_event) { tb_warn(tb, "domain does not have event handler\n"); - return; + return true; } - tb->cm_ops->handle_event(tb, type, buf, size); + switch (type) { + case TB_CFG_PKG_XDOMAIN_REQ: + case TB_CFG_PKG_XDOMAIN_RESP: + return tb_xdomain_handle_request(tb, type, buf, size); + + default: + tb->cm_ops->handle_event(tb, type, buf, size); + } + + return true; } /** @@ -443,9 +548,92 @@ int tb_domain_disconnect_pcie_paths(struct tb *tb) return tb->cm_ops->disconnect_pcie_paths(tb); } +/** + * tb_domain_approve_xdomain_paths() - Enable DMA paths for XDomain + * @tb: Domain enabling the DMA paths + * @xd: XDomain DMA paths are created to + * + * Calls connection manager specific method to enable DMA paths to the + * XDomain in question. + * + * Return: 0% in case of success and negative errno otherwise. In + * particular returns %-ENOTSUPP if the connection manager + * implementation does not support XDomains. + */ +int tb_domain_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + if (!tb->cm_ops->approve_xdomain_paths) + return -ENOTSUPP; + + return tb->cm_ops->approve_xdomain_paths(tb, xd); +} + +/** + * tb_domain_disconnect_xdomain_paths() - Disable DMA paths for XDomain + * @tb: Domain disabling the DMA paths + * @xd: XDomain whose DMA paths are disconnected + * + * Calls connection manager specific method to disconnect DMA paths to + * the XDomain in question. + * + * Return: 0% in case of success and negative errno otherwise. In + * particular returns %-ENOTSUPP if the connection manager + * implementation does not support XDomains. + */ +int tb_domain_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + if (!tb->cm_ops->disconnect_xdomain_paths) + return -ENOTSUPP; + + return tb->cm_ops->disconnect_xdomain_paths(tb, xd); +} + +static int disconnect_xdomain(struct device *dev, void *data) +{ + struct tb_xdomain *xd; + struct tb *tb = data; + int ret = 0; + + xd = tb_to_xdomain(dev); + if (xd && xd->tb == tb) + ret = tb_xdomain_disable_paths(xd); + + return ret; +} + +/** + * tb_domain_disconnect_all_paths() - Disconnect all paths for the domain + * @tb: Domain whose paths are disconnected + * + * This function can be used to disconnect all paths (PCIe, XDomain) for + * example in preparation for host NVM firmware upgrade. After this is + * called the paths cannot be established without resetting the switch. + * + * Return: %0 in case of success and negative errno otherwise. + */ +int tb_domain_disconnect_all_paths(struct tb *tb) +{ + int ret; + + ret = tb_domain_disconnect_pcie_paths(tb); + if (ret) + return ret; + + return bus_for_each_dev(&tb_bus_type, NULL, tb, disconnect_xdomain); +} + int tb_domain_init(void) { - return bus_register(&tb_bus_type); + int ret; + + ret = tb_xdomain_init(); + if (ret) + return ret; + ret = bus_register(&tb_bus_type); + if (ret) + tb_xdomain_exit(); + + return ret; } void tb_domain_exit(void) @@ -453,4 +641,5 @@ void tb_domain_exit(void) bus_unregister(&tb_bus_type); ida_destroy(&tb_domain_ida); tb_switch_exit(); + tb_xdomain_exit(); } diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 8c22b91ed0405..ab02d13f40b70 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -60,6 +60,8 @@ * @get_route: Find a route string for given switch * @device_connected: Handle device connected ICM message * @device_disconnected: Handle device disconnected ICM message + * @xdomain_connected - Handle XDomain connected ICM message + * @xdomain_disconnected - Handle XDomain disconnected ICM message */ struct icm { struct mutex request_lock; @@ -74,6 +76,10 @@ struct icm { const struct icm_pkg_header *hdr); void (*device_disconnected)(struct tb *tb, const struct icm_pkg_header *hdr); + void (*xdomain_connected)(struct tb *tb, + const struct icm_pkg_header *hdr); + void (*xdomain_disconnected)(struct tb *tb, + const struct icm_pkg_header *hdr); }; struct icm_notification { @@ -89,7 +95,10 @@ static inline struct tb *icm_to_tb(struct icm *icm) static inline u8 phy_port_from_route(u64 route, u8 depth) { - return tb_phy_port_from_link(route >> ((depth - 1) * 8)); + u8 link; + + link = depth ? route >> ((depth - 1) * 8) : route; + return tb_phy_port_from_link(link); } static inline u8 dual_link_from_link(u8 link) @@ -320,6 +329,51 @@ static int icm_fr_challenge_switch_key(struct tb *tb, struct tb_switch *sw, return 0; } +static int icm_fr_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + struct icm_fr_pkg_approve_xdomain_response reply; + struct icm_fr_pkg_approve_xdomain request; + int ret; + + memset(&request, 0, sizeof(request)); + request.hdr.code = ICM_APPROVE_XDOMAIN; + request.link_info = xd->depth << ICM_LINK_INFO_DEPTH_SHIFT | xd->link; + memcpy(&request.remote_uuid, xd->remote_uuid, sizeof(*xd->remote_uuid)); + + request.transmit_path = xd->transmit_path; + request.transmit_ring = xd->transmit_ring; + request.receive_path = xd->receive_path; + request.receive_ring = xd->receive_ring; + + memset(&reply, 0, sizeof(reply)); + ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), + 1, ICM_TIMEOUT); + if (ret) + return ret; + + if (reply.hdr.flags & ICM_FLAGS_ERROR) + return -EIO; + + return 0; +} + +static int icm_fr_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + u8 phy_port; + u8 cmd; + + phy_port = tb_phy_port_from_link(xd->link); + if (phy_port == 0) + cmd = NHI_MAILBOX_DISCONNECT_PA; + else + cmd = NHI_MAILBOX_DISCONNECT_PB; + + nhi_mailbox_cmd(tb->nhi, cmd, 1); + usleep_range(10, 50); + nhi_mailbox_cmd(tb->nhi, cmd, 2); + return 0; +} + static void remove_switch(struct tb_switch *sw) { struct tb_switch *parent_sw; @@ -475,6 +529,141 @@ icm_fr_device_disconnected(struct tb *tb, const struct icm_pkg_header *hdr) tb_switch_put(sw); } +static void remove_xdomain(struct tb_xdomain *xd) +{ + struct tb_switch *sw; + + sw = tb_to_switch(xd->dev.parent); + tb_port_at(xd->route, sw)->xdomain = NULL; + tb_xdomain_remove(xd); +} + +static void +icm_fr_xdomain_connected(struct tb *tb, const struct icm_pkg_header *hdr) +{ + const struct icm_fr_event_xdomain_connected *pkg = + (const struct icm_fr_event_xdomain_connected *)hdr; + struct tb_xdomain *xd; + struct tb_switch *sw; + u8 link, depth; + bool approved; + u64 route; + + /* + * After NVM upgrade adding root switch device fails because we + * initiated reset. During that time ICM might still send + * XDomain connected message which we ignore here. + */ + if (!tb->root_switch) + return; + + link = pkg->link_info & ICM_LINK_INFO_LINK_MASK; + depth = (pkg->link_info & ICM_LINK_INFO_DEPTH_MASK) >> + ICM_LINK_INFO_DEPTH_SHIFT; + approved = pkg->link_info & ICM_LINK_INFO_APPROVED; + + if (link > ICM_MAX_LINK || depth > ICM_MAX_DEPTH) { + tb_warn(tb, "invalid topology %u.%u, ignoring\n", link, depth); + return; + } + + route = get_route(pkg->local_route_hi, pkg->local_route_lo); + + xd = tb_xdomain_find_by_uuid(tb, &pkg->remote_uuid); + if (xd) { + u8 xd_phy_port, phy_port; + + xd_phy_port = phy_port_from_route(xd->route, xd->depth); + phy_port = phy_port_from_route(route, depth); + + if (xd->depth == depth && xd_phy_port == phy_port) { + xd->link = link; + xd->route = route; + xd->is_unplugged = false; + tb_xdomain_put(xd); + return; + } + + /* + * If we find an existing XDomain connection remove it + * now. We need to go through login handshake and + * everything anyway to be able to re-establish the + * connection. + */ + remove_xdomain(xd); + tb_xdomain_put(xd); + } + + /* + * Look if there already exists an XDomain in the same place + * than the new one and in that case remove it because it is + * most likely another host that got disconnected. + */ + xd = tb_xdomain_find_by_link_depth(tb, link, depth); + if (!xd) { + u8 dual_link; + + dual_link = dual_link_from_link(link); + if (dual_link) + xd = tb_xdomain_find_by_link_depth(tb, dual_link, + depth); + } + if (xd) { + remove_xdomain(xd); + tb_xdomain_put(xd); + } + + /* + * If the user disconnected a switch during suspend and + * connected another host to the same port, remove the switch + * first. + */ + sw = get_switch_at_route(tb->root_switch, route); + if (sw) + remove_switch(sw); + + sw = tb_switch_find_by_link_depth(tb, link, depth); + if (!sw) { + tb_warn(tb, "no switch exists at %u.%u, ignoring\n", link, + depth); + return; + } + + xd = tb_xdomain_alloc(sw->tb, &sw->dev, route, + &pkg->local_uuid, &pkg->remote_uuid); + if (!xd) { + tb_switch_put(sw); + return; + } + + xd->link = link; + xd->depth = depth; + + tb_port_at(route, sw)->xdomain = xd; + + tb_xdomain_add(xd); + tb_switch_put(sw); +} + +static void +icm_fr_xdomain_disconnected(struct tb *tb, const struct icm_pkg_header *hdr) +{ + const struct icm_fr_event_xdomain_disconnected *pkg = + (const struct icm_fr_event_xdomain_disconnected *)hdr; + struct tb_xdomain *xd; + + /* + * If the connection is through one or multiple devices, the + * XDomain device is removed along with them so it is fine if we + * cannot find it here. + */ + xd = tb_xdomain_find_by_uuid(tb, &pkg->remote_uuid); + if (xd) { + remove_xdomain(xd); + tb_xdomain_put(xd); + } +} + static struct pci_dev *get_upstream_port(struct pci_dev *pdev) { struct pci_dev *parent; @@ -594,6 +783,12 @@ static void icm_handle_notification(struct work_struct *work) case ICM_EVENT_DEVICE_DISCONNECTED: icm->device_disconnected(tb, n->pkg); break; + case ICM_EVENT_XDOMAIN_CONNECTED: + icm->xdomain_connected(tb, n->pkg); + break; + case ICM_EVENT_XDOMAIN_DISCONNECTED: + icm->xdomain_disconnected(tb, n->pkg); + break; } mutex_unlock(&tb->lock); @@ -927,6 +1122,10 @@ static void icm_unplug_children(struct tb_switch *sw) if (tb_is_upstream_port(port)) continue; + if (port->xdomain) { + port->xdomain->is_unplugged = true; + continue; + } if (!port->remote) continue; @@ -943,6 +1142,13 @@ static void icm_free_unplugged_children(struct tb_switch *sw) if (tb_is_upstream_port(port)) continue; + + if (port->xdomain && port->xdomain->is_unplugged) { + tb_xdomain_remove(port->xdomain); + port->xdomain = NULL; + continue; + } + if (!port->remote) continue; @@ -1009,8 +1215,10 @@ static int icm_start(struct tb *tb) tb->root_switch->no_nvm_upgrade = x86_apple_machine; ret = tb_switch_add(tb->root_switch); - if (ret) + if (ret) { tb_switch_put(tb->root_switch); + tb->root_switch = NULL; + } return ret; } @@ -1042,6 +1250,8 @@ static const struct tb_cm_ops icm_fr_ops = { .add_switch_key = icm_fr_add_switch_key, .challenge_switch_key = icm_fr_challenge_switch_key, .disconnect_pcie_paths = icm_disconnect_pcie_paths, + .approve_xdomain_paths = icm_fr_approve_xdomain_paths, + .disconnect_xdomain_paths = icm_fr_disconnect_xdomain_paths, }; struct tb *icm_probe(struct tb_nhi *nhi) @@ -1064,6 +1274,8 @@ struct tb *icm_probe(struct tb_nhi *nhi) icm->get_route = icm_fr_get_route; icm->device_connected = icm_fr_device_connected; icm->device_disconnected = icm_fr_device_disconnected; + icm->xdomain_connected = icm_fr_xdomain_connected; + icm->xdomain_disconnected = icm_fr_xdomain_disconnected; tb->cm_ops = &icm_fr_ops; break; @@ -1077,6 +1289,8 @@ struct tb *icm_probe(struct tb_nhi *nhi) icm->get_route = icm_ar_get_route; icm->device_connected = icm_fr_device_connected; icm->device_disconnected = icm_fr_device_disconnected; + icm->xdomain_connected = icm_fr_xdomain_connected; + icm->xdomain_disconnected = icm_fr_xdomain_disconnected; tb->cm_ops = &icm_fr_ops; break; } diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 5b5bb2c436be2..0e05828983db5 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -157,6 +157,8 @@ enum nhi_mailbox_cmd { NHI_MAILBOX_SAVE_DEVS = 0x05, NHI_MAILBOX_DISCONNECT_PCIE_PATHS = 0x06, NHI_MAILBOX_DRV_UNLOADS = 0x07, + NHI_MAILBOX_DISCONNECT_PA = 0x10, + NHI_MAILBOX_DISCONNECT_PB = 0x11, NHI_MAILBOX_ALLOW_ALL_DEVS = 0x23, }; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 53f40c57df59c..dfc357d33e1e4 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -171,11 +171,11 @@ static int nvm_authenticate_host(struct tb_switch *sw) /* * Root switch NVM upgrade requires that we disconnect the - * existing PCIe paths first (in case it is not in safe mode + * existing paths first (in case it is not in safe mode * already). */ if (!sw->safe_mode) { - ret = tb_domain_disconnect_pcie_paths(sw->tb); + ret = tb_domain_disconnect_all_paths(sw->tb); if (ret) return ret; /* @@ -1363,6 +1363,9 @@ void tb_switch_remove(struct tb_switch *sw) if (sw->ports[i].remote) tb_switch_remove(sw->ports[i].remote->sw); sw->ports[i].remote = NULL; + if (sw->ports[i].xdomain) + tb_xdomain_remove(sw->ports[i].xdomain); + sw->ports[i].xdomain = NULL; } if (!sw->is_unplugged) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index ea21d927bd094..74af9d4929ab4 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -9,6 +9,7 @@ #include #include +#include #include #include "tb_regs.h" @@ -109,14 +110,25 @@ struct tb_switch { /** * struct tb_port - a thunderbolt port, part of a tb_switch + * @config: Cached port configuration read from registers + * @sw: Switch the port belongs to + * @remote: Remote port (%NULL if not connected) + * @xdomain: Remote host (%NULL if not connected) + * @cap_phy: Offset, zero if not found + * @port: Port number on switch + * @disabled: Disabled by eeprom + * @dual_link_port: If the switch is connected using two ports, points + * to the other port. + * @link_nr: Is this primary or secondary port on the dual_link. */ struct tb_port { struct tb_regs_port_header config; struct tb_switch *sw; - struct tb_port *remote; /* remote port, NULL if not connected */ - int cap_phy; /* offset, zero if not found */ - u8 port; /* port number on switch */ - bool disabled; /* disabled by eeprom */ + struct tb_port *remote; + struct tb_xdomain *xdomain; + int cap_phy; + u8 port; + bool disabled; struct tb_port *dual_link_port; u8 link_nr:1; }; @@ -189,6 +201,8 @@ struct tb_path { * @add_switch_key: Add key to switch * @challenge_switch_key: Challenge switch using key * @disconnect_pcie_paths: Disconnects PCIe paths before NVM update + * @approve_xdomain_paths: Approve (establish) XDomain DMA paths + * @disconnect_xdomain_paths: Disconnect XDomain DMA paths */ struct tb_cm_ops { int (*driver_ready)(struct tb *tb); @@ -205,6 +219,8 @@ struct tb_cm_ops { int (*challenge_switch_key)(struct tb *tb, struct tb_switch *sw, const u8 *challenge, u8 *response); int (*disconnect_pcie_paths)(struct tb *tb); + int (*approve_xdomain_paths)(struct tb *tb, struct tb_xdomain *xd); + int (*disconnect_xdomain_paths)(struct tb *tb, struct tb_xdomain *xd); }; static inline void *tb_priv(struct tb *tb) @@ -331,6 +347,8 @@ extern struct device_type tb_switch_type; int tb_domain_init(void); void tb_domain_exit(void); void tb_switch_exit(void); +int tb_xdomain_init(void); +void tb_xdomain_exit(void); struct tb *tb_domain_alloc(struct tb_nhi *nhi, size_t privsize); int tb_domain_add(struct tb *tb); @@ -343,6 +361,9 @@ int tb_domain_approve_switch(struct tb *tb, struct tb_switch *sw); int tb_domain_approve_switch_key(struct tb *tb, struct tb_switch *sw); int tb_domain_challenge_switch_key(struct tb *tb, struct tb_switch *sw); int tb_domain_disconnect_pcie_paths(struct tb *tb); +int tb_domain_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd); +int tb_domain_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd); +int tb_domain_disconnect_all_paths(struct tb *tb); static inline void tb_domain_put(struct tb *tb) { @@ -422,4 +443,14 @@ static inline u64 tb_downstream_route(struct tb_port *port) | ((u64) port->port << (port->sw->config.depth * 8)); } +bool tb_xdomain_handle_request(struct tb *tb, enum tb_cfg_pkg_type type, + const void *buf, size_t size); +struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent, + u64 route, const uuid_t *local_uuid, + const uuid_t *remote_uuid); +void tb_xdomain_add(struct tb_xdomain *xd); +void tb_xdomain_remove(struct tb_xdomain *xd); +struct tb_xdomain *tb_xdomain_find_by_link_depth(struct tb *tb, u8 link, + u8 depth); + #endif diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h index f2b2550cd97c5..b0a092baa6054 100644 --- a/drivers/thunderbolt/tb_msgs.h +++ b/drivers/thunderbolt/tb_msgs.h @@ -101,11 +101,14 @@ enum icm_pkg_code { ICM_CHALLENGE_DEVICE = 0x5, ICM_ADD_DEVICE_KEY = 0x6, ICM_GET_ROUTE = 0xa, + ICM_APPROVE_XDOMAIN = 0x10, }; enum icm_event_code { ICM_EVENT_DEVICE_CONNECTED = 3, ICM_EVENT_DEVICE_DISCONNECTED = 4, + ICM_EVENT_XDOMAIN_CONNECTED = 6, + ICM_EVENT_XDOMAIN_DISCONNECTED = 7, }; struct icm_pkg_header { @@ -188,6 +191,25 @@ struct icm_fr_event_device_disconnected { u16 link_info; }; +struct icm_fr_event_xdomain_connected { + struct icm_pkg_header hdr; + u16 reserved; + u16 link_info; + uuid_t remote_uuid; + uuid_t local_uuid; + u32 local_route_hi; + u32 local_route_lo; + u32 remote_route_hi; + u32 remote_route_lo; +}; + +struct icm_fr_event_xdomain_disconnected { + struct icm_pkg_header hdr; + u16 reserved; + u16 link_info; + uuid_t remote_uuid; +}; + struct icm_fr_pkg_add_device_key { struct icm_pkg_header hdr; uuid_t ep_uuid; @@ -224,6 +246,28 @@ struct icm_fr_pkg_challenge_device_response { u32 response[8]; }; +struct icm_fr_pkg_approve_xdomain { + struct icm_pkg_header hdr; + u16 reserved; + u16 link_info; + uuid_t remote_uuid; + u16 transmit_path; + u16 transmit_ring; + u16 receive_path; + u16 receive_ring; +}; + +struct icm_fr_pkg_approve_xdomain_response { + struct icm_pkg_header hdr; + u16 reserved; + u16 link_info; + uuid_t remote_uuid; + u16 transmit_path; + u16 transmit_ring; + u16 receive_path; + u16 receive_ring; +}; + /* Alpine Ridge only messages */ struct icm_ar_pkg_get_route { @@ -240,4 +284,83 @@ struct icm_ar_pkg_get_route_response { u32 route_lo; }; +/* XDomain messages */ + +struct tb_xdomain_header { + u32 route_hi; + u32 route_lo; + u32 length_sn; +}; + +#define TB_XDOMAIN_LENGTH_MASK GENMASK(5, 0) +#define TB_XDOMAIN_SN_MASK GENMASK(28, 27) +#define TB_XDOMAIN_SN_SHIFT 27 + +enum tb_xdp_type { + UUID_REQUEST_OLD = 1, + UUID_RESPONSE = 2, + PROPERTIES_REQUEST, + PROPERTIES_RESPONSE, + PROPERTIES_CHANGED_REQUEST, + PROPERTIES_CHANGED_RESPONSE, + ERROR_RESPONSE, + UUID_REQUEST = 12, +}; + +struct tb_xdp_header { + struct tb_xdomain_header xd_hdr; + uuid_t uuid; + u32 type; +}; + +struct tb_xdp_properties { + struct tb_xdp_header hdr; + uuid_t src_uuid; + uuid_t dst_uuid; + u16 offset; + u16 reserved; +}; + +struct tb_xdp_properties_response { + struct tb_xdp_header hdr; + uuid_t src_uuid; + uuid_t dst_uuid; + u16 offset; + u16 data_length; + u32 generation; + u32 data[0]; +}; + +/* + * Max length of data array single XDomain property response is allowed + * to carry. + */ +#define TB_XDP_PROPERTIES_MAX_DATA_LENGTH \ + (((256 - 4 - sizeof(struct tb_xdp_properties_response))) / 4) + +/* Maximum size of the total property block in dwords we allow */ +#define TB_XDP_PROPERTIES_MAX_LENGTH 500 + +struct tb_xdp_properties_changed { + struct tb_xdp_header hdr; + uuid_t src_uuid; +}; + +struct tb_xdp_properties_changed_response { + struct tb_xdp_header hdr; +}; + +enum tb_xdp_error { + ERROR_SUCCESS, + ERROR_UNKNOWN_PACKET, + ERROR_UNKNOWN_DOMAIN, + ERROR_NOT_SUPPORTED, + ERROR_NOT_READY, +}; + +struct tb_xdp_error_response { + struct tb_xdp_header hdr; + u32 error; +}; + #endif diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c new file mode 100644 index 0000000000000..f2d06f6f7be97 --- /dev/null +++ b/drivers/thunderbolt/xdomain.c @@ -0,0 +1,1576 @@ +/* + * Thunderbolt XDomain discovery protocol support + * + * Copyright (C) 2017, Intel Corporation + * Authors: Michael Jamet + * Mika Westerberg + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include + +#include "tb.h" + +#define XDOMAIN_DEFAULT_TIMEOUT 5000 /* ms */ +#define XDOMAIN_PROPERTIES_RETRIES 60 +#define XDOMAIN_PROPERTIES_CHANGED_RETRIES 10 + +struct xdomain_request_work { + struct work_struct work; + struct tb_xdp_header *pkg; + struct tb *tb; +}; + +/* Serializes access to the properties and protocol handlers below */ +static DEFINE_MUTEX(xdomain_lock); + +/* Properties exposed to the remote domains */ +static struct tb_property_dir *xdomain_property_dir; +static u32 *xdomain_property_block; +static u32 xdomain_property_block_len; +static u32 xdomain_property_block_gen; + +/* Additional protocol handlers */ +static LIST_HEAD(protocol_handlers); + +/* UUID for XDomain discovery protocol: b638d70e-42ff-40bb-97c2-90e2c0b2ff07 */ +static const uuid_t tb_xdp_uuid = + UUID_INIT(0xb638d70e, 0x42ff, 0x40bb, + 0x97, 0xc2, 0x90, 0xe2, 0xc0, 0xb2, 0xff, 0x07); + +static bool tb_xdomain_match(const struct tb_cfg_request *req, + const struct ctl_pkg *pkg) +{ + switch (pkg->frame.eof) { + case TB_CFG_PKG_ERROR: + return true; + + case TB_CFG_PKG_XDOMAIN_RESP: { + const struct tb_xdp_header *res_hdr = pkg->buffer; + const struct tb_xdp_header *req_hdr = req->request; + u8 req_seq, res_seq; + + if (pkg->frame.size < req->response_size / 4) + return false; + + /* Make sure route matches */ + if ((res_hdr->xd_hdr.route_hi & ~BIT(31)) != + req_hdr->xd_hdr.route_hi) + return false; + if ((res_hdr->xd_hdr.route_lo) != req_hdr->xd_hdr.route_lo) + return false; + + /* Then check that the sequence number matches */ + res_seq = res_hdr->xd_hdr.length_sn & TB_XDOMAIN_SN_MASK; + res_seq >>= TB_XDOMAIN_SN_SHIFT; + req_seq = req_hdr->xd_hdr.length_sn & TB_XDOMAIN_SN_MASK; + req_seq >>= TB_XDOMAIN_SN_SHIFT; + if (res_seq != req_seq) + return false; + + /* Check that the XDomain protocol matches */ + if (!uuid_equal(&res_hdr->uuid, &req_hdr->uuid)) + return false; + + return true; + } + + default: + return false; + } +} + +static bool tb_xdomain_copy(struct tb_cfg_request *req, + const struct ctl_pkg *pkg) +{ + memcpy(req->response, pkg->buffer, req->response_size); + req->result.err = 0; + return true; +} + +static void response_ready(void *data) +{ + tb_cfg_request_put(data); +} + +static int __tb_xdomain_response(struct tb_ctl *ctl, const void *response, + size_t size, enum tb_cfg_pkg_type type) +{ + struct tb_cfg_request *req; + + req = tb_cfg_request_alloc(); + if (!req) + return -ENOMEM; + + req->match = tb_xdomain_match; + req->copy = tb_xdomain_copy; + req->request = response; + req->request_size = size; + req->request_type = type; + + return tb_cfg_request(ctl, req, response_ready, req); +} + +/** + * tb_xdomain_response() - Send a XDomain response message + * @xd: XDomain to send the message + * @response: Response to send + * @size: Size of the response + * @type: PDF type of the response + * + * This can be used to send a XDomain response message to the other + * domain. No response for the message is expected. + * + * Return: %0 in case of success and negative errno in case of failure + */ +int tb_xdomain_response(struct tb_xdomain *xd, const void *response, + size_t size, enum tb_cfg_pkg_type type) +{ + return __tb_xdomain_response(xd->tb->ctl, response, size, type); +} +EXPORT_SYMBOL_GPL(tb_xdomain_response); + +static int __tb_xdomain_request(struct tb_ctl *ctl, const void *request, + size_t request_size, enum tb_cfg_pkg_type request_type, void *response, + size_t response_size, enum tb_cfg_pkg_type response_type, + unsigned int timeout_msec) +{ + struct tb_cfg_request *req; + struct tb_cfg_result res; + + req = tb_cfg_request_alloc(); + if (!req) + return -ENOMEM; + + req->match = tb_xdomain_match; + req->copy = tb_xdomain_copy; + req->request = request; + req->request_size = request_size; + req->request_type = request_type; + req->response = response; + req->response_size = response_size; + req->response_type = response_type; + + res = tb_cfg_request_sync(ctl, req, timeout_msec); + + tb_cfg_request_put(req); + + return res.err == 1 ? -EIO : res.err; +} + +/** + * tb_xdomain_request() - Send a XDomain request + * @xd: XDomain to send the request + * @request: Request to send + * @request_size: Size of the request in bytes + * @request_type: PDF type of the request + * @response: Response is copied here + * @response_size: Expected size of the response in bytes + * @response_type: Expected PDF type of the response + * @timeout_msec: Timeout in milliseconds to wait for the response + * + * This function can be used to send XDomain control channel messages to + * the other domain. The function waits until the response is received + * or when timeout triggers. Whichever comes first. + * + * Return: %0 in case of success and negative errno in case of failure + */ +int tb_xdomain_request(struct tb_xdomain *xd, const void *request, + size_t request_size, enum tb_cfg_pkg_type request_type, + void *response, size_t response_size, + enum tb_cfg_pkg_type response_type, unsigned int timeout_msec) +{ + return __tb_xdomain_request(xd->tb->ctl, request, request_size, + request_type, response, response_size, + response_type, timeout_msec); +} +EXPORT_SYMBOL_GPL(tb_xdomain_request); + +static inline void tb_xdp_fill_header(struct tb_xdp_header *hdr, u64 route, + u8 sequence, enum tb_xdp_type type, size_t size) +{ + u32 length_sn; + + length_sn = (size - sizeof(hdr->xd_hdr)) / 4; + length_sn |= (sequence << TB_XDOMAIN_SN_SHIFT) & TB_XDOMAIN_SN_MASK; + + hdr->xd_hdr.route_hi = upper_32_bits(route); + hdr->xd_hdr.route_lo = lower_32_bits(route); + hdr->xd_hdr.length_sn = length_sn; + hdr->type = type; + memcpy(&hdr->uuid, &tb_xdp_uuid, sizeof(tb_xdp_uuid)); +} + +static int tb_xdp_handle_error(const struct tb_xdp_header *hdr) +{ + const struct tb_xdp_error_response *error; + + if (hdr->type != ERROR_RESPONSE) + return 0; + + error = (const struct tb_xdp_error_response *)hdr; + + switch (error->error) { + case ERROR_UNKNOWN_PACKET: + case ERROR_UNKNOWN_DOMAIN: + return -EIO; + case ERROR_NOT_SUPPORTED: + return -ENOTSUPP; + case ERROR_NOT_READY: + return -EAGAIN; + default: + break; + } + + return 0; +} + +static int tb_xdp_error_response(struct tb_ctl *ctl, u64 route, u8 sequence, + enum tb_xdp_error error) +{ + struct tb_xdp_error_response res; + + memset(&res, 0, sizeof(res)); + tb_xdp_fill_header(&res.hdr, route, sequence, ERROR_RESPONSE, + sizeof(res)); + res.error = error; + + return __tb_xdomain_response(ctl, &res, sizeof(res), + TB_CFG_PKG_XDOMAIN_RESP); +} + +static int tb_xdp_properties_request(struct tb_ctl *ctl, u64 route, + const uuid_t *src_uuid, const uuid_t *dst_uuid, int retry, + u32 **block, u32 *generation) +{ + struct tb_xdp_properties_response *res; + struct tb_xdp_properties req; + u16 data_len, len; + size_t total_size; + u32 *data = NULL; + int ret; + + total_size = sizeof(*res) + TB_XDP_PROPERTIES_MAX_DATA_LENGTH * 4; + res = kzalloc(total_size, GFP_KERNEL); + if (!res) + return -ENOMEM; + + memset(&req, 0, sizeof(req)); + tb_xdp_fill_header(&req.hdr, route, retry % 4, PROPERTIES_REQUEST, + sizeof(req)); + memcpy(&req.src_uuid, src_uuid, sizeof(*src_uuid)); + memcpy(&req.dst_uuid, dst_uuid, sizeof(*dst_uuid)); + + len = 0; + data_len = 0; + + do { + ret = __tb_xdomain_request(ctl, &req, sizeof(req), + TB_CFG_PKG_XDOMAIN_REQ, res, + total_size, TB_CFG_PKG_XDOMAIN_RESP, + XDOMAIN_DEFAULT_TIMEOUT); + if (ret) + goto err; + + ret = tb_xdp_handle_error(&res->hdr); + if (ret) + goto err; + + /* + * Package length includes the whole payload without the + * XDomain header. Validate first that the package is at + * least size of the response structure. + */ + len = res->hdr.xd_hdr.length_sn & TB_XDOMAIN_LENGTH_MASK; + if (len < sizeof(*res) / 4) { + ret = -EINVAL; + goto err; + } + + len += sizeof(res->hdr.xd_hdr) / 4; + len -= sizeof(*res) / 4; + + if (res->offset != req.offset) { + ret = -EINVAL; + goto err; + } + + /* + * First time allocate block that has enough space for + * the whole properties block. + */ + if (!data) { + data_len = res->data_length; + if (data_len > TB_XDP_PROPERTIES_MAX_LENGTH) { + ret = -E2BIG; + goto err; + } + + data = kcalloc(data_len, sizeof(u32), GFP_KERNEL); + if (!data) { + ret = -ENOMEM; + goto err; + } + } + + memcpy(data + req.offset, res->data, len * 4); + req.offset += len; + } while (!data_len || req.offset < data_len); + + *block = data; + *generation = res->generation; + + kfree(res); + + return data_len; + +err: + kfree(data); + kfree(res); + + return ret; +} + +static int tb_xdp_properties_response(struct tb *tb, struct tb_ctl *ctl, + u64 route, u8 sequence, const uuid_t *src_uuid, + const struct tb_xdp_properties *req) +{ + struct tb_xdp_properties_response *res; + size_t total_size; + u16 len; + int ret; + + /* + * Currently we expect all requests to be directed to us. The + * protocol supports forwarding, though which we might add + * support later on. + */ + if (!uuid_equal(src_uuid, &req->dst_uuid)) { + tb_xdp_error_response(ctl, route, sequence, + ERROR_UNKNOWN_DOMAIN); + return 0; + } + + mutex_lock(&xdomain_lock); + + if (req->offset >= xdomain_property_block_len) { + mutex_unlock(&xdomain_lock); + return -EINVAL; + } + + len = xdomain_property_block_len - req->offset; + len = min_t(u16, len, TB_XDP_PROPERTIES_MAX_DATA_LENGTH); + total_size = sizeof(*res) + len * 4; + + res = kzalloc(total_size, GFP_KERNEL); + if (!res) { + mutex_unlock(&xdomain_lock); + return -ENOMEM; + } + + tb_xdp_fill_header(&res->hdr, route, sequence, PROPERTIES_RESPONSE, + total_size); + res->generation = xdomain_property_block_gen; + res->data_length = xdomain_property_block_len; + res->offset = req->offset; + uuid_copy(&res->src_uuid, src_uuid); + uuid_copy(&res->dst_uuid, &req->src_uuid); + memcpy(res->data, &xdomain_property_block[req->offset], len * 4); + + mutex_unlock(&xdomain_lock); + + ret = __tb_xdomain_response(ctl, res, total_size, + TB_CFG_PKG_XDOMAIN_RESP); + + kfree(res); + return ret; +} + +static int tb_xdp_properties_changed_request(struct tb_ctl *ctl, u64 route, + int retry, const uuid_t *uuid) +{ + struct tb_xdp_properties_changed_response res; + struct tb_xdp_properties_changed req; + int ret; + + memset(&req, 0, sizeof(req)); + tb_xdp_fill_header(&req.hdr, route, retry % 4, + PROPERTIES_CHANGED_REQUEST, sizeof(req)); + uuid_copy(&req.src_uuid, uuid); + + memset(&res, 0, sizeof(res)); + ret = __tb_xdomain_request(ctl, &req, sizeof(req), + TB_CFG_PKG_XDOMAIN_REQ, &res, sizeof(res), + TB_CFG_PKG_XDOMAIN_RESP, + XDOMAIN_DEFAULT_TIMEOUT); + if (ret) + return ret; + + return tb_xdp_handle_error(&res.hdr); +} + +static int +tb_xdp_properties_changed_response(struct tb_ctl *ctl, u64 route, u8 sequence) +{ + struct tb_xdp_properties_changed_response res; + + memset(&res, 0, sizeof(res)); + tb_xdp_fill_header(&res.hdr, route, sequence, + PROPERTIES_CHANGED_RESPONSE, sizeof(res)); + return __tb_xdomain_response(ctl, &res, sizeof(res), + TB_CFG_PKG_XDOMAIN_RESP); +} + +/** + * tb_register_protocol_handler() - Register protocol handler + * @handler: Handler to register + * + * This allows XDomain service drivers to hook into incoming XDomain + * messages. After this function is called the service driver needs to + * be able to handle calls to callback whenever a package with the + * registered protocol is received. + */ +int tb_register_protocol_handler(struct tb_protocol_handler *handler) +{ + if (!handler->uuid || !handler->callback) + return -EINVAL; + if (uuid_equal(handler->uuid, &tb_xdp_uuid)) + return -EINVAL; + + mutex_lock(&xdomain_lock); + list_add_tail(&handler->list, &protocol_handlers); + mutex_unlock(&xdomain_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(tb_register_protocol_handler); + +/** + * tb_unregister_protocol_handler() - Unregister protocol handler + * @handler: Handler to unregister + * + * Removes the previously registered protocol handler. + */ +void tb_unregister_protocol_handler(struct tb_protocol_handler *handler) +{ + mutex_lock(&xdomain_lock); + list_del_init(&handler->list); + mutex_unlock(&xdomain_lock); +} +EXPORT_SYMBOL_GPL(tb_unregister_protocol_handler); + +static void tb_xdp_handle_request(struct work_struct *work) +{ + struct xdomain_request_work *xw = container_of(work, typeof(*xw), work); + const struct tb_xdp_header *pkg = xw->pkg; + const struct tb_xdomain_header *xhdr = &pkg->xd_hdr; + struct tb *tb = xw->tb; + struct tb_ctl *ctl = tb->ctl; + const uuid_t *uuid; + int ret = 0; + u8 sequence; + u64 route; + + route = ((u64)xhdr->route_hi << 32 | xhdr->route_lo) & ~BIT_ULL(63); + sequence = xhdr->length_sn & TB_XDOMAIN_SN_MASK; + sequence >>= TB_XDOMAIN_SN_SHIFT; + + mutex_lock(&tb->lock); + if (tb->root_switch) + uuid = tb->root_switch->uuid; + else + uuid = NULL; + mutex_unlock(&tb->lock); + + if (!uuid) { + tb_xdp_error_response(ctl, route, sequence, ERROR_NOT_READY); + goto out; + } + + switch (pkg->type) { + case PROPERTIES_REQUEST: + ret = tb_xdp_properties_response(tb, ctl, route, sequence, uuid, + (const struct tb_xdp_properties *)pkg); + break; + + case PROPERTIES_CHANGED_REQUEST: { + const struct tb_xdp_properties_changed *xchg = + (const struct tb_xdp_properties_changed *)pkg; + struct tb_xdomain *xd; + + ret = tb_xdp_properties_changed_response(ctl, route, sequence); + + /* + * Since the properties have been changed, let's update + * the xdomain related to this connection as well in + * case there is a change in services it offers. + */ + xd = tb_xdomain_find_by_uuid_locked(tb, &xchg->src_uuid); + if (xd) { + queue_delayed_work(tb->wq, &xd->get_properties_work, + msecs_to_jiffies(50)); + tb_xdomain_put(xd); + } + + break; + } + + default: + break; + } + + if (ret) { + tb_warn(tb, "failed to send XDomain response for %#x\n", + pkg->type); + } + +out: + kfree(xw->pkg); + kfree(xw); +} + +static void +tb_xdp_schedule_request(struct tb *tb, const struct tb_xdp_header *hdr, + size_t size) +{ + struct xdomain_request_work *xw; + + xw = kmalloc(sizeof(*xw), GFP_KERNEL); + if (!xw) + return; + + INIT_WORK(&xw->work, tb_xdp_handle_request); + xw->pkg = kmemdup(hdr, size, GFP_KERNEL); + xw->tb = tb; + + queue_work(tb->wq, &xw->work); +} + +/** + * tb_register_service_driver() - Register XDomain service driver + * @drv: Driver to register + * + * Registers new service driver from @drv to the bus. + */ +int tb_register_service_driver(struct tb_service_driver *drv) +{ + drv->driver.bus = &tb_bus_type; + return driver_register(&drv->driver); +} +EXPORT_SYMBOL_GPL(tb_register_service_driver); + +/** + * tb_unregister_service_driver() - Unregister XDomain service driver + * @xdrv: Driver to unregister + * + * Unregisters XDomain service driver from the bus. + */ +void tb_unregister_service_driver(struct tb_service_driver *drv) +{ + driver_unregister(&drv->driver); +} +EXPORT_SYMBOL_GPL(tb_unregister_service_driver); + +static ssize_t key_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + /* + * It should be null terminated but anything else is pretty much + * allowed. + */ + return sprintf(buf, "%*pEp\n", (int)strlen(svc->key), svc->key); +} +static DEVICE_ATTR_RO(key); + +static int get_modalias(struct tb_service *svc, char *buf, size_t size) +{ + return snprintf(buf, size, "tbsvc:k%sp%08Xv%08Xr%08X", svc->key, + svc->prtcid, svc->prtcvers, svc->prtcrevs); +} + +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + /* Full buffer size except new line and null termination */ + get_modalias(svc, buf, PAGE_SIZE - 2); + return sprintf(buf, "%s\n", buf); +} +static DEVICE_ATTR_RO(modalias); + +static ssize_t prtcid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + return sprintf(buf, "%u\n", svc->prtcid); +} +static DEVICE_ATTR_RO(prtcid); + +static ssize_t prtcvers_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + return sprintf(buf, "%u\n", svc->prtcvers); +} +static DEVICE_ATTR_RO(prtcvers); + +static ssize_t prtcrevs_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + return sprintf(buf, "%u\n", svc->prtcrevs); +} +static DEVICE_ATTR_RO(prtcrevs); + +static ssize_t prtcstns_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + + return sprintf(buf, "0x%08x\n", svc->prtcstns); +} +static DEVICE_ATTR_RO(prtcstns); + +static struct attribute *tb_service_attrs[] = { + &dev_attr_key.attr, + &dev_attr_modalias.attr, + &dev_attr_prtcid.attr, + &dev_attr_prtcvers.attr, + &dev_attr_prtcrevs.attr, + &dev_attr_prtcstns.attr, + NULL, +}; + +static struct attribute_group tb_service_attr_group = { + .attrs = tb_service_attrs, +}; + +static const struct attribute_group *tb_service_attr_groups[] = { + &tb_service_attr_group, + NULL, +}; + +static int tb_service_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + char modalias[64]; + + get_modalias(svc, modalias, sizeof(modalias)); + return add_uevent_var(env, "MODALIAS=%s", modalias); +} + +static void tb_service_release(struct device *dev) +{ + struct tb_service *svc = container_of(dev, struct tb_service, dev); + struct tb_xdomain *xd = tb_service_parent(svc); + + ida_simple_remove(&xd->service_ids, svc->id); + kfree(svc->key); + kfree(svc); +} + +struct device_type tb_service_type = { + .name = "thunderbolt_service", + .groups = tb_service_attr_groups, + .uevent = tb_service_uevent, + .release = tb_service_release, +}; +EXPORT_SYMBOL_GPL(tb_service_type); + +static int remove_missing_service(struct device *dev, void *data) +{ + struct tb_xdomain *xd = data; + struct tb_service *svc; + + svc = tb_to_service(dev); + if (!svc) + return 0; + + if (!tb_property_find(xd->properties, svc->key, + TB_PROPERTY_TYPE_DIRECTORY)) + device_unregister(dev); + + return 0; +} + +static int find_service(struct device *dev, void *data) +{ + const struct tb_property *p = data; + struct tb_service *svc; + + svc = tb_to_service(dev); + if (!svc) + return 0; + + return !strcmp(svc->key, p->key); +} + +static int populate_service(struct tb_service *svc, + struct tb_property *property) +{ + struct tb_property_dir *dir = property->value.dir; + struct tb_property *p; + + /* Fill in standard properties */ + p = tb_property_find(dir, "prtcid", TB_PROPERTY_TYPE_VALUE); + if (p) + svc->prtcid = p->value.immediate; + p = tb_property_find(dir, "prtcvers", TB_PROPERTY_TYPE_VALUE); + if (p) + svc->prtcvers = p->value.immediate; + p = tb_property_find(dir, "prtcrevs", TB_PROPERTY_TYPE_VALUE); + if (p) + svc->prtcrevs = p->value.immediate; + p = tb_property_find(dir, "prtcstns", TB_PROPERTY_TYPE_VALUE); + if (p) + svc->prtcstns = p->value.immediate; + + svc->key = kstrdup(property->key, GFP_KERNEL); + if (!svc->key) + return -ENOMEM; + + return 0; +} + +static void enumerate_services(struct tb_xdomain *xd) +{ + struct tb_service *svc; + struct tb_property *p; + struct device *dev; + + /* + * First remove all services that are not available anymore in + * the updated property block. + */ + device_for_each_child_reverse(&xd->dev, xd, remove_missing_service); + + /* Then re-enumerate properties creating new services as we go */ + tb_property_for_each(xd->properties, p) { + if (p->type != TB_PROPERTY_TYPE_DIRECTORY) + continue; + + /* If the service exists already we are fine */ + dev = device_find_child(&xd->dev, p, find_service); + if (dev) { + put_device(dev); + continue; + } + + svc = kzalloc(sizeof(*svc), GFP_KERNEL); + if (!svc) + break; + + if (populate_service(svc, p)) { + kfree(svc); + break; + } + + svc->id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); + svc->dev.bus = &tb_bus_type; + svc->dev.type = &tb_service_type; + svc->dev.parent = &xd->dev; + dev_set_name(&svc->dev, "%s.%d", dev_name(&xd->dev), svc->id); + + if (device_register(&svc->dev)) { + put_device(&svc->dev); + break; + } + } +} + +static int populate_properties(struct tb_xdomain *xd, + struct tb_property_dir *dir) +{ + const struct tb_property *p; + + /* Required properties */ + p = tb_property_find(dir, "deviceid", TB_PROPERTY_TYPE_VALUE); + if (!p) + return -EINVAL; + xd->device = p->value.immediate; + + p = tb_property_find(dir, "vendorid", TB_PROPERTY_TYPE_VALUE); + if (!p) + return -EINVAL; + xd->vendor = p->value.immediate; + + kfree(xd->device_name); + xd->device_name = NULL; + kfree(xd->vendor_name); + xd->vendor_name = NULL; + + /* Optional properties */ + p = tb_property_find(dir, "deviceid", TB_PROPERTY_TYPE_TEXT); + if (p) + xd->device_name = kstrdup(p->value.text, GFP_KERNEL); + p = tb_property_find(dir, "vendorid", TB_PROPERTY_TYPE_TEXT); + if (p) + xd->vendor_name = kstrdup(p->value.text, GFP_KERNEL); + + return 0; +} + +/* Called with @xd->lock held */ +static void tb_xdomain_restore_paths(struct tb_xdomain *xd) +{ + if (!xd->resume) + return; + + xd->resume = false; + if (xd->transmit_path) { + dev_dbg(&xd->dev, "re-establishing DMA path\n"); + tb_domain_approve_xdomain_paths(xd->tb, xd); + } +} + +static void tb_xdomain_get_properties(struct work_struct *work) +{ + struct tb_xdomain *xd = container_of(work, typeof(*xd), + get_properties_work.work); + struct tb_property_dir *dir; + struct tb *tb = xd->tb; + bool update = false; + u32 *block = NULL; + u32 gen = 0; + int ret; + + ret = tb_xdp_properties_request(tb->ctl, xd->route, xd->local_uuid, + xd->remote_uuid, xd->properties_retries, + &block, &gen); + if (ret < 0) { + if (xd->properties_retries-- > 0) { + queue_delayed_work(xd->tb->wq, &xd->get_properties_work, + msecs_to_jiffies(1000)); + } else { + /* Give up now */ + dev_err(&xd->dev, + "failed read XDomain properties from %pUb\n", + xd->remote_uuid); + } + return; + } + + xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES; + + mutex_lock(&xd->lock); + + /* Only accept newer generation properties */ + if (xd->properties && gen <= xd->property_block_gen) { + /* + * On resume it is likely that the properties block is + * not changed (unless the other end added or removed + * services). However, we need to make sure the existing + * DMA paths are restored properly. + */ + tb_xdomain_restore_paths(xd); + goto err_free_block; + } + + dir = tb_property_parse_dir(block, ret); + if (!dir) { + dev_err(&xd->dev, "failed to parse XDomain properties\n"); + goto err_free_block; + } + + ret = populate_properties(xd, dir); + if (ret) { + dev_err(&xd->dev, "missing XDomain properties in response\n"); + goto err_free_dir; + } + + /* Release the existing one */ + if (xd->properties) { + tb_property_free_dir(xd->properties); + update = true; + } + + xd->properties = dir; + xd->property_block_gen = gen; + + tb_xdomain_restore_paths(xd); + + mutex_unlock(&xd->lock); + + kfree(block); + + /* + * Now the device should be ready enough so we can add it to the + * bus and let userspace know about it. If the device is already + * registered, we notify the userspace that it has changed. + */ + if (!update) { + if (device_add(&xd->dev)) { + dev_err(&xd->dev, "failed to add XDomain device\n"); + return; + } + } else { + kobject_uevent(&xd->dev.kobj, KOBJ_CHANGE); + } + + enumerate_services(xd); + return; + +err_free_dir: + tb_property_free_dir(dir); +err_free_block: + kfree(block); + mutex_unlock(&xd->lock); +} + +static void tb_xdomain_properties_changed(struct work_struct *work) +{ + struct tb_xdomain *xd = container_of(work, typeof(*xd), + properties_changed_work.work); + int ret; + + ret = tb_xdp_properties_changed_request(xd->tb->ctl, xd->route, + xd->properties_changed_retries, xd->local_uuid); + if (ret) { + if (xd->properties_changed_retries-- > 0) + queue_delayed_work(xd->tb->wq, + &xd->properties_changed_work, + msecs_to_jiffies(1000)); + return; + } + + xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES; +} + +static ssize_t device_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + + return sprintf(buf, "%#x\n", xd->device); +} +static DEVICE_ATTR_RO(device); + +static ssize_t +device_name_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + int ret; + + if (mutex_lock_interruptible(&xd->lock)) + return -ERESTARTSYS; + ret = sprintf(buf, "%s\n", xd->device_name ? xd->device_name : ""); + mutex_unlock(&xd->lock); + + return ret; +} +static DEVICE_ATTR_RO(device_name); + +static ssize_t vendor_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + + return sprintf(buf, "%#x\n", xd->vendor); +} +static DEVICE_ATTR_RO(vendor); + +static ssize_t +vendor_name_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + int ret; + + if (mutex_lock_interruptible(&xd->lock)) + return -ERESTARTSYS; + ret = sprintf(buf, "%s\n", xd->vendor_name ? xd->vendor_name : ""); + mutex_unlock(&xd->lock); + + return ret; +} +static DEVICE_ATTR_RO(vendor_name); + +static ssize_t unique_id_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + + return sprintf(buf, "%pUb\n", xd->remote_uuid); +} +static DEVICE_ATTR_RO(unique_id); + +static struct attribute *xdomain_attrs[] = { + &dev_attr_device.attr, + &dev_attr_device_name.attr, + &dev_attr_unique_id.attr, + &dev_attr_vendor.attr, + &dev_attr_vendor_name.attr, + NULL, +}; + +static struct attribute_group xdomain_attr_group = { + .attrs = xdomain_attrs, +}; + +static const struct attribute_group *xdomain_attr_groups[] = { + &xdomain_attr_group, + NULL, +}; + +static void tb_xdomain_release(struct device *dev) +{ + struct tb_xdomain *xd = container_of(dev, struct tb_xdomain, dev); + + put_device(xd->dev.parent); + + tb_property_free_dir(xd->properties); + ida_destroy(&xd->service_ids); + + kfree(xd->local_uuid); + kfree(xd->remote_uuid); + kfree(xd->device_name); + kfree(xd->vendor_name); + kfree(xd); +} + +static void start_handshake(struct tb_xdomain *xd) +{ + xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES; + xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES; + + /* Start exchanging properties with the other host */ + queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, + msecs_to_jiffies(100)); + queue_delayed_work(xd->tb->wq, &xd->get_properties_work, + msecs_to_jiffies(1000)); +} + +static void stop_handshake(struct tb_xdomain *xd) +{ + xd->properties_retries = 0; + xd->properties_changed_retries = 0; + + cancel_delayed_work_sync(&xd->get_properties_work); + cancel_delayed_work_sync(&xd->properties_changed_work); +} + +static int __maybe_unused tb_xdomain_suspend(struct device *dev) +{ + stop_handshake(tb_to_xdomain(dev)); + return 0; +} + +static int __maybe_unused tb_xdomain_resume(struct device *dev) +{ + struct tb_xdomain *xd = tb_to_xdomain(dev); + + /* + * Ask tb_xdomain_get_properties() restore any existing DMA + * paths after properties are re-read. + */ + xd->resume = true; + start_handshake(xd); + + return 0; +} + +static const struct dev_pm_ops tb_xdomain_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(tb_xdomain_suspend, tb_xdomain_resume) +}; + +struct device_type tb_xdomain_type = { + .name = "thunderbolt_xdomain", + .release = tb_xdomain_release, + .pm = &tb_xdomain_pm_ops, +}; +EXPORT_SYMBOL_GPL(tb_xdomain_type); + +/** + * tb_xdomain_alloc() - Allocate new XDomain object + * @tb: Domain where the XDomain belongs + * @parent: Parent device (the switch through the connection to the + * other domain is reached). + * @route: Route string used to reach the other domain + * @local_uuid: Our local domain UUID + * @remote_uuid: UUID of the other domain + * + * Allocates new XDomain structure and returns pointer to that. The + * object must be released by calling tb_xdomain_put(). + */ +struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent, + u64 route, const uuid_t *local_uuid, + const uuid_t *remote_uuid) +{ + struct tb_xdomain *xd; + + xd = kzalloc(sizeof(*xd), GFP_KERNEL); + if (!xd) + return NULL; + + xd->tb = tb; + xd->route = route; + ida_init(&xd->service_ids); + mutex_init(&xd->lock); + INIT_DELAYED_WORK(&xd->get_properties_work, tb_xdomain_get_properties); + INIT_DELAYED_WORK(&xd->properties_changed_work, + tb_xdomain_properties_changed); + + xd->local_uuid = kmemdup(local_uuid, sizeof(uuid_t), GFP_KERNEL); + if (!xd->local_uuid) + goto err_free; + + xd->remote_uuid = kmemdup(remote_uuid, sizeof(uuid_t), GFP_KERNEL); + if (!xd->remote_uuid) + goto err_free_local_uuid; + + device_initialize(&xd->dev); + xd->dev.parent = get_device(parent); + xd->dev.bus = &tb_bus_type; + xd->dev.type = &tb_xdomain_type; + xd->dev.groups = xdomain_attr_groups; + dev_set_name(&xd->dev, "%u-%llx", tb->index, route); + + return xd; + +err_free_local_uuid: + kfree(xd->local_uuid); +err_free: + kfree(xd); + + return NULL; +} + +/** + * tb_xdomain_add() - Add XDomain to the bus + * @xd: XDomain to add + * + * This function starts XDomain discovery protocol handshake and + * eventually adds the XDomain to the bus. After calling this function + * the caller needs to call tb_xdomain_remove() in order to remove and + * release the object regardless whether the handshake succeeded or not. + */ +void tb_xdomain_add(struct tb_xdomain *xd) +{ + /* Start exchanging properties with the other host */ + start_handshake(xd); +} + +static int unregister_service(struct device *dev, void *data) +{ + device_unregister(dev); + return 0; +} + +/** + * tb_xdomain_remove() - Remove XDomain from the bus + * @xd: XDomain to remove + * + * This will stop all ongoing configuration work and remove the XDomain + * along with any services from the bus. When the last reference to @xd + * is released the object will be released as well. + */ +void tb_xdomain_remove(struct tb_xdomain *xd) +{ + stop_handshake(xd); + + device_for_each_child_reverse(&xd->dev, xd, unregister_service); + + if (!device_is_registered(&xd->dev)) + put_device(&xd->dev); + else + device_unregister(&xd->dev); +} + +/** + * tb_xdomain_enable_paths() - Enable DMA paths for XDomain connection + * @xd: XDomain connection + * @transmit_path: HopID of the transmit path the other end is using to + * send packets + * @transmit_ring: DMA ring used to receive packets from the other end + * @receive_path: HopID of the receive path the other end is using to + * receive packets + * @receive_ring: DMA ring used to send packets to the other end + * + * The function enables DMA paths accordingly so that after successful + * return the caller can send and receive packets using high-speed DMA + * path. + * + * Return: %0 in case of success and negative errno in case of error + */ +int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path, + u16 transmit_ring, u16 receive_path, + u16 receive_ring) +{ + int ret; + + mutex_lock(&xd->lock); + + if (xd->transmit_path) { + ret = xd->transmit_path == transmit_path ? 0 : -EBUSY; + goto exit_unlock; + } + + xd->transmit_path = transmit_path; + xd->transmit_ring = transmit_ring; + xd->receive_path = receive_path; + xd->receive_ring = receive_ring; + + ret = tb_domain_approve_xdomain_paths(xd->tb, xd); + +exit_unlock: + mutex_unlock(&xd->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tb_xdomain_enable_paths); + +/** + * tb_xdomain_disable_paths() - Disable DMA paths for XDomain connection + * @xd: XDomain connection + * + * This does the opposite of tb_xdomain_enable_paths(). After call to + * this the caller is not expected to use the rings anymore. + * + * Return: %0 in case of success and negative errno in case of error + */ +int tb_xdomain_disable_paths(struct tb_xdomain *xd) +{ + int ret = 0; + + mutex_lock(&xd->lock); + if (xd->transmit_path) { + xd->transmit_path = 0; + xd->transmit_ring = 0; + xd->receive_path = 0; + xd->receive_ring = 0; + + ret = tb_domain_disconnect_xdomain_paths(xd->tb, xd); + } + mutex_unlock(&xd->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tb_xdomain_disable_paths); + +struct tb_xdomain_lookup { + const uuid_t *uuid; + u8 link; + u8 depth; +}; + +static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw, + const struct tb_xdomain_lookup *lookup) +{ + int i; + + for (i = 1; i <= sw->config.max_port_number; i++) { + struct tb_port *port = &sw->ports[i]; + struct tb_xdomain *xd; + + if (tb_is_upstream_port(port)) + continue; + + if (port->xdomain) { + xd = port->xdomain; + + if (lookup->uuid) { + if (uuid_equal(xd->remote_uuid, lookup->uuid)) + return xd; + } else if (lookup->link == xd->link && + lookup->depth == xd->depth) { + return xd; + } + } else if (port->remote) { + xd = switch_find_xdomain(port->remote->sw, lookup); + if (xd) + return xd; + } + } + + return NULL; +} + +/** + * tb_xdomain_find_by_uuid() - Find an XDomain by UUID + * @tb: Domain where the XDomain belongs to + * @uuid: UUID to look for + * + * Finds XDomain by walking through the Thunderbolt topology below @tb. + * The returned XDomain will have its reference count increased so the + * caller needs to call tb_xdomain_put() when it is done with the + * object. + * + * This will find all XDomains including the ones that are not yet added + * to the bus (handshake is still in progress). + * + * The caller needs to hold @tb->lock. + */ +struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid) +{ + struct tb_xdomain_lookup lookup; + struct tb_xdomain *xd; + + memset(&lookup, 0, sizeof(lookup)); + lookup.uuid = uuid; + + xd = switch_find_xdomain(tb->root_switch, &lookup); + if (xd) { + get_device(&xd->dev); + return xd; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(tb_xdomain_find_by_uuid); + +/** + * tb_xdomain_find_by_link_depth() - Find an XDomain by link and depth + * @tb: Domain where the XDomain belongs to + * @link: Root switch link number + * @depth: Depth in the link + * + * Finds XDomain by walking through the Thunderbolt topology below @tb. + * The returned XDomain will have its reference count increased so the + * caller needs to call tb_xdomain_put() when it is done with the + * object. + * + * This will find all XDomains including the ones that are not yet added + * to the bus (handshake is still in progress). + * + * The caller needs to hold @tb->lock. + */ +struct tb_xdomain *tb_xdomain_find_by_link_depth(struct tb *tb, u8 link, + u8 depth) +{ + struct tb_xdomain_lookup lookup; + struct tb_xdomain *xd; + + memset(&lookup, 0, sizeof(lookup)); + lookup.link = link; + lookup.depth = depth; + + xd = switch_find_xdomain(tb->root_switch, &lookup); + if (xd) { + get_device(&xd->dev); + return xd; + } + + return NULL; +} + +bool tb_xdomain_handle_request(struct tb *tb, enum tb_cfg_pkg_type type, + const void *buf, size_t size) +{ + const struct tb_protocol_handler *handler, *tmp; + const struct tb_xdp_header *hdr = buf; + unsigned int length; + int ret = 0; + + /* We expect the packet is at least size of the header */ + length = hdr->xd_hdr.length_sn & TB_XDOMAIN_LENGTH_MASK; + if (length != size / 4 - sizeof(hdr->xd_hdr) / 4) + return true; + if (length < sizeof(*hdr) / 4 - sizeof(hdr->xd_hdr) / 4) + return true; + + /* + * Handle XDomain discovery protocol packets directly here. For + * other protocols (based on their UUID) we call registered + * handlers in turn. + */ + if (uuid_equal(&hdr->uuid, &tb_xdp_uuid)) { + if (type == TB_CFG_PKG_XDOMAIN_REQ) { + tb_xdp_schedule_request(tb, hdr, size); + return true; + } + return false; + } + + mutex_lock(&xdomain_lock); + list_for_each_entry_safe(handler, tmp, &protocol_handlers, list) { + if (!uuid_equal(&hdr->uuid, handler->uuid)) + continue; + + mutex_unlock(&xdomain_lock); + ret = handler->callback(buf, size, handler->data); + mutex_lock(&xdomain_lock); + + if (ret) + break; + } + mutex_unlock(&xdomain_lock); + + return ret > 0; +} + +static int rebuild_property_block(void) +{ + u32 *block, len; + int ret; + + ret = tb_property_format_dir(xdomain_property_dir, NULL, 0); + if (ret < 0) + return ret; + + len = ret; + + block = kcalloc(len, sizeof(u32), GFP_KERNEL); + if (!block) + return -ENOMEM; + + ret = tb_property_format_dir(xdomain_property_dir, block, len); + if (ret) { + kfree(block); + return ret; + } + + kfree(xdomain_property_block); + xdomain_property_block = block; + xdomain_property_block_len = len; + xdomain_property_block_gen++; + + return 0; +} + +static int update_xdomain(struct device *dev, void *data) +{ + struct tb_xdomain *xd; + + xd = tb_to_xdomain(dev); + if (xd) { + queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, + msecs_to_jiffies(50)); + } + + return 0; +} + +static void update_all_xdomains(void) +{ + bus_for_each_dev(&tb_bus_type, NULL, NULL, update_xdomain); +} + +static bool remove_directory(const char *key, const struct tb_property_dir *dir) +{ + struct tb_property *p; + + p = tb_property_find(xdomain_property_dir, key, + TB_PROPERTY_TYPE_DIRECTORY); + if (p && p->value.dir == dir) { + tb_property_remove(p); + return true; + } + return false; +} + +/** + * tb_register_property_dir() - Register property directory to the host + * @key: Key (name) of the directory to add + * @dir: Directory to add + * + * Service drivers can use this function to add new property directory + * to the host available properties. The other connected hosts are + * notified so they can re-read properties of this host if they are + * interested. + * + * Return: %0 on success and negative errno on failure + */ +int tb_register_property_dir(const char *key, struct tb_property_dir *dir) +{ + int ret; + + if (!key || strlen(key) > 8) + return -EINVAL; + + mutex_lock(&xdomain_lock); + if (tb_property_find(xdomain_property_dir, key, + TB_PROPERTY_TYPE_DIRECTORY)) { + ret = -EEXIST; + goto err_unlock; + } + + ret = tb_property_add_dir(xdomain_property_dir, key, dir); + if (ret) + goto err_unlock; + + ret = rebuild_property_block(); + if (ret) { + remove_directory(key, dir); + goto err_unlock; + } + + mutex_unlock(&xdomain_lock); + update_all_xdomains(); + return 0; + +err_unlock: + mutex_unlock(&xdomain_lock); + return ret; +} +EXPORT_SYMBOL_GPL(tb_register_property_dir); + +/** + * tb_unregister_property_dir() - Removes property directory from host + * @key: Key (name) of the directory + * @dir: Directory to remove + * + * This will remove the existing directory from this host and notify the + * connected hosts about the change. + */ +void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir) +{ + int ret = 0; + + mutex_lock(&xdomain_lock); + if (remove_directory(key, dir)) + ret = rebuild_property_block(); + mutex_unlock(&xdomain_lock); + + if (!ret) + update_all_xdomains(); +} +EXPORT_SYMBOL_GPL(tb_unregister_property_dir); + +int tb_xdomain_init(void) +{ + int ret; + + xdomain_property_dir = tb_property_create_dir(NULL); + if (!xdomain_property_dir) + return -ENOMEM; + + /* + * Initialize standard set of properties without any service + * directories. Those will be added by service drivers + * themselves when they are loaded. + */ + tb_property_add_immediate(xdomain_property_dir, "vendorid", + PCI_VENDOR_ID_INTEL); + tb_property_add_text(xdomain_property_dir, "vendorid", "Intel Corp."); + tb_property_add_immediate(xdomain_property_dir, "deviceid", 0x1); + tb_property_add_text(xdomain_property_dir, "deviceid", + utsname()->nodename); + tb_property_add_immediate(xdomain_property_dir, "devicerv", 0x80000100); + + ret = rebuild_property_block(); + if (ret) { + tb_property_free_dir(xdomain_property_dir); + xdomain_property_dir = NULL; + } + + return ret; +} + +void tb_xdomain_exit(void) +{ + kfree(xdomain_property_block); + tb_property_free_dir(xdomain_property_dir); +} diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 694cebb50f72c..7625c3b81f84c 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -683,5 +683,31 @@ struct fsl_mc_device_id { const char obj_type[16]; }; +/** + * struct tb_service_id - Thunderbolt service identifiers + * @match_flags: Flags used to match the structure + * @protocol_key: Protocol key the service supports + * @protocol_id: Protocol id the service supports + * @protocol_version: Version of the protocol + * @protocol_revision: Revision of the protocol software + * @driver_data: Driver specific data + * + * Thunderbolt XDomain services are exposed as devices where each device + * carries the protocol information the service supports. Thunderbolt + * XDomain service drivers match against that information. + */ +struct tb_service_id { + __u32 match_flags; + char protocol_key[8 + 1]; + __u32 protocol_id; + __u32 protocol_version; + __u32 protocol_revision; + kernel_ulong_t driver_data; +}; + +#define TBSVC_MATCH_PROTOCOL_KEY 0x0001 +#define TBSVC_MATCH_PROTOCOL_ID 0x0002 +#define TBSVC_MATCH_PROTOCOL_VERSION 0x0004 +#define TBSVC_MATCH_PROTOCOL_REVISION 0x0008 #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 43b8d1e093411..18c0e3d5e85cb 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -17,6 +17,7 @@ #include #include #include +#include #include enum tb_cfg_pkg_type { @@ -77,6 +78,8 @@ struct tb { }; extern struct bus_type tb_bus_type; +extern struct device_type tb_service_type; +extern struct device_type tb_xdomain_type; #define TB_LINKS_PER_PHY_PORT 2 @@ -155,4 +158,243 @@ struct tb_property *tb_property_get_next(struct tb_property_dir *dir, property; \ property = tb_property_get_next(dir, property)) +int tb_register_property_dir(const char *key, struct tb_property_dir *dir); +void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); + +/** + * struct tb_xdomain - Cross-domain (XDomain) connection + * @dev: XDomain device + * @tb: Pointer to the domain + * @remote_uuid: UUID of the remote domain (host) + * @local_uuid: Cached local UUID + * @route: Route string the other domain can be reached + * @vendor: Vendor ID of the remote domain + * @device: Device ID of the demote domain + * @lock: Lock to serialize access to the following fields of this structure + * @vendor_name: Name of the vendor (or %NULL if not known) + * @device_name: Name of the device (or %NULL if not known) + * @is_unplugged: The XDomain is unplugged + * @resume: The XDomain is being resumed + * @transmit_path: HopID which the remote end expects us to transmit + * @transmit_ring: Local ring (hop) where outgoing packets are pushed + * @receive_path: HopID which we expect the remote end to transmit + * @receive_ring: Local ring (hop) where incoming packets arrive + * @service_ids: Used to generate IDs for the services + * @properties: Properties exported by the remote domain + * @property_block_gen: Generation of @properties + * @properties_lock: Lock protecting @properties. + * @get_properties_work: Work used to get remote domain properties + * @properties_retries: Number of times left to read properties + * @properties_changed_work: Work used to notify the remote domain that + * our properties have changed + * @properties_changed_retries: Number of times left to send properties + * changed notification + * @link: Root switch link the remote domain is connected (ICM only) + * @depth: Depth in the chain the remote domain is connected (ICM only) + * + * This structure represents connection across two domains (hosts). + * Each XDomain contains zero or more services which are exposed as + * &struct tb_service objects. + * + * Service drivers may access this structure if they need to enumerate + * non-standard properties but they need hold @lock when doing so + * because properties can be changed asynchronously in response to + * changes in the remote domain. + */ +struct tb_xdomain { + struct device dev; + struct tb *tb; + uuid_t *remote_uuid; + const uuid_t *local_uuid; + u64 route; + u16 vendor; + u16 device; + struct mutex lock; + const char *vendor_name; + const char *device_name; + bool is_unplugged; + bool resume; + u16 transmit_path; + u16 transmit_ring; + u16 receive_path; + u16 receive_ring; + struct ida service_ids; + struct tb_property_dir *properties; + u32 property_block_gen; + struct delayed_work get_properties_work; + int properties_retries; + struct delayed_work properties_changed_work; + int properties_changed_retries; + u8 link; + u8 depth; +}; + +int tb_xdomain_enable_paths(struct tb_xdomain *xd, u16 transmit_path, + u16 transmit_ring, u16 receive_path, + u16 receive_ring); +int tb_xdomain_disable_paths(struct tb_xdomain *xd); +struct tb_xdomain *tb_xdomain_find_by_uuid(struct tb *tb, const uuid_t *uuid); + +static inline struct tb_xdomain * +tb_xdomain_find_by_uuid_locked(struct tb *tb, const uuid_t *uuid) +{ + struct tb_xdomain *xd; + + mutex_lock(&tb->lock); + xd = tb_xdomain_find_by_uuid(tb, uuid); + mutex_unlock(&tb->lock); + + return xd; +} + +static inline struct tb_xdomain *tb_xdomain_get(struct tb_xdomain *xd) +{ + if (xd) + get_device(&xd->dev); + return xd; +} + +static inline void tb_xdomain_put(struct tb_xdomain *xd) +{ + if (xd) + put_device(&xd->dev); +} + +static inline bool tb_is_xdomain(const struct device *dev) +{ + return dev->type == &tb_xdomain_type; +} + +static inline struct tb_xdomain *tb_to_xdomain(struct device *dev) +{ + if (tb_is_xdomain(dev)) + return container_of(dev, struct tb_xdomain, dev); + return NULL; +} + +int tb_xdomain_response(struct tb_xdomain *xd, const void *response, + size_t size, enum tb_cfg_pkg_type type); +int tb_xdomain_request(struct tb_xdomain *xd, const void *request, + size_t request_size, enum tb_cfg_pkg_type request_type, + void *response, size_t response_size, + enum tb_cfg_pkg_type response_type, + unsigned int timeout_msec); + +/** + * tb_protocol_handler - Protocol specific handler + * @uuid: XDomain messages with this UUID are dispatched to this handler + * @callback: Callback called with the XDomain message. Returning %1 + * here tells the XDomain core that the message was handled + * by this handler and should not be forwared to other + * handlers. + * @data: Data passed with the callback + * @list: Handlers are linked using this + * + * Thunderbolt services can hook into incoming XDomain requests by + * registering protocol handler. Only limitation is that the XDomain + * discovery protocol UUID cannot be registered since it is handled by + * the core XDomain code. + * + * The @callback must check that the message is really directed to the + * service the driver implements. + */ +struct tb_protocol_handler { + const uuid_t *uuid; + int (*callback)(const void *buf, size_t size, void *data); + void *data; + struct list_head list; +}; + +int tb_register_protocol_handler(struct tb_protocol_handler *handler); +void tb_unregister_protocol_handler(struct tb_protocol_handler *handler); + +/** + * struct tb_service - Thunderbolt service + * @dev: XDomain device + * @id: ID of the service (shown in sysfs) + * @key: Protocol key from the properties directory + * @prtcid: Protocol ID from the properties directory + * @prtcvers: Protocol version from the properties directory + * @prtcrevs: Protocol software revision from the properties directory + * @prtcstns: Protocol settings mask from the properties directory + * + * Each domain exposes set of services it supports as collection of + * properties. For each service there will be one corresponding + * &struct tb_service. Service drivers are bound to these. + */ +struct tb_service { + struct device dev; + int id; + const char *key; + u32 prtcid; + u32 prtcvers; + u32 prtcrevs; + u32 prtcstns; +}; + +static inline struct tb_service *tb_service_get(struct tb_service *svc) +{ + if (svc) + get_device(&svc->dev); + return svc; +} + +static inline void tb_service_put(struct tb_service *svc) +{ + if (svc) + put_device(&svc->dev); +} + +static inline bool tb_is_service(const struct device *dev) +{ + return dev->type == &tb_service_type; +} + +static inline struct tb_service *tb_to_service(struct device *dev) +{ + if (tb_is_service(dev)) + return container_of(dev, struct tb_service, dev); + return NULL; +} + +/** + * tb_service_driver - Thunderbolt service driver + * @driver: Driver structure + * @probe: Called when the driver is probed + * @remove: Called when the driver is removed (optional) + * @shutdown: Called at shutdown time to stop the service (optional) + * @id_table: Table of service identifiers the driver supports + */ +struct tb_service_driver { + struct device_driver driver; + int (*probe)(struct tb_service *svc, const struct tb_service_id *id); + void (*remove)(struct tb_service *svc); + void (*shutdown)(struct tb_service *svc); + const struct tb_service_id *id_table; +}; + +#define TB_SERVICE(key, id) \ + .match_flags = TBSVC_MATCH_PROTOCOL_KEY | \ + TBSVC_MATCH_PROTOCOL_ID, \ + .protocol_key = (key), \ + .protocol_id = (id) + +int tb_register_service_driver(struct tb_service_driver *drv); +void tb_unregister_service_driver(struct tb_service_driver *drv); + +static inline void *tb_service_get_drvdata(const struct tb_service *svc) +{ + return dev_get_drvdata(&svc->dev); +} + +static inline void tb_service_set_drvdata(struct tb_service *svc, void *data) +{ + dev_set_drvdata(&svc->dev, data); +} + +static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) +{ + return tb_to_xdomain(svc->dev.parent); +} + #endif /* THUNDERBOLT_H_ */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index e4d90e50f6fec..57263f2f8f2fa 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -206,5 +206,12 @@ int main(void) DEVID_FIELD(fsl_mc_device_id, vendor); DEVID_FIELD(fsl_mc_device_id, obj_type); + DEVID(tb_service_id); + DEVID_FIELD(tb_service_id, match_flags); + DEVID_FIELD(tb_service_id, protocol_key); + DEVID_FIELD(tb_service_id, protocol_id); + DEVID_FIELD(tb_service_id, protocol_version); + DEVID_FIELD(tb_service_id, protocol_revision); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 29d6699d5a06c..6ef6e63f96fd9 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1301,6 +1301,31 @@ static int do_fsl_mc_entry(const char *filename, void *symval, } ADD_TO_DEVTABLE("fslmc", fsl_mc_device_id, do_fsl_mc_entry); +/* Looks like: tbsvc:kSpNvNrN */ +static int do_tbsvc_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD(symval, tb_service_id, match_flags); + DEF_FIELD_ADDR(symval, tb_service_id, protocol_key); + DEF_FIELD(symval, tb_service_id, protocol_id); + DEF_FIELD(symval, tb_service_id, protocol_version); + DEF_FIELD(symval, tb_service_id, protocol_revision); + + strcpy(alias, "tbsvc:"); + if (match_flags & TBSVC_MATCH_PROTOCOL_KEY) + sprintf(alias + strlen(alias), "k%s", *protocol_key); + else + strcat(alias + strlen(alias), "k*"); + ADD(alias, "p", match_flags & TBSVC_MATCH_PROTOCOL_ID, protocol_id); + ADD(alias, "v", match_flags & TBSVC_MATCH_PROTOCOL_VERSION, + protocol_version); + ADD(alias, "r", match_flags & TBSVC_MATCH_PROTOCOL_REVISION, + protocol_revision); + + add_wildcard(alias); + return 1; +} +ADD_TO_DEVTABLE("tbsvc", tb_service_id, do_tbsvc_entry); + /* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) { -- GitLab From 8c6bba10fb9262d7b3a11e86a40621d5b37810a6 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:35 +0300 Subject: [PATCH 0774/1507] thunderbolt: Configure interrupt throttling for all interrupts This will keep the interrupt delivery rate reasonable. The value used here (128 us) is a recommendation from the hardware people. This code is based on the work done by Amir Levy and Michael Jamet. Signed-off-by: Michael Jamet Signed-off-by: Mika Westerberg Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi.c | 23 ++++++++++++++++++++--- drivers/thunderbolt/nhi_regs.h | 2 ++ 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 05af126a24359..8a7a3d0133f9b 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -651,6 +651,22 @@ static int nhi_suspend_noirq(struct device *dev) return tb_domain_suspend_noirq(tb); } +static void nhi_enable_int_throttling(struct tb_nhi *nhi) +{ + /* Throttling is specified in 256ns increments */ + u32 throttle = DIV_ROUND_UP(128 * NSEC_PER_USEC, 256); + unsigned int i; + + /* + * Configure interrupt throttling for all vectors even if we + * only use few. + */ + for (i = 0; i < MSIX_MAX_VECS; i++) { + u32 reg = REG_INT_THROTTLING_RATE + i * 4; + iowrite32(throttle, nhi->iobase + reg); + } +} + static int nhi_resume_noirq(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -663,6 +679,8 @@ static int nhi_resume_noirq(struct device *dev) */ if (!pci_device_is_present(pdev)) tb->nhi->going_away = true; + else + nhi_enable_int_throttling(tb->nhi); return tb_domain_resume_noirq(tb); } @@ -717,6 +735,8 @@ static int nhi_init_msi(struct tb_nhi *nhi) /* In case someone left them on. */ nhi_disable_interrupts(nhi); + nhi_enable_int_throttling(nhi); + ida_init(&nhi->msix_ida); /* @@ -796,9 +816,6 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); - /* magic value - clock related? */ - iowrite32(3906250 / 10000, nhi->iobase + 0x38c00); - tb = icm_probe(nhi); if (!tb) tb = tb_probe(nhi); diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index 09ed574e92ff3..46eff69b19ad4 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -95,6 +95,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_INT_THROTTLING_RATE 0x38c00 + /* Interrupt Vector Allocation */ #define REG_INT_VEC_ALLOC_BASE 0x38c40 #define REG_INT_VEC_ALLOC_BITS 4 -- GitLab From 9fb1e654dcf781e71a0ea7c5bdfea3ba85d1d06d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:36 +0300 Subject: [PATCH 0775/1507] thunderbolt: Add support for frame mode When high-speed DMA paths are used to transfer arbitrary data over a Thunderbolt link, DMA rings should be in frame mode instead of raw mode. The latter is used by the control channel (ring 0). In frame mode each data frame can hold up to 4kB payload. This patch modifies the DMA ring code to allow configuring a ring to be in frame mode by passing a new flag (RING_FLAG_FRAME) to the ring when it is allocated. In addition there might be need to enable end-to-end (E2E) workaround for the ring to prevent losing Rx frames in certain situations. We add another flag (RING_FLAG_E2E) that can be used for this purpose. This code is based on the work done by Amir Levy and Michael Jamet. Signed-off-by: Michael Jamet Signed-off-by: Mika Westerberg Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/ctl.c | 3 +- drivers/thunderbolt/nhi.c | 76 +++++++++++++++++++++------------- drivers/thunderbolt/nhi.h | 10 ++++- drivers/thunderbolt/nhi_regs.h | 2 + 4 files changed, 61 insertions(+), 30 deletions(-) diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index 46e393c5fd1d1..05400b77dcd79 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -618,7 +618,8 @@ struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data) if (!ctl->tx) goto err; - ctl->rx = ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND); + ctl->rx = ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff, + 0xffff); if (!ctl->rx) goto err; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 8a7a3d0133f9b..bebcad3d2c1fb 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -21,6 +21,12 @@ #define RING_TYPE(ring) ((ring)->is_tx ? "TX ring" : "RX ring") +/* + * Used to enable end-to-end workaround for missing RX packets. Do not + * use this ring for anything else. + */ +#define RING_E2E_UNUSED_HOPID 2 + /* * Minimal number of vectors when we use MSI-X. Two for control channel * Rx/Tx and the rest four are for cross domain DMA paths. @@ -229,23 +235,6 @@ static void ring_work(struct work_struct *work) frame->eof = ring->descriptors[ring->tail].eof; frame->sof = ring->descriptors[ring->tail].sof; frame->flags = ring->descriptors[ring->tail].flags; - if (frame->sof != 0) - dev_WARN(&ring->nhi->pdev->dev, - "%s %d got unexpected SOF: %#x\n", - RING_TYPE(ring), ring->hop, - frame->sof); - /* - * known flags: - * raw not enabled, interupt not set: 0x2=0010 - * raw enabled: 0xa=1010 - * raw not enabled: 0xb=1011 - * partial frame (>MAX_FRAME_SIZE): 0xe=1110 - */ - if (frame->flags != 0xa) - dev_WARN(&ring->nhi->pdev->dev, - "%s %d got unexpected flags: %#x\n", - RING_TYPE(ring), ring->hop, - frame->flags); } ring->tail = (ring->tail + 1) % ring->size; } @@ -321,12 +310,17 @@ static void ring_release_msix(struct tb_ring *ring) } static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size, - bool transmit, unsigned int flags) + bool transmit, unsigned int flags, + u16 sof_mask, u16 eof_mask) { struct tb_ring *ring = NULL; dev_info(&nhi->pdev->dev, "allocating %s ring %d of size %d\n", transmit ? "TX" : "RX", hop, size); + /* Tx Ring 2 is reserved for E2E workaround */ + if (transmit && hop == RING_E2E_UNUSED_HOPID) + return NULL; + mutex_lock(&nhi->lock); if (hop >= nhi->hop_count) { dev_WARN(&nhi->pdev->dev, "invalid hop: %d\n", hop); @@ -353,6 +347,8 @@ static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size, ring->is_tx = transmit; ring->size = size; ring->flags = flags; + ring->sof_mask = sof_mask; + ring->eof_mask = eof_mask; ring->head = 0; ring->tail = 0; ring->running = false; @@ -384,13 +380,13 @@ static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size, struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, unsigned int flags) { - return ring_alloc(nhi, hop, size, true, flags); + return ring_alloc(nhi, hop, size, true, flags, 0, 0); } struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags) + unsigned int flags, u16 sof_mask, u16 eof_mask) { - return ring_alloc(nhi, hop, size, false, flags); + return ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask); } /** @@ -400,6 +396,9 @@ struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, */ void ring_start(struct tb_ring *ring) { + u16 frame_size; + u32 flags; + mutex_lock(&ring->nhi->lock); mutex_lock(&ring->lock); if (ring->nhi->going_away) @@ -411,18 +410,39 @@ void ring_start(struct tb_ring *ring) dev_info(&ring->nhi->pdev->dev, "starting %s %d\n", RING_TYPE(ring), ring->hop); + if (ring->flags & RING_FLAG_FRAME) { + /* Means 4096 */ + frame_size = 0; + flags = RING_FLAG_ENABLE; + } else { + frame_size = TB_FRAME_SIZE; + flags = RING_FLAG_ENABLE | RING_FLAG_RAW; + } + + if (ring->flags & RING_FLAG_E2E && !ring->is_tx) { + u32 hop; + + /* + * In order not to lose Rx packets we enable end-to-end + * workaround which transfers Rx credits to an unused Tx + * HopID. + */ + hop = RING_E2E_UNUSED_HOPID << REG_RX_OPTIONS_E2E_HOP_SHIFT; + hop &= REG_RX_OPTIONS_E2E_HOP_MASK; + flags |= hop | RING_FLAG_E2E_FLOW_CONTROL; + } + ring_iowrite64desc(ring, ring->descriptors_dma, 0); if (ring->is_tx) { ring_iowrite32desc(ring, ring->size, 12); ring_iowrite32options(ring, 0, 4); /* time releated ? */ - ring_iowrite32options(ring, - RING_FLAG_ENABLE | RING_FLAG_RAW, 0); + ring_iowrite32options(ring, flags, 0); } else { - ring_iowrite32desc(ring, - (TB_FRAME_SIZE << 16) | ring->size, 12); - ring_iowrite32options(ring, 0xffffffff, 4); /* SOF EOF mask */ - ring_iowrite32options(ring, - RING_FLAG_ENABLE | RING_FLAG_RAW, 0); + u32 sof_eof_mask = ring->sof_mask << 16 | ring->eof_mask; + + ring_iowrite32desc(ring, (frame_size << 16) | ring->size, 12); + ring_iowrite32options(ring, sof_eof_mask, 4); + ring_iowrite32options(ring, flags, 0); } ring_interrupt_active(ring, true); ring->running = true; diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 0e05828983db5..4503ddbeccb39 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -56,6 +56,8 @@ struct tb_nhi { * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise. * @vector: MSI-X vector number the ring uses (only set if @irq is > 0) * @flags: Ring specific flags + * @sof_mask: Bit mask used to detect start of frame PDF + * @eof_mask: Bit mask used to detect end of frame PDF */ struct tb_ring { struct mutex lock; @@ -74,10 +76,16 @@ struct tb_ring { int irq; u8 vector; unsigned int flags; + u16 sof_mask; + u16 eof_mask; }; /* Leave ring interrupt enabled on suspend */ #define RING_FLAG_NO_SUSPEND BIT(0) +/* Configure the ring to be in frame mode */ +#define RING_FLAG_FRAME BIT(1) +/* Enable end-to-end flow control */ +#define RING_FLAG_E2E BIT(2) struct ring_frame; typedef void (*ring_cb)(struct tb_ring*, struct ring_frame*, bool canceled); @@ -100,7 +108,7 @@ struct ring_frame { struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, unsigned int flags); struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags); + unsigned int flags, u16 sof_mask, u16 eof_mask); void ring_start(struct tb_ring *ring); void ring_stop(struct tb_ring *ring); void ring_free(struct tb_ring *ring); diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index 46eff69b19ad4..491a4c0c18fc1 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -77,6 +77,8 @@ struct ring_desc { * ..: unknown */ #define REG_RX_OPTIONS_BASE 0x29800 +#define REG_RX_OPTIONS_E2E_HOP_MASK GENMASK(22, 12) +#define REG_RX_OPTIONS_E2E_HOP_SHIFT 12 /* * three bitfields: tx, rx, rx overflow -- GitLab From 3b3d9f4da96493e4f68d0a80ab210763a24f8b33 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:37 +0300 Subject: [PATCH 0776/1507] thunderbolt: Export ring handling functions to modules These are used by Thunderbolt services to send and receive frames over the high-speed DMA rings. We also put the functions to tb_ namespace to make sure we do not collide with others and add missing kernel-doc comments for the exported functions. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/ctl.c | 20 ++--- drivers/thunderbolt/nhi.c | 62 +++++++++----- drivers/thunderbolt/nhi.h | 147 +-------------------------------- include/linux/thunderbolt.h | 158 ++++++++++++++++++++++++++++++++++++ 4 files changed, 211 insertions(+), 176 deletions(-) diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index 05400b77dcd79..dd10789e1dbb3 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -359,7 +359,7 @@ static int tb_ctl_tx(struct tb_ctl *ctl, const void *data, size_t len, cpu_to_be32_array(pkg->buffer, data, len / 4); *(__be32 *) (pkg->buffer + len) = tb_crc(pkg->buffer, len); - res = ring_tx(ctl->tx, &pkg->frame); + res = tb_ring_tx(ctl->tx, &pkg->frame); if (res) /* ring is stopped */ tb_ctl_pkg_free(pkg); return res; @@ -376,7 +376,7 @@ static bool tb_ctl_handle_event(struct tb_ctl *ctl, enum tb_cfg_pkg_type type, static void tb_ctl_rx_submit(struct ctl_pkg *pkg) { - ring_rx(pkg->ctl->rx, &pkg->frame); /* + tb_ring_rx(pkg->ctl->rx, &pkg->frame); /* * We ignore failures during stop. * All rx packets are referenced * from ctl->rx_packets, so we do @@ -614,11 +614,11 @@ struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data) if (!ctl->frame_pool) goto err; - ctl->tx = ring_alloc_tx(nhi, 0, 10, RING_FLAG_NO_SUSPEND); + ctl->tx = tb_ring_alloc_tx(nhi, 0, 10, RING_FLAG_NO_SUSPEND); if (!ctl->tx) goto err; - ctl->rx = ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff, + ctl->rx = tb_ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff, 0xffff); if (!ctl->rx) goto err; @@ -652,9 +652,9 @@ void tb_ctl_free(struct tb_ctl *ctl) return; if (ctl->rx) - ring_free(ctl->rx); + tb_ring_free(ctl->rx); if (ctl->tx) - ring_free(ctl->tx); + tb_ring_free(ctl->tx); /* free RX packets */ for (i = 0; i < TB_CTL_RX_PKG_COUNT; i++) @@ -673,8 +673,8 @@ void tb_ctl_start(struct tb_ctl *ctl) { int i; tb_ctl_info(ctl, "control channel starting...\n"); - ring_start(ctl->tx); /* is used to ack hotplug packets, start first */ - ring_start(ctl->rx); + tb_ring_start(ctl->tx); /* is used to ack hotplug packets, start first */ + tb_ring_start(ctl->rx); for (i = 0; i < TB_CTL_RX_PKG_COUNT; i++) tb_ctl_rx_submit(ctl->rx_packets[i]); @@ -695,8 +695,8 @@ void tb_ctl_stop(struct tb_ctl *ctl) ctl->running = false; mutex_unlock(&ctl->request_queue_lock); - ring_stop(ctl->rx); - ring_stop(ctl->tx); + tb_ring_stop(ctl->rx); + tb_ring_stop(ctl->tx); if (!list_empty(&ctl->request_queue)) tb_ctl_WARN(ctl, "dangling request in request_queue\n"); diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index bebcad3d2c1fb..e0a47f7581cbb 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -253,7 +253,7 @@ static void ring_work(struct work_struct *work) } } -int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame) +int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame) { int ret = 0; mutex_lock(&ring->lock); @@ -266,6 +266,7 @@ int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame) mutex_unlock(&ring->lock); return ret; } +EXPORT_SYMBOL_GPL(__tb_ring_enqueue); static irqreturn_t ring_msix(int irq, void *data) { @@ -309,9 +310,9 @@ static void ring_release_msix(struct tb_ring *ring) ring->irq = 0; } -static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size, - bool transmit, unsigned int flags, - u16 sof_mask, u16 eof_mask) +static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, + bool transmit, unsigned int flags, + u16 sof_mask, u16 eof_mask) { struct tb_ring *ring = NULL; dev_info(&nhi->pdev->dev, "allocating %s ring %d of size %d\n", @@ -377,24 +378,42 @@ static struct tb_ring *ring_alloc(struct tb_nhi *nhi, u32 hop, int size, return NULL; } -struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags) +/** + * tb_ring_alloc_tx() - Allocate DMA ring for transmit + * @nhi: Pointer to the NHI the ring is to be allocated + * @hop: HopID (ring) to allocate + * @size: Number of entries in the ring + * @flags: Flags for the ring + */ +struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags) { - return ring_alloc(nhi, hop, size, true, flags, 0, 0); + return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0); } +EXPORT_SYMBOL_GPL(tb_ring_alloc_tx); -struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags, u16 sof_mask, u16 eof_mask) +/** + * tb_ring_alloc_rx() - Allocate DMA ring for receive + * @nhi: Pointer to the NHI the ring is to be allocated + * @hop: HopID (ring) to allocate + * @size: Number of entries in the ring + * @flags: Flags for the ring + * @sof_mask: Mask of PDF values that start a frame + * @eof_mask: Mask of PDF values that end a frame + */ +struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags, u16 sof_mask, u16 eof_mask) { - return ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask); + return tb_ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask); } +EXPORT_SYMBOL_GPL(tb_ring_alloc_rx); /** - * ring_start() - enable a ring + * tb_ring_start() - enable a ring * - * Must not be invoked in parallel with ring_stop(). + * Must not be invoked in parallel with tb_ring_stop(). */ -void ring_start(struct tb_ring *ring) +void tb_ring_start(struct tb_ring *ring) { u16 frame_size; u32 flags; @@ -450,21 +469,22 @@ void ring_start(struct tb_ring *ring) mutex_unlock(&ring->lock); mutex_unlock(&ring->nhi->lock); } - +EXPORT_SYMBOL_GPL(tb_ring_start); /** - * ring_stop() - shutdown a ring + * tb_ring_stop() - shutdown a ring * * Must not be invoked from a callback. * - * This method will disable the ring. Further calls to ring_tx/ring_rx will - * return -ESHUTDOWN until ring_stop has been called. + * This method will disable the ring. Further calls to + * tb_ring_tx/tb_ring_rx will return -ESHUTDOWN until ring_stop has been + * called. * * All enqueued frames will be canceled and their callbacks will be executed * with frame->canceled set to true (on the callback thread). This method * returns only after all callback invocations have finished. */ -void ring_stop(struct tb_ring *ring) +void tb_ring_stop(struct tb_ring *ring) { mutex_lock(&ring->nhi->lock); mutex_lock(&ring->lock); @@ -497,9 +517,10 @@ void ring_stop(struct tb_ring *ring) schedule_work(&ring->work); flush_work(&ring->work); } +EXPORT_SYMBOL_GPL(tb_ring_stop); /* - * ring_free() - free ring + * tb_ring_free() - free ring * * When this method returns all invocations of ring->callback will have * finished. @@ -508,7 +529,7 @@ void ring_stop(struct tb_ring *ring) * * Must NOT be called from ring_frame->callback! */ -void ring_free(struct tb_ring *ring) +void tb_ring_free(struct tb_ring *ring) { mutex_lock(&ring->nhi->lock); /* @@ -550,6 +571,7 @@ void ring_free(struct tb_ring *ring) mutex_destroy(&ring->lock); kfree(ring); } +EXPORT_SYMBOL_GPL(tb_ring_free); /** * nhi_mailbox_cmd() - Send a command through NHI mailbox diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 4503ddbeccb39..771d09ca5dc50 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -7,152 +7,7 @@ #ifndef DSL3510_H_ #define DSL3510_H_ -#include -#include -#include - -/** - * struct tb_nhi - thunderbolt native host interface - * @lock: Must be held during ring creation/destruction. Is acquired by - * interrupt_work when dispatching interrupts to individual rings. - * @pdev: Pointer to the PCI device - * @iobase: MMIO space of the NHI - * @tx_rings: All Tx rings available on this host controller - * @rx_rings: All Rx rings available on this host controller - * @msix_ida: Used to allocate MSI-X vectors for rings - * @going_away: The host controller device is about to disappear so when - * this flag is set, avoid touching the hardware anymore. - * @interrupt_work: Work scheduled to handle ring interrupt when no - * MSI-X is used. - * @hop_count: Number of rings (end point hops) supported by NHI. - */ -struct tb_nhi { - struct mutex lock; - struct pci_dev *pdev; - void __iomem *iobase; - struct tb_ring **tx_rings; - struct tb_ring **rx_rings; - struct ida msix_ida; - bool going_away; - struct work_struct interrupt_work; - u32 hop_count; -}; - -/** - * struct tb_ring - thunderbolt TX or RX ring associated with a NHI - * @lock: Lock serializing actions to this ring. Must be acquired after - * nhi->lock. - * @nhi: Pointer to the native host controller interface - * @size: Size of the ring - * @hop: Hop (DMA channel) associated with this ring - * @head: Head of the ring (write next descriptor here) - * @tail: Tail of the ring (complete next descriptor here) - * @descriptors: Allocated descriptors for this ring - * @queue: Queue holding frames to be transferred over this ring - * @in_flight: Queue holding frames that are currently in flight - * @work: Interrupt work structure - * @is_tx: Is the ring Tx or Rx - * @running: Is the ring running - * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise. - * @vector: MSI-X vector number the ring uses (only set if @irq is > 0) - * @flags: Ring specific flags - * @sof_mask: Bit mask used to detect start of frame PDF - * @eof_mask: Bit mask used to detect end of frame PDF - */ -struct tb_ring { - struct mutex lock; - struct tb_nhi *nhi; - int size; - int hop; - int head; - int tail; - struct ring_desc *descriptors; - dma_addr_t descriptors_dma; - struct list_head queue; - struct list_head in_flight; - struct work_struct work; - bool is_tx:1; - bool running:1; - int irq; - u8 vector; - unsigned int flags; - u16 sof_mask; - u16 eof_mask; -}; - -/* Leave ring interrupt enabled on suspend */ -#define RING_FLAG_NO_SUSPEND BIT(0) -/* Configure the ring to be in frame mode */ -#define RING_FLAG_FRAME BIT(1) -/* Enable end-to-end flow control */ -#define RING_FLAG_E2E BIT(2) - -struct ring_frame; -typedef void (*ring_cb)(struct tb_ring*, struct ring_frame*, bool canceled); - -/** - * struct ring_frame - for use with ring_rx/ring_tx - */ -struct ring_frame { - dma_addr_t buffer_phy; - ring_cb callback; - struct list_head list; - u32 size:12; /* TX: in, RX: out*/ - u32 flags:12; /* RX: out */ - u32 eof:4; /* TX:in, RX: out */ - u32 sof:4; /* TX:in, RX: out */ -}; - -#define TB_FRAME_SIZE 0x100 /* minimum size for ring_rx */ - -struct tb_ring *ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags); -struct tb_ring *ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags, u16 sof_mask, u16 eof_mask); -void ring_start(struct tb_ring *ring); -void ring_stop(struct tb_ring *ring); -void ring_free(struct tb_ring *ring); - -int __ring_enqueue(struct tb_ring *ring, struct ring_frame *frame); - -/** - * ring_rx() - enqueue a frame on an RX ring - * - * frame->buffer, frame->buffer_phy and frame->callback have to be set. The - * buffer must contain at least TB_FRAME_SIZE bytes. - * - * frame->callback will be invoked with frame->size, frame->flags, frame->eof, - * frame->sof set once the frame has been received. - * - * If ring_stop is called after the packet has been enqueued frame->callback - * will be called with canceled set to true. - * - * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise. - */ -static inline int ring_rx(struct tb_ring *ring, struct ring_frame *frame) -{ - WARN_ON(ring->is_tx); - return __ring_enqueue(ring, frame); -} - -/** - * ring_tx() - enqueue a frame on an TX ring - * - * frame->buffer, frame->buffer_phy, frame->callback, frame->size, frame->eof - * and frame->sof have to be set. - * - * frame->callback will be invoked with once the frame has been transmitted. - * - * If ring_stop is called after the packet has been enqueued frame->callback - * will be called with canceled set to true. - * - * Return: Returns ESHUTDOWN if ring_stop has been called. Zero otherwise. - */ -static inline int ring_tx(struct tb_ring *ring, struct ring_frame *frame) -{ - WARN_ON(!ring->is_tx); - return __ring_enqueue(ring, frame); -} +#include enum nhi_fw_mode { NHI_FW_SAFE_MODE, diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 18c0e3d5e85cb..9ddb83ad890f4 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -15,10 +15,12 @@ #define THUNDERBOLT_H_ #include +#include #include #include #include #include +#include enum tb_cfg_pkg_type { TB_CFG_PKG_READ = 1, @@ -397,4 +399,160 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) return tb_to_xdomain(svc->dev.parent); } +/** + * struct tb_nhi - thunderbolt native host interface + * @lock: Must be held during ring creation/destruction. Is acquired by + * interrupt_work when dispatching interrupts to individual rings. + * @pdev: Pointer to the PCI device + * @iobase: MMIO space of the NHI + * @tx_rings: All Tx rings available on this host controller + * @rx_rings: All Rx rings available on this host controller + * @msix_ida: Used to allocate MSI-X vectors for rings + * @going_away: The host controller device is about to disappear so when + * this flag is set, avoid touching the hardware anymore. + * @interrupt_work: Work scheduled to handle ring interrupt when no + * MSI-X is used. + * @hop_count: Number of rings (end point hops) supported by NHI. + */ +struct tb_nhi { + struct mutex lock; + struct pci_dev *pdev; + void __iomem *iobase; + struct tb_ring **tx_rings; + struct tb_ring **rx_rings; + struct ida msix_ida; + bool going_away; + struct work_struct interrupt_work; + u32 hop_count; +}; + +/** + * struct tb_ring - thunderbolt TX or RX ring associated with a NHI + * @lock: Lock serializing actions to this ring. Must be acquired after + * nhi->lock. + * @nhi: Pointer to the native host controller interface + * @size: Size of the ring + * @hop: Hop (DMA channel) associated with this ring + * @head: Head of the ring (write next descriptor here) + * @tail: Tail of the ring (complete next descriptor here) + * @descriptors: Allocated descriptors for this ring + * @queue: Queue holding frames to be transferred over this ring + * @in_flight: Queue holding frames that are currently in flight + * @work: Interrupt work structure + * @is_tx: Is the ring Tx or Rx + * @running: Is the ring running + * @irq: MSI-X irq number if the ring uses MSI-X. %0 otherwise. + * @vector: MSI-X vector number the ring uses (only set if @irq is > 0) + * @flags: Ring specific flags + * @sof_mask: Bit mask used to detect start of frame PDF + * @eof_mask: Bit mask used to detect end of frame PDF + */ +struct tb_ring { + struct mutex lock; + struct tb_nhi *nhi; + int size; + int hop; + int head; + int tail; + struct ring_desc *descriptors; + dma_addr_t descriptors_dma; + struct list_head queue; + struct list_head in_flight; + struct work_struct work; + bool is_tx:1; + bool running:1; + int irq; + u8 vector; + unsigned int flags; + u16 sof_mask; + u16 eof_mask; +}; + +/* Leave ring interrupt enabled on suspend */ +#define RING_FLAG_NO_SUSPEND BIT(0) +/* Configure the ring to be in frame mode */ +#define RING_FLAG_FRAME BIT(1) +/* Enable end-to-end flow control */ +#define RING_FLAG_E2E BIT(2) + +struct ring_frame; +typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled); + +/** + * struct ring_frame - For use with ring_rx/ring_tx + * @buffer_phy: DMA mapped address of the frame + * @callback: Callback called when the frame is finished + * @list: Frame is linked to a queue using this + * @size: Size of the frame in bytes (%0 means %4096) + * @flags: Flags for the frame (see &enum ring_desc_flags) + * @eof: End of frame protocol defined field + * @sof: Start of frame protocol defined field + */ +struct ring_frame { + dma_addr_t buffer_phy; + ring_cb callback; + struct list_head list; + u32 size:12; + u32 flags:12; + u32 eof:4; + u32 sof:4; +}; + +/* Minimum size for ring_rx */ +#define TB_FRAME_SIZE 0x100 + +struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags); +struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, + unsigned int flags, u16 sof_mask, + u16 eof_mask); +void tb_ring_start(struct tb_ring *ring); +void tb_ring_stop(struct tb_ring *ring); +void tb_ring_free(struct tb_ring *ring); + +int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame); + +/** + * tb_ring_rx() - enqueue a frame on an RX ring + * @ring: Ring to enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy and @frame->callback have to be set. The + * buffer must contain at least %TB_FRAME_SIZE bytes. + * + * @frame->callback will be invoked with @frame->size, @frame->flags, + * @frame->eof, @frame->sof set once the frame has been received. + * + * If ring_stop() is called after the packet has been enqueued + * @frame->callback will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + +/** + * tb_ring_tx() - enqueue a frame on an TX ring + * @ring: Ring the enqueue the frame + * @frame: Frame to enqueue + * + * @frame->buffer, @frame->buffer_phy, @frame->callback, @frame->size, + * @frame->eof and @frame->sof have to be set. + * + * @frame->callback will be invoked with once the frame has been transmitted. + * + * If ring_stop() is called after the packet has been enqueued @frame->callback + * will be called with canceled set to true. + * + * Return: Returns %-ESHUTDOWN if ring_stop has been called. Zero otherwise. + */ +static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame) +{ + WARN_ON(!ring->is_tx); + return __tb_ring_enqueue(ring, frame); +} + #endif /* THUNDERBOLT_H_ */ -- GitLab From 2a91ec63f8a11e70d4b958dd4df867fec0247179 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:38 +0300 Subject: [PATCH 0777/1507] thunderbolt: Move ring descriptor flags to thunderbolt.h A Thunderbolt service driver might need to check if there was an error with the descriptor when in frame mode. We also add two Rx specific error flags RING_DESC_CRC_ERROR and RING_DESC_BUFFER_OVERRUN. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi_regs.h | 7 ------- include/linux/thunderbolt.h | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index 491a4c0c18fc1..5ed6934e31e76 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -17,13 +17,6 @@ enum ring_flags { RING_FLAG_ENABLE = 1 << 31, }; -enum ring_desc_flags { - RING_DESC_ISOCH = 0x1, /* TX only? */ - RING_DESC_COMPLETED = 0x2, /* set by NHI */ - RING_DESC_POSTED = 0x4, /* always set this */ - RING_DESC_INTERRUPT = 0x8, /* request an interrupt on completion */ -}; - /** * struct ring_desc - TX/RX ring entry * diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 9ddb83ad890f4..e3b9af7be0adb 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -478,6 +478,24 @@ struct tb_ring { struct ring_frame; typedef void (*ring_cb)(struct tb_ring *, struct ring_frame *, bool canceled); +/** + * enum ring_desc_flags - Flags for DMA ring descriptor + * %RING_DESC_ISOCH: Enable isonchronous DMA (Tx only) + * %RING_DESC_CRC_ERROR: In frame mode CRC check failed for the frame (Rx only) + * %RING_DESC_COMPLETED: Descriptor completed (set by NHI) + * %RING_DESC_POSTED: Always set this + * %RING_DESC_BUFFER_OVERRUN: RX buffer overrun + * %RING_DESC_INTERRUPT: Request an interrupt on completion + */ +enum ring_desc_flags { + RING_DESC_ISOCH = 0x1, + RING_DESC_CRC_ERROR = 0x1, + RING_DESC_COMPLETED = 0x2, + RING_DESC_POSTED = 0x4, + RING_DESC_BUFFER_OVERRUN = 0x04, + RING_DESC_INTERRUPT = 0x8, +}; + /** * struct ring_frame - For use with ring_rx/ring_tx * @buffer_phy: DMA mapped address of the frame -- GitLab From 22b7de1000e66d739c431d6be4e7e97c69fa7c98 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:39 +0300 Subject: [PATCH 0778/1507] thunderbolt: Use spinlock in ring serialization This makes it possible to enqueue frames also from atomic context which is needed for example, when networking packets are sent over a Thunderbolt cable. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi.c | 26 ++++++++++++++------------ include/linux/thunderbolt.h | 2 +- 2 files changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index e0a47f7581cbb..7d1891ec3c47f 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -212,8 +212,10 @@ static void ring_work(struct work_struct *work) struct tb_ring *ring = container_of(work, typeof(*ring), work); struct ring_frame *frame; bool canceled = false; + unsigned long flags; LIST_HEAD(done); - mutex_lock(&ring->lock); + + spin_lock_irqsave(&ring->lock, flags); if (!ring->running) { /* Move all frames to done and mark them as canceled. */ @@ -241,7 +243,8 @@ static void ring_work(struct work_struct *work) ring_write_descriptors(ring); invoke_callback: - mutex_unlock(&ring->lock); /* allow callbacks to schedule new work */ + /* allow callbacks to schedule new work */ + spin_unlock_irqrestore(&ring->lock, flags); while (!list_empty(&done)) { frame = list_first_entry(&done, typeof(*frame), list); /* @@ -255,15 +258,17 @@ static void ring_work(struct work_struct *work) int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame) { + unsigned long flags; int ret = 0; - mutex_lock(&ring->lock); + + spin_lock_irqsave(&ring->lock, flags); if (ring->running) { list_add_tail(&frame->list, &ring->queue); ring_write_descriptors(ring); } else { ret = -ESHUTDOWN; } - mutex_unlock(&ring->lock); + spin_unlock_irqrestore(&ring->lock, flags); return ret; } EXPORT_SYMBOL_GPL(__tb_ring_enqueue); @@ -338,7 +343,7 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, if (!ring) goto err; - mutex_init(&ring->lock); + spin_lock_init(&ring->lock); INIT_LIST_HEAD(&ring->queue); INIT_LIST_HEAD(&ring->in_flight); INIT_WORK(&ring->work, ring_work); @@ -371,8 +376,6 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, return ring; err: - if (ring) - mutex_destroy(&ring->lock); kfree(ring); mutex_unlock(&nhi->lock); return NULL; @@ -419,7 +422,7 @@ void tb_ring_start(struct tb_ring *ring) u32 flags; mutex_lock(&ring->nhi->lock); - mutex_lock(&ring->lock); + spin_lock_irq(&ring->lock); if (ring->nhi->going_away) goto err; if (ring->running) { @@ -466,7 +469,7 @@ void tb_ring_start(struct tb_ring *ring) ring_interrupt_active(ring, true); ring->running = true; err: - mutex_unlock(&ring->lock); + spin_unlock_irq(&ring->lock); mutex_unlock(&ring->nhi->lock); } EXPORT_SYMBOL_GPL(tb_ring_start); @@ -487,7 +490,7 @@ EXPORT_SYMBOL_GPL(tb_ring_start); void tb_ring_stop(struct tb_ring *ring) { mutex_lock(&ring->nhi->lock); - mutex_lock(&ring->lock); + spin_lock_irq(&ring->lock); dev_info(&ring->nhi->pdev->dev, "stopping %s %d\n", RING_TYPE(ring), ring->hop); if (ring->nhi->going_away) @@ -508,7 +511,7 @@ void tb_ring_stop(struct tb_ring *ring) ring->running = false; err: - mutex_unlock(&ring->lock); + spin_unlock_irq(&ring->lock); mutex_unlock(&ring->nhi->lock); /* @@ -568,7 +571,6 @@ void tb_ring_free(struct tb_ring *ring) * to finish before freeing the ring. */ flush_work(&ring->work); - mutex_destroy(&ring->lock); kfree(ring); } EXPORT_SYMBOL_GPL(tb_ring_free); diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index e3b9af7be0adb..cf9e42db780fb 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -448,7 +448,7 @@ struct tb_nhi { * @eof_mask: Bit mask used to detect end of frame PDF */ struct tb_ring { - struct mutex lock; + spinlock_t lock; struct tb_nhi *nhi; int size; int hop; -- GitLab From 59120e06101db72442acf4c8b364a0c76d8faa68 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:40 +0300 Subject: [PATCH 0779/1507] thunderbolt: Use spinlock in NHI serialization This is needed because ring polling functionality can be called from atomic contexts when networking and other high-speed traffic is transferred over a Thunderbolt cable. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi.c | 75 ++++++++++++++++++++----------------- include/linux/thunderbolt.h | 2 +- 2 files changed, 42 insertions(+), 35 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 7d1891ec3c47f..0b3c0640048b8 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -327,21 +327,9 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, if (transmit && hop == RING_E2E_UNUSED_HOPID) return NULL; - mutex_lock(&nhi->lock); - if (hop >= nhi->hop_count) { - dev_WARN(&nhi->pdev->dev, "invalid hop: %d\n", hop); - goto err; - } - if (transmit && nhi->tx_rings[hop]) { - dev_WARN(&nhi->pdev->dev, "TX hop %d already allocated\n", hop); - goto err; - } else if (!transmit && nhi->rx_rings[hop]) { - dev_WARN(&nhi->pdev->dev, "RX hop %d already allocated\n", hop); - goto err; - } ring = kzalloc(sizeof(*ring), GFP_KERNEL); if (!ring) - goto err; + return NULL; spin_lock_init(&ring->lock); INIT_LIST_HEAD(&ring->queue); @@ -359,25 +347,45 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, ring->tail = 0; ring->running = false; - if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND)) - goto err; - ring->descriptors = dma_alloc_coherent(&ring->nhi->pdev->dev, size * sizeof(*ring->descriptors), &ring->descriptors_dma, GFP_KERNEL | __GFP_ZERO); if (!ring->descriptors) - goto err; + goto err_free_ring; + if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND)) + goto err_free_descs; + + spin_lock_irq(&nhi->lock); + if (hop >= nhi->hop_count) { + dev_WARN(&nhi->pdev->dev, "invalid hop: %d\n", hop); + goto err_release_msix; + } + if (transmit && nhi->tx_rings[hop]) { + dev_WARN(&nhi->pdev->dev, "TX hop %d already allocated\n", hop); + goto err_release_msix; + } else if (!transmit && nhi->rx_rings[hop]) { + dev_WARN(&nhi->pdev->dev, "RX hop %d already allocated\n", hop); + goto err_release_msix; + } if (transmit) nhi->tx_rings[hop] = ring; else nhi->rx_rings[hop] = ring; - mutex_unlock(&nhi->lock); + spin_unlock_irq(&nhi->lock); + return ring; -err: +err_release_msix: + spin_unlock_irq(&nhi->lock); + ring_release_msix(ring); +err_free_descs: + dma_free_coherent(&ring->nhi->pdev->dev, + ring->size * sizeof(*ring->descriptors), + ring->descriptors, ring->descriptors_dma); +err_free_ring: kfree(ring); - mutex_unlock(&nhi->lock); + return NULL; } @@ -421,8 +429,8 @@ void tb_ring_start(struct tb_ring *ring) u16 frame_size; u32 flags; - mutex_lock(&ring->nhi->lock); - spin_lock_irq(&ring->lock); + spin_lock_irq(&ring->nhi->lock); + spin_lock(&ring->lock); if (ring->nhi->going_away) goto err; if (ring->running) { @@ -469,8 +477,8 @@ void tb_ring_start(struct tb_ring *ring) ring_interrupt_active(ring, true); ring->running = true; err: - spin_unlock_irq(&ring->lock); - mutex_unlock(&ring->nhi->lock); + spin_unlock(&ring->lock); + spin_unlock_irq(&ring->nhi->lock); } EXPORT_SYMBOL_GPL(tb_ring_start); @@ -489,8 +497,8 @@ EXPORT_SYMBOL_GPL(tb_ring_start); */ void tb_ring_stop(struct tb_ring *ring) { - mutex_lock(&ring->nhi->lock); - spin_lock_irq(&ring->lock); + spin_lock_irq(&ring->nhi->lock); + spin_lock(&ring->lock); dev_info(&ring->nhi->pdev->dev, "stopping %s %d\n", RING_TYPE(ring), ring->hop); if (ring->nhi->going_away) @@ -511,8 +519,8 @@ void tb_ring_stop(struct tb_ring *ring) ring->running = false; err: - spin_unlock_irq(&ring->lock); - mutex_unlock(&ring->nhi->lock); + spin_unlock(&ring->lock); + spin_unlock_irq(&ring->nhi->lock); /* * schedule ring->work to invoke callbacks on all remaining frames. @@ -534,7 +542,7 @@ EXPORT_SYMBOL_GPL(tb_ring_stop); */ void tb_ring_free(struct tb_ring *ring) { - mutex_lock(&ring->nhi->lock); + spin_lock_irq(&ring->nhi->lock); /* * Dissociate the ring from the NHI. This also ensures that * nhi_interrupt_work cannot reschedule ring->work. @@ -564,7 +572,7 @@ void tb_ring_free(struct tb_ring *ring) RING_TYPE(ring), ring->hop); - mutex_unlock(&ring->nhi->lock); + spin_unlock_irq(&ring->nhi->lock); /** * ring->work can no longer be scheduled (it is scheduled only * by nhi_interrupt_work, ring_stop and ring_msix). Wait for it @@ -639,7 +647,7 @@ static void nhi_interrupt_work(struct work_struct *work) int type = 0; /* current interrupt type 0: TX, 1: RX, 2: RX overflow */ struct tb_ring *ring; - mutex_lock(&nhi->lock); + spin_lock_irq(&nhi->lock); /* * Starting at REG_RING_NOTIFY_BASE there are three status bitfields @@ -677,7 +685,7 @@ static void nhi_interrupt_work(struct work_struct *work) /* we do not check ring->running, this is done in ring->work */ schedule_work(&ring->work); } - mutex_unlock(&nhi->lock); + spin_unlock_irq(&nhi->lock); } static irqreturn_t nhi_msi(int irq, void *data) @@ -767,7 +775,6 @@ static void nhi_shutdown(struct tb_nhi *nhi) devm_free_irq(&nhi->pdev->dev, nhi->pdev->irq, nhi); flush_work(&nhi->interrupt_work); } - mutex_destroy(&nhi->lock); ida_destroy(&nhi->msix_ida); } @@ -856,7 +863,7 @@ static int nhi_probe(struct pci_dev *pdev, const struct pci_device_id *id) return res; } - mutex_init(&nhi->lock); + spin_lock_init(&nhi->lock); pci_set_master(pdev); diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index cf9e42db780fb..d59e3f9a35c47 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -415,7 +415,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @hop_count: Number of rings (end point hops) supported by NHI. */ struct tb_nhi { - struct mutex lock; + spinlock_t lock; struct pci_dev *pdev; void __iomem *iobase; struct tb_ring **tx_rings; -- GitLab From 4ffe722eefcb07c76701f03e0d759fbaecedf79f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:41 +0300 Subject: [PATCH 0780/1507] thunderbolt: Add polling mode for rings In order to support things like networking over Thunderbolt cable, there needs to be a way to switch the ring to a mode where it can be polled with the interrupt masked. We implement such mode so that the caller can allocate a ring by passing pointer to a function that is then called when an interrupt is triggered. Completed frames can be fetched using tb_ring_poll() and the interrupt can be re-enabled when the caller is finished with polling by using tb_ring_poll_complete(). Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/ctl.c | 2 +- drivers/thunderbolt/nhi.c | 126 +++++++++++++++++++++++++++++++++--- include/linux/thunderbolt.h | 23 +++++-- 3 files changed, 134 insertions(+), 17 deletions(-) diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index dd10789e1dbb3..d079dbba2c036 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -619,7 +619,7 @@ struct tb_ctl *tb_ctl_alloc(struct tb_nhi *nhi, event_cb cb, void *cb_data) goto err; ctl->rx = tb_ring_alloc_rx(nhi, 0, 10, RING_FLAG_NO_SUSPEND, 0xffff, - 0xffff); + 0xffff, NULL, NULL); if (!ctl->rx) goto err; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 0b3c0640048b8..af0a80ddf5948 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -252,7 +252,8 @@ static void ring_work(struct work_struct *work) * Do not hold on to it. */ list_del_init(&frame->list); - frame->callback(ring, frame, canceled); + if (frame->callback) + frame->callback(ring, frame, canceled); } } @@ -273,11 +274,106 @@ int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame) } EXPORT_SYMBOL_GPL(__tb_ring_enqueue); +/** + * tb_ring_poll() - Poll one completed frame from the ring + * @ring: Ring to poll + * + * This function can be called when @start_poll callback of the @ring + * has been called. It will read one completed frame from the ring and + * return it to the caller. Returns %NULL if there is no more completed + * frames. + */ +struct ring_frame *tb_ring_poll(struct tb_ring *ring) +{ + struct ring_frame *frame = NULL; + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + if (!ring->running) + goto unlock; + if (ring_empty(ring)) + goto unlock; + + if (ring->descriptors[ring->tail].flags & RING_DESC_COMPLETED) { + frame = list_first_entry(&ring->in_flight, typeof(*frame), + list); + list_del_init(&frame->list); + + if (!ring->is_tx) { + frame->size = ring->descriptors[ring->tail].length; + frame->eof = ring->descriptors[ring->tail].eof; + frame->sof = ring->descriptors[ring->tail].sof; + frame->flags = ring->descriptors[ring->tail].flags; + } + + ring->tail = (ring->tail + 1) % ring->size; + } + +unlock: + spin_unlock_irqrestore(&ring->lock, flags); + return frame; +} +EXPORT_SYMBOL_GPL(tb_ring_poll); + +static void __ring_interrupt_mask(struct tb_ring *ring, bool mask) +{ + int idx = ring_interrupt_index(ring); + int reg = REG_RING_INTERRUPT_BASE + idx / 32 * 4; + int bit = idx % 32; + u32 val; + + val = ioread32(ring->nhi->iobase + reg); + if (mask) + val &= ~BIT(bit); + else + val |= BIT(bit); + iowrite32(val, ring->nhi->iobase + reg); +} + +/* Both @nhi->lock and @ring->lock should be held */ +static void __ring_interrupt(struct tb_ring *ring) +{ + if (!ring->running) + return; + + if (ring->start_poll) { + __ring_interrupt_mask(ring, false); + ring->start_poll(ring->poll_data); + } else { + schedule_work(&ring->work); + } +} + +/** + * tb_ring_poll_complete() - Re-start interrupt for the ring + * @ring: Ring to re-start the interrupt + * + * This will re-start (unmask) the ring interrupt once the user is done + * with polling. + */ +void tb_ring_poll_complete(struct tb_ring *ring) +{ + unsigned long flags; + + spin_lock_irqsave(&ring->nhi->lock, flags); + spin_lock(&ring->lock); + if (ring->start_poll) + __ring_interrupt_mask(ring, false); + spin_unlock(&ring->lock); + spin_unlock_irqrestore(&ring->nhi->lock, flags); +} +EXPORT_SYMBOL_GPL(tb_ring_poll_complete); + static irqreturn_t ring_msix(int irq, void *data) { struct tb_ring *ring = data; - schedule_work(&ring->work); + spin_lock(&ring->nhi->lock); + spin_lock(&ring->lock); + __ring_interrupt(ring); + spin_unlock(&ring->lock); + spin_unlock(&ring->nhi->lock); + return IRQ_HANDLED; } @@ -317,7 +413,9 @@ static void ring_release_msix(struct tb_ring *ring) static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, bool transmit, unsigned int flags, - u16 sof_mask, u16 eof_mask) + u16 sof_mask, u16 eof_mask, + void (*start_poll)(void *), + void *poll_data) { struct tb_ring *ring = NULL; dev_info(&nhi->pdev->dev, "allocating %s ring %d of size %d\n", @@ -346,6 +444,8 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, ring->head = 0; ring->tail = 0; ring->running = false; + ring->start_poll = start_poll; + ring->poll_data = poll_data; ring->descriptors = dma_alloc_coherent(&ring->nhi->pdev->dev, size * sizeof(*ring->descriptors), @@ -399,7 +499,7 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, unsigned int flags) { - return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0); + return tb_ring_alloc(nhi, hop, size, true, flags, 0, 0, NULL, NULL); } EXPORT_SYMBOL_GPL(tb_ring_alloc_tx); @@ -411,11 +511,17 @@ EXPORT_SYMBOL_GPL(tb_ring_alloc_tx); * @flags: Flags for the ring * @sof_mask: Mask of PDF values that start a frame * @eof_mask: Mask of PDF values that end a frame + * @start_poll: If not %NULL the ring will call this function when an + * interrupt is triggered and masked, instead of callback + * in each Rx frame. + * @poll_data: Optional data passed to @start_poll */ struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags, u16 sof_mask, u16 eof_mask) + unsigned int flags, u16 sof_mask, u16 eof_mask, + void (*start_poll)(void *), void *poll_data) { - return tb_ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask); + return tb_ring_alloc(nhi, hop, size, false, flags, sof_mask, eof_mask, + start_poll, poll_data); } EXPORT_SYMBOL_GPL(tb_ring_alloc_rx); @@ -556,6 +662,7 @@ void tb_ring_free(struct tb_ring *ring) dev_WARN(&ring->nhi->pdev->dev, "%s %d still running\n", RING_TYPE(ring), ring->hop); } + spin_unlock_irq(&ring->nhi->lock); ring_release_msix(ring); @@ -572,7 +679,6 @@ void tb_ring_free(struct tb_ring *ring) RING_TYPE(ring), ring->hop); - spin_unlock_irq(&ring->nhi->lock); /** * ring->work can no longer be scheduled (it is scheduled only * by nhi_interrupt_work, ring_stop and ring_msix). Wait for it @@ -682,8 +788,10 @@ static void nhi_interrupt_work(struct work_struct *work) hop); continue; } - /* we do not check ring->running, this is done in ring->work */ - schedule_work(&ring->work); + + spin_lock(&ring->lock); + __ring_interrupt(ring); + spin_unlock(&ring->lock); } spin_unlock_irq(&nhi->lock); } diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index d59e3f9a35c47..36925e3aec7c5 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -446,6 +446,9 @@ struct tb_nhi { * @flags: Ring specific flags * @sof_mask: Bit mask used to detect start of frame PDF * @eof_mask: Bit mask used to detect end of frame PDF + * @start_poll: Called when ring interrupt is triggered to start + * polling. Passing %NULL keeps the ring in interrupt mode. + * @poll_data: Data passed to @start_poll */ struct tb_ring { spinlock_t lock; @@ -466,6 +469,8 @@ struct tb_ring { unsigned int flags; u16 sof_mask; u16 eof_mask; + void (*start_poll)(void *data); + void *poll_data; }; /* Leave ring interrupt enabled on suspend */ @@ -499,7 +504,7 @@ enum ring_desc_flags { /** * struct ring_frame - For use with ring_rx/ring_tx * @buffer_phy: DMA mapped address of the frame - * @callback: Callback called when the frame is finished + * @callback: Callback called when the frame is finished (optional) * @list: Frame is linked to a queue using this * @size: Size of the frame in bytes (%0 means %4096) * @flags: Flags for the frame (see &enum ring_desc_flags) @@ -522,8 +527,8 @@ struct ring_frame { struct tb_ring *tb_ring_alloc_tx(struct tb_nhi *nhi, int hop, int size, unsigned int flags); struct tb_ring *tb_ring_alloc_rx(struct tb_nhi *nhi, int hop, int size, - unsigned int flags, u16 sof_mask, - u16 eof_mask); + unsigned int flags, u16 sof_mask, u16 eof_mask, + void (*start_poll)(void *), void *poll_data); void tb_ring_start(struct tb_ring *ring); void tb_ring_stop(struct tb_ring *ring); void tb_ring_free(struct tb_ring *ring); @@ -535,8 +540,8 @@ int __tb_ring_enqueue(struct tb_ring *ring, struct ring_frame *frame); * @ring: Ring to enqueue the frame * @frame: Frame to enqueue * - * @frame->buffer, @frame->buffer_phy and @frame->callback have to be set. The - * buffer must contain at least %TB_FRAME_SIZE bytes. + * @frame->buffer, @frame->buffer_phy have to be set. The buffer must + * contain at least %TB_FRAME_SIZE bytes. * * @frame->callback will be invoked with @frame->size, @frame->flags, * @frame->eof, @frame->sof set once the frame has been received. @@ -557,8 +562,8 @@ static inline int tb_ring_rx(struct tb_ring *ring, struct ring_frame *frame) * @ring: Ring the enqueue the frame * @frame: Frame to enqueue * - * @frame->buffer, @frame->buffer_phy, @frame->callback, @frame->size, - * @frame->eof and @frame->sof have to be set. + * @frame->buffer, @frame->buffer_phy, @frame->size, @frame->eof and + * @frame->sof have to be set. * * @frame->callback will be invoked with once the frame has been transmitted. * @@ -573,4 +578,8 @@ static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame) return __tb_ring_enqueue(ring, frame); } +/* Used only when the ring is in polling mode */ +struct ring_frame *tb_ring_poll(struct tb_ring *ring); +void tb_ring_poll_complete(struct tb_ring *ring); + #endif /* THUNDERBOLT_H_ */ -- GitLab From 3304559e353f098d7e0ed5ca981e26c406513e12 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:42 +0300 Subject: [PATCH 0781/1507] thunderbolt: Add function to retrieve DMA device for the ring This is needed when Thunderbolt service drivers need to DMA map memory before it is passed down to the ring. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/thunderbolt.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 36925e3aec7c5..7b69853188b1a 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -582,4 +583,16 @@ static inline int tb_ring_tx(struct tb_ring *ring, struct ring_frame *frame) struct ring_frame *tb_ring_poll(struct tb_ring *ring); void tb_ring_poll_complete(struct tb_ring *ring); +/** + * tb_ring_dma_device() - Return device used for DMA mapping + * @ring: Ring whose DMA device is retrieved + * + * Use this function when you are mapping DMA for buffers that are + * passed to the ring for sending/receiving. + */ +static inline struct device *tb_ring_dma_device(struct tb_ring *ring) +{ + return &ring->nhi->pdev->dev; +} + #endif /* THUNDERBOLT_H_ */ -- GitLab From 9a01c7c26cf7cbd1f58d06319e798833e85ff550 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:43 +0300 Subject: [PATCH 0782/1507] thunderbolt: Allocate ring HopID automatically if requested Thunderbolt services should not care which HopID (ring) they use for sending and receiving packets over the high-speed DMA path, so make tb_ring_alloc_rx() and tb_ring_alloc_tx() accept negative HopID. This means that the NHI will allocate next available HopID for the caller automatically. These HopIDs will be allocated from the range which is not reserved for the Thunderbolt protocol (8 .. hop_count - 1). The allocated HopID can be retrieved from ring->hop field after the ring has been allocated successfully if needed. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi.c | 78 ++++++++++++++++++++++++++++++--------- 1 file changed, 60 insertions(+), 18 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index af0a80ddf5948..0e79eebfcbb7a 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -26,6 +26,8 @@ * use this ring for anything else. */ #define RING_E2E_UNUSED_HOPID 2 +/* HopIDs 0-7 are reserved by the Thunderbolt protocol */ +#define RING_FIRST_USABLE_HOPID 8 /* * Minimal number of vectors when we use MSI-X. Two for control channel @@ -411,6 +413,62 @@ static void ring_release_msix(struct tb_ring *ring) ring->irq = 0; } +static int nhi_alloc_hop(struct tb_nhi *nhi, struct tb_ring *ring) +{ + int ret = 0; + + spin_lock_irq(&nhi->lock); + + if (ring->hop < 0) { + unsigned int i; + + /* + * Automatically allocate HopID from the non-reserved + * range 8 .. hop_count - 1. + */ + for (i = RING_FIRST_USABLE_HOPID; i < nhi->hop_count; i++) { + if (ring->is_tx) { + if (!nhi->tx_rings[i]) { + ring->hop = i; + break; + } + } else { + if (!nhi->rx_rings[i]) { + ring->hop = i; + break; + } + } + } + } + + if (ring->hop < 0 || ring->hop >= nhi->hop_count) { + dev_warn(&nhi->pdev->dev, "invalid hop: %d\n", ring->hop); + ret = -EINVAL; + goto err_unlock; + } + if (ring->is_tx && nhi->tx_rings[ring->hop]) { + dev_warn(&nhi->pdev->dev, "TX hop %d already allocated\n", + ring->hop); + ret = -EBUSY; + goto err_unlock; + } else if (!ring->is_tx && nhi->rx_rings[ring->hop]) { + dev_warn(&nhi->pdev->dev, "RX hop %d already allocated\n", + ring->hop); + ret = -EBUSY; + goto err_unlock; + } + + if (ring->is_tx) + nhi->tx_rings[ring->hop] = ring; + else + nhi->rx_rings[ring->hop] = ring; + +err_unlock: + spin_unlock_irq(&nhi->lock); + + return ret; +} + static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, bool transmit, unsigned int flags, u16 sof_mask, u16 eof_mask, @@ -456,28 +514,12 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size, if (ring_request_msix(ring, flags & RING_FLAG_NO_SUSPEND)) goto err_free_descs; - spin_lock_irq(&nhi->lock); - if (hop >= nhi->hop_count) { - dev_WARN(&nhi->pdev->dev, "invalid hop: %d\n", hop); + if (nhi_alloc_hop(nhi, ring)) goto err_release_msix; - } - if (transmit && nhi->tx_rings[hop]) { - dev_WARN(&nhi->pdev->dev, "TX hop %d already allocated\n", hop); - goto err_release_msix; - } else if (!transmit && nhi->rx_rings[hop]) { - dev_WARN(&nhi->pdev->dev, "RX hop %d already allocated\n", hop); - goto err_release_msix; - } - if (transmit) - nhi->tx_rings[hop] = ring; - else - nhi->rx_rings[hop] = ring; - spin_unlock_irq(&nhi->lock); return ring; err_release_msix: - spin_unlock_irq(&nhi->lock); ring_release_msix(ring); err_free_descs: dma_free_coherent(&ring->nhi->pdev->dev, @@ -506,7 +548,7 @@ EXPORT_SYMBOL_GPL(tb_ring_alloc_tx); /** * tb_ring_alloc_rx() - Allocate DMA ring for receive * @nhi: Pointer to the NHI the ring is to be allocated - * @hop: HopID (ring) to allocate + * @hop: HopID (ring) to allocate. Pass %-1 for automatic allocation. * @size: Number of entries in the ring * @flags: Flags for the ring * @sof_mask: Mask of PDF values that start a frame -- GitLab From 467cd25bf2aec14c2e2990512248b72f46f94c53 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:44 +0300 Subject: [PATCH 0783/1507] MAINTAINERS: Add thunderbolt.h to the Thunderbolt driver entry The new API header (include/linux/thunderbolt.h) is maintained by the Thunderbolt driver maintainers. Signed-off-by: Mika Westerberg Reviewed-by: Michael Jamet Reviewed-by: Yehezkel Bernat Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6671f375f7fcd..c1c90d962012a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13278,6 +13278,7 @@ M: Mika Westerberg M: Yehezkel Bernat S: Maintained F: drivers/thunderbolt/ +F: include/linux/thunderbolt.h THUNDERX GPIO DRIVER M: David Daney -- GitLab From e69b6c02b4c3b8d03be7136f90dd9551ad5a5a5e Mon Sep 17 00:00:00 2001 From: Amir Levy Date: Mon, 2 Oct 2017 13:38:45 +0300 Subject: [PATCH 0784/1507] net: Add support for networking over Thunderbolt cable ThunderboltIP is a protocol created by Apple to tunnel IP/ethernet traffic over a Thunderbolt cable. The protocol consists of configuration phase where each side sends ThunderboltIP login packets (the protocol is determined by UUID in the XDomain packet header) over the configuration channel. Once both sides get positive acknowledgment to their login packet, they configure high-speed DMA path accordingly. This DMA path is then used to transmit and receive networking traffic. This patch creates a virtual ethernet interface the host software can use in the same way as any other networking interface. Once the interface is brought up successfully network packets get tunneled over the Thunderbolt cable to the remote host and back. The connection is terminated by sending a ThunderboltIP logout packet over the configuration channel. We do this when the network interface is brought down by user or the driver is unloaded. Signed-off-by: Amir Levy Signed-off-by: Michael Jamet Signed-off-by: Mika Westerberg Reviewed-by: Yehezkel Bernat Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- Documentation/admin-guide/thunderbolt.rst | 24 + drivers/net/Kconfig | 12 + drivers/net/Makefile | 3 + drivers/net/thunderbolt.c | 1362 +++++++++++++++++++++ 4 files changed, 1401 insertions(+) create mode 100644 drivers/net/thunderbolt.c diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst index 6a4cd1f159ca7..5c62d11d77e86 100644 --- a/Documentation/admin-guide/thunderbolt.rst +++ b/Documentation/admin-guide/thunderbolt.rst @@ -197,3 +197,27 @@ information is missing. To recover from this mode, one needs to flash a valid NVM image to the host host controller in the same way it is done in the previous chapter. + +Networking over Thunderbolt cable +--------------------------------- +Thunderbolt technology allows software communication across two hosts +connected by a Thunderbolt cable. + +It is possible to tunnel any kind of traffic over Thunderbolt link but +currently we only support Apple ThunderboltIP protocol. + +If the other host is running Windows or macOS only thing you need to +do is to connect Thunderbolt cable between the two hosts, the +``thunderbolt-net`` is loaded automatically. If the other host is also +Linux you should load ``thunderbolt-net`` manually on one host (it does +not matter which one):: + + # modprobe thunderbolt-net + +This triggers module load on the other host automatically. If the driver +is built-in to the kernel image, there is no need to do anything. + +The driver will create one virtual ethernet interface per Thunderbolt +port which are named like ``thunderbolt0`` and so on. From this point +you can either use standard userspace tools like ``ifconfig`` to +configure the interface or let your GUI to handle it automatically. diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index aba0d652095b0..0936da592e12a 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -483,6 +483,18 @@ config FUJITSU_ES This driver provides support for Extended Socket network device on Extended Partitioning of FUJITSU PRIMEQUEST 2000 E2 series. +config THUNDERBOLT_NET + tristate "Networking over Thunderbolt cable" + depends on THUNDERBOLT && INET + help + Select this if you want to create network between two + computers over a Thunderbolt cable. The driver supports Apple + ThunderboltIP protocol and allows communication with any host + supporting the same protocol including Windows and macOS. + + To compile this driver a module, choose M here. The module will be + called thunderbolt-net. + source "drivers/net/hyperv/Kconfig" endif # NETDEVICES diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 8dff900085d6e..7c8f4dd3a7c5c 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -74,3 +74,6 @@ obj-$(CONFIG_HYPERV_NET) += hyperv/ obj-$(CONFIG_NTB_NETDEV) += ntb_netdev.o obj-$(CONFIG_FUJITSU_ES) += fjes/ + +thunderbolt-net-y += thunderbolt.o +obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c new file mode 100644 index 0000000000000..1a7bc0bf45980 --- /dev/null +++ b/drivers/net/thunderbolt.c @@ -0,0 +1,1362 @@ +/* + * Networking over Thunderbolt cable using Apple ThunderboltIP protocol + * + * Copyright (C) 2017, Intel Corporation + * Authors: Amir Levy + * Michael Jamet + * Mika Westerberg + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* Protocol timeouts in ms */ +#define TBNET_LOGIN_DELAY 4500 +#define TBNET_LOGIN_TIMEOUT 500 +#define TBNET_LOGOUT_TIMEOUT 100 + +#define TBNET_RING_SIZE 256 +#define TBNET_LOCAL_PATH 0xf +#define TBNET_LOGIN_RETRIES 60 +#define TBNET_LOGOUT_RETRIES 5 +#define TBNET_MATCH_FRAGS_ID BIT(1) +#define TBNET_MAX_MTU SZ_64K +#define TBNET_FRAME_SIZE SZ_4K +#define TBNET_MAX_PAYLOAD_SIZE \ + (TBNET_FRAME_SIZE - sizeof(struct thunderbolt_ip_frame_header)) +/* Rx packets need to hold space for skb_shared_info */ +#define TBNET_RX_MAX_SIZE \ + (TBNET_FRAME_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define TBNET_RX_PAGE_ORDER get_order(TBNET_RX_MAX_SIZE) +#define TBNET_RX_PAGE_SIZE (PAGE_SIZE << TBNET_RX_PAGE_ORDER) + +#define TBNET_L0_PORT_NUM(route) ((route) & GENMASK(5, 0)) + +/** + * struct thunderbolt_ip_frame_header - Header for each Thunderbolt frame + * @frame_size: size of the data with the frame + * @frame_index: running index on the frames + * @frame_id: ID of the frame to match frames to specific packet + * @frame_count: how many frames assembles a full packet + * + * Each data frame passed to the high-speed DMA ring has this header. If + * the XDomain network directory announces that %TBNET_MATCH_FRAGS_ID is + * supported then @frame_id is filled, otherwise it stays %0. + */ +struct thunderbolt_ip_frame_header { + u32 frame_size; + u16 frame_index; + u16 frame_id; + u32 frame_count; +}; + +enum thunderbolt_ip_frame_pdf { + TBIP_PDF_FRAME_START = 1, + TBIP_PDF_FRAME_END, +}; + +enum thunderbolt_ip_type { + TBIP_LOGIN, + TBIP_LOGIN_RESPONSE, + TBIP_LOGOUT, + TBIP_STATUS, +}; + +struct thunderbolt_ip_header { + u32 route_hi; + u32 route_lo; + u32 length_sn; + uuid_t uuid; + uuid_t initiator_uuid; + uuid_t target_uuid; + u32 type; + u32 command_id; +}; + +#define TBIP_HDR_LENGTH_MASK GENMASK(5, 0) +#define TBIP_HDR_SN_MASK GENMASK(28, 27) +#define TBIP_HDR_SN_SHIFT 27 + +struct thunderbolt_ip_login { + struct thunderbolt_ip_header hdr; + u32 proto_version; + u32 transmit_path; + u32 reserved[4]; +}; + +#define TBIP_LOGIN_PROTO_VERSION 1 + +struct thunderbolt_ip_login_response { + struct thunderbolt_ip_header hdr; + u32 status; + u32 receiver_mac[2]; + u32 receiver_mac_len; + u32 reserved[4]; +}; + +struct thunderbolt_ip_logout { + struct thunderbolt_ip_header hdr; +}; + +struct thunderbolt_ip_status { + struct thunderbolt_ip_header hdr; + u32 status; +}; + +struct tbnet_stats { + u64 tx_packets; + u64 rx_packets; + u64 tx_bytes; + u64 rx_bytes; + u64 rx_errors; + u64 tx_errors; + u64 rx_length_errors; + u64 rx_over_errors; + u64 rx_crc_errors; + u64 rx_missed_errors; +}; + +struct tbnet_frame { + struct net_device *dev; + struct page *page; + struct ring_frame frame; +}; + +struct tbnet_ring { + struct tbnet_frame frames[TBNET_RING_SIZE]; + unsigned int cons; + unsigned int prod; + struct tb_ring *ring; +}; + +/** + * struct tbnet - ThunderboltIP network driver private data + * @svc: XDomain service the driver is bound to + * @xd: XDomain the service blongs to + * @handler: ThunderboltIP configuration protocol handler + * @dev: Networking device + * @napi: NAPI structure for Rx polling + * @stats: Network statistics + * @skb: Network packet that is currently processed on Rx path + * @command_id: ID used for next configuration protocol packet + * @login_sent: ThunderboltIP login message successfully sent + * @login_received: ThunderboltIP login message received from the remote + * host + * @transmit_path: HopID the other end needs to use building the + * opposite side path. + * @connection_lock: Lock serializing access to @login_sent, + * @login_received and @transmit_path. + * @login_retries: Number of login retries currently done + * @login_work: Worker to send ThunderboltIP login packets + * @connected_work: Worker that finalizes the ThunderboltIP connection + * setup and enables DMA paths for high speed data + * transfers + * @rx_hdr: Copy of the currently processed Rx frame. Used when a + * network packet consists of multiple Thunderbolt frames. + * In host byte order. + * @rx_ring: Software ring holding Rx frames + * @frame_id: Frame ID use for next Tx packet + * (if %TBNET_MATCH_FRAGS_ID is supported in both ends) + * @tx_ring: Software ring holding Tx frames + */ +struct tbnet { + const struct tb_service *svc; + struct tb_xdomain *xd; + struct tb_protocol_handler handler; + struct net_device *dev; + struct napi_struct napi; + struct tbnet_stats stats; + struct sk_buff *skb; + atomic_t command_id; + bool login_sent; + bool login_received; + u32 transmit_path; + struct mutex connection_lock; + int login_retries; + struct delayed_work login_work; + struct work_struct connected_work; + struct thunderbolt_ip_frame_header rx_hdr; + struct tbnet_ring rx_ring; + atomic_t frame_id; + struct tbnet_ring tx_ring; +}; + +/* Network property directory UUID: c66189ca-1cce-4195-bdb8-49592e5f5a4f */ +static const uuid_t tbnet_dir_uuid = + UUID_INIT(0xc66189ca, 0x1cce, 0x4195, + 0xbd, 0xb8, 0x49, 0x59, 0x2e, 0x5f, 0x5a, 0x4f); + +/* ThunderboltIP protocol UUID: 798f589e-3616-8a47-97c6-5664a920c8dd */ +static const uuid_t tbnet_svc_uuid = + UUID_INIT(0x798f589e, 0x3616, 0x8a47, + 0x97, 0xc6, 0x56, 0x64, 0xa9, 0x20, 0xc8, 0xdd); + +static struct tb_property_dir *tbnet_dir; + +static void tbnet_fill_header(struct thunderbolt_ip_header *hdr, u64 route, + u8 sequence, const uuid_t *initiator_uuid, const uuid_t *target_uuid, + enum thunderbolt_ip_type type, size_t size, u32 command_id) +{ + u32 length_sn; + + /* Length does not include route_hi/lo and length_sn fields */ + length_sn = (size - 3 * 4) / 4; + length_sn |= (sequence << TBIP_HDR_SN_SHIFT) & TBIP_HDR_SN_MASK; + + hdr->route_hi = upper_32_bits(route); + hdr->route_lo = lower_32_bits(route); + hdr->length_sn = length_sn; + uuid_copy(&hdr->uuid, &tbnet_svc_uuid); + uuid_copy(&hdr->initiator_uuid, initiator_uuid); + uuid_copy(&hdr->target_uuid, target_uuid); + hdr->type = type; + hdr->command_id = command_id; +} + +static int tbnet_login_response(struct tbnet *net, u64 route, u8 sequence, + u32 command_id) +{ + struct thunderbolt_ip_login_response reply; + struct tb_xdomain *xd = net->xd; + + memset(&reply, 0, sizeof(reply)); + tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid, + xd->remote_uuid, TBIP_LOGIN_RESPONSE, sizeof(reply), + command_id); + memcpy(reply.receiver_mac, net->dev->dev_addr, ETH_ALEN); + reply.receiver_mac_len = ETH_ALEN; + + return tb_xdomain_response(xd, &reply, sizeof(reply), + TB_CFG_PKG_XDOMAIN_RESP); +} + +static int tbnet_login_request(struct tbnet *net, u8 sequence) +{ + struct thunderbolt_ip_login_response reply; + struct thunderbolt_ip_login request; + struct tb_xdomain *xd = net->xd; + + memset(&request, 0, sizeof(request)); + tbnet_fill_header(&request.hdr, xd->route, sequence, xd->local_uuid, + xd->remote_uuid, TBIP_LOGIN, sizeof(request), + atomic_inc_return(&net->command_id)); + + request.proto_version = TBIP_LOGIN_PROTO_VERSION; + request.transmit_path = TBNET_LOCAL_PATH; + + return tb_xdomain_request(xd, &request, sizeof(request), + TB_CFG_PKG_XDOMAIN_RESP, &reply, + sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP, + TBNET_LOGIN_TIMEOUT); +} + +static int tbnet_logout_response(struct tbnet *net, u64 route, u8 sequence, + u32 command_id) +{ + struct thunderbolt_ip_status reply; + struct tb_xdomain *xd = net->xd; + + memset(&reply, 0, sizeof(reply)); + tbnet_fill_header(&reply.hdr, route, sequence, xd->local_uuid, + xd->remote_uuid, TBIP_STATUS, sizeof(reply), + atomic_inc_return(&net->command_id)); + return tb_xdomain_response(xd, &reply, sizeof(reply), + TB_CFG_PKG_XDOMAIN_RESP); +} + +static int tbnet_logout_request(struct tbnet *net) +{ + struct thunderbolt_ip_logout request; + struct thunderbolt_ip_status reply; + struct tb_xdomain *xd = net->xd; + + memset(&request, 0, sizeof(request)); + tbnet_fill_header(&request.hdr, xd->route, 0, xd->local_uuid, + xd->remote_uuid, TBIP_LOGOUT, sizeof(request), + atomic_inc_return(&net->command_id)); + + return tb_xdomain_request(xd, &request, sizeof(request), + TB_CFG_PKG_XDOMAIN_RESP, &reply, + sizeof(reply), TB_CFG_PKG_XDOMAIN_RESP, + TBNET_LOGOUT_TIMEOUT); +} + +static void start_login(struct tbnet *net) +{ + mutex_lock(&net->connection_lock); + net->login_sent = false; + net->login_received = false; + mutex_unlock(&net->connection_lock); + + queue_delayed_work(system_long_wq, &net->login_work, + msecs_to_jiffies(1000)); +} + +static void stop_login(struct tbnet *net) +{ + cancel_delayed_work_sync(&net->login_work); + cancel_work_sync(&net->connected_work); +} + +static inline unsigned int tbnet_frame_size(const struct tbnet_frame *tf) +{ + return tf->frame.size ? : TBNET_FRAME_SIZE; +} + +static void tbnet_free_buffers(struct tbnet_ring *ring) +{ + unsigned int i; + + for (i = 0; i < TBNET_RING_SIZE; i++) { + struct device *dma_dev = tb_ring_dma_device(ring->ring); + struct tbnet_frame *tf = &ring->frames[i]; + enum dma_data_direction dir; + unsigned int order; + size_t size; + + if (!tf->page) + continue; + + if (ring->ring->is_tx) { + dir = DMA_TO_DEVICE; + order = 0; + size = tbnet_frame_size(tf); + } else { + dir = DMA_FROM_DEVICE; + order = TBNET_RX_PAGE_ORDER; + size = TBNET_RX_PAGE_SIZE; + } + + if (tf->frame.buffer_phy) + dma_unmap_page(dma_dev, tf->frame.buffer_phy, size, + dir); + + __free_pages(tf->page, order); + tf->page = NULL; + } + + ring->cons = 0; + ring->prod = 0; +} + +static void tbnet_tear_down(struct tbnet *net, bool send_logout) +{ + netif_carrier_off(net->dev); + netif_stop_queue(net->dev); + + stop_login(net); + + mutex_lock(&net->connection_lock); + + if (net->login_sent && net->login_received) { + int retries = TBNET_LOGOUT_RETRIES; + + while (send_logout && retries-- > 0) { + int ret = tbnet_logout_request(net); + if (ret != -ETIMEDOUT) + break; + } + + tb_ring_stop(net->rx_ring.ring); + tb_ring_stop(net->tx_ring.ring); + tbnet_free_buffers(&net->rx_ring); + tbnet_free_buffers(&net->tx_ring); + + if (tb_xdomain_disable_paths(net->xd)) + netdev_warn(net->dev, "failed to disable DMA paths\n"); + } + + net->login_retries = 0; + net->login_sent = false; + net->login_received = false; + + mutex_unlock(&net->connection_lock); +} + +static int tbnet_handle_packet(const void *buf, size_t size, void *data) +{ + const struct thunderbolt_ip_login *pkg = buf; + struct tbnet *net = data; + u32 command_id; + int ret = 0; + u8 sequence; + u64 route; + + /* Make sure the packet is for us */ + if (size < sizeof(struct thunderbolt_ip_header)) + return 0; + if (!uuid_equal(&pkg->hdr.initiator_uuid, net->xd->remote_uuid)) + return 0; + if (!uuid_equal(&pkg->hdr.target_uuid, net->xd->local_uuid)) + return 0; + + route = ((u64)pkg->hdr.route_hi << 32) | pkg->hdr.route_lo; + route &= ~BIT_ULL(63); + if (route != net->xd->route) + return 0; + + sequence = pkg->hdr.length_sn & TBIP_HDR_SN_MASK; + sequence >>= TBIP_HDR_SN_SHIFT; + command_id = pkg->hdr.command_id; + + switch (pkg->hdr.type) { + case TBIP_LOGIN: + if (!netif_running(net->dev)) + break; + + ret = tbnet_login_response(net, route, sequence, + pkg->hdr.command_id); + if (!ret) { + mutex_lock(&net->connection_lock); + net->login_received = true; + net->transmit_path = pkg->transmit_path; + + /* If we reached the number of max retries or + * previous logout, schedule another round of + * login retries + */ + if (net->login_retries >= TBNET_LOGIN_RETRIES || + !net->login_sent) { + net->login_retries = 0; + queue_delayed_work(system_long_wq, + &net->login_work, 0); + } + mutex_unlock(&net->connection_lock); + + queue_work(system_long_wq, &net->connected_work); + } + break; + + case TBIP_LOGOUT: + ret = tbnet_logout_response(net, route, sequence, command_id); + if (!ret) + tbnet_tear_down(net, false); + break; + + default: + return 0; + } + + if (ret) + netdev_warn(net->dev, "failed to send ThunderboltIP response\n"); + + return 1; +} + +static unsigned int tbnet_available_buffers(const struct tbnet_ring *ring) +{ + return ring->prod - ring->cons; +} + +static int tbnet_alloc_rx_buffers(struct tbnet *net, unsigned int nbuffers) +{ + struct tbnet_ring *ring = &net->rx_ring; + int ret; + + while (nbuffers--) { + struct device *dma_dev = tb_ring_dma_device(ring->ring); + unsigned int index = ring->prod & (TBNET_RING_SIZE - 1); + struct tbnet_frame *tf = &ring->frames[index]; + dma_addr_t dma_addr; + + if (tf->page) + break; + + /* Allocate page (order > 0) so that it can hold maximum + * ThunderboltIP frame (4kB) and the additional room for + * SKB shared info required by build_skb(). + */ + tf->page = dev_alloc_pages(TBNET_RX_PAGE_ORDER); + if (!tf->page) { + ret = -ENOMEM; + goto err_free; + } + + dma_addr = dma_map_page(dma_dev, tf->page, 0, + TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(dma_dev, dma_addr)) { + ret = -ENOMEM; + goto err_free; + } + + tf->frame.buffer_phy = dma_addr; + tf->dev = net->dev; + + tb_ring_rx(ring->ring, &tf->frame); + + ring->prod++; + } + + return 0; + +err_free: + tbnet_free_buffers(ring); + return ret; +} + +static struct tbnet_frame *tbnet_get_tx_buffer(struct tbnet *net) +{ + struct tbnet_ring *ring = &net->tx_ring; + struct tbnet_frame *tf; + unsigned int index; + + if (!tbnet_available_buffers(ring)) + return NULL; + + index = ring->cons++ & (TBNET_RING_SIZE - 1); + + tf = &ring->frames[index]; + tf->frame.size = 0; + tf->frame.buffer_phy = 0; + + return tf; +} + +static void tbnet_tx_callback(struct tb_ring *ring, struct ring_frame *frame, + bool canceled) +{ + struct tbnet_frame *tf = container_of(frame, typeof(*tf), frame); + struct device *dma_dev = tb_ring_dma_device(ring); + struct tbnet *net = netdev_priv(tf->dev); + + dma_unmap_page(dma_dev, tf->frame.buffer_phy, tbnet_frame_size(tf), + DMA_TO_DEVICE); + + /* Return buffer to the ring */ + net->tx_ring.prod++; + + if (tbnet_available_buffers(&net->tx_ring) >= TBNET_RING_SIZE / 2) + netif_wake_queue(net->dev); +} + +static int tbnet_alloc_tx_buffers(struct tbnet *net) +{ + struct tbnet_ring *ring = &net->tx_ring; + unsigned int i; + + for (i = 0; i < TBNET_RING_SIZE; i++) { + struct tbnet_frame *tf = &ring->frames[i]; + + tf->page = alloc_page(GFP_KERNEL); + if (!tf->page) { + tbnet_free_buffers(ring); + return -ENOMEM; + } + + tf->dev = net->dev; + tf->frame.callback = tbnet_tx_callback; + tf->frame.sof = TBIP_PDF_FRAME_START; + tf->frame.eof = TBIP_PDF_FRAME_END; + } + + ring->cons = 0; + ring->prod = TBNET_RING_SIZE - 1; + + return 0; +} + +static void tbnet_connected_work(struct work_struct *work) +{ + struct tbnet *net = container_of(work, typeof(*net), connected_work); + bool connected; + int ret; + + if (netif_carrier_ok(net->dev)) + return; + + mutex_lock(&net->connection_lock); + connected = net->login_sent && net->login_received; + mutex_unlock(&net->connection_lock); + + if (!connected) + return; + + /* Both logins successful so enable the high-speed DMA paths and + * start the network device queue. + */ + ret = tb_xdomain_enable_paths(net->xd, TBNET_LOCAL_PATH, + net->rx_ring.ring->hop, + net->transmit_path, + net->tx_ring.ring->hop); + if (ret) { + netdev_err(net->dev, "failed to enable DMA paths\n"); + return; + } + + tb_ring_start(net->tx_ring.ring); + tb_ring_start(net->rx_ring.ring); + + ret = tbnet_alloc_rx_buffers(net, TBNET_RING_SIZE); + if (ret) + goto err_stop_rings; + + ret = tbnet_alloc_tx_buffers(net); + if (ret) + goto err_free_rx_buffers; + + netif_carrier_on(net->dev); + netif_start_queue(net->dev); + return; + +err_free_rx_buffers: + tbnet_free_buffers(&net->rx_ring); +err_stop_rings: + tb_ring_stop(net->rx_ring.ring); + tb_ring_stop(net->tx_ring.ring); +} + +static void tbnet_login_work(struct work_struct *work) +{ + struct tbnet *net = container_of(work, typeof(*net), login_work.work); + unsigned long delay = msecs_to_jiffies(TBNET_LOGIN_DELAY); + int ret; + + if (netif_carrier_ok(net->dev)) + return; + + ret = tbnet_login_request(net, net->login_retries % 4); + if (ret) { + if (net->login_retries++ < TBNET_LOGIN_RETRIES) { + queue_delayed_work(system_long_wq, &net->login_work, + delay); + } else { + netdev_info(net->dev, "ThunderboltIP login timed out\n"); + } + } else { + net->login_retries = 0; + + mutex_lock(&net->connection_lock); + net->login_sent = true; + mutex_unlock(&net->connection_lock); + + queue_work(system_long_wq, &net->connected_work); + } +} + +static bool tbnet_check_frame(struct tbnet *net, const struct tbnet_frame *tf, + const struct thunderbolt_ip_frame_header *hdr) +{ + u32 frame_id, frame_count, frame_size, frame_index; + unsigned int size; + + if (tf->frame.flags & RING_DESC_CRC_ERROR) { + net->stats.rx_crc_errors++; + return false; + } else if (tf->frame.flags & RING_DESC_BUFFER_OVERRUN) { + net->stats.rx_over_errors++; + return false; + } + + /* Should be greater than just header i.e. contains data */ + size = tbnet_frame_size(tf); + if (size <= sizeof(*hdr)) { + net->stats.rx_length_errors++; + return false; + } + + frame_count = le32_to_cpu(hdr->frame_count); + frame_size = le32_to_cpu(hdr->frame_size); + frame_index = le16_to_cpu(hdr->frame_index); + frame_id = le16_to_cpu(hdr->frame_id); + + if ((frame_size > size - sizeof(*hdr)) || !frame_size) { + net->stats.rx_length_errors++; + return false; + } + + /* In case we're in the middle of packet, validate the frame + * header based on first fragment of the packet. + */ + if (net->skb && net->rx_hdr.frame_count) { + /* Check the frame count fits the count field */ + if (frame_count != net->rx_hdr.frame_count) { + net->stats.rx_length_errors++; + return false; + } + + /* Check the frame identifiers are incremented correctly, + * and id is matching. + */ + if (frame_index != net->rx_hdr.frame_index + 1 || + frame_id != net->rx_hdr.frame_id) { + net->stats.rx_missed_errors++; + return false; + } + + if (net->skb->len + frame_size > TBNET_MAX_MTU) { + net->stats.rx_length_errors++; + return false; + } + + return true; + } + + /* Start of packet, validate the frame header */ + if (frame_count == 0 || frame_count > TBNET_RING_SIZE / 4) { + net->stats.rx_length_errors++; + return false; + } + if (frame_index != 0) { + net->stats.rx_missed_errors++; + return false; + } + + return true; +} + +static int tbnet_poll(struct napi_struct *napi, int budget) +{ + struct tbnet *net = container_of(napi, struct tbnet, napi); + unsigned int cleaned_count = tbnet_available_buffers(&net->rx_ring); + struct device *dma_dev = tb_ring_dma_device(net->rx_ring.ring); + unsigned int rx_packets = 0; + + while (rx_packets < budget) { + const struct thunderbolt_ip_frame_header *hdr; + unsigned int hdr_size = sizeof(*hdr); + struct sk_buff *skb = NULL; + struct ring_frame *frame; + struct tbnet_frame *tf; + struct page *page; + bool last = true; + u32 frame_size; + + /* Return some buffers to hardware, one at a time is too + * slow so allocate MAX_SKB_FRAGS buffers at the same + * time. + */ + if (cleaned_count >= MAX_SKB_FRAGS) { + tbnet_alloc_rx_buffers(net, cleaned_count); + cleaned_count = 0; + } + + frame = tb_ring_poll(net->rx_ring.ring); + if (!frame) + break; + + dma_unmap_page(dma_dev, frame->buffer_phy, + TBNET_RX_PAGE_SIZE, DMA_FROM_DEVICE); + + tf = container_of(frame, typeof(*tf), frame); + + page = tf->page; + tf->page = NULL; + net->rx_ring.cons++; + cleaned_count++; + + hdr = page_address(page); + if (!tbnet_check_frame(net, tf, hdr)) { + __free_pages(page, TBNET_RX_PAGE_ORDER); + dev_kfree_skb_any(net->skb); + net->skb = NULL; + continue; + } + + frame_size = le32_to_cpu(hdr->frame_size); + + skb = net->skb; + if (!skb) { + skb = build_skb(page_address(page), + TBNET_RX_PAGE_SIZE); + if (!skb) { + __free_pages(page, TBNET_RX_PAGE_ORDER); + net->stats.rx_errors++; + break; + } + + skb_reserve(skb, hdr_size); + skb_put(skb, frame_size); + + net->skb = skb; + } else { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + page, hdr_size, frame_size, + TBNET_RX_PAGE_SIZE - hdr_size); + } + + net->rx_hdr.frame_size = frame_size; + net->rx_hdr.frame_count = le32_to_cpu(hdr->frame_count); + net->rx_hdr.frame_index = le16_to_cpu(hdr->frame_index); + net->rx_hdr.frame_id = le16_to_cpu(hdr->frame_id); + last = net->rx_hdr.frame_index == net->rx_hdr.frame_count - 1; + + rx_packets++; + net->stats.rx_bytes += frame_size; + + if (last) { + skb->protocol = eth_type_trans(skb, net->dev); + napi_gro_receive(&net->napi, skb); + net->skb = NULL; + } + } + + net->stats.rx_packets += rx_packets; + + if (cleaned_count) + tbnet_alloc_rx_buffers(net, cleaned_count); + + if (rx_packets >= budget) + return budget; + + napi_complete_done(napi, rx_packets); + /* Re-enable the ring interrupt */ + tb_ring_poll_complete(net->rx_ring.ring); + + return rx_packets; +} + +static void tbnet_start_poll(void *data) +{ + struct tbnet *net = data; + + napi_schedule(&net->napi); +} + +static int tbnet_open(struct net_device *dev) +{ + struct tbnet *net = netdev_priv(dev); + struct tb_xdomain *xd = net->xd; + u16 sof_mask, eof_mask; + struct tb_ring *ring; + + netif_carrier_off(dev); + + ring = tb_ring_alloc_tx(xd->tb->nhi, -1, TBNET_RING_SIZE, + RING_FLAG_FRAME); + if (!ring) { + netdev_err(dev, "failed to allocate Tx ring\n"); + return -ENOMEM; + } + net->tx_ring.ring = ring; + + sof_mask = BIT(TBIP_PDF_FRAME_START); + eof_mask = BIT(TBIP_PDF_FRAME_END); + + ring = tb_ring_alloc_rx(xd->tb->nhi, -1, TBNET_RING_SIZE, + RING_FLAG_FRAME | RING_FLAG_E2E, sof_mask, + eof_mask, tbnet_start_poll, net); + if (!ring) { + netdev_err(dev, "failed to allocate Rx ring\n"); + tb_ring_free(net->tx_ring.ring); + net->tx_ring.ring = NULL; + return -ENOMEM; + } + net->rx_ring.ring = ring; + + napi_enable(&net->napi); + start_login(net); + + return 0; +} + +static int tbnet_stop(struct net_device *dev) +{ + struct tbnet *net = netdev_priv(dev); + + napi_disable(&net->napi); + + tbnet_tear_down(net, true); + + tb_ring_free(net->rx_ring.ring); + net->rx_ring.ring = NULL; + tb_ring_free(net->tx_ring.ring); + net->tx_ring.ring = NULL; + + return 0; +} + +static bool tbnet_xmit_map(struct device *dma_dev, struct tbnet_frame *tf) +{ + dma_addr_t dma_addr; + + dma_addr = dma_map_page(dma_dev, tf->page, 0, tbnet_frame_size(tf), + DMA_TO_DEVICE); + if (dma_mapping_error(dma_dev, dma_addr)) + return false; + + tf->frame.buffer_phy = dma_addr; + return true; +} + +static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb, + struct tbnet_frame **frames, u32 frame_count) +{ + struct thunderbolt_ip_frame_header *hdr = page_address(frames[0]->page); + struct device *dma_dev = tb_ring_dma_device(net->tx_ring.ring); + __wsum wsum = htonl(skb->len - skb_transport_offset(skb)); + unsigned int i, len, offset = skb_transport_offset(skb); + __be16 protocol = skb->protocol; + void *data = skb->data; + void *dest = hdr + 1; + __sum16 *tucso; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + /* No need to calculate checksum so we just update the + * total frame count and map the frames for DMA. + */ + for (i = 0; i < frame_count; i++) { + hdr = page_address(frames[i]->page); + hdr->frame_count = cpu_to_le32(frame_count); + if (!tbnet_xmit_map(dma_dev, frames[i])) + goto err_unmap; + } + + return true; + } + + if (protocol == htons(ETH_P_8021Q)) { + struct vlan_hdr *vhdr, vh; + + vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(vh), &vh); + if (!vhdr) + return false; + + protocol = vhdr->h_vlan_encapsulated_proto; + } + + /* Data points on the beginning of packet. + * Check is the checksum absolute place in the packet. + * ipcso will update IP checksum. + * tucso will update TCP/UPD checksum. + */ + if (protocol == htons(ETH_P_IP)) { + __sum16 *ipcso = dest + ((void *)&(ip_hdr(skb)->check) - data); + + *ipcso = 0; + *ipcso = ip_fast_csum(dest + skb_network_offset(skb), + ip_hdr(skb)->ihl); + + if (ip_hdr(skb)->protocol == IPPROTO_TCP) + tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data); + else if (ip_hdr(skb)->protocol == IPPROTO_UDP) + tucso = dest + ((void *)&(udp_hdr(skb)->check) - data); + else + return false; + + *tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, 0, + ip_hdr(skb)->protocol, 0); + } else if (skb_is_gso_v6(skb)) { + tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data); + *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, 0, + IPPROTO_TCP, 0); + return false; + } else if (protocol == htons(ETH_P_IPV6)) { + tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset; + *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, 0, + ipv6_hdr(skb)->nexthdr, 0); + } else { + return false; + } + + /* First frame was headers, rest of the frames contain data. + * Calculate checksum over each frame. + */ + for (i = 0; i < frame_count; i++) { + hdr = page_address(frames[i]->page); + dest = (void *)(hdr + 1) + offset; + len = le32_to_cpu(hdr->frame_size) - offset; + wsum = csum_partial(dest, len, wsum); + hdr->frame_count = cpu_to_le32(frame_count); + + offset = 0; + } + + *tucso = csum_fold(wsum); + + /* Checksum is finally calculated and we don't touch the memory + * anymore, so DMA map the frames now. + */ + for (i = 0; i < frame_count; i++) { + if (!tbnet_xmit_map(dma_dev, frames[i])) + goto err_unmap; + } + + return true; + +err_unmap: + while (i--) + dma_unmap_page(dma_dev, frames[i]->frame.buffer_phy, + tbnet_frame_size(frames[i]), DMA_TO_DEVICE); + + return false; +} + +static void *tbnet_kmap_frag(struct sk_buff *skb, unsigned int frag_num, + unsigned int *len) +{ + const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num]; + + *len = skb_frag_size(frag); + return kmap_atomic(skb_frag_page(frag)) + frag->page_offset; +} + +static netdev_tx_t tbnet_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct tbnet *net = netdev_priv(dev); + struct tbnet_frame *frames[MAX_SKB_FRAGS]; + u16 frame_id = atomic_read(&net->frame_id); + struct thunderbolt_ip_frame_header *hdr; + unsigned int len = skb_headlen(skb); + unsigned int data_len = skb->len; + unsigned int nframes, i; + unsigned int frag = 0; + void *src = skb->data; + u32 frame_index = 0; + bool unmap = false; + void *dest; + + nframes = DIV_ROUND_UP(data_len, TBNET_MAX_PAYLOAD_SIZE); + if (tbnet_available_buffers(&net->tx_ring) < nframes) { + netif_stop_queue(net->dev); + return NETDEV_TX_BUSY; + } + + frames[frame_index] = tbnet_get_tx_buffer(net); + if (!frames[frame_index]) + goto err_drop; + + hdr = page_address(frames[frame_index]->page); + dest = hdr + 1; + + /* If overall packet is bigger than the frame data size */ + while (data_len > TBNET_MAX_PAYLOAD_SIZE) { + unsigned int size_left = TBNET_MAX_PAYLOAD_SIZE; + + hdr->frame_size = cpu_to_le32(TBNET_MAX_PAYLOAD_SIZE); + hdr->frame_index = cpu_to_le16(frame_index); + hdr->frame_id = cpu_to_le16(frame_id); + + do { + if (len > size_left) { + /* Copy data onto Tx buffer data with + * full frame size then break and go to + * next frame + */ + memcpy(dest, src, size_left); + len -= size_left; + dest += size_left; + src += size_left; + break; + } + + memcpy(dest, src, len); + size_left -= len; + dest += len; + + if (unmap) { + kunmap_atomic(src); + unmap = false; + } + + /* Ensure all fragments have been processed */ + if (frag < skb_shinfo(skb)->nr_frags) { + /* Map and then unmap quickly */ + src = tbnet_kmap_frag(skb, frag++, &len); + unmap = true; + } else if (unlikely(size_left > 0)) { + goto err_drop; + } + } while (size_left > 0); + + data_len -= TBNET_MAX_PAYLOAD_SIZE; + frame_index++; + + frames[frame_index] = tbnet_get_tx_buffer(net); + if (!frames[frame_index]) + goto err_drop; + + hdr = page_address(frames[frame_index]->page); + dest = hdr + 1; + } + + hdr->frame_size = cpu_to_le32(data_len); + hdr->frame_index = cpu_to_le16(frame_index); + hdr->frame_id = cpu_to_le16(frame_id); + + frames[frame_index]->frame.size = data_len + sizeof(*hdr); + + /* In case the remaining data_len is smaller than a frame */ + while (len < data_len) { + memcpy(dest, src, len); + data_len -= len; + dest += len; + + if (unmap) { + kunmap_atomic(src); + unmap = false; + } + + if (frag < skb_shinfo(skb)->nr_frags) { + src = tbnet_kmap_frag(skb, frag++, &len); + unmap = true; + } else if (unlikely(data_len > 0)) { + goto err_drop; + } + } + + memcpy(dest, src, data_len); + + if (unmap) + kunmap_atomic(src); + + if (!tbnet_xmit_csum_and_map(net, skb, frames, frame_index + 1)) + goto err_drop; + + for (i = 0; i < frame_index + 1; i++) + tb_ring_tx(net->tx_ring.ring, &frames[i]->frame); + + if (net->svc->prtcstns & TBNET_MATCH_FRAGS_ID) + atomic_inc(&net->frame_id); + + net->stats.tx_packets++; + net->stats.tx_bytes += skb->len; + + dev_consume_skb_any(skb); + + return NETDEV_TX_OK; + +err_drop: + /* We can re-use the buffers */ + net->tx_ring.cons -= frame_index; + + dev_kfree_skb_any(skb); + net->stats.tx_errors++; + + return NETDEV_TX_OK; +} + +static void tbnet_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct tbnet *net = netdev_priv(dev); + + stats->tx_packets = net->stats.tx_packets; + stats->rx_packets = net->stats.rx_packets; + stats->tx_bytes = net->stats.tx_bytes; + stats->rx_bytes = net->stats.rx_bytes; + stats->rx_errors = net->stats.rx_errors + net->stats.rx_length_errors + + net->stats.rx_over_errors + net->stats.rx_crc_errors + + net->stats.rx_missed_errors; + stats->tx_errors = net->stats.tx_errors; + stats->rx_length_errors = net->stats.rx_length_errors; + stats->rx_over_errors = net->stats.rx_over_errors; + stats->rx_crc_errors = net->stats.rx_crc_errors; + stats->rx_missed_errors = net->stats.rx_missed_errors; +} + +static const struct net_device_ops tbnet_netdev_ops = { + .ndo_open = tbnet_open, + .ndo_stop = tbnet_stop, + .ndo_start_xmit = tbnet_start_xmit, + .ndo_get_stats64 = tbnet_get_stats64, +}; + +static void tbnet_generate_mac(struct net_device *dev) +{ + const struct tbnet *net = netdev_priv(dev); + const struct tb_xdomain *xd = net->xd; + u8 phy_port; + u32 hash; + + phy_port = tb_phy_port_from_link(TBNET_L0_PORT_NUM(xd->route)); + + /* Unicast and locally administered MAC */ + dev->dev_addr[0] = phy_port << 4 | 0x02; + hash = jhash2((u32 *)xd->local_uuid, 4, 0); + memcpy(dev->dev_addr + 1, &hash, sizeof(hash)); + hash = jhash2((u32 *)xd->local_uuid, 4, hash); + dev->dev_addr[5] = hash & 0xff; +} + +static int tbnet_probe(struct tb_service *svc, const struct tb_service_id *id) +{ + struct tb_xdomain *xd = tb_service_parent(svc); + struct net_device *dev; + struct tbnet *net; + int ret; + + dev = alloc_etherdev(sizeof(*net)); + if (!dev) + return -ENOMEM; + + SET_NETDEV_DEV(dev, &svc->dev); + + net = netdev_priv(dev); + INIT_DELAYED_WORK(&net->login_work, tbnet_login_work); + INIT_WORK(&net->connected_work, tbnet_connected_work); + mutex_init(&net->connection_lock); + atomic_set(&net->command_id, 0); + atomic_set(&net->frame_id, 0); + net->svc = svc; + net->dev = dev; + net->xd = xd; + + tbnet_generate_mac(dev); + + strcpy(dev->name, "thunderbolt%d"); + dev->netdev_ops = &tbnet_netdev_ops; + + /* ThunderboltIP takes advantage of TSO packets but instead of + * segmenting them we just split the packet into Thunderbolt + * frames (maximum payload size of each frame is 4084 bytes) and + * calculate checksum over the whole packet here. + * + * The receiving side does the opposite if the host OS supports + * LRO, otherwise it needs to split the large packet into MTU + * sized smaller packets. + * + * In order to receive large packets from the networking stack, + * we need to announce support for most of the offloading + * features here. + */ + dev->hw_features = NETIF_F_SG | NETIF_F_ALL_TSO | NETIF_F_GRO | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + dev->features = dev->hw_features | NETIF_F_HIGHDMA; + dev->hard_header_len += sizeof(struct thunderbolt_ip_frame_header); + + netif_napi_add(dev, &net->napi, tbnet_poll, NAPI_POLL_WEIGHT); + + /* MTU range: 68 - 65522 */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = TBNET_MAX_MTU - ETH_HLEN; + + net->handler.uuid = &tbnet_svc_uuid; + net->handler.callback = tbnet_handle_packet, + net->handler.data = net; + tb_register_protocol_handler(&net->handler); + + tb_service_set_drvdata(svc, net); + + ret = register_netdev(dev); + if (ret) { + tb_unregister_protocol_handler(&net->handler); + free_netdev(dev); + return ret; + } + + return 0; +} + +static void tbnet_remove(struct tb_service *svc) +{ + struct tbnet *net = tb_service_get_drvdata(svc); + + unregister_netdev(net->dev); + tb_unregister_protocol_handler(&net->handler); + free_netdev(net->dev); +} + +static void tbnet_shutdown(struct tb_service *svc) +{ + tbnet_tear_down(tb_service_get_drvdata(svc), true); +} + +static int __maybe_unused tbnet_suspend(struct device *dev) +{ + struct tb_service *svc = tb_to_service(dev); + struct tbnet *net = tb_service_get_drvdata(svc); + + stop_login(net); + if (netif_running(net->dev)) { + netif_device_detach(net->dev); + tb_ring_stop(net->rx_ring.ring); + tb_ring_stop(net->tx_ring.ring); + tbnet_free_buffers(&net->rx_ring); + tbnet_free_buffers(&net->tx_ring); + } + + return 0; +} + +static int __maybe_unused tbnet_resume(struct device *dev) +{ + struct tb_service *svc = tb_to_service(dev); + struct tbnet *net = tb_service_get_drvdata(svc); + + netif_carrier_off(net->dev); + if (netif_running(net->dev)) { + netif_device_attach(net->dev); + start_login(net); + } + + return 0; +} + +static const struct dev_pm_ops tbnet_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(tbnet_suspend, tbnet_resume) +}; + +static const struct tb_service_id tbnet_ids[] = { + { TB_SERVICE("network", 1) }, + { }, +}; +MODULE_DEVICE_TABLE(tbsvc, tbnet_ids); + +static struct tb_service_driver tbnet_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "thunderbolt-net", + .pm = &tbnet_pm_ops, + }, + .probe = tbnet_probe, + .remove = tbnet_remove, + .shutdown = tbnet_shutdown, + .id_table = tbnet_ids, +}; + +static int __init tbnet_init(void) +{ + int ret; + + tbnet_dir = tb_property_create_dir(&tbnet_dir_uuid); + if (!tbnet_dir) + return -ENOMEM; + + tb_property_add_immediate(tbnet_dir, "prtcid", 1); + tb_property_add_immediate(tbnet_dir, "prtcvers", 1); + tb_property_add_immediate(tbnet_dir, "prtcrevs", 1); + tb_property_add_immediate(tbnet_dir, "prtcstns", + TBNET_MATCH_FRAGS_ID); + + ret = tb_register_property_dir("network", tbnet_dir); + if (ret) { + tb_property_free_dir(tbnet_dir); + return ret; + } + + return tb_register_service_driver(&tbnet_driver); +} +module_init(tbnet_init); + +static void __exit tbnet_exit(void) +{ + tb_unregister_service_driver(&tbnet_driver); + tb_unregister_property_dir("network", tbnet_dir); + tb_property_free_dir(tbnet_dir); +} +module_exit(tbnet_exit); + +MODULE_AUTHOR("Amir Levy "); +MODULE_AUTHOR("Michael Jamet "); +MODULE_AUTHOR("Mika Westerberg "); +MODULE_DESCRIPTION("Thunderbolt network driver"); +MODULE_LICENSE("GPL v2"); -- GitLab From c024297e7be34b6f0e578afc76c5b9f7708a5832 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 2 Oct 2017 13:38:46 +0300 Subject: [PATCH 0785/1507] MAINTAINERS: Add entry for Thunderbolt network driver I will be maintaining the Thunderbolt network driver along with Michael and Yehezkel. Signed-off-by: Michael Jamet Signed-off-by: Yehezkel Bernat Signed-off-by: Mika Westerberg Signed-off-by: David S. Miller --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index c1c90d962012a..5231392cf4bd7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13280,6 +13280,14 @@ S: Maintained F: drivers/thunderbolt/ F: include/linux/thunderbolt.h +THUNDERBOLT NETWORK DRIVER +M: Michael Jamet +M: Mika Westerberg +M: Yehezkel Bernat +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/thunderbolt.c + THUNDERX GPIO DRIVER M: David Daney S: Maintained -- GitLab From d312fefea8387503375f728855c9a62de20c9665 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 2 Oct 2017 19:31:24 +0100 Subject: [PATCH 0786/1507] ahci: don't ignore result code of ahci_reset_controller() ahci_pci_reset_controller() calls ahci_reset_controller(), which may fail, but ignores the result code and always returns success. This may result in failures like below ahci 0000:02:00.0: version 3.0 ahci 0000:02:00.0: enabling device (0000 -> 0003) ahci 0000:02:00.0: SSS flag set, parallel bus scan disabled ahci 0000:02:00.0: controller reset failed (0xffffffff) ahci 0000:02:00.0: failed to stop engine (-5) ... repeated many times ... ahci 0000:02:00.0: failed to stop engine (-5) Unable to handle kernel paging request at virtual address ffff0000093f9018 ... PC is at ahci_stop_engine+0x5c/0xd8 [libahci] LR is at ahci_deinit_port.constprop.12+0x1c/0xc0 [libahci] ... [] ahci_stop_engine+0x5c/0xd8 [libahci] [] ahci_deinit_port.constprop.12+0x1c/0xc0 [libahci] [] ahci_init_controller+0x80/0x168 [libahci] [] ahci_pci_init_controller+0x60/0x68 [ahci] [] ahci_init_one+0x75c/0xd88 [ahci] [] local_pci_probe+0x3c/0xb8 [] pci_device_probe+0x138/0x170 [] driver_probe_device+0x2dc/0x458 [] __driver_attach+0x114/0x118 [] bus_for_each_dev+0x60/0xa0 [] driver_attach+0x20/0x28 [] bus_add_driver+0x1f0/0x2a8 [] driver_register+0x60/0xf8 [] __pci_register_driver+0x3c/0x48 [] ahci_pci_driver_init+0x1c/0x1000 [ahci] [] do_one_initcall+0x38/0x120 where an obvious hardware level failure results in an unnecessary 15 second delay and a subsequent crash. So record the result code of ahci_reset_controller() and relay it, rather than ignoring it. Signed-off-by: Ard Biesheuvel Signed-off-by: Tejun Heo --- drivers/ata/ahci.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cb9b0e9090e3b..9f78bb03bb763 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -621,8 +621,11 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, static int ahci_pci_reset_controller(struct ata_host *host) { struct pci_dev *pdev = to_pci_dev(host->dev); + int rc; - ahci_reset_controller(host); + rc = ahci_reset_controller(host); + if (rc) + return rc; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { struct ahci_host_priv *hpriv = host->private_data; -- GitLab From e50d5751c807853cd0fce0b5c46479cc6274014f Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Mon, 24 Jul 2017 18:17:42 -0700 Subject: [PATCH 0787/1507] i40e: limit lan queue count in large CPU count machine When a machine has more CPUs than queue pairs, e.g. 512 cores, the counting gets a little funky and turns off Flow Director with the message: not enough queues for Flow Director. Flow Director feature is disabled This patch limits the number of lan queues initially allocated to be sure we have some left for FD and other features. Signed-off-by: Shannon Nelson Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 47f71d7c3ae0a..387f0863f7940 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11093,6 +11093,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) static void i40e_determine_queue_usage(struct i40e_pf *pf) { int queues_left; + int q_max; pf->num_lan_qps = 0; @@ -11139,10 +11140,12 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) I40E_FLAG_DCB_ENABLED); dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n"); } - pf->num_lan_qps = max_t(int, pf->rss_size_max, - num_online_cpus()); - pf->num_lan_qps = min_t(int, pf->num_lan_qps, - pf->hw.func_caps.num_tx_qp); + + /* limit lan qps to the smaller of qps, cpus or msix */ + q_max = max_t(int, pf->rss_size_max, num_online_cpus()); + q_max = min_t(int, q_max, pf->hw.func_caps.num_tx_qp); + q_max = min_t(int, q_max, pf->hw.func_caps.num_msix_vectors); + pf->num_lan_qps = q_max; queues_left -= pf->num_lan_qps; } -- GitLab From 5872866e166c38ad1c1028fb9cf7dd756c0ef43e Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Thu, 27 Jul 2017 03:17:09 -0700 Subject: [PATCH 0788/1507] i40e: remove logically dead code This patch removes the !vf condition check that cannot be true in i40e_ndo_set_vf_trust function Detected by CoverityScan, CID 1397531 Logically dead code Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index a75396c157d95..e6b95e1e1a337 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3354,8 +3354,6 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) vf = &pf->vf[vf_id]; - if (!vf) - return -EINVAL; if (setting == vf->trusted) goto out; -- GitLab From 54902349ee95045b67e2f0c39b75f5418540064b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 6 Aug 2017 23:37:01 +0200 Subject: [PATCH 0789/1507] i40e: Fix a potential NULL pointer dereference If 'kzalloc()' fails, a NULL pointer will be dereferenced. Return an error code (-ENOMEM) instead. Signed-off-by: Christophe JAILLET Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e6b95e1e1a337..9e3667fc7f6ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -423,6 +423,9 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf, (sizeof(struct virtchnl_iwarp_qv_info) * (qvlist_info->num_vectors - 1)); vf->qvlist_info = kzalloc(size, GFP_KERNEL); + if (!vf->qvlist_info) + return -ENOMEM; + vf->qvlist_info->num_vectors = qvlist_info->num_vectors; msix_vf = pf->hw.func_caps.num_msix_vectors_vf; -- GitLab From d60bcc798000e015940fb47eb23b79dd2fda5c9e Mon Sep 17 00:00:00 2001 From: Filip Sadowski Date: Tue, 22 Aug 2017 06:57:43 -0400 Subject: [PATCH 0790/1507] i40e: Fix reporting of supported link modes This patch fixes incorrect reporting of supported link modes on some NICs. Signed-off-by: Filip Sadowski Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40e/i40e_adminq_cmd.h | 20 +++++++++++++++++-- drivers/net/ethernet/intel/i40e/i40e_common.c | 11 +++++++++- .../ethernet/intel/i40evf/i40e_adminq_cmd.h | 20 +++++++++++++++++-- 3 files changed, 46 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index e2a9ec80a6237..5d0291c1337ee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1734,6 +1734,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, I40E_PHY_TYPE_10GBASE_AOC = 0xC, I40E_PHY_TYPE_40GBASE_AOC = 0xD, + I40E_PHY_TYPE_UNRECOGNIZED = 0xE, + I40E_PHY_TYPE_UNSUPPORTED = 0xF, I40E_PHY_TYPE_100BASE_TX = 0x11, I40E_PHY_TYPE_1000BASE_T = 0x12, I40E_PHY_TYPE_10GBASE_T = 0x13, @@ -1752,6 +1754,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_EMPTY = 0xFE, + I40E_PHY_TYPE_DEFAULT = 0xFF, I40E_PHY_TYPE_MAX }; @@ -1942,19 +1946,31 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 #define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ +/* Since firmware API 1.7 loopback field keeps power class info as well */ +#define I40E_AQ_LOOPBACK_MASK 0x07 +#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 +#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) __le16 max_frame_size; u8 config; #define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 power_desc; + union { + struct { + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 #define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; + u8 reserved[4]; + }; + struct { + u8 link_type[4]; + u8 link_type_ext; + }; + }; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 7346d8850c8e8..64c15f4c9d2bd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1821,7 +1821,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw_link_info->fec_info = resp->config & (I40E_AQ_CONFIG_FEC_KR_ENA | I40E_AQ_CONFIG_FEC_RS_ENA); hw_link_info->ext_info = resp->ext_info; - hw_link_info->loopback = resp->loopback; + hw_link_info->loopback = resp->loopback & I40E_AQ_LOOPBACK_MASK; hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size); hw_link_info->pacing = resp->config & I40E_AQ_CONFIG_PACING_MASK; @@ -1852,6 +1852,15 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE) hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU; + if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && + hw->aq.api_min_ver >= 7) { + __le32 tmp; + + memcpy(&tmp, resp->link_type, sizeof(tmp)); + hw->phy.phy_types = le32_to_cpu(tmp); + hw->phy.phy_types |= ((u64)resp->link_type_ext << 32); + } + /* save link status information */ if (link) *link = *hw_link_info; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index f9f48d1900b0a..709d114fc305d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1730,6 +1730,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, I40E_PHY_TYPE_10GBASE_AOC = 0xC, I40E_PHY_TYPE_40GBASE_AOC = 0xD, + I40E_PHY_TYPE_UNRECOGNIZED = 0xE, + I40E_PHY_TYPE_UNSUPPORTED = 0xF, I40E_PHY_TYPE_100BASE_TX = 0x11, I40E_PHY_TYPE_1000BASE_T = 0x12, I40E_PHY_TYPE_10GBASE_T = 0x13, @@ -1748,6 +1750,8 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_EMPTY = 0xFE, + I40E_PHY_TYPE_DEFAULT = 0xFF, I40E_PHY_TYPE_MAX }; @@ -1938,19 +1942,31 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 #define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ +/* Since firmware API 1.7 loopback field keeps power class info as well */ +#define I40E_AQ_LOOPBACK_MASK 0x07 +#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 +#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) __le16 max_frame_size; u8 config; #define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 power_desc; + union { + struct { + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 #define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; + u8 reserved[4]; + }; + struct { + u8 link_type[4]; + u8 link_type_ext; + }; + }; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); -- GitLab From 9c0e5caf6398d6b892dc5046c421890e32ab5fa3 Mon Sep 17 00:00:00 2001 From: Filip Sadowski Date: Tue, 22 Aug 2017 06:57:44 -0400 Subject: [PATCH 0791/1507] i40e: Add support for 'ethtool -m' This patch adds support for 'ethtool -m' command which displays information about (Q)SFP+ module plugged into NIC's cage. Signed-off-by: Filip Sadowski Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40e/i40e_adminq_cmd.h | 18 ++ drivers/net/ethernet/intel/i40e/i40e_common.c | 69 ++++++++ .../net/ethernet/intel/i40e/i40e_ethtool.c | 154 ++++++++++++++++++ .../net/ethernet/intel/i40e/i40e_prototype.h | 9 + drivers/net/ethernet/intel/i40e/i40e_type.h | 13 ++ .../ethernet/intel/i40evf/i40e_adminq_cmd.h | 18 ++ .../net/ethernet/intel/i40evf/i40e_common.c | 69 ++++++++ .../ethernet/intel/i40evf/i40e_prototype.h | 9 + drivers/net/ethernet/intel/i40evf/i40e_type.h | 12 ++ 9 files changed, 371 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 5d0291c1337ee..ed7bbe14bc6e3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -244,6 +244,8 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_set_phy_debug = 0x0622, i40e_aqc_opc_upload_ext_phy_fm = 0x0625, i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, /* NVM commands */ i40e_aqc_opc_nvm_read = 0x0701, @@ -2053,6 +2055,22 @@ struct i40e_aqc_run_phy_activity { I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); +/* Set PHY Register command (0x0628) */ +/* Get PHY Register command (0x0629) */ +struct i40e_aqc_phy_register_access { + u8 phy_interface; +#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 + u8 dev_address; + u8 reserved1[2]; + __le32 reg_address; + __le32 reg_value; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); + /* NVM Read command (indirect 0x0701) * NVM Erase commands (direct 0x0702) * NVM Update commands (indirect 0x0703) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 64c15f4c9d2bd..fada037998508 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -5062,6 +5062,75 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) wr32(hw, reg_addr, reg_val); } +/** + * i40e_aq_set_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: new register value + * @cmd_details: pointer to command details structure or NULL + * + * Write the external PHY register. + **/ +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + cmd->reg_value = cpu_to_le32(reg_val); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** + * i40e_aq_get_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: read register value + * @cmd_details: pointer to command details structure or NULL + * + * Read the external PHY register. + **/ +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + if (!status) + *reg_val = le32_to_cpu(cmd->reg_value); + + return status; +} + /** * i40e_aq_write_ppp - Write pipeline personalization profile (ppp) * @hw: pointer to the hw struct diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 05e89864f781c..1136d02e2e956 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4196,6 +4196,158 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) return 0; } +/** + * i40e_get_module_info - get (Q)SFP+ module type info + * @netdev: network interface device structure + * @modinfo: module EEPROM size and layout information structure + **/ +static int i40e_get_module_info(struct net_device *netdev, + struct ethtool_modinfo *modinfo) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + u32 sff8472_comp = 0; + u32 sff8472_swap = 0; + u32 sff8636_rev = 0; + i40e_status status; + u32 type = 0; + + /* Check if firmware supports reading module EEPROM. */ + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) { + netdev_err(vsi->netdev, "Module EEPROM memory read not supported. Please update the NVM image.\n"); + return -EINVAL; + } + + status = i40e_update_link_info(hw); + if (status) + return -EIO; + + if (hw->phy.link_info.phy_type == I40E_PHY_TYPE_EMPTY) { + netdev_err(vsi->netdev, "Cannot read module EEPROM memory. No module connected.\n"); + return -EINVAL; + } + + type = hw->phy.link_info.module_type[0]; + + switch (type) { + case I40E_MODULE_TYPE_SFP: + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + I40E_I2C_EEPROM_DEV_ADDR, + I40E_MODULE_SFF_8472_COMP, + &sff8472_comp, NULL); + if (status) + return -EIO; + + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + I40E_I2C_EEPROM_DEV_ADDR, + I40E_MODULE_SFF_8472_SWAP, + &sff8472_swap, NULL); + if (status) + return -EIO; + + /* Check if the module requires address swap to access + * the other EEPROM memory page. + */ + if (sff8472_swap & I40E_MODULE_SFF_ADDR_MODE) { + netdev_warn(vsi->netdev, "Module address swap to access page 0xA2 is not supported.\n"); + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else if (sff8472_comp == 0x00) { + /* Module is not SFF-8472 compliant */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + break; + case I40E_MODULE_TYPE_QSFP_PLUS: + /* Read from memory page 0. */ + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + 0, + I40E_MODULE_REVISION_ADDR, + &sff8636_rev, NULL); + if (status) + return -EIO; + /* Determine revision compliance byte */ + if (sff8636_rev > 0x02) { + /* Module is SFF-8636 compliant */ + modinfo->type = ETH_MODULE_SFF_8636; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + } + break; + case I40E_MODULE_TYPE_QSFP28: + modinfo->type = ETH_MODULE_SFF_8636; + modinfo->eeprom_len = I40E_MODULE_QSFP_MAX_LEN; + break; + default: + netdev_err(vsi->netdev, "Module type unrecognized\n"); + return -EINVAL; + } + return 0; +} + +/** + * i40e_get_module_eeprom - fills buffer with (Q)SFP+ module memory contents + * @netdev: network interface device structure + * @ee: EEPROM dump request structure + * @data: buffer to be filled with EEPROM contents + **/ +static int i40e_get_module_eeprom(struct net_device *netdev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + bool is_sfp = false; + i40e_status status; + u32 value = 0; + int i; + + if (!ee || !ee->len || !data) + return -EINVAL; + + if (hw->phy.link_info.module_type[0] == I40E_MODULE_TYPE_SFP) + is_sfp = true; + + for (i = 0; i < ee->len; i++) { + u32 offset = i + ee->offset; + u32 addr = is_sfp ? I40E_I2C_EEPROM_DEV_ADDR : 0; + + /* Check if we need to access the other memory page */ + if (is_sfp) { + if (offset >= ETH_MODULE_SFF_8079_LEN) { + offset -= ETH_MODULE_SFF_8079_LEN; + addr = I40E_I2C_EEPROM_DEV_ADDR2; + } + } else { + while (offset >= ETH_MODULE_SFF_8436_LEN) { + /* Compute memory page number and offset. */ + offset -= ETH_MODULE_SFF_8436_LEN / 2; + addr++; + } + } + + status = i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, + addr, offset, &value, NULL); + if (status) + return -EIO; + data[i] = value; + } + return 0; +} + static const struct ethtool_ops i40e_ethtool_ops = { .get_drvinfo = i40e_get_drvinfo, .get_regs_len = i40e_get_regs_len, @@ -4228,6 +4380,8 @@ static const struct ethtool_ops i40e_ethtool_ops = { .set_rxfh = i40e_set_rxfh, .get_channels = i40e_get_channels, .set_channels = i40e_set_channels, + .get_module_info = i40e_get_module_info, + .get_module_eeprom = i40e_get_module_eeprom, .get_ts_info = i40e_get_ts_info, .get_priv_flags = i40e_get_priv_flags, .set_priv_flags = i40e_set_priv_flags, diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index a39b131978915..01502561035c2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -360,6 +360,15 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); + i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, u16 reg, u8 phy_addr, u16 *value); i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index fd4bbdd88b575..8b0b9f826b7f6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -428,6 +428,18 @@ struct i40e_nvm_access { u8 data[1]; }; +/* (Q)SFP module access definitions */ +#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 +#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 +#define I40E_MODULE_TYPE_ADDR 0x00 +#define I40E_MODULE_REVISION_ADDR 0x01 +#define I40E_MODULE_SFF_8472_COMP 0x5E +#define I40E_MODULE_SFF_8472_SWAP 0x5C +#define I40E_MODULE_SFF_ADDR_MODE 0x04 +#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D +#define I40E_MODULE_TYPE_QSFP28 0x11 +#define I40E_MODULE_QSFP_MAX_LEN 640 + /* PCI bus types */ enum i40e_bus_type { i40e_bus_type_unknown = 0, @@ -598,6 +610,7 @@ struct i40e_hw { struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ #define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0) +#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) u64 flags; /* debug mask */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 709d114fc305d..eee7ece42b392 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -244,6 +244,8 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_set_phy_debug = 0x0622, i40e_aqc_opc_upload_ext_phy_fm = 0x0625, i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, /* NVM commands */ i40e_aqc_opc_nvm_read = 0x0701, @@ -2046,6 +2048,22 @@ struct i40e_aqc_run_phy_activity { I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); +/* Set PHY Register command (0x0628) */ +/* Get PHY Register command (0x0629) */ +struct i40e_aqc_phy_register_access { + u8 phy_interface; +#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 +#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 + u8 dev_address; + u8 reserved1[2]; + __le32 reg_address; + __le32 reg_value; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); + /* NVM Read command (indirect 0x0701) * NVM Erase commands (direct 0x0702) * NVM Update commands (indirect 0x0703) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 8d3a2bfe186af..7d70bf69b2492 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -1041,6 +1041,75 @@ void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) wr32(hw, reg_addr, reg_val); } +/** + * i40evf_aq_set_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: new register value + * @cmd_details: pointer to command details structure or NULL + * + * Reset the external PHY. + **/ +i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + cmd->reg_value = cpu_to_le32(reg_val); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} + +/** + * i40evf_aq_get_phy_register + * @hw: pointer to the hw struct + * @phy_select: select which phy should be accessed + * @dev_addr: PHY device address + * @reg_addr: PHY register address + * @reg_val: read register value + * @cmd_details: pointer to command details structure or NULL + * + * Reset the external PHY. + **/ +i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_phy_register_access *cmd = + (struct i40e_aqc_phy_register_access *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_register); + + cmd->phy_interface = phy_select; + cmd->dev_address = dev_addr; + cmd->reg_address = cpu_to_le32(reg_addr); + + status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); + if (!status) + *reg_val = le32_to_cpu(cmd->reg_value); + + return status; +} + /** * i40e_aq_send_msg_to_pf * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index c9836bba487de..b624b59940758 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -111,6 +111,15 @@ i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); +i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); + i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 phy_addr, u16 *value); i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 2ea919d9cdcf0..b53584e3d580b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -401,6 +401,18 @@ struct i40e_nvm_access { u8 data[1]; }; +/* (Q)SFP module access definitions */ +#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 +#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 +#define I40E_MODULE_TYPE_ADDR 0x00 +#define I40E_MODULE_REVISION_ADDR 0x01 +#define I40E_MODULE_SFF_8472_COMP 0x5E +#define I40E_MODULE_SFF_8472_SWAP 0x5C +#define I40E_MODULE_SFF_ADDR_MODE 0x04 +#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D +#define I40E_MODULE_TYPE_QSFP28 0x11 +#define I40E_MODULE_QSFP_MAX_LEN 640 + /* PCI bus types */ enum i40e_bus_type { i40e_bus_type_unknown = 0, -- GitLab From 00f6c2f5e20bbdb638e58c50c6e6b1d8b796d6f6 Mon Sep 17 00:00:00 2001 From: Mariusz Stachura Date: Tue, 22 Aug 2017 06:57:45 -0400 Subject: [PATCH 0792/1507] i40e: use admin queue for setting LEDs behavior Instead of accessing register directly, use newly added AQC in order to blink LEDs. Introduce and utilize a new flag to prevent excessive API version checking. Signed-off-by: Mariusz Stachura Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_adminq.c | 6 + drivers/net/ethernet/intel/i40e/i40e_common.c | 115 ++++++++++++++---- drivers/net/ethernet/intel/i40evf/i40e_type.h | 2 + 3 files changed, 99 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index ba04988e05980..08f63226105a8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -607,6 +607,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) &oem_lo); hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo; + if (hw->mac.type == I40E_MAC_XL710 && + hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && + hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) { + hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE; + } + if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { ret_code = I40E_ERR_FIRMWARE_API_VERSION; goto init_adminq_free_arq; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index fada037998508..a4838779de5d1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -4836,6 +4836,74 @@ i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, return status; } +/** + * i40e_led_get_reg - read LED register + * @hw: pointer to the HW structure + * @led_addr: LED register address + * @reg_val: read register value + **/ +static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr, + u32 *reg_val) +{ + enum i40e_status_code status; + u8 phy_addr = 0; + u8 port_num; + u32 i; + + *reg_val = 0; + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + reg_val, NULL); + } else { + i = rd32(hw, I40E_PFGEN_PORTNUM); + port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); + phy_addr = i40e_get_phy_address(hw, port_num); + status = i40e_read_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + (u16 *)reg_val); + } + return status; +} + +/** + * i40e_led_set_reg - write LED register + * @hw: pointer to the HW structure + * @led_addr: LED register address + * @reg_val: register value to write + **/ +static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr, + u32 reg_val) +{ + enum i40e_status_code status; + u8 phy_addr = 0; + u8 port_num; + u32 i; + + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_set_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + reg_val, NULL); + } else { + i = rd32(hw, I40E_PFGEN_PORTNUM); + port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); + phy_addr = i40e_get_phy_address(hw, port_num); + status = i40e_write_phy_register_clause45(hw, + I40E_PHY_COM_REG_PAGE, + led_addr, phy_addr, + (u16)reg_val); + } + + return status; +} + /** * i40e_led_get_phy - return current on/off mode * @hw: pointer to the hw struct @@ -4853,7 +4921,19 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, u16 temp_addr; u8 port_num; u32 i; - + u32 reg_val_aq; + + if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { + status = + i40e_aq_get_phy_register(hw, + I40E_AQ_PHY_REG_ACCESS_EXTERNAL, + I40E_PHY_COM_REG_PAGE, + I40E_PHY_LED_PROV_REG_1, + ®_val_aq, NULL); + if (status == I40E_SUCCESS) + *val = (u16)reg_val_aq; + return status; + } temp_addr = I40E_PHY_LED_PROV_REG_1; i = rd32(hw, I40E_PFGEN_PORTNUM); port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); @@ -4888,51 +4968,38 @@ i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on, u16 led_addr, u32 mode) { i40e_status status = 0; - u16 led_ctl = 0; - u16 led_reg = 0; - u8 phy_addr = 0; - u8 port_num; - u32 i; + u32 led_ctl = 0; + u32 led_reg = 0; - i = rd32(hw, I40E_PFGEN_PORTNUM); - port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); - phy_addr = i40e_get_phy_address(hw, port_num); - status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_led_get_reg(hw, led_addr, &led_reg); if (status) return status; led_ctl = led_reg; if (led_reg & I40E_PHY_LED_LINK_MODE_MASK) { led_reg = 0; - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, - led_reg); + status = i40e_led_set_reg(hw, led_addr, led_reg); if (status) return status; } - status = i40e_read_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, &led_reg); + status = i40e_led_get_reg(hw, led_addr, &led_reg); if (status) goto restore_config; if (on) led_reg = I40E_PHY_LED_MANUAL_ON; else led_reg = 0; - status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_reg); + + status = i40e_led_set_reg(hw, led_addr, led_reg); if (status) goto restore_config; if (mode & I40E_PHY_LED_MODE_ORIG) { led_ctl = (mode & I40E_PHY_LED_MODE_MASK); - status = i40e_write_phy_register_clause45(hw, - I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); + status = i40e_led_set_reg(hw, led_addr, led_ctl); } return status; + restore_config: - status = i40e_write_phy_register_clause45(hw, I40E_PHY_COM_REG_PAGE, - led_addr, phy_addr, led_ctl); + status = i40e_led_set_reg(hw, led_addr, led_ctl); return status; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index b53584e3d580b..48eacf5e73e44 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -568,6 +568,8 @@ struct i40e_hw { /* LLDP/DCBX Status */ u16 dcbx_status; +#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) + /* DCBX info */ struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */ struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ -- GitLab From ba4e003d29c1d32776f156695fb00adf7df86ee2 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 22 Aug 2017 06:57:46 -0400 Subject: [PATCH 0793/1507] i40e: don't hold spinlock while resetting VF When we refactored handling of the PVID in commit 9af52f60b2d9 ("i40e: use (add|rm)_vlan_all_mac helper functions when changing PVID") we introduced a scheduling while atomic regression. This occurred because we now held the spinlock across a call to i40e_reset_vf(), which results in a usleep_range() call that triggers a scheduling while atomic bug. This was rare as it only occurred if the user configured a VLAN on a VF and also attempted to reconfigure the VF from the host system with a port VLAN. We do need to hold the lock while calling i40e_is_vsi_in_vlan(), but we should not be holding it while we reset the VF. We'll fix this by introducing a separate helper function i40e_vsi_has_vlans which checks whether we have a PVID and whether the VSI has configured VLANs. This helper function will manage its own need for the mac_filter_hash_lock. Then, we can move the acquiring of the spinlock until after we reset the VF, which ensures that we do not sleep while holding the lock. Using a separate function like this makes the code more clear and is easier to read than attempting to release and re-acquire the spinlock when we reset the VF. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 36 ++++++++++++++++--- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 9e3667fc7f6ae..53ead127b293d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2925,6 +2925,34 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) return ret; } +/** + * i40e_vsi_has_vlans - True if VSI has configured VLANs + * @vsi: pointer to the vsi + * + * Check if a VSI has configured any VLANs. False if we have a port VLAN or if + * we have no configured VLANs. Do not call while holding the + * mac_filter_hash_lock. + */ +static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi) +{ + bool have_vlans; + + /* If we have a port VLAN, then the VSI cannot have any VLANs + * configured, as all MAC/VLAN filters will be assigned to the PVID. + */ + if (vsi->info.pvid) + return false; + + /* Since we don't have a PVID, we know that if the device is in VLAN + * mode it must be because of a VLAN filter configured on this VSI. + */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + have_vlans = i40e_is_vsi_in_vlan(vsi); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + + return have_vlans; +} + /** * i40e_ndo_set_vf_port_vlan * @netdev: network interface device structure @@ -2977,10 +3005,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - /* Locked once because multiple functions below iterate list */ - spin_lock_bh(&vsi->mac_filter_hash_lock); - - if (le16_to_cpu(vsi->info.pvid) == 0 && i40e_is_vsi_in_vlan(vsi)) { + if (i40e_vsi_has_vlans(vsi)) { dev_err(&pf->pdev->dev, "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", vf_id); @@ -2993,6 +3018,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, vsi = pf->vsi[vf->lan_vsi_idx]; } + /* Locked once because multiple functions below iterate list */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + /* Check for condition where there was already a port VLAN ID * filter set and now it is being deleted by setting it to zero. * Additionally check for the condition where there was a port -- GitLab From eeeddbb80640ef63466a54bc118f66c81487bc42 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 22 Aug 2017 06:57:47 -0400 Subject: [PATCH 0794/1507] i40e: drop i40e_pf *pf from i40e_vc_disable_vf() It's never used, and the vf structure could get back to the PF if necessary. Lets just drop the extra unneeded parameter. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 53ead127b293d..70a79864177af 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -154,12 +154,11 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) /** * i40e_vc_disable_vf - * @pf: pointer to the PF info * @vf: pointer to the VF info * * Disable the VF through a SW reset **/ -static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf) +static inline void i40e_vc_disable_vf(struct i40e_vf *vf) { i40e_vc_notify_vf_reset(vf); i40e_reset_vf(vf, false); @@ -2918,7 +2917,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } /* Force the VF driver stop so it has to reload with new MAC address */ - i40e_vc_disable_vf(pf, vf); + i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n"); error_param: @@ -3013,7 +3012,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, * the right thing by reconfiguring his network correctly * and then reloading the VF driver. */ - i40e_vc_disable_vf(pf, vf); + i40e_vc_disable_vf(vf); /* During reset the VF got a new VSI, so refresh the pointer. */ vsi = pf->vsi[vf->lan_vsi_idx]; } -- GitLab From f18d20218a14d11d8fd6ed32e66ad199c8c93280 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 22 Aug 2017 06:57:48 -0400 Subject: [PATCH 0795/1507] i40e: make use of i40e_vc_disable_vf Replace i40e_vc_notify_vf_reset and i40e_reset_vf with a call to i40e_vc_disable_vf which does this exact thing. This matches similar code patterns throughout the driver. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 70a79864177af..94ee243f110e0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3388,8 +3388,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) goto out; vf->trusted = setting; - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_disable_vf(vf); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); out: -- GitLab From d43d60e5eb9504aa6f8f390aa0313cc8e3816b82 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 22 Aug 2017 06:57:49 -0400 Subject: [PATCH 0796/1507] i40e: ensure reset occurs when disabling VF It is possible although rare that we may not reset when i40e_vc_disable_vf() is called. This can lead to some weird circumstances with some values not being properly set. Modify i40e_reset_vf() to return a code indicating whether it reset or not. Now, i40e_vc_disable_vf() can wait until a reset actually occurs. If it fails to free up within a reasonable time frame we'll display a warning message. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 42 +++++++++++++++---- .../ethernet/intel/i40e/i40e_virtchnl_pf.h | 4 +- 2 files changed, 35 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 94ee243f110e0..7742cf3d38d91 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -156,12 +156,28 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) * i40e_vc_disable_vf * @vf: pointer to the VF info * - * Disable the VF through a SW reset + * Disable the VF through a SW reset. **/ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) { + int i; + i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + + /* We want to ensure that an actual reset occurs initiated after this + * function was called. However, we do not want to wait forever, so + * we'll give a reasonable time and print a message if we failed to + * ensure a reset. + */ + for (i = 0; i < 20; i++) { + if (i40e_reset_vf(vf, false)) + return; + usleep_range(10000, 20000); + } + + dev_warn(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); } /** @@ -1051,9 +1067,9 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * reset the VF + * Returns true if the VF is reset, false otherwise. **/ -void i40e_reset_vf(struct i40e_vf *vf, bool flr) +bool i40e_reset_vf(struct i40e_vf *vf, bool flr) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; @@ -1061,9 +1077,11 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) u32 reg; int i; - /* If VFs have been disabled, there is no need to reset */ + /* If the VFs have been disabled, this means something else is + * resetting the VF, so we shouldn't continue. + */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return; + return false; i40e_trigger_vf_reset(vf, flr); @@ -1100,6 +1118,8 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); + + return true; } /** @@ -1111,8 +1131,10 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) * VF, then do all the waiting in one chunk, and finally finish restoring each * VF after the wait. This is useful during PF routines which need to reset * all VFs, as otherwise it must perform these resets in a serialized fashion. + * + * Returns true if any VFs were reset, and false otherwise. **/ -void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) +bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) { struct i40e_hw *hw = &pf->hw; struct i40e_vf *vf; @@ -1121,11 +1143,11 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) /* If we don't have any VFs, then there is nothing to reset */ if (!pf->num_alloc_vfs) - return; + return false; /* If VFs have been disabled, there is no need to reset */ if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) - return; + return false; /* Begin reset on all VFs at once */ for (v = 0; v < pf->num_alloc_vfs; v++) @@ -1200,6 +1222,8 @@ void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); + + return true; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5111d05d5f2f0..5ea42ad094bcc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -122,8 +122,8 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); -void i40e_reset_vf(struct i40e_vf *vf, bool flr); -void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); +bool i40e_reset_vf(struct i40e_vf *vf, bool flr); +bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ -- GitLab From 5b36e8d04b4439c9ceb814bfdfe1284737f9c632 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 22 Aug 2017 06:57:50 -0400 Subject: [PATCH 0797/1507] i40evf: Enable VF to request an alternate queue allocation Currently the VF gets a default number of allocated queues from HW on init and it could choose to enable or disable those allocated queues. This makes it such that the VF can request more or less underlying allocated queues from the PF. First the VF negotiates the number of queues it wants that can be supported by the PF and if successful asks for a reset. During reset the PF will reallocate the HW queues for the VF and will then remap the new queues. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40evf/i40evf.h | 4 + .../ethernet/intel/i40evf/i40evf_ethtool.c | 38 +++++++- .../net/ethernet/intel/i40evf/i40evf_main.c | 94 ++++++++++++++++++- .../ethernet/intel/i40evf/i40evf_virtchnl.c | 44 ++++++++- 4 files changed, 173 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 82f69031e5cdb..5982362c56430 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -102,6 +102,7 @@ struct i40e_vsi { #define I40E_TX_CTXTDESC(R, i) \ (&(((struct i40e_tx_context_desc *)((R)->desc))[i])) #define MAX_QUEUES 16 +#define I40EVF_MAX_REQ_QUEUES 4 #define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) #define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) @@ -200,6 +201,7 @@ struct i40evf_adapter { struct list_head vlan_filter_list; char misc_vector_name[IFNAMSIZ + 9]; int num_active_queues; + int num_req_queues; /* TX */ struct i40e_ring *tx_rings; @@ -235,6 +237,7 @@ struct i40evf_adapter { #define I40EVF_FLAG_PROMISC_ON BIT(18) #define I40EVF_FLAG_ALLMULTI_ON BIT(19) #define I40EVF_FLAG_LEGACY_RX BIT(20) +#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED @@ -349,6 +352,7 @@ void i40evf_deconfigure_queues(struct i40evf_adapter *adapter); void i40evf_enable_queues(struct i40evf_adapter *adapter); void i40evf_disable_queues(struct i40evf_adapter *adapter); void i40evf_map_queues(struct i40evf_adapter *adapter); +int i40evf_request_queues(struct i40evf_adapter *adapter, int num); void i40evf_add_ether_addrs(struct i40evf_adapter *adapter); void i40evf_del_ether_addrs(struct i40evf_adapter *adapter); void i40evf_add_vlans(struct i40evf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index 65874d6b3ab9d..da006fa3fec1c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -669,7 +669,7 @@ static void i40evf_get_channels(struct net_device *netdev, struct i40evf_adapter *adapter = netdev_priv(netdev); /* Report maximum channels */ - ch->max_combined = adapter->num_active_queues; + ch->max_combined = I40EVF_MAX_REQ_QUEUES; ch->max_other = NONQ_VECS; ch->other_count = NONQ_VECS; @@ -677,6 +677,41 @@ static void i40evf_get_channels(struct net_device *netdev, ch->combined_count = adapter->num_active_queues; } +/** + * i40evf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with the PF then do a reset. During + * reset we'll realloc queues and fix the RSS table. Returns 0 on success, + * negative on failure. + **/ +static int i40evf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + int num_req = ch->combined_count; + + if (num_req != adapter->num_active_queues && + !(adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { + dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); + return -EINVAL; + } + + /* All of these should have already been checked by ethtool before this + * even gets to us, but just to be sure. + */ + if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES) + return -EINVAL; + + if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) + return -EINVAL; + + adapter->num_req_queues = num_req; + return i40evf_request_queues(adapter, num_req); +} + /** * i40evf_get_rxfh_key_size - get the RSS hash key size * @netdev: network interface device structure @@ -785,6 +820,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .get_rxfh = i40evf_get_rxfh, .set_rxfh = i40evf_set_rxfh, .get_channels = i40evf_get_channels, + .set_channels = i40evf_set_channels, .get_rxfh_key_size = i40evf_get_rxfh_key_size, .get_link_ksettings = i40evf_get_link_ksettings, }; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 69ef6c1d5364f..8c513ce84345d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1189,9 +1189,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) { int i, num_active_queues; - num_active_queues = min_t(int, - adapter->vsi_res->num_queue_pairs, - (int)(num_online_cpus())); + /* If we're in reset reallocating queues we don't actually know yet for + * certain the PF gave us the number of queues we asked for but we'll + * assume it did. Once basic reset is finished we'll confirm once we + * start negotiating config with PF. + */ + if (adapter->num_req_queues) + num_active_queues = adapter->num_req_queues; + else + num_active_queues = min_t(int, + adapter->vsi_res->num_queue_pairs, + (int)(num_online_cpus())); + adapter->tx_rings = kcalloc(num_active_queues, sizeof(struct i40e_ring), GFP_KERNEL); @@ -1539,6 +1548,48 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter) adapter->rss_lut = NULL; } +/** + * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors + * @adapter: board private structure + * + * Returns 0 on success, negative on failure + **/ +static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int err; + + if (netif_running(netdev)) + i40evf_free_traffic_irqs(adapter); + i40evf_free_misc_irq(adapter); + i40evf_reset_interrupt_capability(adapter); + i40evf_free_q_vectors(adapter); + i40evf_free_queues(adapter); + + err = i40evf_init_interrupt_scheme(adapter); + if (err) + goto err; + + netif_tx_stop_all_queues(netdev); + + err = i40evf_request_misc_irq(adapter); + if (err) + goto err; + + set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + + err = i40evf_map_rings_to_vectors(adapter); + if (err) + goto err; + + if (RSS_AQ(adapter)) + adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + else + err = i40evf_init_rss(adapter); +err: + return err; +} + /** * i40evf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long @@ -1885,8 +1936,15 @@ static void i40evf_reset_task(struct work_struct *work) if (err) dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", err); + adapter->aq_required = 0; - adapter->aq_required = I40EVF_FLAG_AQ_GET_CONFIG; + if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { + err = i40evf_reinit_interrupt_scheme(adapter); + if (err) + goto reset_err; + } + + adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG; adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; /* re-add all MAC filters */ @@ -1916,6 +1974,15 @@ static void i40evf_reset_task(struct work_struct *work) if (err) goto reset_err; + if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { + err = i40evf_request_traffic_irqs(adapter, + netdev->name); + if (err) + goto reset_err; + + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + } + i40evf_configure(adapter); i40evf_up_complete(adapter); @@ -2431,9 +2498,9 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw) int i40evf_process_config(struct i40evf_adapter *adapter) { struct virtchnl_vf_resource *vfres = adapter->vf_res; + int i, num_req_queues = adapter->num_req_queues; struct net_device *netdev = adapter->netdev; struct i40e_vsi *vsi = &adapter->vsi; - int i; netdev_features_t hw_enc_features; netdev_features_t hw_features; @@ -2447,6 +2514,23 @@ int i40evf_process_config(struct i40evf_adapter *adapter) return -ENODEV; } + if (num_req_queues && + num_req_queues != adapter->vsi_res->num_queue_pairs) { + /* Problem. The PF gave us fewer queues than what we had + * negotiated in our request. Need a reset to see if we can't + * get back to a working state. + */ + dev_err(&adapter->pdev->dev, + "Requested %d queues, but PF only gave us %d.\n", + num_req_queues, + adapter->vsi_res->num_queue_pairs); + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; + i40evf_schedule_reset(adapter); + return -ENODEV; + } + adapter->num_req_queues = 0; + hw_enc_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 2bb0fe00361f2..2bb81c39d85fa 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -160,7 +160,8 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | - VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -384,6 +385,32 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) kfree(vimi); } +/** + * i40evf_request_queues + * @adapter: adapter structure + * @num: number of requested queues + * + * We get a default number of queues from the PF. This enables us to request a + * different number. Returns 0 on success, negative on failure + **/ +int i40evf_request_queues(struct i40evf_adapter *adapter, int num) +{ + struct virtchnl_vf_res_request vfres; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot request queues, command %d pending\n", + adapter->current_op); + return -EBUSY; + } + + vfres.num_queue_pairs = num; + + adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; + return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, + (u8 *)&vfres, sizeof(vfres)); +} + /** * i40evf_add_ether_addrs * @adapter: adapter structure @@ -1068,6 +1095,21 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, "Invalid message %d from PF\n", v_opcode); } break; + case VIRTCHNL_OP_REQUEST_QUEUES: { + struct virtchnl_vf_res_request *vfres = + (struct virtchnl_vf_res_request *)msg; + if (vfres->num_queue_pairs == adapter->num_req_queues) { + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + i40evf_schedule_reset(adapter); + } else { + dev_info(&adapter->pdev->dev, + "Requested %d queues, PF can support %d\n", + adapter->num_req_queues, + vfres->num_queue_pairs); + adapter->num_req_queues = 0; + } + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", -- GitLab From 1b7b7596aeebc21913bad49eb6a2c364c4b2988a Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 22 Aug 2017 06:57:51 -0400 Subject: [PATCH 0798/1507] i40e: make i40evf_map_rings_to_vectors void This function cannot fail, so why is it returning a value? And why are we checking it? Why shouldn't we just make it void? Why is this commit message made up of only questions? Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 8c513ce84345d..f2f1e754c2ce3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -430,12 +430,11 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) * group the rings as "efficiently" as possible. You would add new * mapping configurations in here. **/ -static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) +static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) { int rings_remaining = adapter->num_active_queues; int ridx = 0, vidx = 0; int q_vectors; - int err = 0; q_vectors = adapter->num_msix_vectors - NONQ_VECS; @@ -451,8 +450,6 @@ static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) } adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; - - return err; } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1578,9 +1575,7 @@ static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) set_bit(__I40E_VSI_DOWN, adapter->vsi.state); - err = i40evf_map_rings_to_vectors(adapter); - if (err) - goto err; + i40evf_map_rings_to_vectors(adapter); if (RSS_AQ(adapter)) adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; -- GitLab From 41d0a4d0c8b144e44d92ea95e975d2434748d806 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 22 Aug 2017 06:57:52 -0400 Subject: [PATCH 0799/1507] i40e: fix handling of vf_states variable Currently we inappropriately clear the vf_states variable with a null assignment. This is problematic because we should be using atomic bitops on this variable and we don't actually want to clear all the flags. We should just clear the ones we know we want to clear. Additionally remove the I40E_VF_STATE_FCOEENA bit because it is no longer being used. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 5 ++++- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h | 1 - 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 7742cf3d38d91..989a65d60ac95 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -879,7 +879,8 @@ static void i40e_free_vf_res(struct i40e_vf *vf) } /* reset some of the state variables keeping track of the resources */ vf->num_queue_pairs = 0; - vf->vf_states = 0; + clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); + clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); } /** @@ -1586,6 +1587,8 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_IWARP)) { vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_IWARP; set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); + } else { + clear_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 5ea42ad094bcc..5efc4f92bb375 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -56,7 +56,6 @@ enum i40e_vf_states { I40E_VF_STATE_INIT = 0, I40E_VF_STATE_ACTIVE, I40E_VF_STATE_IWARPENA, - I40E_VF_STATE_FCOEENA, I40E_VF_STATE_DISABLED, I40E_VF_STATE_MC_PROMISC, I40E_VF_STATE_UC_PROMISC, -- GitLab From c53d11f669c0e7d0daf46a717b6712ad0b09de99 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 22 Aug 2017 06:57:53 -0400 Subject: [PATCH 0800/1507] i40e: fix client notify of VF reset Currently there is a bug in which the PF driver fails to inform clients of a VF reset which then causes clients to leak resources. The bug exists because we were incorrectly checking the I40E_VF_STATE_PRE_ENABLE bit. When a VF is first init we go through a reset to initialize variables and allocate resources but we don't want to inform clients of this first reset since the client isn't fully enabled yet so we set a state bit signifying we're in a "pre-enabled" client state. During the first reset we should be clearing the bit, allowing all following resets to notify the client of the reset when the bit is not set. This patch fixes the issue by negating the 'test_and_clear_bit' check to accurately reflect the behavior we want. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 989a65d60ac95..04568137e029d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1050,8 +1050,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf) set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); /* Do not notify the client during VF init */ - if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE, - &vf->vf_states)) + if (!test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE, + &vf->vf_states)) i40e_notify_client_of_vf_reset(pf, abs_vf_id); vf->num_vlan = 0; } -- GitLab From ab243ec9401d164531cc9bc07fb32231d72d1280 Mon Sep 17 00:00:00 2001 From: Scott Peterson Date: Tue, 22 Aug 2017 06:57:54 -0400 Subject: [PATCH 0801/1507] i40e: Stop dropping 802.1ad tags - eth proto 0x88a8 Enable i40e to pass traffic with VLAN tags using the 802.1ad ethernet protocol ID (0x88a8). This requires NIC firmware providing version 1.7 of the API. With older NIC firmware 802.1ad tagged packets will continue to be dropped. No VLAN offloads nor RSS are supported for 802.1ad VLANs. Signed-off-by: Scott Peterson Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_adminq.c | 6 ++++++ .../net/ethernet/intel/i40e/i40e_adminq_cmd.h | 17 ++++++++++++++++- drivers/net/ethernet/intel/i40e/i40e_common.c | 6 +++++- drivers/net/ethernet/intel/i40e/i40e_main.c | 7 +++++++ drivers/net/ethernet/intel/i40e/i40e_type.h | 6 ++++++ .../net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 17 ++++++++++++++++- drivers/net/ethernet/intel/i40evf/i40e_type.h | 6 ++++++ 7 files changed, 62 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 08f63226105a8..9dcb2a961197b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -613,6 +613,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE; } + /* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */ + if (hw->aq.api_maj_ver > 1 || + (hw->aq.api_maj_ver == 1 && + hw->aq.api_min_ver >= 7)) + hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE; + if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { ret_code = I40E_ERR_FIRMWARE_API_VERSION; goto init_adminq_free_arq; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index ed7bbe14bc6e3..4c85ea9cd89ae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -775,7 +775,22 @@ struct i40e_aqc_set_switch_config { #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; - u8 reserved[12]; + /* The ethertype in switch_tag is dropped on ingress and used + * internally by the switch. Set this to zero for the default + * of 0x88a8 (802.1ad). Should be zero for firmware API + * versions lower than 1.7. + */ + __le16 switch_tag; + /* The ethertypes in first_tag and second_tag are used to + * match the outer and inner VLAN tags (respectively) when HW + * double VLAN tagging is enabled via the set port parameters + * AQ command. Otherwise these are both ignored. Set them to + * zero for their defaults of 0x8100 (802.1Q). Should be zero + * for firmware API versions lower than 1.7. + */ + __le16 first_tag; + __le16 second_tag; + u8 reserved[6]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index a4838779de5d1..60542beda7ade 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -2402,7 +2402,11 @@ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, i40e_aqc_opc_set_switch_config); scfg->flags = cpu_to_le16(flags); scfg->valid_flags = cpu_to_le16(valid_flags); - + if (hw->flags & I40E_HW_FLAG_802_1AD_CAPABLE) { + scfg->switch_tag = cpu_to_le16(hw->switch_tag); + scfg->first_tag = cpu_to_le16(hw->first_tag); + scfg->second_tag = cpu_to_le16(hw->second_tag); + } status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 387f0863f7940..3f9e89b054ece 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11361,6 +11361,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.bus_id = pdev->bus->number; pf->instance = pfs_found; + /* Select something other than the 802.1ad ethertype for the + * switch to use internally and drop on ingress. + */ + hw->switch_tag = 0xffff; + hw->first_tag = ETH_P_8021AD; + hw->second_tag = ETH_P_8021Q; + INIT_LIST_HEAD(&pf->l3_flex_pit_list); INIT_LIST_HEAD(&pf->l4_flex_pit_list); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 8b0b9f826b7f6..4b32b1d38a661 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -610,9 +610,15 @@ struct i40e_hw { struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ #define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0) +#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) u64 flags; + /* Used in set switch config AQ command */ + u16 switch_tag; + u16 first_tag; + u16 second_tag; + /* debug mask */ u32 debug_mask; char err_str[16]; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index eee7ece42b392..ed5602f4bbcd6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -771,7 +771,22 @@ struct i40e_aqc_set_switch_config { #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; - u8 reserved[12]; + /* The ethertype in switch_tag is dropped on ingress and used + * internally by the switch. Set this to zero for the default + * of 0x88a8 (802.1ad). Should be zero for firmware API + * versions lower than 1.7. + */ + __le16 switch_tag; + /* The ethertypes in first_tag and second_tag are used to + * match the outer and inner VLAN tags (respectively) when HW + * double VLAN tagging is enabled via the set port parameters + * AQ command. Otherwise these are both ignored. Set them to + * zero for their defaults of 0x8100 (802.1Q). Should be zero + * for firmware API versions lower than 1.7. + */ + __le16 first_tag; + __le16 second_tag; + u8 reserved[6]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 48eacf5e73e44..9364b67fff9c4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -568,6 +568,7 @@ struct i40e_hw { /* LLDP/DCBX Status */ u16 dcbx_status; +#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) /* DCBX info */ @@ -575,6 +576,11 @@ struct i40e_hw { struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ + /* Used in set switch config AQ command */ + u16 switch_tag; + u16 first_tag; + u16 second_tag; + /* debug mask */ u32 debug_mask; char err_str[16]; -- GitLab From cb1dab0e01969d63717c7464cb5d75c77a39bf02 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 29 Sep 2017 16:22:57 +0800 Subject: [PATCH 0802/1507] drm/sun4i: hdmi: Disable clks in bind function error path and unbind function The HDMI driver enables the bus and mod clocks in the bind function, but does not disable them if it then bails our due to any errors. Neither does it disable the clocks in the unbind function. Fix this by adding a proper error path to the bind function, and clk_disable_unprepare calls to the unbind function. Also rename the err_cleanup_connector label to err_cleanup_encoder, since it is the encoder that gets cleaned up. Fixes: 9c5681011a0c ("drm/sun4i: Add HDMI support") Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20170929082306.16193-6-wens@csie.org --- drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 9ea6cd5a1370d..3cf1a6932facf 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -302,26 +302,29 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, hdmi->mod_clk = devm_clk_get(dev, "mod"); if (IS_ERR(hdmi->mod_clk)) { dev_err(dev, "Couldn't get the HDMI mod clock\n"); - return PTR_ERR(hdmi->mod_clk); + ret = PTR_ERR(hdmi->mod_clk); + goto err_disable_bus_clk; } clk_prepare_enable(hdmi->mod_clk); hdmi->pll0_clk = devm_clk_get(dev, "pll-0"); if (IS_ERR(hdmi->pll0_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n"); - return PTR_ERR(hdmi->pll0_clk); + ret = PTR_ERR(hdmi->pll0_clk); + goto err_disable_mod_clk; } hdmi->pll1_clk = devm_clk_get(dev, "pll-1"); if (IS_ERR(hdmi->pll1_clk)) { dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n"); - return PTR_ERR(hdmi->pll1_clk); + ret = PTR_ERR(hdmi->pll1_clk); + goto err_disable_mod_clk; } ret = sun4i_tmds_create(hdmi); if (ret) { dev_err(dev, "Couldn't create the TMDS clock\n"); - return ret; + goto err_disable_mod_clk; } writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG); @@ -362,7 +365,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, ret = sun4i_hdmi_i2c_create(dev, hdmi); if (ret) { dev_err(dev, "Couldn't create the HDMI I2C adapter\n"); - return ret; + goto err_disable_mod_clk; } drm_encoder_helper_add(&hdmi->encoder, @@ -422,6 +425,10 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, drm_encoder_cleanup(&hdmi->encoder); err_del_i2c_adapter: i2c_del_adapter(hdmi->i2c); +err_disable_mod_clk: + clk_disable_unprepare(hdmi->mod_clk); +err_disable_bus_clk: + clk_disable_unprepare(hdmi->bus_clk); return ret; } @@ -434,6 +441,8 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, drm_connector_cleanup(&hdmi->connector); drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); + clk_disable_unprepare(hdmi->mod_clk); + clk_disable_unprepare(hdmi->bus_clk); } static const struct component_ops sun4i_hdmi_ops = { -- GitLab From 6e60a3bbb45bd8b307269d6a821ee2c72d815846 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 2 Oct 2017 16:22:08 -0400 Subject: [PATCH 0803/1507] nbd: fix -ERESTARTSYS handling Christoph made it so that if we return'ed BLK_STS_RESOURCE whenever we got ERESTARTSYS from sending our packets we'd return BLK_STS_OK, which means we'd never requeue and just hang. We really need to return the right value from the upper layer. Fixes: fc17b6534eb8 ("blk-mq: switch ->queue_rq return value to blk_status_t") Signed-off-by: Josef Bacik Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3684e21d543f2..883dfebd3014b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -820,9 +820,13 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); + if (ret < 0) + ret = BLK_STS_IOERR; + else if (!ret) + ret = BLK_STS_OK; complete(&cmd->send_complete); - return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK; + return ret; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, -- GitLab From eefca20eb20c66b06cf5ed09b49b1a7caaa27b7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Oct 2017 12:20:51 -0700 Subject: [PATCH 0804/1507] socket, bpf: fix possible use after free Starting from linux-4.4, 3WHS no longer takes the listener lock. Since this time, we might hit a use-after-free in sk_filter_charge(), if the filter we got in the memcpy() of the listener content just happened to be replaced by a thread changing listener BPF filter. To fix this, we need to make sure the filter refcount is not already zero before incrementing it again. Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Signed-off-by: Eric Dumazet Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/core/filter.c | 12 ++++++++---- net/core/sock.c | 5 ++++- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 82edad58d0668..74b8c91fb5f44 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -989,10 +989,14 @@ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { - bool ret = __sk_filter_charge(sk, fp); - if (ret) - refcount_inc(&fp->refcnt); - return ret; + if (!refcount_inc_not_zero(&fp->refcnt)) + return false; + + if (!__sk_filter_charge(sk, fp)) { + sk_filter_release(fp); + return false; + } + return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) diff --git a/net/core/sock.c b/net/core/sock.c index 7d55c05f449d3..23953b741a41f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1684,13 +1684,16 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sock_reset_flag(newsk, SOCK_DONE); - filter = rcu_dereference_protected(newsk->sk_filter, 1); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter != NULL) /* though it's an empty new sock, the charging may fail * if sysctl_optmem_max was changed between creation of * original socket and cloning */ is_charged = sk_filter_charge(newsk, filter); + RCU_INIT_POINTER(newsk->sk_filter, filter); + rcu_read_unlock(); if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) { /* We need to make sure that we don't uncharge the new -- GitLab From 28a0bc4120d38a394499382ba21d6965a67a3703 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 27 Sep 2017 21:35:12 -0400 Subject: [PATCH 0805/1507] scsi: sd: Implement blacklist option for WRITE SAME w/ UNMAP SBC-4 states: "A MAXIMUM UNMAP LBA COUNT field set to a non-zero value indicates the maximum number of LBAs that may be unmapped by an UNMAP command" "A MAXIMUM WRITE SAME LENGTH field set to a non-zero value indicates the maximum number of contiguous logical blocks that the device server allows to be unmapped or written in a single WRITE SAME command." Despite the spec being clear on the topic, some devices incorrectly expect WRITE SAME commands with the UNMAP bit set to be limited to the value reported in MAXIMUM UNMAP LBA COUNT in the Block Limits VPD. Implement a blacklist option that can be used to accommodate devices with this behavior. Cc: Reported-by: Bill Kuzeja Reported-by: Ewan D. Milne Reviewed-by: Ewan D. Milne Tested-by: Laurence Oberman Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_scan.c | 3 +++ drivers/scsi/sd.c | 16 ++++++++++++---- include/scsi/scsi_device.h | 1 + include/scsi/scsi_devinfo.h | 1 + 4 files changed, 17 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index e7818afeda2be..15590a063ad94 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -956,6 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, if (*bflags & BLIST_NO_DIF) sdev->no_dif = 1; + if (*bflags & BLIST_UNMAP_LIMIT_WS) + sdev->unmap_limit_for_ws = 1; + sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT; if (*bflags & BLIST_TRY_VPD_PAGES) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index fb9f8b5f4673c..3d26a729825c9 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -715,13 +715,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS16_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS10_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 82e93ee94708c..67c5a9f223f77 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -192,6 +192,7 @@ struct scsi_device { unsigned no_dif:1; /* T10 PI (DIF) should be disabled */ unsigned broken_fua:1; /* Don't set FUA bit */ unsigned lun_in_cdb:1; /* Store LUN bits in CDB[1] */ + unsigned unmap_limit_for_ws:1; /* Use the UNMAP limit for WRITE SAME */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 9592570e092a3..36b03013d6291 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -29,5 +29,6 @@ #define BLIST_TRY_VPD_PAGES 0x10000000 /* Attempt to read VPD pages */ #define BLIST_NO_RSOC 0x20000000 /* don't try to issue RSOC */ #define BLIST_MAX_1024 0x40000000 /* maximum 1024 sector cdb length */ +#define BLIST_UNMAP_LIMIT_WS 0x80000000 /* Use UNMAP limit for WRITE SAME */ #endif -- GitLab From 77082ca503bed061f7fbda7cfd7c93beda967a41 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 27 Sep 2017 21:38:59 -0400 Subject: [PATCH 0806/1507] scsi: sd: Do not override max_sectors_kb sysfs setting A user may lower the max_sectors_kb setting in sysfs to accommodate certain workloads. Previously we would always set the max I/O size to either the block layer default or the optional preferred I/O size reported by the device. Keep the current heuristics for the initial setting of max_sectors_kb. For subsequent invocations, only update the current queue limit if it exceeds the capabilities of the hardware. Cc: Reported-by: Don Brace Reviewed-by: Martin Wilck Tested-by: Don Brace Signed-off-by: Martin K. Petersen --- drivers/scsi/sd.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3d26a729825c9..d175c5c5ccf87 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3107,8 +3107,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_security(sdkp, buffer); } - sdkp->first_scan = 0; - /* * We now have all cache related info, determine how we deal * with flush requests. @@ -3123,7 +3121,7 @@ static int sd_revalidate_disk(struct gendisk *disk) q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); /* - * Use the device's preferred I/O size for reads and writes + * Determine the device's preferred I/O size for reads and writes * unless the reported value is unreasonably small, large, or * garbage. */ @@ -3137,8 +3135,19 @@ static int sd_revalidate_disk(struct gendisk *disk) rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), (sector_t)BLK_DEF_MAX_SECTORS); - /* Combine with controller limits */ - q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); + /* Do not exceed controller limit */ + rw_max = min(rw_max, queue_max_hw_sectors(q)); + + /* + * Only update max_sectors if previously unset or if the current value + * exceeds the capabilities of the hardware. + */ + if (sdkp->first_scan || + q->limits.max_sectors > q->limits.max_dev_sectors || + q->limits.max_sectors > q->limits.max_hw_sectors) + q->limits.max_sectors = rw_max; + + sdkp->first_scan = 0; set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity)); sd_config_write_same(sdkp); -- GitLab From 9e10b5121ad991ea6e84ca40b15a04cdc551bfe9 Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Thu, 13 Jul 2017 09:11:21 -0700 Subject: [PATCH 0807/1507] scsi: libiscsi: Fix use-after-free race during iscsi_session_teardown Session attributes exposed through sysfs were freed before the device was destroyed, resulting in a potential use-after-free. Free these attributes after removing the device. Signed-off-by: Khazhismel Kumykov Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index bd4605a34f54d..c62e8d111fd97 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2851,9 +2851,6 @@ EXPORT_SYMBOL_GPL(iscsi_session_setup); /** * iscsi_session_teardown - destroy session, host, and cls_session * @cls_session: iscsi session - * - * The driver must have called iscsi_remove_session before - * calling this. */ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) { @@ -2863,6 +2860,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) iscsi_pool_free(&session->cmdpool); + iscsi_remove_session(cls_session); + kfree(session->password); kfree(session->password_in); kfree(session->username); @@ -2877,7 +2876,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->portal_type); kfree(session->discovery_parent_type); - iscsi_destroy_session(cls_session); + iscsi_free_session(cls_session); + iscsi_host_dec_session_cnt(shost); module_put(owner); } -- GitLab From 1c048a250aae1aaab0ba9dbec908f0c6cdb8614f Mon Sep 17 00:00:00 2001 From: Khazhismel Kumykov Date: Thu, 13 Jul 2017 09:11:22 -0700 Subject: [PATCH 0808/1507] scsi: libiscsi: Remove iscsi_destroy_session iscsi_session_teardown was the only user of this function. Function currently is just short for iscsi_remove_session + iscsi_free_session. Signed-off-by: Khazhismel Kumykov Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 16 ---------------- include/scsi/scsi_transport_iscsi.h | 1 - 2 files changed, 17 deletions(-) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 0190aeff5f7fd..7404d26895f5b 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2210,22 +2210,6 @@ void iscsi_free_session(struct iscsi_cls_session *session) } EXPORT_SYMBOL_GPL(iscsi_free_session); -/** - * iscsi_destroy_session - destroy iscsi session - * @session: iscsi_session - * - * Can be called by a LLD or iscsi_transport. There must not be - * any running connections. - */ -int iscsi_destroy_session(struct iscsi_cls_session *session) -{ - iscsi_remove_session(session); - ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n"); - iscsi_free_session(session); - return 0; -} -EXPORT_SYMBOL_GPL(iscsi_destroy_session); - /** * iscsi_create_conn - create iscsi class connection * @session: iscsi cls session diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 6183d20a01fbe..b266d2a3bcb1d 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -434,7 +434,6 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, unsigned int target_id); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); -extern int iscsi_destroy_session(struct iscsi_cls_session *session); extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); -- GitLab From 88e65389fce1f68ba6d13ae2fc0f8d7e5c338c52 Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Mon, 2 Oct 2017 12:59:38 -0500 Subject: [PATCH 0809/1507] scsi: ibmvscsis: Fix write_pending failure path For write_pending if the queue is down or client failed then return -EIO so that LIO can properly process the completed command. Prior we returned 0 since LIO could not handle it properly. Now with commit fa7e25cf13a6 ("target: Fix unknown fabric callback queue-full errors") that patch addresses LIO's ability to handle things right. Signed-off-by: Bryant G. Ly Signed-off-by: Martin K. Petersen --- drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 785fb42f66502..2799a6b08f736 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -3767,7 +3767,7 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd) */ if ((vscsi->flags & (CLIENT_FAILED | RESPONSE_Q_DOWN))) { pr_err("write_pending failed since: %d\n", vscsi->flags); - return 0; + return -EIO; } rc = srp_transfer_data(cmd, &vio_iu(iue)->srp.cmd, ibmvscsis_rdma, -- GitLab From 3b7af5c0fd9631762d1c4d7b4cee76f571dd3c2c Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Wed, 27 Sep 2017 12:55:51 +0800 Subject: [PATCH 0810/1507] powerpc: Fix action argument for cpufeatures-based TLB flush Commit 41d0c2ecde19 ("powerpc/powernv: Fix local TLB flush for boot and MCE on POWER9") introduced calls to __flush_tlb_power[89] from the cpufeatures code, specifying the number of sets to flush. However, these functions take an action argument, not a number of sets. This means we hit the BUG() in __flush_tlb_{206,300} when using cpufeatures-style configuration. This change passes TLB_INVAL_SCOPE_GLOBAL instead. Fixes: 41d0c2ecde19 ("powerpc/powernv: Fix local TLB flush for boot and MCE on POWER9") Cc: stable@vger.kernel.org # v4.13+ Signed-off-by: Jeremy Kerr Reviewed-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 1df770e8cbe03..7275fed271afa 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -102,10 +102,10 @@ static void cpufeatures_flush_tlb(void) case PVR_POWER8: case PVR_POWER8E: case PVR_POWER8NVL: - __flush_tlb_power8(POWER8_TLB_SETS); + __flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL); break; case PVR_POWER9: - __flush_tlb_power9(POWER9_TLB_SETS_HASH); + __flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL); break; default: pr_err("unknown CPU version for boot TLB flush\n"); -- GitLab From 070e004912fed099263408bf2ff1bbc6926abe2e Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Sun, 1 Oct 2017 16:33:03 +0200 Subject: [PATCH 0811/1507] powerpc/4xx: Fix compile error with 64K pages on 40x, 44x MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The mmu context on the 40x, 44x does not define pte_frag entry. This causes gcc abort the compilation due to: setup-common.c: In function ‘setup_arch’: setup-common.c:908: error: ‘mm_context_t’ has no ‘pte_frag’ This patch fixes the issue by removing the pte_frag initialization in setup-common.c. This is possible, because the compiler will do the initialization, since the mm_context is a sub struct of init_mm. init_mm is declared in mm_types.h as external linkage. According to C99 6.2.4.3: An object whose identifier is declared with external linkage [...] has static storage duration. C99 defines in 6.7.8.10 that: If an object that has static storage duration is not initialized explicitly, then: - if it has pointer type, it is initialized to a null pointer Fixes: b1923caa6e64 ("powerpc: Merge 32-bit and 64-bit setup_arch()") Signed-off-by: Christian Lamparter Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/setup-common.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 0ac741fae90ea..2e3bc16d02b28 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -904,9 +904,6 @@ void __init setup_arch(char **cmdline_p) #endif #endif -#ifdef CONFIG_PPC_64K_PAGES - init_mm.context.pte_frag = NULL; -#endif #ifdef CONFIG_SPAPR_TCE_IOMMU mm_iommu_init(&init_mm); #endif -- GitLab From e63aaaa6be54c956b9603590ea436b003407bb3e Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Wed, 20 Sep 2017 12:31:28 +0530 Subject: [PATCH 0812/1507] netfilter: nf_tables: Release memory obtained by kasprintf Free memory region, if nf_tables_set_alloc_name is not successful. Fixes: 387454901bd6 ("netfilter: nf_tables: Allow set names of up to 255 chars") Signed-off-by: Arvind Yadav Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f98ca8c6aa59d..34adedcb239ea 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2741,8 +2741,10 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; - if (!strcmp(set->name, i->name)) + if (!strcmp(set->name, i->name)) { + kfree(set->name); return -ENFILE; + } } return 0; } -- GitLab From 2b0b8499ae75df91455bbeb7491d45affc384fb0 Mon Sep 17 00:00:00 2001 From: Shu Wang Date: Tue, 12 Sep 2017 10:14:54 +0800 Subject: [PATCH 0813/1507] ftrace: Fix kmemleak in unregister_ftrace_graph The trampoline allocated by function tracer was overwriten by function_graph tracer, and caused a memory leak. The save_global_trampoline should have saved the previous trampoline in register_ftrace_graph() and restored it in unregister_ftrace_graph(). But as it is implemented, save_global_trampoline was only used in unregister_ftrace_graph as default value 0, and it overwrote the previous trampoline's value. Causing the previous allocated trampoline to be lost. kmmeleak backtrace: kmemleak_vmalloc+0x77/0xc0 __vmalloc_node_range+0x1b5/0x2c0 module_alloc+0x7c/0xd0 arch_ftrace_update_trampoline+0xb5/0x290 ftrace_startup+0x78/0x210 register_ftrace_function+0x8b/0xd0 function_trace_init+0x4f/0x80 tracing_set_tracer+0xe6/0x170 tracing_set_trace_write+0x90/0xd0 __vfs_write+0x37/0x170 vfs_write+0xb2/0x1b0 SyS_write+0x55/0xc0 do_syscall_64+0x67/0x180 return_from_SYSCALL_64+0x0/0x6a [ Looking further into this, I found that this was left over from when the function and function graph tracers shared the same ftrace_ops. But in commit 5f151b2401 ("ftrace: Fix function_profiler and function tracer together"), the two were separated, and the save_global_trampoline no longer was necessary (and it may have been broken back then too). -- Steven Rostedt ] Link: http://lkml.kernel.org/r/20170912021454.5976-1-shuwang@redhat.com Cc: stable@vger.kernel.org Fixes: 5f151b2401 ("ftrace: Fix function_profiler and function tracer together") Signed-off-by: Shu Wang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6abfafd7f173c..8319e09e15b94 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4954,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -6808,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } -- GitLab From f39b536ce9248e9799ff900358d6f073ab2e6c55 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 25 Sep 2017 20:19:02 -0700 Subject: [PATCH 0814/1507] rcu: Remove extraneous READ_ONCE()s from rcu_irq_{enter,exit}() The read of ->dynticks_nmi_nesting in rcu_irq_enter() and rcu_irq_exit() is currently protected with READ_ONCE(). However, this protection is unnecessary because (1) ->dynticks_nmi_nesting is updated only by the current CPU, (2) Although NMI handlers can update this field, they reset it back to its old value before return, and (3) Interrupts are disabled, so nothing else can modify it. The value of ->dynticks_nmi_nesting is thus effectively constant, and so no protection is required. This commit therefore removes the READ_ONCE() protection from these two accesses. Link: http://lkml.kernel.org/r/20170926031902.GA2074@linux.vnet.ibm.com Reported-by: Linus Torvalds Signed-off-by: Paul E. McKenney Signed-off-by: Steven Rostedt (VMware) --- kernel/rcu/tree.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 63bee8e1b193e..c03152f7e458f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -890,7 +890,7 @@ void rcu_irq_exit(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -1027,7 +1027,7 @@ void rcu_irq_enter(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; oldval = rdtp->dynticks_nesting; -- GitLab From 0b40f457488d966878eec413a91f27d9b21e6ce5 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:14 -0700 Subject: [PATCH 0815/1507] fm10k: prepare_for_reset() when we lose PCIe Link If we lose PCIe link, such as when an unannounced PFLR event occurs, or when a device is surprise removed, we currently detach the device and close the netdev. This unfortunately leaves a lot of things still active, such as the msix_mbx_pf IRQ, and Tx/Rx resources. This can cause problems because the register reads will return potentially invalid values which may result in unknown driver behavior. Begin the process of resetting using fm10k_prepare_for_reset(), much in the same way as the suspend and resume cycle does. This will attempt to shutdown as much as possible, in order to prevent possible issues. A naive implementation for this has issues, because there are now multiple flows calling the reset logic and setting a reset bit. This would cause problems, because the "re-attach" routine might call fm10k_handle_reset() prior to the reset actually finishing. Instead, we'll add state bits to indicate which flow actually initiated the reset. For the general reset flow, we'll assume that if someone else is resetting that we do not need to handle it at all, so it does not need its own state bit. For the suspend case, we will simply issue a warning indicating that we are attempting to recover from this case when resuming. For the detached subtask, we'll simply refuse to re-attach until we've actually initiated a reset as part of that flow. Finally, we'll stop attempting to manage the mailbox subtask when we're detached, since there's nothing we can do if we don't have a PCIe address. Overall this produces a much cleaner shutdown and recovery cycle for a PCIe surprise remove event. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k.h | 2 + drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 103 ++++++++++++++----- 2 files changed, 79 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 689c413b7782f..ba70c58ca9205 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -270,6 +270,8 @@ enum fm10k_flags_t { enum fm10k_state_t { __FM10K_RESETTING, + __FM10K_RESET_DETACHED, + __FM10K_RESET_SUSPENDED, __FM10K_DOWN, __FM10K_SERVICE_SCHED, __FM10K_SERVICE_REQUEST, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9575f7c1862d5..4e5e3e64beda2 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -153,7 +153,15 @@ static void fm10k_service_timer(unsigned long data) fm10k_service_event_schedule(interface); } -static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) +/** + * fm10k_prepare_for_reset - Prepare the driver and device for a pending reset + * @interface: fm10k private data structure + * + * This function prepares for a device reset by shutting as much down as we + * can. It does nothing and returns false if __FM10K_RESETTING was already set + * prior to calling this function. It returns true if it actually did work. + */ +static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface) { struct net_device *netdev = interface->netdev; @@ -162,8 +170,9 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) /* put off any impending NetWatchDogTimeout */ netif_trans_update(netdev); - while (test_and_set_bit(__FM10K_RESETTING, interface->state)) - usleep_range(1000, 2000); + /* Nothing to do if a reset is already in progress */ + if (test_and_set_bit(__FM10K_RESETTING, interface->state)) + return false; rtnl_lock(); @@ -181,6 +190,8 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) interface->last_reset = jiffies + (10 * HZ); rtnl_unlock(); + + return true; } static int fm10k_handle_reset(struct fm10k_intfc *interface) @@ -189,6 +200,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; int err; + WARN_ON(!test_bit(__FM10K_RESETTING, interface->state)); + rtnl_lock(); pci_set_master(interface->pdev); @@ -267,51 +280,75 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; u32 __iomem *hw_addr; u32 value; + int err; - /* do nothing if device is still present or hw_addr is set */ + /* do nothing if netdev is still present or hw_addr is set */ if (netif_device_present(netdev) || interface->hw.hw_addr) return; + /* We've lost the PCIe register space, and can no longer access the + * device. Shut everything except the detach subtask down and prepare + * to reset the device in case we recover. If we actually prepare for + * reset, indicate that we're detached. + */ + if (fm10k_prepare_for_reset(interface)) + set_bit(__FM10K_RESET_DETACHED, interface->state); + /* check the real address space to see if we've recovered */ hw_addr = READ_ONCE(interface->uc_addr); value = readl(hw_addr); if (~value) { + /* Make sure the reset was initiated because we detached, + * otherwise we might race with a different reset flow. + */ + if (!test_and_clear_bit(__FM10K_RESET_DETACHED, + interface->state)) + return; + + /* Restore the hardware address */ interface->hw.hw_addr = interface->uc_addr; + + /* PCIe link has been restored, and the device is active + * again. Restore everything and reset the device. + */ + err = fm10k_handle_reset(interface); + if (err) { + netdev_err(netdev, "Unable to reset device: %d\n", err); + interface->hw.hw_addr = NULL; + return; + } + + /* Re-attach the netdev */ netif_device_attach(netdev); - set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); netdev_warn(netdev, "PCIe link restored, device now attached\n"); return; } - - rtnl_lock(); - - if (netif_running(netdev)) - dev_close(netdev); - - rtnl_unlock(); } -static void fm10k_reinit(struct fm10k_intfc *interface) +static void fm10k_reset_subtask(struct fm10k_intfc *interface) { int err; - fm10k_prepare_for_reset(interface); - - err = fm10k_handle_reset(interface); - if (err) - dev_err(&interface->pdev->dev, - "fm10k_handle_reset failed: %d\n", err); -} - -static void fm10k_reset_subtask(struct fm10k_intfc *interface) -{ if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags)) return; + /* If another thread has already prepared to reset the device, we + * should not attempt to handle a reset here, since we'd race with + * that thread. This may happen if we suspend the device or if the + * PCIe link is lost. In this case, we'll just ignore the RESET + * request, as it will (eventually) be taken care of when the thread + * which actually started the reset is finished. + */ + if (!fm10k_prepare_for_reset(interface)) + return; + netdev_err(interface->netdev, "Reset interface\n"); - fm10k_reinit(interface); + err = fm10k_handle_reset(interface); + if (err) + dev_err(&interface->pdev->dev, + "fm10k_handle_reset failed: %d\n", err); } /** @@ -381,6 +418,10 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) **/ static void fm10k_mbx_subtask(struct fm10k_intfc *interface) { + /* If we're resetting, bail out */ + if (test_bit(__FM10K_RESETTING, interface->state)) + return; + /* process upstream mailbox and update device state */ fm10k_watchdog_update_host_state(interface); @@ -630,9 +671,11 @@ static void fm10k_service_task(struct work_struct *work) interface = container_of(work, struct fm10k_intfc, service_task); + /* Check whether we're detached first */ + fm10k_detach_subtask(interface); + /* tasks run even when interface is down */ fm10k_mbx_subtask(interface); - fm10k_detach_subtask(interface); fm10k_reset_subtask(interface); /* tasks only run when interface is up */ @@ -2177,7 +2220,8 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) */ fm10k_stop_service_event(interface); - fm10k_prepare_for_reset(interface); + if (fm10k_prepare_for_reset(interface)) + set_bit(__FM10K_RESET_SUSPENDED, interface->state); } static int fm10k_handle_resume(struct fm10k_intfc *interface) @@ -2185,6 +2229,13 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; int err; + /* Even if we didn't properly prepare for reset in + * fm10k_prepare_suspend, we'll attempt to resume anyways. + */ + if (!test_and_clear_bit(__FM10K_RESET_SUSPENDED, interface->state)) + dev_warn(&interface->pdev->dev, + "Device was shut down as part of suspend... Attempting to recover\n"); + /* reset statistics starting values */ hw->mac.ops.rebind_hw_stats(hw, &interface->stats); -- GitLab From b4fcd43661df0d84cc4e030ab7a26533114889b9 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:15 -0700 Subject: [PATCH 0816/1507] fm10k: use spinlock to implement mailbox lock Lets not re-invent the locking wheel. Remove our bitlock and use a proper spinlock instead. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k.h | 15 +++++---------- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 3 +++ 2 files changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index ba70c58ca9205..74542e9d63c77 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -276,7 +276,6 @@ enum fm10k_state_t { __FM10K_SERVICE_SCHED, __FM10K_SERVICE_REQUEST, __FM10K_SERVICE_DISABLE, - __FM10K_MBX_LOCK, __FM10K_LINK_DOWN, __FM10K_UPDATING_STATS, /* This value must be last and determines the BITMAP size */ @@ -346,6 +345,8 @@ struct fm10k_intfc { struct fm10k_hw_stats stats; struct fm10k_hw hw; + /* Mailbox lock */ + spinlock_t mbx_lock; u32 __iomem *uc_addr; u32 __iomem *sw_addr; u16 msg_enable; @@ -386,23 +387,17 @@ struct fm10k_intfc { static inline void fm10k_mbx_lock(struct fm10k_intfc *interface) { - /* busy loop if we cannot obtain the lock as some calls - * such as ndo_set_rx_mode may be made in atomic context - */ - while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state)) - udelay(20); + spin_lock(&interface->mbx_lock); } static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface) { - /* flush memory to make sure state is correct */ - smp_mb__before_atomic(); - clear_bit(__FM10K_MBX_LOCK, interface->state); + spin_unlock(&interface->mbx_lock); } static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface) { - return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state); + return spin_trylock(&interface->mbx_lock); } /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 4e5e3e64beda2..240772ad5d696 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1921,6 +1921,9 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, netdev_rss_key_fill(rss_key, sizeof(rss_key)); memcpy(interface->rssrk, rss_key, sizeof(rss_key)); + /* Initialize the mailbox lock */ + spin_lock_init(&interface->mbx_lock); + /* Start off interface as being down */ set_bit(__FM10K_DOWN, interface->state); set_bit(__FM10K_UPDATING_STATS, interface->state); -- GitLab From 8249c47c6ba48cd3eba7c3ca7f8e733ee815c39b Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:16 -0700 Subject: [PATCH 0817/1507] fm10k: use generic PM hooks instead of legacy PCIe power hooks Replace the PCI specific legacy power management hooks with the new generic power management hooks which work properly for both suspend and hibernate. The new generic system is better and properly handles the lower level PCIe power management rather than forcing the driver to handle it. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 67 +++++++------------- 1 file changed, 22 insertions(+), 45 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 240772ad5d696..aef39909e4a2e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2264,36 +2264,19 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) #ifdef CONFIG_PM /** - * fm10k_resume - Restore device to pre-sleep state - * @pdev: PCI device information struct + * fm10k_resume - Generic PM resume hook + * @dev: generic device structure * - * fm10k_resume is called after the system has powered back up from a sleep - * state and is ready to resume operation. This function is meant to restore - * the device back to its pre-sleep state. + * Generic PM hook used when waking the device from a low power state after + * suspend or hibernation. This function does not need to handle lower PCIe + * device state as the stack takes care of that for us. **/ -static int fm10k_resume(struct pci_dev *pdev) +static int fm10k_resume(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); + struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; - u32 err; - - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - /* pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); - - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n"); - return err; - } - pci_set_master(pdev); - - pci_wake_from_d3(pdev, false); + int err; /* refresh hw_addr in case it was dropped */ hw->hw_addr = interface->uc_addr; @@ -2308,36 +2291,27 @@ static int fm10k_resume(struct pci_dev *pdev) } /** - * fm10k_suspend - Prepare the device for a system sleep state - * @pdev: PCI device information struct + * fm10k_suspend - Generic PM suspend hook + * @dev: generic device structure * - * fm10k_suspend is meant to shutdown the device prior to the system entering - * a sleep state. The fm10k hardware does not support wake on lan so the - * driver simply needs to shut down the device so it is in a low power state. + * Generic PM hook used when setting the device into a low power state for + * system suspend or hibernation. This function does not need to handle lower + * PCIe device state as the stack takes care of that for us. **/ -static int fm10k_suspend(struct pci_dev *pdev, - pm_message_t __always_unused state) +static int fm10k_suspend(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(pdev); + struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); struct net_device *netdev = interface->netdev; - int err = 0; netif_device_detach(netdev); fm10k_prepare_suspend(interface); - err = pci_save_state(pdev); - if (err) - return err; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - return 0; } #endif /* CONFIG_PM */ + /** * fm10k_io_error_detected - called when PCI error is detected * @pdev: Pointer to PCI device @@ -2447,15 +2421,18 @@ static const struct pci_error_handlers fm10k_err_handler = { .reset_done = fm10k_io_reset_done, }; +static SIMPLE_DEV_PM_OPS(fm10k_pm_ops, fm10k_suspend, fm10k_resume); + static struct pci_driver fm10k_driver = { .name = fm10k_driver_name, .id_table = fm10k_pci_tbl, .probe = fm10k_probe, .remove = fm10k_remove, #ifdef CONFIG_PM - .suspend = fm10k_suspend, - .resume = fm10k_resume, -#endif + .driver = { + .pm = &fm10k_pm_ops, + }, +#endif /* CONFIG_PM */ .sriov_configure = fm10k_iov_configure, .err_handler = &fm10k_err_handler }; -- GitLab From fc9173682dcf73cfe3324267424ef17e854bb444 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:17 -0700 Subject: [PATCH 0818/1507] fm10k: introduce a message queue for MAC/VLAN messages Under some circumstances, when dealing with a large number of MAC address or VLAN updates at once, the fm10k driver, particularly the VFs can overload the mailbox with too many messages at once. This results in a mailbox timeout, which causes the driver to initiate a reset. During the reset, we re-send all the same messages that originally caused the timeout. This results in a cycle of resets each triggering a future reset. To fix or avoid this, we introduce a workqueue item which monitors a queue of MAC and VLAN requests. These requests are queued to the end of the list, and we process as a FIFO periodically. Initially we only handle requests for the netdev, but we do handle unicast MAC addresses, multicast MAC addresses, and update VLAN requests. A future patch will add support to use this queue for handling MAC update requests from the VF<->PF mailbox. The MAC/VLAN work item will keep checking to make sure that each request does not overflow the mailbox and cause a timeout. If it might, then the work item will reschedule itself a short time later. This avoids any reset cycle, since we never send the message if the mailbox is not ready. As an alternative, we tried increasing the mailbox message FIFO, but this just delays the problem and results in needless memory waste on the system. Our new message queue is dynamically allocated so only uses as much memory as it needs. Additionally, it need not be contiguous like the Tx and Rx FIFOs. Note that this patch chose to only create a queue for MAC and VLAN messages, since these are the only messages sent in a large enough volume to cause the reset loop. Other messages are very unlikely to overflow the mailbox Tx FIFO so easily. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k.h | 39 ++++ .../net/ethernet/intel/fm10k/fm10k_netdev.c | 199 +++++++++++++---- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 201 ++++++++++++++++++ 3 files changed, 397 insertions(+), 42 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 74542e9d63c77..40856bc0f3b98 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -248,6 +248,29 @@ struct fm10k_udp_port { __be16 port; }; +enum fm10k_macvlan_request_type { + FM10K_UC_MAC_REQUEST, + FM10K_MC_MAC_REQUEST, + FM10K_VLAN_REQUEST +}; + +struct fm10k_macvlan_request { + enum fm10k_macvlan_request_type type; + struct list_head list; + union { + struct fm10k_mac_request { + u8 addr[ETH_ALEN]; + u16 glort; + u16 vid; + } mac; + struct fm10k_vlan_request { + u32 vid; + u8 vsi; + } vlan; + }; + bool set; +}; + /* one work queue for entire driver */ extern struct workqueue_struct *fm10k_workqueue; @@ -276,6 +299,9 @@ enum fm10k_state_t { __FM10K_SERVICE_SCHED, __FM10K_SERVICE_REQUEST, __FM10K_SERVICE_DISABLE, + __FM10K_MACVLAN_SCHED, + __FM10K_MACVLAN_REQUEST, + __FM10K_MACVLAN_DISABLE, __FM10K_LINK_DOWN, __FM10K_UPDATING_STATS, /* This value must be last and determines the BITMAP size */ @@ -368,6 +394,12 @@ struct fm10k_intfc { struct list_head vxlan_port; struct list_head geneve_port; + /* MAC/VLAN update queue */ + struct list_head macvlan_requests; + struct delayed_work macvlan_task; + /* MAC/VLAN update queue lock */ + spinlock_t macvlan_lock; + #ifdef CONFIG_DEBUG_FS struct dentry *dbg_intfc; #endif /* CONFIG_DEBUG_FS */ @@ -487,6 +519,7 @@ void fm10k_up(struct fm10k_intfc *interface); void fm10k_down(struct fm10k_intfc *interface); void fm10k_update_stats(struct fm10k_intfc *interface); void fm10k_service_event_schedule(struct fm10k_intfc *interface); +void fm10k_macvlan_schedule(struct fm10k_intfc *interface); void fm10k_update_rx_drop_en(struct fm10k_intfc *interface); #ifdef CONFIG_NET_POLL_CONTROLLER void fm10k_netpoll(struct net_device *netdev); @@ -507,6 +540,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *); int fm10k_setup_tc(struct net_device *dev, u8 tc); int fm10k_open(struct net_device *netdev); int fm10k_close(struct net_device *netdev); +int fm10k_queue_vlan_request(struct fm10k_intfc *interface, u32 vid, + u8 vsi, bool set); +int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort, + const unsigned char *addr, u16 vid, bool set); +void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface, + u16 glort, bool vlans); /* Ethtool */ void fm10k_set_ethtool_ops(struct net_device *dev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 77d495fedced0..81e4425f05294 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -758,11 +758,132 @@ static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface) return (hw->mac.type == fm10k_mac_vf || interface->host_ready); } +/** + * fm10k_queue_vlan_request - Queue a VLAN update request + * @interface: the fm10k interface structure + * @vid: the VLAN vid + * @vsi: VSI index number + * @set: whether to set or clear + * + * This function queues up a VLAN update. For VFs, this must be sent to the + * managing PF over the mailbox. For PFs, we'll use the same handling so that + * it's similar to the VF. This avoids storming the PF<->VF mailbox with too + * many VLAN updates during reset. + */ +int fm10k_queue_vlan_request(struct fm10k_intfc *interface, + u32 vid, u8 vsi, bool set) +{ + struct fm10k_macvlan_request *request; + unsigned long flags; + + /* This must be atomic since we may be called while the netdev + * addr_list_lock is held + */ + request = kzalloc(sizeof(*request), GFP_ATOMIC); + if (!request) + return -ENOMEM; + + request->type = FM10K_VLAN_REQUEST; + request->vlan.vid = vid; + request->vlan.vsi = vsi; + request->set = set; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add_tail(&request->list, &interface->macvlan_requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + fm10k_macvlan_schedule(interface); + + return 0; +} + +/** + * fm10k_queue_mac_request - Queue a MAC update request + * @interface: the fm10k interface structure + * @glort: the target glort for this update + * @addr: the address to update + * @vid: the vid to update + * @sync: whether to add or remove + * + * This function queues up a MAC request for sending to the switch manager. + * A separate thread monitors the queue and sends updates to the switch + * manager. Return 0 on success, and negative error code on failure. + **/ +int fm10k_queue_mac_request(struct fm10k_intfc *interface, u16 glort, + const unsigned char *addr, u16 vid, bool set) +{ + struct fm10k_macvlan_request *request; + unsigned long flags; + + /* This must be atomic since we may be called while the netdev + * addr_list_lock is held + */ + request = kzalloc(sizeof(*request), GFP_ATOMIC); + if (!request) + return -ENOMEM; + + if (is_multicast_ether_addr(addr)) + request->type = FM10K_MC_MAC_REQUEST; + else + request->type = FM10K_UC_MAC_REQUEST; + + ether_addr_copy(request->mac.addr, addr); + request->mac.glort = glort; + request->mac.vid = vid; + request->set = set; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add_tail(&request->list, &interface->macvlan_requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + fm10k_macvlan_schedule(interface); + + return 0; +} + +/** + * fm10k_clear_macvlan_queue - Cancel pending updates for a given glort + * @interface: the fm10k interface structure + * @glort: the target glort to clear + * @vlans: true to clear VLAN messages, false to ignore them + * + * Cancel any outstanding MAC/VLAN requests for a given glort. This is + * expected to be called when a logical port goes down. + **/ +void fm10k_clear_macvlan_queue(struct fm10k_intfc *interface, + u16 glort, bool vlans) + +{ + struct fm10k_macvlan_request *r, *tmp; + unsigned long flags; + + spin_lock_irqsave(&interface->macvlan_lock, flags); + + /* Free any outstanding MAC/VLAN requests for this interface */ + list_for_each_entry_safe(r, tmp, &interface->macvlan_requests, list) { + switch (r->type) { + case FM10K_MC_MAC_REQUEST: + case FM10K_UC_MAC_REQUEST: + /* Don't free requests for other interfaces */ + if (r->mac.glort != glort) + break; + /* fall through */ + case FM10K_VLAN_REQUEST: + if (vlans) { + list_del(&r->list); + kfree(r); + } + break; + } + } + + spin_unlock_irqrestore(&interface->macvlan_lock, flags); +} + static int fm10k_uc_vlan_unsync(struct net_device *netdev, const unsigned char *uc_addr) { struct fm10k_intfc *interface = netdev_priv(netdev); - struct fm10k_hw *hw = &interface->hw; u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); @@ -771,10 +892,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, - vid, set, 0); - + err = fm10k_queue_mac_request(interface, glort, uc_addr, vid, set); if (err) return err; @@ -786,7 +904,6 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, const unsigned char *mc_addr) { struct fm10k_intfc *interface = netdev_priv(netdev); - struct fm10k_hw *hw = &interface->hw; u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); @@ -795,9 +912,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); - + err = fm10k_queue_mac_request(interface, glort, mc_addr, vid, set); if (err) return err; @@ -855,18 +970,14 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) /* only need to update the VLAN if not in promiscuous mode */ if (!(netdev->flags & IFF_PROMISC)) { - err = hw->mac.ops.update_vlan(hw, vid, 0, set); + err = fm10k_queue_vlan_request(interface, vid, 0, set); if (err) goto err_out; } - /* update our base MAC address if host's mailbox is ready */ - if (fm10k_host_mbx_ready(interface)) - err = hw->mac.ops.update_uc_addr(hw, interface->glort, - hw->mac.addr, vid, set, 0); - else - err = -EHOSTDOWN; - + /* Update our base MAC address */ + err = fm10k_queue_mac_request(interface, interface->glort, + hw->mac.addr, vid, set); if (err) goto err_out; @@ -910,7 +1021,6 @@ static u16 fm10k_find_next_vlan(struct fm10k_intfc *interface, u16 vid) static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface) { - struct fm10k_hw *hw = &interface->hw; u32 vid, prev_vid; /* loop through and find any gaps in the table */ @@ -922,7 +1032,7 @@ static void fm10k_clear_unused_vlans(struct fm10k_intfc *interface) /* send request to clear multiple bits at a time */ prev_vid += (vid - prev_vid - 1) << FM10K_VLAN_LENGTH_SHIFT; - hw->mac.ops.update_vlan(hw, prev_vid, 0, false); + fm10k_queue_vlan_request(interface, prev_vid, 0, false); } } @@ -937,15 +1047,11 @@ static int __fm10k_uc_sync(struct net_device *dev, if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - /* update table with current entries if host's mailbox is ready */ - if (!fm10k_host_mbx_ready(interface)) - return -EHOSTDOWN; - for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - err = hw->mac.ops.update_uc_addr(hw, glort, addr, - vid, sync, 0); + err = fm10k_queue_mac_request(interface, glort, + addr, vid, sync); if (err) return err; } @@ -1002,15 +1108,18 @@ static int __fm10k_mc_sync(struct net_device *dev, struct fm10k_intfc *interface = netdev_priv(dev); struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; + s32 err; - /* update table with current entries if host's mailbox is ready */ - if (!fm10k_host_mbx_ready(interface)) - return 0; + if (!is_multicast_ether_addr(addr)) + return -EADDRNOTAVAIL; for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync); + err = fm10k_queue_mac_request(interface, glort, + addr, vid, sync); + if (err) + return err; } return 0; @@ -1050,7 +1159,8 @@ static void fm10k_set_rx_mode(struct net_device *dev) if (interface->xcast_mode != xcast_mode) { /* update VLAN table */ if (xcast_mode == FM10K_XCAST_MODE_PROMISC) - hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, true); + fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, + 0, true); if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_clear_unused_vlans(interface); @@ -1098,22 +1208,20 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) interface->glort_count, true); /* update VLAN table */ - hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, - xcast_mode == FM10K_XCAST_MODE_PROMISC); + fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0, + xcast_mode == FM10K_XCAST_MODE_PROMISC); /* Add filter for VLAN 0 */ - hw->mac.ops.update_vlan(hw, 0, 0, true); + fm10k_queue_vlan_request(interface, 0, 0, true); /* update table with current entries */ for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { - hw->mac.ops.update_vlan(hw, vid, 0, true); + fm10k_queue_vlan_request(interface, vid, 0, true); - /* Update unicast entries if host's mailbox is ready */ - if (fm10k_host_mbx_ready(interface)) - hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, - vid, true, 0); + fm10k_queue_mac_request(interface, glort, + hw->mac.addr, vid, true); } /* update xcast mode before synchronizing addresses if host's mailbox @@ -1140,6 +1248,13 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; + /* Wait for MAC/VLAN work to finish */ + while (test_bit(__FM10K_MACVLAN_SCHED, interface->state)) + usleep_range(1000, 2000); + + /* Cancel pending MAC/VLAN requests */ + fm10k_clear_macvlan_queue(interface, interface->glort, true); + fm10k_mbx_lock(interface); /* clear the logical port state on lower device if host's mailbox is @@ -1374,8 +1489,8 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, if (fm10k_host_mbx_ready(interface)) { hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, - 0, true, 0); + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + 0, true); } fm10k_mbx_unlock(interface); @@ -1414,8 +1529,8 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) if (fm10k_host_mbx_ready(interface)) { hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, - 0, false, 0); + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + 0, false); } fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index aef39909e4a2e..58538ce997e1c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -91,6 +91,76 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface) return FM10K_REMOVED(hw->hw_addr) ? -ENODEV : 0; } +/** + * fm10k_macvlan_schedule - Schedule MAC/VLAN queue task + * @interface: fm10k private interface structure + * + * Schedule the MAC/VLAN queue monitor task. If the MAC/VLAN task cannot be + * started immediately, request that it be restarted when possible. + */ +void fm10k_macvlan_schedule(struct fm10k_intfc *interface) +{ + /* Avoid processing the MAC/VLAN queue when the service task is + * disabled, or when we're resetting the device. + */ + if (!test_bit(__FM10K_MACVLAN_DISABLE, interface->state) && + !test_and_set_bit(__FM10K_MACVLAN_SCHED, interface->state)) { + clear_bit(__FM10K_MACVLAN_REQUEST, interface->state); + /* We delay the actual start of execution in order to allow + * multiple MAC/VLAN updates to accumulate before handling + * them, and to allow some time to let the mailbox drain + * between runs. + */ + queue_delayed_work(fm10k_workqueue, + &interface->macvlan_task, 10); + } else { + set_bit(__FM10K_MACVLAN_REQUEST, interface->state); + } +} + +/** + * fm10k_stop_macvlan_task - Stop the MAC/VLAN queue monitor + * @interface: fm10k private interface structure + * + * Wait until the MAC/VLAN queue task has stopped, and cancel any future + * requests. + */ +static void fm10k_stop_macvlan_task(struct fm10k_intfc *interface) +{ + /* Disable the MAC/VLAN work item */ + set_bit(__FM10K_MACVLAN_DISABLE, interface->state); + + /* Make sure we waited until any current invocations have stopped */ + cancel_delayed_work_sync(&interface->macvlan_task); + + /* We set the __FM10K_MACVLAN_SCHED bit when we schedule the task. + * However, it may not be unset of the MAC/VLAN task never actually + * got a chance to run. Since we've canceled the task here, and it + * cannot be rescheuled right now, we need to ensure the scheduled bit + * gets unset. + */ + clear_bit(__FM10K_MACVLAN_SCHED, interface->state); +} + +/** + * fm10k_resume_macvlan_task - Restart the MAC/VLAN queue monitor + * @interface: fm10k private interface structure + * + * Clear the __FM10K_MACVLAN_DISABLE bit and, if a request occurred, schedule + * the MAC/VLAN work monitor. + */ +static void fm10k_resume_macvlan_task(struct fm10k_intfc *interface) +{ + /* Re-enable the MAC/VLAN work item */ + clear_bit(__FM10K_MACVLAN_DISABLE, interface->state); + + /* We might have received a MAC/VLAN request while disabled. If so, + * kick off the queue now. + */ + if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state)) + fm10k_macvlan_schedule(interface); +} + void fm10k_service_event_schedule(struct fm10k_intfc *interface) { if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) && @@ -174,6 +244,12 @@ static bool fm10k_prepare_for_reset(struct fm10k_intfc *interface) if (test_and_set_bit(__FM10K_RESETTING, interface->state)) return false; + /* As the MAC/VLAN task will be accessing registers it must not be + * running while we reset. Although the task will not be scheduled + * once we start resetting it may already be running + */ + fm10k_stop_macvlan_task(interface); + rtnl_lock(); fm10k_iov_suspend(interface->pdev); @@ -258,6 +334,8 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) rtnl_unlock(); + fm10k_resume_macvlan_task(interface); + clear_bit(__FM10K_RESETTING, interface->state); return err; @@ -686,6 +764,112 @@ static void fm10k_service_task(struct work_struct *work) fm10k_service_event_complete(interface); } +/** + * fm10k_macvlan_task - send queued MAC/VLAN requests to switch manager + * @work: pointer to work_struct containing our data + * + * This work item handles sending MAC/VLAN updates to the switch manager. When + * the interface is up, it will attempt to queue mailbox messages to the + * switch manager requesting updates for MAC/VLAN pairs. If the Tx fifo of the + * mailbox is full, it will reschedule itself to try again in a short while. + * This ensures that the driver does not overload the switch mailbox with too + * many simultaneous requests, causing an unnecessary reset. + **/ +static void fm10k_macvlan_task(struct work_struct *work) +{ + struct fm10k_macvlan_request *item; + struct fm10k_intfc *interface; + struct delayed_work *dwork; + struct list_head *requests; + struct fm10k_hw *hw; + unsigned long flags; + + dwork = to_delayed_work(work); + interface = container_of(dwork, struct fm10k_intfc, macvlan_task); + hw = &interface->hw; + requests = &interface->macvlan_requests; + + do { + /* Pop the first item off the list */ + spin_lock_irqsave(&interface->macvlan_lock, flags); + item = list_first_entry_or_null(requests, + struct fm10k_macvlan_request, + list); + if (item) + list_del_init(&item->list); + + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + + /* We have no more items to process */ + if (!item) + goto done; + + fm10k_mbx_lock(interface); + + /* Check that we have plenty of space to send the message. We + * want to ensure that the mailbox stays low enough to avoid a + * change in the host state, otherwise we may see spurious + * link up / link down notifications. + */ + if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU + 5)) { + hw->mbx.ops.process(hw, &hw->mbx); + set_bit(__FM10K_MACVLAN_REQUEST, interface->state); + fm10k_mbx_unlock(interface); + + /* Put the request back on the list */ + spin_lock_irqsave(&interface->macvlan_lock, flags); + list_add(&item->list, requests); + spin_unlock_irqrestore(&interface->macvlan_lock, flags); + break; + } + + switch (item->type) { + case FM10K_MC_MAC_REQUEST: + hw->mac.ops.update_mc_addr(hw, + item->mac.glort, + item->mac.addr, + item->mac.vid, + item->set); + break; + case FM10K_UC_MAC_REQUEST: + hw->mac.ops.update_uc_addr(hw, + item->mac.glort, + item->mac.addr, + item->mac.vid, + item->set, + 0); + break; + case FM10K_VLAN_REQUEST: + hw->mac.ops.update_vlan(hw, + item->vlan.vid, + item->vlan.vsi, + item->set); + break; + default: + break; + } + + fm10k_mbx_unlock(interface); + + /* Free the item now that we've sent the update */ + kfree(item); + } while (true); + +done: + WARN_ON(!test_bit(__FM10K_MACVLAN_SCHED, interface->state)); + + /* flush memory to make sure state is correct */ + smp_mb__before_atomic(); + clear_bit(__FM10K_MACVLAN_SCHED, interface->state); + + /* If a MAC/VLAN request was scheduled since we started, we should + * re-schedule. However, there is no reason to re-schedule if there is + * no work to do. + */ + if (test_bit(__FM10K_MACVLAN_REQUEST, interface->state)) + fm10k_macvlan_schedule(interface); +} + /** * fm10k_configure_tx_ring - Configure Tx ring after Reset * @interface: board private structure @@ -1918,11 +2102,15 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, INIT_LIST_HEAD(&interface->vxlan_port); INIT_LIST_HEAD(&interface->geneve_port); + /* Initialize the MAC/VLAN queue */ + INIT_LIST_HEAD(&interface->macvlan_requests); + netdev_rss_key_fill(rss_key, sizeof(rss_key)); memcpy(interface->rssrk, rss_key, sizeof(rss_key)); /* Initialize the mailbox lock */ spin_lock_init(&interface->mbx_lock); + spin_lock_init(&interface->macvlan_lock); /* Start off interface as being down */ set_bit(__FM10K_DOWN, interface->state); @@ -2131,6 +2319,9 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) (unsigned long)interface); INIT_WORK(&interface->service_task, fm10k_service_task); + /* Setup the MAC/VLAN queue */ + INIT_DELAYED_WORK(&interface->macvlan_task, fm10k_macvlan_task); + /* kick off service timer now, even when interface is down */ mod_timer(&interface->service_timer, (HZ * 2) + jiffies); @@ -2184,6 +2375,10 @@ static void fm10k_remove(struct pci_dev *pdev) del_timer_sync(&interface->service_timer); fm10k_stop_service_event(interface); + fm10k_stop_macvlan_task(interface); + + /* Remove all pending MAC/VLAN requests */ + fm10k_clear_macvlan_queue(interface, interface->glort, true); /* free netdev, this may bounce the interrupts due to setup_tc */ if (netdev->reg_state == NETREG_REGISTERED) @@ -2220,6 +2415,9 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) * a surprise remove if the PCIe device is disabled while we're * stopped. We stop the watchdog task until after we resume software * activity. + * + * Note that the MAC/VLAN task will be stopped as part of preparing + * for reset so we don't need to handle it here. */ fm10k_stop_service_event(interface); @@ -2259,6 +2457,9 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* restart the service task */ fm10k_start_service_event(interface); + /* Restart the MAC/VLAN request queue in-case of outstanding events */ + fm10k_macvlan_schedule(interface); + return err; } -- GitLab From 1f5c27e52857c9ba8f1ee4ed5093bee1a341f330 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:18 -0700 Subject: [PATCH 0819/1507] fm10k: use the MAC/VLAN queue for VF<->PF MAC/VLAN requests Now that we have a working MAC/VLAN queue for handling MAC/VLAN messages from the netdev, replace the default handler for the VF<->PF messages. This new handler is very similar to the default code, but uses the MAC/VLAN queue instead of sending the message directly. Unfortunately we can't easily re-use the default code, so we'll just replace the entire function. This ensures that a VF requesting a large number of VLANs or MAC addresses does not start a reset cycle, as explained in the commit which introduced the message queue. Signed-off-by: Jacob Keller Reviewed-by: Ngai-mint Kwan Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 132 ++++++++++++++++++- drivers/net/ethernet/intel/fm10k/fm10k_pf.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_pf.h | 3 +- 3 files changed, 133 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 03897720bf0b5..4a17cc903eedc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -35,10 +35,133 @@ static s32 fm10k_iov_msg_error(struct fm10k_hw *hw, u32 **results, return fm10k_tlv_msg_error(hw, results, mbx); } +/** + * fm10k_iov_msg_queue_mac_vlan - Message handler for MAC/VLAN request from VF + * @hw: Pointer to hardware structure + * @results: Pointer array to message, results[0] is pointer to message + * @mbx: Pointer to mailbox information structure + * + * This function is a custom handler for MAC/VLAN requests from the VF. The + * assumption is that it is acceptable to directly hand off the message from + * the VF to the PF's switch manager. However, we use a MAC/VLAN message + * queue to avoid overloading the mailbox when a large number of requests + * come in. + **/ +static s32 fm10k_iov_msg_queue_mac_vlan(struct fm10k_hw *hw, u32 **results, + struct fm10k_mbx_info *mbx) +{ + struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; + struct fm10k_intfc *interface = hw->back; + u8 mac[ETH_ALEN]; + u32 *result; + int err = 0; + bool set; + u16 vlan; + u32 vid; + + /* we shouldn't be updating rules on a disabled interface */ + if (!FM10K_VF_FLAG_ENABLED(vf_info)) + err = FM10K_ERR_PARAM; + + if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) { + result = results[FM10K_MAC_VLAN_MSG_VLAN]; + + /* record VLAN id requested */ + err = fm10k_tlv_attr_get_u32(result, &vid); + if (err) + return err; + + set = !(vid & FM10K_VLAN_CLEAR); + vid &= ~FM10K_VLAN_CLEAR; + + /* if the length field has been set, this is a multi-bit + * update request. For multi-bit requests, simply disallow + * them when the pf_vid has been set. In this case, the PF + * should have already cleared the VLAN_TABLE, and if we + * allowed them, it could allow a rogue VF to receive traffic + * on a VLAN it was not assigned. In the single-bit case, we + * need to modify requests for VLAN 0 to use the default PF or + * SW vid when assigned. + */ + + if (vid >> 16) { + /* prevent multi-bit requests when PF has + * administratively set the VLAN for this VF + */ + if (vf_info->pf_vid) + return FM10K_ERR_PARAM; + } else { + err = fm10k_iov_select_vid(vf_info, (u16)vid); + if (err < 0) + return err; + + vid = err; + } + + /* update VSI info for VF in regards to VLAN table */ + err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); + } + + if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) { + result = results[FM10K_MAC_VLAN_MSG_MAC]; + + /* record unicast MAC address requested */ + err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); + if (err) + return err; + + /* block attempts to set MAC for a locked device */ + if (is_valid_ether_addr(vf_info->mac) && + !ether_addr_equal(mac, vf_info->mac)) + return FM10K_ERR_PARAM; + + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + + vlan = (u16)err; + + /* Add this request to the MAC/VLAN queue */ + err = fm10k_queue_mac_request(interface, vf_info->glort, + mac, vlan, set); + } + + if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) { + result = results[FM10K_MAC_VLAN_MSG_MULTICAST]; + + /* record multicast MAC address requested */ + err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan); + if (err) + return err; + + /* verify that the VF is allowed to request multicast */ + if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED)) + return FM10K_ERR_PARAM; + + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + + vlan = (u16)err; + + /* Add this request to the MAC/VLAN queue */ + err = fm10k_queue_mac_request(interface, vf_info->glort, + mac, vlan, set); + } + + return err; +} + static const struct fm10k_msg_data iov_mbx_data[] = { FM10K_TLV_MSG_TEST_HANDLER(fm10k_tlv_msg_test), FM10K_VF_MSG_MSIX_HANDLER(fm10k_iov_msg_msix_pf), - FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_mac_vlan_pf), + FM10K_VF_MSG_MAC_VLAN_HANDLER(fm10k_iov_msg_queue_mac_vlan), FM10K_VF_MSG_LPORT_STATE_HANDLER(fm10k_iov_msg_lport_state_pf), FM10K_TLV_MSG_ERROR_HANDLER(fm10k_iov_msg_error), }; @@ -126,8 +249,10 @@ s32 fm10k_iov_mbx(struct fm10k_intfc *interface) hw->mbx.ops.process(hw, &hw->mbx); /* verify port mapping is valid, if not reset port */ - if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) + if (vf_info->vf_flags && !fm10k_glort_valid_pf(hw, glort)) { hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, glort, false); + } /* reset VFs that have mailbox timed out */ if (!mbx->timeout) { @@ -190,6 +315,7 @@ void fm10k_iov_suspend(struct pci_dev *pdev) hw->iov.ops.reset_resources(hw, vf_info); hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, vf_info->glort, false); } } @@ -414,6 +540,8 @@ static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface, /* disable LPORT for this VF which clears switch rules */ hw->iov.ops.reset_lport(hw, vf_info); + fm10k_clear_macvlan_queue(interface, vf_info->glort, false); + /* assign new MAC+VLAN for this VF */ hw->iov.ops.assign_default_mac_vlan(hw, vf_info); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 9e4fb3a443763..425d814aed4d5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1186,7 +1186,7 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, * Will report an error if the VLAN ID is out of range. For VID = 0, it will * return either the pf_vid or sw_vid depending on which one is set. */ -static s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) +s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) { if (!vid) return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index 3336d3c10760a..e04d41f1a5325 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -114,6 +114,7 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[]; #define FM10K_PF_MSG_ERR_HANDLER(msg, func) \ FM10K_MSG_HANDLER(FM10K_PF_MSG_ID_##msg, fm10k_err_msg_attr, func) +s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid); s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *); -- GitLab From ef57ab791c81b3a83c75a312b15b42f7440bb425 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 10 Jul 2017 13:23:19 -0700 Subject: [PATCH 0820/1507] fm10k: bump version number Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 189d52a8a6053..5d56ed5ad7a64 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -28,7 +28,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.21.7-k" +#define DRV_VERSION "0.22.1-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; -- GitLab From c0ad8ef3df091ef179d78dccb810024612dcfa44 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 11 Aug 2017 09:17:15 -0700 Subject: [PATCH 0821/1507] fm10k: Fix misuse of net_ratelimit() Correct the backward logic using !net_ratelimit() Miscellanea: o Add a blank line before the error return label Signed-off-by: Joe Perches Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5d56ed5ad7a64..dbd69310f263e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -806,9 +806,10 @@ static int fm10k_tso(struct fm10k_ring *tx_ring, tx_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); return 1; + err_vxlan: tx_ring->netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL; - if (!net_ratelimit()) + if (net_ratelimit()) netdev_err(tx_ring->netdev, "TSO requested for unsupported tunnel, disabling offload\n"); return -1; -- GitLab From 87be98927eb0bfa5484dfbe5ba2f6b7f91dd9187 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 11 Aug 2017 11:14:37 -0700 Subject: [PATCH 0822/1507] fm10k: prefer %s and __func__ for diagnostic prints Don't hard code the function names in the diagnostic output when these reset related routines fail. Instead, use %s and __func__ so that future refactors don't need to change the print outs. Additionally, while we are here, add missing function header comments for the new reset_prepare and reset_done function handlers. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 58538ce997e1c..1e9ae3197b172 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -2588,11 +2588,18 @@ static void fm10k_io_resume(struct pci_dev *pdev) if (err) dev_warn(&pdev->dev, - "fm10k_io_resume failed: %d\n", err); + "%s failed: %d\n", __func__, err); else netif_device_attach(netdev); } +/** + * fm10k_io_reset_prepare - called when PCI function is about to be reset + * @pdev: Pointer to PCI device + * + * This callback is called when the PCI function is about to be reset, + * allowing the device driver to prepare for it. + */ static void fm10k_io_reset_prepare(struct pci_dev *pdev) { /* warn incase we have any active VF devices */ @@ -2602,6 +2609,13 @@ static void fm10k_io_reset_prepare(struct pci_dev *pdev) fm10k_prepare_suspend(pci_get_drvdata(pdev)); } +/** + * fm10k_io_reset_done - called when PCI function has finished resetting + * @pdev: Pointer to PCI device + * + * This callback is called just after the PCI function is reset, such as via + * /sys/class/net//device/reset or similar. + */ static void fm10k_io_reset_done(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); @@ -2609,7 +2623,7 @@ static void fm10k_io_reset_done(struct pci_dev *pdev) if (err) { dev_warn(&pdev->dev, - "fm10k_io_reset_notify failed: %d\n", err); + "%s failed: %d\n", __func__, err); netif_device_detach(interface->netdev); } } -- GitLab From 2fb1e946450a4fef74bb72f360555f7760d816f0 Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Tue, 26 Sep 2017 16:47:04 +1000 Subject: [PATCH 0823/1507] KVM: PPC: Book3S: Fix server always zero from kvmppc_xive_get_xive() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In KVM's XICS-on-XIVE emulation, kvmppc_xive_get_xive() returns the value of state->guest_server as "server". However, this value is not set by it's counterpart kvmppc_xive_set_xive(). When the guest uses this interface to migrate interrupts away from a CPU that is going offline, it sees all interrupts as belonging to CPU 0, so they are left assigned to (now) offline CPUs. This patch removes the guest_server field from the state, and returns act_server in it's place (that is, the CPU actually handling the interrupt, which may differ from the one requested). Fixes: 5af50993850a ("KVM: PPC: Book3S HV: Native usage of the XIVE interrupt controller") Cc: stable@vger.kernel.org Signed-off-by: Sam Bobroff Acked-by: Benjamin Herrenschmidt Signed-off-by: Radim Krčmář --- arch/powerpc/kvm/book3s_xive.c | 5 ++--- arch/powerpc/kvm/book3s_xive.h | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 13304622ab1c7..bf457843e0321 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -622,7 +622,7 @@ int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server, return -EINVAL; state = &sb->irq_state[idx]; arch_spin_lock(&sb->lock); - *server = state->guest_server; + *server = state->act_server; *priority = state->guest_priority; arch_spin_unlock(&sb->lock); @@ -1331,7 +1331,7 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr) xive->saved_src_count++; /* Convert saved state into something compatible with xics */ - val = state->guest_server; + val = state->act_server; prio = state->saved_scan_prio; if (prio == MASKED) { @@ -1507,7 +1507,6 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) /* First convert prio and mark interrupt as untargetted */ act_prio = xive_prio_from_guest(guest_prio); state->act_priority = MASKED; - state->guest_server = server; /* * We need to drop the lock due to the mutex below. Hopefully diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 5938f7644dc17..6ba63f8e8a614 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -35,7 +35,6 @@ struct kvmppc_xive_irq_state { struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */ /* Targetting as set by guest */ - u32 guest_server; /* Current guest selected target */ u8 guest_priority; /* Guest set priority */ u8 saved_priority; /* Saved priority when masking */ -- GitLab From 3e256ac5b1ec307e5dd5a4c99fbdbc651446c738 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 11 Aug 2017 11:14:58 -0700 Subject: [PATCH 0824/1507] fm10k: fix mis-ordered parameters in declaration for .ndo_set_vf_bw We've had support for setting both a minimum and maximum bandwidth via .ndo_set_vf_bw since commit 883a9ccbae56 ("fm10k: Add support for SR-IOV to driver", 2014-09-20). Likely because we do not support minimum rates, the declaration mis-ordered the "unused" parameter, which causes warnings when analyzed with cppcheck. Fix this warning by properly declaring the min_rate and max_rate variables in the declaration and definition (rather than using "unused"). Also rename "rate" to max_rate so as to clarify that we only support setting the maximum rate. Signed-off-by: Jacob Keller Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/fm10k/fm10k.h | 4 ++-- drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 9 +++++---- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 40856bc0f3b98..46973fb234c56 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -562,8 +562,8 @@ s32 fm10k_iov_update_pvid(struct fm10k_intfc *interface, u16 glort, u16 pvid); int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac); int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, u8 qos, __be16 vlan_proto); -int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, int rate, - int unused); +int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, + int __always_unused min_rate, int max_rate); int fm10k_ndo_get_vf_config(struct net_device *netdev, int vf_idx, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 4a17cc903eedc..ea3ab24265ee0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -613,7 +613,7 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid, } int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, - int __always_unused unused, int rate) + int __always_unused min_rate, int max_rate) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_iov_data *iov_data = interface->iov_data; @@ -624,14 +624,15 @@ int fm10k_ndo_set_vf_bw(struct net_device *netdev, int vf_idx, return -EINVAL; /* rate limit cannot be less than 10Mbs or greater than link speed */ - if (rate && ((rate < FM10K_VF_TC_MIN) || rate > FM10K_VF_TC_MAX)) + if (max_rate && + (max_rate < FM10K_VF_TC_MIN || max_rate > FM10K_VF_TC_MAX)) return -EINVAL; /* store values */ - iov_data->vf_info[vf_idx].rate = rate; + iov_data->vf_info[vf_idx].rate = max_rate; /* update hardware configuration */ - hw->iov.ops.configure_tc(hw, vf_idx, rate); + hw->iov.ops.configure_tc(hw, vf_idx, max_rate); return 0; } -- GitLab From a047fbae23e1d94da28f81fb0f86fab4e473a094 Mon Sep 17 00:00:00 2001 From: Arjun Vynipadath Date: Tue, 3 Oct 2017 11:43:05 +0530 Subject: [PATCH 0825/1507] cxgb4: Update comment for min_mtu We have lost a comment for minimum mtu value set for netdevice with 'commit d894be57ca92 ("ethernet: use net core MTU range checking in more drivers"). Updating it accordingly. Signed-off-by: Arjun Vynipadath Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 13b636b0af5fc..fe4cbe22d5d73 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5024,7 +5024,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; /* MTU range: 81 - 9600 */ - netdev->min_mtu = 81; + netdev->min_mtu = 81; /* accommodate SACK */ netdev->max_mtu = MAX_MTU; netdev->netdev_ops = &cxgb4_netdev_ops; -- GitLab From abf4bb6b63d0a54266f8e7eff3720c1974063971 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:06 +0200 Subject: [PATCH 0826/1507] skbuff: Add the offload_mr_fwd_mark field Similarly to the offload_fwd_mark field, the offload_mr_fwd_mark field is used to allow partial offloading of MFC multicast routes. Switchdev drivers can offload MFC multicast routes to the hardware by registering to the FIB notification chain. When one of the route output interfaces is not offload-able, i.e. has different parent ID, the route cannot be fully offloaded by the hardware. Examples to non-offload-able devices are a management NIC, dummy device, pimreg device, etc. Similar problem exists in the bridge module, as one bridge can hold interfaces with different parent IDs. At the bridge, the problem is solved by the offload_fwd_mark skb field. Currently, when a route cannot go through full offload, the only solution for a switchdev driver is not to offload it at all and let the packet go through slow path. Using the offload_mr_fwd_mark field, a driver can indicate that a packet was already forwarded by hardware to all the devices with the same parent ID as the input device. Further patches in this patch-set are going to enhance ipmr to skip multicast forwarding to devices with the same parent ID if a packets is marked with that field. The reason why the already existing "offload_fwd_mark" bit cannot be used is that a switchdev driver would want to make the distinction between a packet that has already gone through L2 forwarding but did not go through multicast forwarding, and a packet that has already gone through both L2 and multicast forwarding. For example: when a packet is ingressing from a switchport enslaved to a bridge, which is configured with multicast forwarding, the following scenarios are possible: - The packet can be trapped to the CPU due to exception while multicast forwarding (for example, MTU error). In that case, it had already gone through L2 forwarding in the hardware, thus A switchdev driver would want to set the skb->offload_fwd_mark and not the skb->offload_mr_fwd_mark. - The packet can also be trapped due to a pimreg/dummy device used as one of the output interfaces. In that case, it can go through both L2 and (partial) multicast forwarding inside the hardware, thus a switchdev driver would want to set both the skb->offload_fwd_mark and skb->offload_mr_fwd_mark. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 19e64bfb1a669..ada821466e883 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -772,6 +772,7 @@ struct sk_buff { __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; + __u8 offload_mr_fwd_mark:1; #endif #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; -- GitLab From 5d8b3e69fc5e5ccafc9db1251bb7c78a8622fddd Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:07 +0200 Subject: [PATCH 0827/1507] ipv4: ipmr: Add the parent ID field to VIF struct In order to allow the ipmr module to do partial multicast forwarding according to the device parent ID, add the device parent ID field to the VIF struct. This way, the forwarding path can use the parent ID field without invoking switchdev calls, which requires the RTNL lock. When a new VIF is added, set the device parent ID field in it by invoking the switchdev_port_attr_get call. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 1 + net/ipv4/ipmr.c | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/include/linux/mroute.h b/include/linux/mroute.h index b072a84fbe1c7..8242d05df35e1 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -57,6 +57,7 @@ static inline bool ipmr_rule_default(const struct fib_rule *rule) struct vif_device { struct net_device *dev; /* Device we are using */ + struct netdev_phys_item_id dev_parent_id; /* Device parent ID */ unsigned long bytes_in,bytes_out; unsigned long pkt_in,pkt_out; /* Statistics */ unsigned long rate_limit; /* Traffic shaping (NI) */ diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a844738b38bd4..1b161ada7ae65 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,6 +67,7 @@ #include #include #include +#include struct ipmr_rule { struct fib_rule common; @@ -868,6 +869,9 @@ static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { int vifi = vifc->vifc_vifi; + struct switchdev_attr attr = { + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -942,6 +946,13 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* Fill in the VIF structures */ + attr.orig_dev = dev; + if (!switchdev_port_attr_get(dev, &attr)) { + memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); + v->dev_parent_id.id_len = attr.u.ppid.id_len; + } else { + v->dev_parent_id.id_len = 0; + } v->rate_limit = vifc->vifc_rate_limit; v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; -- GitLab From a5bc9294d70fe85729bb343eef281ccbe78ff119 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:08 +0200 Subject: [PATCH 0828/1507] ipv4: ipmr: Don't forward packets already forwarded by hardware Change the ipmr module to not forward packets if: - The packet is marked with the offload_mr_fwd_mark, and - Both input interface and output interface share the same parent ID. This way, a packet can go through partial multicast forwarding in the hardware, where it will be forwarded only to the devices that share the same parent ID (AKA, reside inside the same hardware). The kernel will forward the packet to all other interfaces. To do this, add the ipmr_offload_forward helper, which per skb, ingress VIF and egress VIF, returns whether the forwarding was offloaded to hardware. The ipmr_queue_xmit frees the skb and does not forward it if the result is a true value. All the forwarding path code compiles out when the CONFIG_NET_SWITCHDEV is not set. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 37 ++++++++++++++++++++++++++++++++----- 1 file changed, 32 insertions(+), 5 deletions(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 1b161ada7ae65..b3ee01b0551bd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1859,10 +1859,33 @@ static inline int ipmr_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } +#ifdef CONFIG_NET_SWITCHDEV +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + struct vif_device *out_vif = &mrt->vif_table[out_vifi]; + struct vif_device *in_vif = &mrt->vif_table[in_vifi]; + + if (!skb->offload_mr_fwd_mark) + return false; + if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) + return false; + return netdev_phys_item_id_same(&out_vif->dev_parent_id, + &in_vif->dev_parent_id); +} +#else +static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, + int in_vifi, int out_vifi) +{ + return false; +} +#endif + /* Processing handlers for ipmr_forward */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *c, int vifi) + int in_vifi, struct sk_buff *skb, + struct mfc_cache *c, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; @@ -1883,6 +1906,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, goto out_free; } + if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) + goto out_free; + if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, @@ -2060,8 +2086,8 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, - psend); + ipmr_queue_xmit(net, mrt, true_vifi, + skb2, cache, psend); } psend = ct; } @@ -2072,9 +2098,10 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, mrt, skb2, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb2, + cache, psend); } else { - ipmr_queue_xmit(net, mrt, skb, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend); return; } } -- GitLab From 267872435515185e2e600a721fdddeea90f96ffa Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:09 +0200 Subject: [PATCH 0829/1507] mlxsw: acl: Introduce ACL trap and forward action Use trap/discard flex action to implement trap and forward. The action will later be used for multicast routing, as the multicast routing mechanism is done using ACL flexible actions in Spectrum hardware. Using that action, it will be possible to implement a trap-and-forward route. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/core_acl_flex_actions.c | 17 +++++++++++++++++ .../mellanox/mlxsw/core_acl_flex_actions.h | 2 ++ 2 files changed, 19 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index bc55d0e76705f..6a979a09ab72d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -676,6 +676,7 @@ enum mlxsw_afa_trapdisc_trap_action { MLXSW_ITEM32(afa, trapdisc, trap_action, 0x00, 24, 4); enum mlxsw_afa_trapdisc_forward_action { + MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD = 1, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD = 3, }; @@ -729,6 +730,22 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) } EXPORT_SYMBOL(mlxsw_afa_block_append_trap); +int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, + u16 trap_id) +{ + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_TRAPDISC_CODE, + MLXSW_AFA_TRAPDISC_SIZE); + + if (!act) + return -ENOBUFS; + mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, + trap_id); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_trap_and_forward); + /* Forwarding Action * ----------------- * Forwarding Action can be used to implement Policy Based Switching (PBS) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 06b0be432b8f5..a8d3314c3a247 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -61,6 +61,8 @@ int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); +int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, + u16 trap_id); int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, u8 local_port, bool in_port); int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, -- GitLab From a0040c8c935548e1efb1a28f07f15d7ec7918055 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:10 +0200 Subject: [PATCH 0830/1507] mlxsw: spectrum: Add trap for multicast trap-and-forward routes When a multicast route is configured with trap-and-forward action, the packets should be marked with skb->offload_mr_fwd_mark, in order to prevent the packets from being forwarded again by the kernel ipmr module. Due to this, it is not possible to use the already existing multicast trap (MLXSW_TRAP_ID_ACL1) as the packet should be marked differently. Add the MLXSW_TRAP_ID_ACL2 which is for trap-and-forward multicast routes, and set the offload_mr_fwd_mark skb field in its handler. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 13 +++++++++++++ drivers/net/ethernet/mellanox/mlxsw/trap.h | 2 ++ 2 files changed, 15 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index e9b94430afed6..3adf237c951ad 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3312,6 +3312,14 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port, return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv); } +static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb, + u8 local_port, void *priv) +{ + skb->offload_mr_fwd_mark = 1; + skb->offload_fwd_mark = 1; + return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv); +} + static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port, void *priv) { @@ -3355,6 +3363,10 @@ static void mlxsw_sp_rx_listener_sample_func(struct sk_buff *skb, u8 local_port, MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action, \ _is_ctrl, SP_##_trap_group, DISCARD) +#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl) \ + MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action, \ + _is_ctrl, SP_##_trap_group, DISCARD) + #define MLXSW_SP_EVENTL(_func, _trap_id) \ MLXSW_EVENTL(_func, _trap_id, SP_EVENT) @@ -3425,6 +3437,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false), MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false), MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false), + MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), }; static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index a98103539f6b5..ec6cef8267ae1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -93,6 +93,8 @@ enum { MLXSW_TRAP_ID_ACL0 = 0x1C0, /* Multicast trap used for routes with trap action */ MLXSW_TRAP_ID_ACL1 = 0x1C1, + /* Multicast trap used for routes with trap-and-forward action */ + MLXSW_TRAP_ID_ACL2 = 0x1C2, MLXSW_TRAP_ID_MAX = 0x1FF }; -- GitLab From 607feadef89ac806df5a0be983afef77247e1541 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:11 +0200 Subject: [PATCH 0831/1507] mlxsw: spectrum: mr_tcam: Add trap-and-forward multicast route In addition to the current multicast route actions, which include trap route action and a forward route action, add the trap-and-forward multicast route action, and implement it in the multicast routing hardware logic. To implement that, add a trap-and-forward ACL action as the last action in the route flexible action set. The used trap is the ACL2 trap, which marks the packets with offload_mr_forward_mark, to prevent the packet from being forwarded again by the kernel. Note: At that stage the offloading logic does not support trap-and-forward multicast routes. This patch adds the support only in the hardware logic. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h | 1 + drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h index c851b237d2530..5d26a122af49d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h @@ -42,6 +42,7 @@ enum mlxsw_sp_mr_route_action { MLXSW_SP_MR_ROUTE_ACTION_FORWARD, MLXSW_SP_MR_ROUTE_ACTION_TRAP, + MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD, }; enum mlxsw_sp_mr_route_prio { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c index cda9e9ad10e38..3ffb28dd40576 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -253,6 +253,7 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err; break; + case MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD: case MLXSW_SP_MR_ROUTE_ACTION_FORWARD: /* If we are about to append a multicast router action, commit * the erif_list. @@ -266,6 +267,13 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp, erif_list->kvdl_index); if (err) goto err; + + if (route_action == MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD) { + err = mlxsw_afa_block_append_trap_and_forward(afa_block, + MLXSW_TRAP_ID_ACL2); + if (err) + goto err; + } break; default: err = -EINVAL; -- GitLab From f60c254998de80feaec8e4122960ab64e8045214 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Tue, 3 Oct 2017 09:58:12 +0200 Subject: [PATCH 0832/1507] mlxsw: spectrum: mr: Support trap-and-forward routes Add the support of trap-and-forward route action in the multicast routing offloading logic. A route will be set to trap-and-forward action if one (or more) of its output interfaces is not offload-able, i.e. does not have a valid Spectrum RIF. This way, a route with mixed output VIFs list, which contains both offload-able and un-offload-able devices can go through partial offloading in hardware, and the rest will be done in the kernel ipmr module. Signed-off-by: Yotam Gigi Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_mr.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 4aaf6ca1be7cc..1f84bb8e91352 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -114,9 +114,9 @@ static bool mlxsw_sp_mr_vif_valid(const struct mlxsw_sp_mr_vif *vif) return mlxsw_sp_mr_vif_regular(vif) && vif->dev && vif->rif; } -static bool mlxsw_sp_mr_vif_rif_invalid(const struct mlxsw_sp_mr_vif *vif) +static bool mlxsw_sp_mr_vif_exists(const struct mlxsw_sp_mr_vif *vif) { - return mlxsw_sp_mr_vif_regular(vif) && vif->dev && !vif->rif; + return vif->dev; } static bool @@ -182,14 +182,13 @@ mlxsw_sp_mr_route_action(const struct mlxsw_sp_mr_route *mr_route) if (!mlxsw_sp_mr_route_valid_evifs_num(mr_route)) return MLXSW_SP_MR_ROUTE_ACTION_TRAP; - /* If either one of the eVIFs is not regular (VIF of type pimreg or - * tunnel) or one of the VIFs has no matching RIF, trap the packet. + /* If one of the eVIFs has no RIF, trap-and-forward the route as there + * is some more routing to do in software too. */ - list_for_each_entry(rve, &mr_route->evif_list, route_node) { - if (!mlxsw_sp_mr_vif_regular(rve->mr_vif) || - mlxsw_sp_mr_vif_rif_invalid(rve->mr_vif)) - return MLXSW_SP_MR_ROUTE_ACTION_TRAP; - } + list_for_each_entry(rve, &mr_route->evif_list, route_node) + if (mlxsw_sp_mr_vif_exists(rve->mr_vif) && !rve->mr_vif->rif) + return MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD; + return MLXSW_SP_MR_ROUTE_ACTION_FORWARD; } -- GitLab From ce024f42c2e28b6bce4ecc1e891b42f57f753892 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 3 Oct 2017 13:20:48 +0300 Subject: [PATCH 0833/1507] net: rtnetlink: fix info leak in RTM_GETSTATS call When RTM_GETSTATS was added the fields of its header struct were not all initialized when returning the result thus leaking 4 bytes of information to user-space per rtnl_fill_statsinfo call, so initialize them now. Thanks to Alexander Potapenko for the detailed report and bisection. Reported-by: Alexander Potapenko Fixes: 10c9ead9f3c6 ("rtnetlink: add new RTM_GETSTATS message to dump link stats") Signed-off-by: Nikolay Aleksandrov Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a78fd61da0ec5..d4bcdcc68e926 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3854,6 +3854,9 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; ifsm = nlmsg_data(nlh); + ifsm->family = PF_UNSPEC; + ifsm->pad1 = 0; + ifsm->pad2 = 0; ifsm->ifindex = dev->ifindex; ifsm->filter_mask = filter_mask; -- GitLab From 161ae6b04d5da0de518ea600d8fffe61208e243c Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 3 Oct 2017 11:39:18 +0100 Subject: [PATCH 0834/1507] net: dsa: lan9303: make functions lan9303_mdio_phy_{read|write} static The functions lan9303_mdio_phy_write and lan9303_mdio_phy_read are local to the source and do not need to be in global scope, so make them static. Cleans up sparse warnings: symbol 'lan9303_mdio_phy_write' was not declared. Should it be static? symbol 'lan9303_mdio_phy_read' was not declared. Should it be static? Signed-off-by: Colin Ian King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/lan9303_mdio.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c index fc16668a487f5..0bc56b9900f94 100644 --- a/drivers/net/dsa/lan9303_mdio.c +++ b/drivers/net/dsa/lan9303_mdio.c @@ -67,14 +67,15 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val) return 0; } -int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg, u16 val) +static int lan9303_mdio_phy_write(struct lan9303 *chip, int phy, int reg, + u16 val) { struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev); return mdiobus_write_nested(sw_dev->device->bus, phy, reg, val); } -int lan9303_mdio_phy_read(struct lan9303 *chip, int phy, int reg) +static int lan9303_mdio_phy_read(struct lan9303 *chip, int phy, int reg) { struct lan9303_mdio *sw_dev = dev_get_drvdata(chip->dev); -- GitLab From 360cc342c9037ed487adf07212000f69c0ffa14d Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 3 Oct 2017 11:46:33 +0100 Subject: [PATCH 0835/1507] net: dsa: mt7530: make functions mt7530_phy_write static The function mt7530_phy_write is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warnings: symbol 'mt7530_phy_write' was not declared. Should it be static? Signed-off-by: Colin Ian King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index faa3b88d2206a..034241696ce21 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -564,7 +564,8 @@ static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum) return mdiobus_read_nested(priv->bus, port, regnum); } -int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) +static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, + u16 val) { struct mt7530_priv *priv = ds->priv; -- GitLab From b508e0b6e47c85a095ef056f3de6ba9d396c490c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 3 Oct 2017 13:53:03 +0300 Subject: [PATCH 0836/1507] mlxsw: spectrum: Fix check for IS_ERR() instead of NULL mlxsw_afa_block_create() doesn't return error pointers, it returns NULL on error. Fixes: 0e14c7777acb ("mlxsw: spectrum: Add the multicast routing hardware logic") Signed-off-by: Dan Carpenter Acked-by: Yotam Gigi Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c index 3ffb28dd40576..3a61896ae4d81 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -239,8 +239,8 @@ mlxsw_sp_mr_tcam_afa_block_create(struct mlxsw_sp *mlxsw_sp, int err; afa_block = mlxsw_afa_block_create(mlxsw_sp->afa); - if (IS_ERR(afa_block)) - return afa_block; + if (!afa_block) + return ERR_PTR(-ENOMEM); err = mlxsw_afa_block_append_counter(afa_block, counter_index); if (err) -- GitLab From b5c7d4e54c9ab830e5c03f92377fe15cbae64d0d Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 3 Oct 2017 13:53:41 +0300 Subject: [PATCH 0837/1507] mlxsw: spectrum: Add missing error code on allocation failure We accidentally return success if the kmalloc_array() call fails. Fixes: 0e14c7777acb ("mlxsw: spectrum: Add the multicast routing hardware logic") Signed-off-by: Dan Carpenter Acked-by: Yotam Gigi Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c index 3a61896ae4d81..39c21c70ac323 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -771,8 +771,10 @@ mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp, parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1, sizeof(*parman_prios), GFP_KERNEL); - if (!parman_prios) + if (!parman_prios) { + err = -ENOMEM; goto err_parman_prios_alloc; + } mr_tcam_region->parman_prios = parman_prios; for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++) -- GitLab From 38b249bc0ca26d57dac65f5f659b39d88899d23d Mon Sep 17 00:00:00 2001 From: Wouter Verhelst Date: Fri, 22 Sep 2017 12:09:54 +0200 Subject: [PATCH 0838/1507] MAINTAINERS: update list for NBD nbd-general@sourceforge.net becomes nbd@other.debian.org, because sourceforge is just a spamtrap these days. Signed-off-by: Wouter Verhelst Reviewed-by: Josef Bacik Signed-off-by: Jens Axboe --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6671f375f7fcd..17a643f670a49 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9348,7 +9348,7 @@ NETWORK BLOCK DEVICE (NBD) M: Josef Bacik S: Maintained L: linux-block@vger.kernel.org -L: nbd-general@lists.sourceforge.net +L: nbd@other.debian.org F: Documentation/blockdev/nbd.txt F: drivers/block/nbd.c F: include/uapi/linux/nbd.h -- GitLab From d410a6417e5e4deb4a9c34164addcebebc9099c9 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 3 Oct 2017 13:18:47 +0200 Subject: [PATCH 0839/1507] ide: free hwif->portdev on hwif_init() failure Recent pci_assign_irq() changes uncovered a problem with missing freeing of ide_port class instance on hwif_init() failure in ide_host_register(): ide0: disabled, no IRQ ide0: failed to initialize IDE interface ide0: disabling port cmd64x 0000:00:02.0: IDE controller (0x1095:0x0646 rev 0x07) CMD64x_IDE 0000:00:02.0: BAR 0: can't reserve [io 0x8050-0x8057] cmd64x 0000:00:02.0: can't reserve resources CMD64x_IDE: probe of 0000:00:02.0 failed with error -16 ide_generic: please use "probe_mask=0x3f" module parameter for probing all legacy ISA IDE ports ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x94/0xd0 sysfs: cannot create duplicate filename '/class/ide_port/ide0' ... Trace: [] __warn+0x160/0x190 [] sysfs_warn_dup+0x94/0xd0 [] warn_slowpath_fmt+0x58/0x70 [] sysfs_warn_dup+0x94/0xd0 [] kernfs_path_from_node+0x30/0x60 [] kernfs_put+0x16c/0x2c0 [] kernfs_put+0x16c/0x2c0 [] sysfs_do_create_link_sd.isra.2+0x100/0x120 [] device_add+0x2a4/0x7c0 [] device_create_groups_vargs+0x14c/0x170 [] device_create_groups_vargs+0x98/0x170 [] device_create+0x50/0x70 [] ide_host_register+0x48c/0xa00 [] ide_host_register+0x450/0xa00 [] device_register+0x20/0x50 [] ide_host_register+0x450/0xa00 [] ide_host_add+0x64/0xe0 [] kobject_uevent_env+0x16c/0x710 [] do_one_initcall+0x68/0x260 [] kernel_init+0x1c/0x1a0 [] kernel_init+0x0/0x1a0 [] ret_from_kernel_thread+0x18/0x20 [] kernel_init+0x0/0x1a0 ---[ end trace 24a70433c3e4d374 ]--- ide0: disabling port Fix the problem by adding missing code to ide_host_register(). Fixes: 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in pci_device_probe()") Fixes: 0e4c2eeb758a ("alpha/PCI: Replace pci_fixup_irqs() call with host bridge IRQ mapping hooks") Link: http://lkml.kernel.org/r/32ec730f-c1b0-5584-cd35-f8a809122b96@roeck-us.net Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Bartlomiej Zolnierkiewicz [bhelgaas: add Fixes:] Signed-off-by: Bjorn Helgaas Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner --- drivers/ide/ide-probe.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 01b2adfd8226b..eaf39e5db08ba 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1451,6 +1451,7 @@ int ide_host_register(struct ide_host *host, const struct ide_port_info *d, if (hwif_init(hwif) == 0) { printk(KERN_INFO "%s: failed to initialize IDE " "interface\n", hwif->name); + device_unregister(hwif->portdev); device_unregister(&hwif->gendev); ide_disable_port(hwif); continue; -- GitLab From a06876a766c27dcedf17a0f60be89609ee23d861 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 3 Oct 2017 14:17:13 +0200 Subject: [PATCH 0840/1507] ide: pci: free PCI BARs on initialization failure Recent pci_assign_irq() changes uncovered a problem with missing freeing of PCI BARs on PCI IDE host initialization failure: ide0: disabled, no IRQ ide0: failed to initialize IDE interface ide0: disabling port cmd64x 0000:00:02.0: IDE controller (0x1095:0x0646 rev 0x07) CMD64x_IDE 0000:00:02.0: BAR 0: can't reserve [io 0x8050-0x8057] cmd64x 0000:00:02.0: can't reserve resources CMD64x_IDE: probe of 0000:00:02.0 failed with error -16 Fix the problem by adding missing freeing of PCI BARs to ide_setup_pci_controller() and ide_pci_init_two(). Fixes: 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in pci_device_probe()") Fixes: 0e4c2eeb758a ("alpha/PCI: Replace pci_fixup_irqs() call with host bridge IRQ mapping hooks") Link: http://lkml.kernel.org/r/32ec730f-c1b0-5584-cd35-f8a809122b96@roeck-us.net Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Bartlomiej Zolnierkiewicz [bhelgaas: add Fixes:] Signed-off-by: Bjorn Helgaas Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner --- drivers/ide/setup-pci.c | 63 ++++++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 23 deletions(-) diff --git a/drivers/ide/setup-pci.c b/drivers/ide/setup-pci.c index 112d2fe1bcdbc..fdc8e813170c3 100644 --- a/drivers/ide/setup-pci.c +++ b/drivers/ide/setup-pci.c @@ -179,6 +179,7 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); /** * ide_pci_enable - do PCI enables * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * * Enable the IDE PCI device. We attempt to enable the device in full @@ -189,9 +190,10 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise); * Returns zero on success or an error code */ -static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) +static int ide_pci_enable(struct pci_dev *dev, int bars, + const struct ide_port_info *d) { - int ret, bars; + int ret; if (pci_enable_device(dev)) { ret = pci_enable_device_io(dev); @@ -216,18 +218,6 @@ static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d) goto out; } - if (d->host_flags & IDE_HFLAG_SINGLE) - bars = (1 << 2) - 1; - else - bars = (1 << 4) - 1; - - if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { - if (d->host_flags & IDE_HFLAG_CS5520) - bars |= (1 << 2); - else - bars |= (1 << 4); - } - ret = pci_request_selected_regions(dev, bars, d->name); if (ret < 0) printk(KERN_ERR "%s %s: can't reserve resources\n", @@ -403,6 +393,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) /** * ide_setup_pci_controller - set up IDE PCI * @dev: PCI device + * @bars: PCI BARs mask * @d: IDE port info * @noisy: verbose flag * @@ -411,7 +402,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d) * and enables it if need be */ -static int ide_setup_pci_controller(struct pci_dev *dev, +static int ide_setup_pci_controller(struct pci_dev *dev, int bars, const struct ide_port_info *d, int noisy) { int ret; @@ -420,7 +411,7 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (noisy) ide_setup_pci_noise(dev, d); - ret = ide_pci_enable(dev, d); + ret = ide_pci_enable(dev, bars, d); if (ret < 0) goto out; @@ -428,16 +419,20 @@ static int ide_setup_pci_controller(struct pci_dev *dev, if (ret < 0) { printk(KERN_ERR "%s %s: error accessing PCI regs\n", d->name, pci_name(dev)); - goto out; + goto out_free_bars; } if (!(pcicmd & PCI_COMMAND_IO)) { /* is device disabled? */ ret = ide_pci_configure(dev, d); if (ret < 0) - goto out; + goto out_free_bars; printk(KERN_INFO "%s %s: device enabled (Linux)\n", d->name, pci_name(dev)); } + goto out; + +out_free_bars: + pci_release_selected_regions(dev, bars); out: return ret; } @@ -540,13 +535,28 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, { struct pci_dev *pdev[] = { dev1, dev2 }; struct ide_host *host; - int ret, i, n_ports = dev2 ? 4 : 2; + int ret, i, n_ports = dev2 ? 4 : 2, bars; struct ide_hw hw[4], *hws[] = { NULL, NULL, NULL, NULL }; + if (d->host_flags & IDE_HFLAG_SINGLE) + bars = (1 << 2) - 1; + else + bars = (1 << 4) - 1; + + if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) { + if (d->host_flags & IDE_HFLAG_CS5520) + bars |= (1 << 2); + else + bars |= (1 << 4); + } + for (i = 0; i < n_ports / 2; i++) { - ret = ide_setup_pci_controller(pdev[i], d, !i); - if (ret < 0) + ret = ide_setup_pci_controller(pdev[i], bars, d, !i); + if (ret < 0) { + if (i == 1) + pci_release_selected_regions(pdev[0], bars); goto out; + } ide_pci_setup_ports(pdev[i], d, &hw[i*2], &hws[i*2]); } @@ -554,7 +564,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, host = ide_host_alloc(d, hws, n_ports); if (host == NULL) { ret = -ENOMEM; - goto out; + goto out_free_bars; } host->dev[0] = &dev1->dev; @@ -576,7 +586,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, * do_ide_setup_pci_device() on the first device! */ if (ret < 0) - goto out; + goto out_free_bars; /* fixup IRQ */ if (ide_pci_is_in_compatibility_mode(pdev[i])) { @@ -589,6 +599,13 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2, ret = ide_host_register(host, d, hws); if (ret) ide_host_free(host); + else + goto out; + +out_free_bars: + i = n_ports / 2; + while (i--) + pci_release_selected_regions(pdev[i], bars); out: return ret; } -- GitLab From b1f9e5e355e909000fcccfd2bc31f7c1ded358ab Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 2 Oct 2017 11:52:47 +0100 Subject: [PATCH 0841/1507] ide: fix IRQ assignment for PCI bus order probing We used to assign IRQs for all devices at boot-time, before any drivers claimed devices. The following commits: 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in pci_device_probe()") 0e4c2eeb758a ("alpha/PCI: Replace pci_fixup_irqs() call with host bridge IRQ mapping hooks") changed this so we now call pci_assign_irq() from pci_device_probe() when we call a driver's probe method. The ide_scan_pcibus() path (enabled by CONFIG_IDEPCI_PCIBUS_ORDER) bypasses pci_device_probe() so it can guarantee devices are claimed in order of PCI bus address. It calls the driver's probe method directly, so it misses the pci_assign_irq() call (and other PCI initialization functions), which causes failures like this: ide0: disabled, no IRQ ide0: failed to initialize IDE interface ide0: disabling port cmd64x 0000:00:02.0: IDE controller (0x1095:0x0646 rev 0x07) CMD64x_IDE 0000:00:02.0: BAR 0: can't reserve [io 0x8050-0x8057] cmd64x 0000:00:02.0: can't reserve resources CMD64x_IDE: probe of 0000:00:02.0 failed with error -16 ide_generic: please use "probe_mask=0x3f" module parameter for probing all legacy ISA IDE ports ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x94/0xd0 sysfs: cannot create duplicate filename '/class/ide_port/ide0' ... Trace: [] sysfs_warn_dup+0x94/0xd0 [] warn_slowpath_fmt+0x58/0x70 [] sysfs_warn_dup+0x94/0xd0 [] kernfs_path_from_node+0x30/0x60 [] kernfs_put+0x16c/0x2c0 [] kernfs_put+0x16c/0x2c0 [] sysfs_do_create_link_sd.isra.2+0x100/0x120 [] device_add+0x2a4/0x7c0 [] device_create_groups_vargs+0x14c/0x170 [] device_create_groups_vargs+0x98/0x170 [] device_create+0x50/0x70 [] ide_host_register+0x48c/0xa00 [] ide_host_register+0x450/0xa00 [] device_register+0x20/0x50 [] ide_host_register+0x450/0xa00 [] ide_host_add+0x64/0xe0 [] kobject_uevent_env+0x16c/0x710 [] do_one_initcall+0x68/0x260 [] kernel_init+0x1c/0x1a0 ... ---[ end trace 24a70433c3e4d374 ]--- ide0: disabling port Fix the IRQ allocation issue by calling pci_assign_irq() from ide_scan_pcidev() before probing the IDE PCI drivers, so that IRQs for a given PCI device are allocated for the IDE PCI drivers to use them for device configuration. Fixes: 30fdfb929e82 ("PCI: Add a call to pci_assign_irq() in pci_device_probe()") Fixes: 0e4c2eeb758a ("alpha/PCI: Replace pci_fixup_irqs() call with host bridge IRQ mapping hooks") Link: http://lkml.kernel.org/r/32ec730f-c1b0-5584-cd35-f8a809122b96@roeck-us.net Reported-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Lorenzo Pieralisi [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Bartlomiej Zolnierkiewicz Acked-by: David S. Miller Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner --- drivers/ide/ide-scan-pci.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/ide/ide-scan-pci.c b/drivers/ide/ide-scan-pci.c index 86aa88aeb3a6b..acf874800ca40 100644 --- a/drivers/ide/ide-scan-pci.c +++ b/drivers/ide/ide-scan-pci.c @@ -56,6 +56,7 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) { struct list_head *l; struct pci_driver *d; + int ret; list_for_each(l, &ide_pci_drivers) { d = list_entry(l, struct pci_driver, node); @@ -63,10 +64,14 @@ static int __init ide_scan_pcidev(struct pci_dev *dev) const struct pci_device_id *id = pci_match_id(d->id_table, dev); - if (id != NULL && d->probe(dev, id) >= 0) { - dev->driver = d; - pci_dev_get(dev); - return 1; + if (id != NULL) { + pci_assign_irq(dev); + ret = d->probe(dev, id); + if (ret >= 0) { + dev->driver = d; + pci_dev_get(dev); + return 1; + } } } } -- GitLab From 71300132975f364a0d3ebf68671a2ce4923191db Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Mon, 2 Oct 2017 16:53:07 +0300 Subject: [PATCH 0842/1507] drm/i915: Fix DDI PHY init if it was already on The common lane power down flag of a DPIO PHY has a funky semantic: after the initial enabling of the PHY (so from a disabled state) this flag will be clear. It will be set only after the PHY will be used for the first time (for instance due to enabling the corresponding pipe) and then become unused (due to disabling the pipe). During the initial PHY enablement we don't know which of the above phases we are in, so move the check for the flag where this is known, the HW readout code. This is where the rest of lane power down status checks are done anyway. This fixes at least a problem on GLK where after module reloading, the common lane power down flag of PHY1 is set, but the PHY is actually powered-on and properly set up. The GRC readout code for other PHYs will hence think that PHY1 is not powered initially and disable it after the GRC readout. This will cause the AUX power well related to PHY1 to get disabled in a stuck state, timing out when we try to enable it later. Cc: Ville Syrjala Fixes: e93da0a0137b ("drm/i915/bxt: Sanitiy check the PHY lane power down status") Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102777 Signed-off-by: Imre Deak Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20171002135307.26117-1-imre.deak@intel.com (cherry picked from commit e19c1eb885ac4186e64c7e484424124f3145318e) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_ddi.c | 3 ++- drivers/gpu/drm/i915/intel_dpio_phy.c | 20 -------------------- 2 files changed, 2 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4b4fd1f8110b2..476681d5940c7 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1655,7 +1655,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, out: if (ret && IS_GEN9_LP(dev_priv)) { tmp = I915_READ(BXT_PHY_CTL(port)); - if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK | + if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK | BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED) DRM_ERROR("Port %c enabled but PHY powered down? " "(PHY_CTL %08x)\n", port_name(port), tmp); diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c index 09b6709297867..de38d014ed39b 100644 --- a/drivers/gpu/drm/i915/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/intel_dpio_phy.c @@ -208,12 +208,6 @@ static const struct bxt_ddi_phy_info glk_ddi_phy_info[] = { }, }; -static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info) -{ - return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) | - BIT(phy_info->channel[DPIO_CH0].port); -} - static const struct bxt_ddi_phy_info * bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count) { @@ -313,7 +307,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, enum dpio_phy phy) { const struct bxt_ddi_phy_info *phy_info; - enum port port; phy_info = bxt_get_phy_info(dev_priv, phy); @@ -335,19 +328,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv, return false; } - for_each_port_masked(port, bxt_phy_port_mask(phy_info)) { - u32 tmp = I915_READ(BXT_PHY_CTL(port)); - - if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) { - DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane " - "for port %c powered down " - "(PHY_CTL %08x)\n", - phy, port_name(port), tmp); - - return false; - } - } - return true; } -- GitLab From 63ba395cd7a52431cbb61658dad3beb5b24e9300 Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Wed, 27 Sep 2017 23:31:03 +0200 Subject: [PATCH 0843/1507] rndis_host: support Novatel Verizon USB730L MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Treat the ef/04/01 interface class/subclass/protocol combination used by the Novatel Verizon USB730L (1410:9030) as a possible RNDIS interface. T: Bus=01 Lev=02 Prnt=02 Port=01 Cnt=02 Dev#= 17 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 3 P: Vendor=1410 ProdID=9030 Rev=03.10 S: Manufacturer=Novatel Wireless S: Product=MiFi USB730L S: SerialNumber=0123456789ABCDEF C: #Ifs= 3 Cfg#= 1 Atr=80 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host I: If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host I: If#= 2 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid Once the network interface is brought up, the user just needs to run a DHCP client to get IP address and routing setup. As a side note, other Novatel Verizon USB730L models with the same vid:pid end up exposing a standard ECM interface which doesn't require any other kernel update to make it work. Signed-off-by: Aleksander Morgado Reviewed-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ether.c | 11 ++++++++++- drivers/net/usb/rndis_host.c | 4 ++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 677a85360db15..29c7e2ec0dcbe 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -54,11 +54,19 @@ static int is_wireless_rndis(struct usb_interface_descriptor *desc) desc->bInterfaceProtocol == 3); } +static int is_novatel_rndis(struct usb_interface_descriptor *desc) +{ + return (desc->bInterfaceClass == USB_CLASS_MISC && + desc->bInterfaceSubClass == 4 && + desc->bInterfaceProtocol == 1); +} + #else #define is_rndis(desc) 0 #define is_activesync(desc) 0 #define is_wireless_rndis(desc) 0 +#define is_novatel_rndis(desc) 0 #endif @@ -150,7 +158,8 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) */ rndis = (is_rndis(&intf->cur_altsetting->desc) || is_activesync(&intf->cur_altsetting->desc) || - is_wireless_rndis(&intf->cur_altsetting->desc)); + is_wireless_rndis(&intf->cur_altsetting->desc) || + is_novatel_rndis(&intf->cur_altsetting->desc)); memset(info, 0, sizeof(*info)); info->control = intf; diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index a151f267aebb9..b807c91abe1da 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -632,6 +632,10 @@ static const struct usb_device_id products [] = { /* RNDIS for tethering */ USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3), .driver_info = (unsigned long) &rndis_info, +}, { + /* Novatel Verizon USB730L */ + USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1), + .driver_info = (unsigned long) &rndis_info, }, { }, // END }; -- GitLab From 4d2c0cda07448ea6980f00102dc3964eb25e241c Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 27 Sep 2017 18:03:49 -0700 Subject: [PATCH 0844/1507] bonding: speed/duplex update at NETDEV_UP event Some NIC drivers don't have correct speed/duplex settings at the time they send NETDEV_UP notification and that messes up the bonding state. Especially 802.3ad mode which is very sensitive to these settings. In the current implementation we invoke bond_update_speed_duplex() when we receive NETDEV_UP, however, ignore the return value. If the values we get are invalid (UNKNOWN), then slave gets removed from the aggregator with speed and duplex set to UNKNOWN while link is still marked as UP. This patch fixes this scenario. Also 802.3ad mode is sensitive to these conditions while other modes are not, so making sure that it doesn't change the behavior for other modes. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d2e94b8559f0f..b19dc033fb369 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3073,7 +3073,16 @@ static int bond_slave_netdev_event(unsigned long event, break; case NETDEV_UP: case NETDEV_CHANGE: - bond_update_speed_duplex(slave); + /* For 802.3ad mode only: + * Getting invalid Speed/Duplex values here will put slave + * in weird state. So mark it as link-down for the time + * being and let link-monitoring (miimon) set it right when + * correct speeds/duplex are available. + */ + if (bond_update_speed_duplex(slave) && + BOND_MODE(bond) == BOND_MODE_8023AD) + slave->link = BOND_LINK_DOWN; + if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); /* Fallthrough */ -- GitLab From 4f02fb7617ba12ac15d261c654b9759ea8f1f1ef Mon Sep 17 00:00:00 2001 From: Joseph Qi Date: Sat, 30 Sep 2017 14:38:49 +0800 Subject: [PATCH 0845/1507] blk-throttle: fix possible io stall when upgrade to max There is a case which will lead to io stall. The case is described as follows. /test1 |-subtest1 /test2 |-subtest2 And subtest1 and subtest2 each has 32 queued bios already. Now upgrade to max. In throtl_upgrade_state, it will try to dispatch bios as follows: 1) tg=subtest1, do nothing; 2) tg=test1, transfer 32 queued bios from subtest1 to test1; no pending left, no need to schedule next dispatch; 3) tg=subtest2, do nothing; 4) tg=test2, transfer 32 queued bios from subtest2 to test2; no pending left, no need to schedule next dispatch; 5) tg=/, transfer 8 queued bios from test1 to /, 8 queued bios from test2 to /, 8 queued bios from test1 to /, and 8 queued bios from test2 to /; note that test1 and test2 each still has 16 queued bios left; 6) tg=/, try to schedule next dispatch, but since disptime is now (update in tg_update_disptime, wait=0), pending timer is not scheduled in fact; 7) In throtl_upgrade_state it totally dispatches 32 queued bios and with 32 left. test1 and test2 each has 16 queued bios; 8) throtl_pending_timer_fn sees the left over bios, but could do nothing, because throtl_select_dispatch returns 0, and test1/test2 has no pending tg. The blktrace shows the following: 8,32 0 0 2.539007641 0 m N throtl upgrade to max 8,32 0 0 2.539072267 0 m N throtl /test2 dispatch nr_queued=16 read=0 write=16 8,32 7 0 2.539077142 0 m N throtl /test1 dispatch nr_queued=16 read=0 write=16 So force schedule dispatch if there are pending children. Reviewed-by: Shaohua Li Signed-off-by: Joseph Qi Signed-off-by: Jens Axboe --- block/blk-throttle.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 0fea76aa0f3ff..17816a028dcbb 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1911,11 +1911,11 @@ static void throtl_upgrade_state(struct throtl_data *td) tg->disptime = jiffies - 1; throtl_select_dispatch(sq); - throtl_schedule_next_dispatch(sq, false); + throtl_schedule_next_dispatch(sq, true); } rcu_read_unlock(); throtl_select_dispatch(&td->service_queue); - throtl_schedule_next_dispatch(&td->service_queue, false); + throtl_schedule_next_dispatch(&td->service_queue, true); queue_work(kthrotld_workqueue, &td->dispatch_work); } -- GitLab From 6cd1a6fef7058de15405b13d6587538853279c7b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 3 Oct 2017 15:58:15 -0600 Subject: [PATCH 0846/1507] null_blk: change configfs dependency to select A recent commit made null_blk depend on configfs, which is kind of annoying since you now have to find this dependency and enable that as well. Discovered this since I no longer had null_blk available on a box I needed to debug, since it got killed when the config updated after the configfs change was merged. Fixes: 3bf2bd20734e ("nullb: add configfs interface") Reviewed-by: Shaohua Li Signed-off-by: Jens Axboe --- drivers/block/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 4a438b8abe27a..2dfe99b328f88 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -17,7 +17,7 @@ if BLK_DEV config BLK_DEV_NULL_BLK tristate "Null test block driver" - depends on CONFIGFS_FS + select CONFIGFS_FS config BLK_DEV_FD tristate "Normal floppy disk support" -- GitLab From 70e62f4bacdf31ea8a59f241c9229120cd06d9d1 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 3 Oct 2017 14:57:16 -0700 Subject: [PATCH 0847/1507] blk-mq-debugfs: fix device sched directory for default scheduler In blk_mq_debugfs_register(), I remembered to set up the per-hctx sched directories if a default scheduler was already configured by blk_mq_sched_init() from blk_mq_init_allocated_queue(), but I didn't do the same for the device-wide sched directory. Fix it. Fixes: d332ce091813 ("blk-mq-debugfs: allow schedulers to register debugfs attributes") Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 980e730956433..de294d775acfa 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -815,10 +815,14 @@ int blk_mq_debugfs_register(struct request_queue *q) goto err; /* - * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir + * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir * didn't exist yet (because we don't know what to name the directory * until the queue is registered to a gendisk). */ + if (q->elevator && !q->sched_debugfs_dir) + blk_mq_debugfs_register_sched(q); + + /* Similarly, blk_mq_init_hctx() couldn't do this previously. */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx)) goto err; -- GitLab From 05946876f0c16f6fe1db692d575aba42b25f0811 Mon Sep 17 00:00:00 2001 From: David Wu Date: Sat, 30 Sep 2017 17:47:23 +0800 Subject: [PATCH 0848/1507] net: stmmac: dwmac-rk: Add RK3128 GMAC support Add constants and callback functions for the dwmac on rk3128 soc. As can be seen, the base structure is the same, only registers and the bits in them moved slightly. Signed-off-by: David Wu Signed-off-by: David S. Miller --- .../bindings/net/rockchip-dwmac.txt | 1 + .../net/ethernet/stmicro/stmmac/dwmac-rk.c | 112 ++++++++++++++++++ 2 files changed, 113 insertions(+) diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt index 6af8eed1adeb1..9c16ee2965a2c 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt @@ -4,6 +4,7 @@ The device node has following properties. Required properties: - compatible: should be "rockchip,-gamc" + "rockchip,rk3128-gmac": found on RK312x SoCs "rockchip,rk3228-gmac": found on RK322x SoCs "rockchip,rk3288-gmac": found on RK3288 SoCs "rockchip,rk3328-gmac": found on RK3328 SoCs diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 99823f54696a1..13133b30b575e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -83,6 +83,117 @@ struct rk_priv_data { (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \ ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE)) +#define RK3128_GRF_MAC_CON0 0x0168 +#define RK3128_GRF_MAC_CON1 0x016c + +/* RK3128_GRF_MAC_CON0 */ +#define RK3128_GMAC_TXCLK_DLY_ENABLE GRF_BIT(14) +#define RK3128_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) +#define RK3128_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) +#define RK3128_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) +#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) +#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) + +/* RK3128_GRF_MAC_CON1 */ +#define RK3128_GMAC_PHY_INTF_SEL_RGMII \ + (GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8)) +#define RK3128_GMAC_PHY_INTF_SEL_RMII \ + (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8)) +#define RK3128_GMAC_FLOW_CTRL GRF_BIT(9) +#define RK3128_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) +#define RK3128_GMAC_SPEED_10M GRF_CLR_BIT(10) +#define RK3128_GMAC_SPEED_100M GRF_BIT(10) +#define RK3128_GMAC_RMII_CLK_25M GRF_BIT(11) +#define RK3128_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) +#define RK3128_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) +#define RK3128_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_RMII_MODE GRF_BIT(14) +#define RK3128_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) + +static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, + int tx_delay, int rx_delay) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_PHY_INTF_SEL_RGMII | + RK3128_GMAC_RMII_MODE_CLR); + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0, + DELAY_ENABLE(RK3128, tx_delay, rx_delay) | + RK3128_GMAC_CLK_RX_DL_CFG(rx_delay) | + RK3128_GMAC_CLK_TX_DL_CFG(tx_delay)); +} + +static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE); +} + +static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + if (speed == 10) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_2_5M); + else if (speed == 100) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_25M); + else if (speed == 1000) + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_CLK_125M); + else + dev_err(dev, "unknown speed value for RGMII! speed=%d", speed); +} + +static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + if (speed == 10) { + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_RMII_CLK_2_5M | + RK3128_GMAC_SPEED_10M); + } else if (speed == 100) { + regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, + RK3128_GMAC_RMII_CLK_25M | + RK3128_GMAC_SPEED_100M); + } else { + dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + } +} + +static const struct rk_gmac_ops rk3128_ops = { + .set_to_rgmii = rk3128_set_to_rgmii, + .set_to_rmii = rk3128_set_to_rmii, + .set_rgmii_speed = rk3128_set_rgmii_speed, + .set_rmii_speed = rk3128_set_rmii_speed, +}; + #define RK3228_GRF_MAC_CON0 0x0900 #define RK3228_GRF_MAC_CON1 0x0904 @@ -1313,6 +1424,7 @@ static int rk_gmac_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume); static const struct of_device_id rk_gmac_dwmac_match[] = { + { .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops }, { .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops }, { .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops }, { .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops }, -- GitLab From 6c5570016b972d9b1f0f6c2dca9cc0422b1f92bf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 2 Oct 2017 23:50:05 +0200 Subject: [PATCH 0849/1507] net: core: decouple ifalias get/set from rtnl lock Device alias can be set by either rtnetlink (rtnl is held) or sysfs. rtnetlink hold the rtnl mutex, sysfs acquires it for this purpose. Add an extra mutex for it and use rcu to protect concurrent accesses. This allows the sysfs path to not take rtnl and would later allow to not hold it when dumping ifalias. Based on suggestion from Eric Dumazet. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++++- net/core/dev.c | 52 +++++++++++++++++++++++++++++---------- net/core/net-sysfs.c | 17 ++++++------- net/core/rtnetlink.c | 13 ++++++++-- 4 files changed, 65 insertions(+), 25 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e1d6ef130611d..d04424cfffbaa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -826,6 +826,11 @@ struct xfrmdev_ops { }; #endif +struct dev_ifalias { + struct rcu_head rcuhead; + char ifalias[]; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1632,7 +1637,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; struct hlist_node name_hlist; - char *ifalias; + struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one @@ -3275,6 +3280,7 @@ void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); +int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); diff --git a/net/core/dev.c b/net/core/dev.c index e350c768d4b5a..1770097cfd86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -188,6 +188,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id); DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +static DEFINE_MUTEX(ifalias_mutex); + /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); @@ -1265,29 +1267,53 @@ int dev_change_name(struct net_device *dev, const char *newname) */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { - char *new_ifalias; - - ASSERT_RTNL(); + struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; - if (!len) { - kfree(dev->ifalias); - dev->ifalias = NULL; - return 0; + if (len) { + new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); + if (!new_alias) + return -ENOMEM; + + memcpy(new_alias->ifalias, alias, len); + new_alias->ifalias[len] = 0; } - new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!new_ifalias) - return -ENOMEM; - dev->ifalias = new_ifalias; - memcpy(dev->ifalias, alias, len); - dev->ifalias[len] = 0; + mutex_lock(&ifalias_mutex); + rcu_swap_protected(dev->ifalias, new_alias, + mutex_is_locked(&ifalias_mutex)); + mutex_unlock(&ifalias_mutex); + + if (new_alias) + kfree_rcu(new_alias, rcuhead); return len; } +/** + * dev_get_alias - get ifalias of a device + * @dev: device + * @alias: buffer to store name of ifalias + * @len: size of buffer + * + * get ifalias for a device. Caller must make sure dev cannot go + * away, e.g. rcu read lock or own a reference count to device. + */ +int dev_get_alias(const struct net_device *dev, char *name, size_t len) +{ + const struct dev_ifalias *alias; + int ret = 0; + + rcu_read_lock(); + alias = rcu_dereference(dev->ifalias); + if (alias) + ret = snprintf(name, len, "%s", alias->ifalias); + rcu_read_unlock(); + + return ret; +} /** * netdev_features_change - device changes features diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 927a6dcbad966..51d5836d8fb99 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -391,10 +391,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, if (len > 0 && buf[len - 1] == '\n') --count; - if (!rtnl_trylock()) - return restart_syscall(); ret = dev_set_alias(netdev, buf, count); - rtnl_unlock(); return ret < 0 ? ret : len; } @@ -403,13 +400,12 @@ static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); + char tmp[IFALIASZ]; ssize_t ret = 0; - if (!rtnl_trylock()) - return restart_syscall(); - if (netdev->ifalias) - ret = sprintf(buf, "%s\n", netdev->ifalias); - rtnl_unlock(); + ret = dev_get_alias(netdev, tmp, sizeof(tmp)); + if (ret > 0) + ret = sprintf(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); @@ -1488,7 +1484,10 @@ static void netdev_release(struct device *d) BUG_ON(dev->reg_state != NETREG_RELEASED); - kfree(dev->ifalias); + /* no need to wait for rcu grace period: + * device is dead and about to be freed. + */ + kfree(rcu_access_pointer(dev->ifalias)); netdev_freemem(dev); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e6955da0d58d8..3961f87cdc760 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1366,6 +1366,16 @@ static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev) return nla_put_u32(skb, IFLA_LINK, ifindex); } +static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, + struct net_device *dev) +{ + char buf[IFALIASZ]; + int ret; + + ret = dev_get_alias(dev, buf, sizeof(buf)); + return ret > 0 ? nla_put_string(skb, IFLA_IFALIAS, buf) : 0; +} + static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev) { @@ -1425,8 +1435,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || - (dev->ifalias && - nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || + nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_changes)) || nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) -- GitLab From 90caccdd8cc0215705f18b92771b449b01e2474a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 3 Oct 2017 15:37:20 -0700 Subject: [PATCH 0850/1507] bpf: fix bpf_tail_call() x64 JIT - bpf prog_array just like all other types of bpf array accepts 32-bit index. Clarify that in the comment. - fix x64 JIT of bpf_tail_call which was incorrectly loading 8 instead of 4 bytes - tighten corresponding check in the interpreter to stay consistent The JIT bug can be triggered after introduction of BPF_F_NUMA_NODE flag in commit 96eabe7a40aa in 4.14. Before that the map_flags would stay zero and though JIT code is wrong it will check bounds correctly. Hence two fixes tags. All other JITs don't have this problem. Signed-off-by: Alexei Starovoitov Fixes: 96eabe7a40aa ("bpf: Allow selecting numa node during map creation") Fixes: b52f00e6a715 ("x86: bpf_jit: implement bpf_tail_call() helper") Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/x86/net/bpf_jit_comp.c | 4 ++-- include/uapi/linux/bpf.h | 2 +- kernel/bpf/core.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c9573660d51e..0554e8aef4d54 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ #define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98f..f90860d1f8979 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a940..7b62df86be1d7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; -- GitLab From 1ae2eaaa229bc350b6f38fbf4ab9c873532aecfb Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:08 -0300 Subject: [PATCH 0851/1507] sctp: silence warns on sctp_stream_init allocations As SCTP supports up to 65535 streams, that can lead to very large allocations in sctp_stream_init(). As Xin Long noticed, systems with small amounts of memory are more prone to not have enough memory and dump warnings on dmesg initiated by user actions. Thus, silence them. Also, if the reallocation of stream->out is not necessary, skip it and keep the memory we already have. Reported-by: Xin Long Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/stream.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 63ea155037149..1afa955580839 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -40,9 +40,14 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, { int i; + gfp |= __GFP_NOWARN; + /* Initial stream->out size may be very big, so free it and alloc - * a new one with new outcnt to save memory. + * a new one with new outcnt to save memory if needed. */ + if (outcnt == stream->outcnt) + goto in; + kfree(stream->out); stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); @@ -53,6 +58,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; +in: if (!incnt) return 0; -- GitLab From e090abd0d81c7bdbf0c0ba2224624be2b15ded0d Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:09 -0300 Subject: [PATCH 0852/1507] sctp: factor out stream->out allocation There is 1 place allocating it and 2 other reallocating. Move such procedures to a common function. Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/stream.c | 52 +++++++++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 1afa955580839..6d0e997d301f8 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -35,6 +35,30 @@ #include #include +static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, + gfp_t gfp) +{ + struct sctp_stream_out *out; + + out = kmalloc_array(outcnt, sizeof(*out), gfp); + if (!out) + return -ENOMEM; + + if (stream->out) { + memcpy(out, stream->out, min(outcnt, stream->outcnt) * + sizeof(*out)); + kfree(stream->out); + } + + if (outcnt > stream->outcnt) + memset(out + stream->outcnt, 0, + (outcnt - stream->outcnt) * sizeof(*out)); + + stream->out = out; + + return 0; +} + int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { @@ -48,11 +72,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, if (outcnt == stream->outcnt) goto in; - kfree(stream->out); - - stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); - if (!stream->out) - return -ENOMEM; + i = sctp_stream_alloc_out(stream, outcnt, gfp); + if (i) + return i; stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) @@ -276,15 +298,9 @@ int sctp_send_add_streams(struct sctp_association *asoc, } if (out) { - struct sctp_stream_out *streamout; - - streamout = krealloc(stream->out, outcnt * sizeof(*streamout), - GFP_KERNEL); - if (!streamout) + retval = sctp_stream_alloc_out(stream, outcnt, GFP_KERNEL); + if (retval) goto out; - - memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); - stream->out = streamout; } chunk = sctp_make_strreset_addstrm(asoc, out, in); @@ -682,10 +698,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_strreset_addstrm *addstrm = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - struct sctp_stream_out *streamout; struct sctp_chunk *chunk = NULL; __u32 request_seq, outcnt; __u16 out, i; + int ret; request_seq = ntohl(addstrm->request_seq); if (TSN_lt(asoc->strreset_inseq, request_seq) || @@ -714,14 +730,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( if (!out || outcnt > SCTP_MAX_STREAM) goto out; - streamout = krealloc(stream->out, outcnt * sizeof(*streamout), - GFP_ATOMIC); - if (!streamout) + ret = sctp_stream_alloc_out(stream, outcnt, GFP_ATOMIC); + if (ret) goto out; - memset(streamout + stream->outcnt, 0, out * sizeof(*streamout)); - stream->out = streamout; - chunk = sctp_make_strreset_addstrm(asoc, out, 0); if (!chunk) goto out; -- GitLab From 1fdb8d8fefe2e7320ea15a65051758a4c4332f05 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:10 -0300 Subject: [PATCH 0853/1507] sctp: factor out stream->in allocation There is 1 place allocating it and another reallocating. Move such procedures to a common function. v2: updated changelog Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/stream.c | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 6d0e997d301f8..952437d656cc7 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -59,6 +59,31 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, return 0; } +static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, + gfp_t gfp) +{ + struct sctp_stream_in *in; + + in = kmalloc_array(incnt, sizeof(*stream->in), gfp); + + if (!in) + return -ENOMEM; + + if (stream->in) { + memcpy(in, stream->in, min(incnt, stream->incnt) * + sizeof(*in)); + kfree(stream->in); + } + + if (incnt > stream->incnt) + memset(in + stream->incnt, 0, + (incnt - stream->incnt) * sizeof(*in)); + + stream->in = in; + + return 0; +} + int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { @@ -84,8 +109,8 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, if (!incnt) return 0; - stream->in = kcalloc(incnt, sizeof(*stream->in), gfp); - if (!stream->in) { + i = sctp_stream_alloc_in(stream, incnt, gfp); + if (i) { kfree(stream->out); stream->out = NULL; return -ENOMEM; @@ -623,7 +648,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_strreset_addstrm *addstrm = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - struct sctp_stream_in *streamin; __u32 request_seq, incnt; __u16 in, i; @@ -670,13 +694,9 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( if (!in || incnt > SCTP_MAX_STREAM) goto out; - streamin = krealloc(stream->in, incnt * sizeof(*streamin), - GFP_ATOMIC); - if (!streamin) + if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) goto out; - memset(streamin + stream->incnt, 0, in * sizeof(*streamin)); - stream->in = streamin; stream->incnt = incnt; result = SCTP_STRRESET_PERFORMED; -- GitLab From f952be79cebd49d04154781d99408867a069d375 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:11 -0300 Subject: [PATCH 0854/1507] sctp: introduce struct sctp_stream_out_ext With the stream schedulers, sctp_stream_out will become too big to be allocated by kmalloc and as we need to allocate with BH disabled, we cannot use __vmalloc in sctp_stream_init(). This patch moves out the stats from sctp_stream_out to sctp_stream_out_ext, which will be allocated only when the application tries to sendmsg something on it. Just the introduction of sctp_stream_out_ext would already fix the issue described above by splitting the allocation in two. Moving the stats to it also reduces the pressure on the allocator as we will ask for less memory atomically when creating the socket and we will use GFP_KERNEL later. Then, for stream schedulers, we will just use sctp_stream_out_ext. Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 10 ++++++++-- net/sctp/chunk.c | 6 +++--- net/sctp/outqueue.c | 4 ++-- net/sctp/socket.c | 27 +++++++++++++++++++++------ net/sctp/stream.c | 16 ++++++++++++++++ 5 files changed, 50 insertions(+), 13 deletions(-) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0477945de1a3c..9b2b30b3ba4df 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -84,6 +84,7 @@ struct sctp_ulpq; struct sctp_ep_common; struct crypto_shash; struct sctp_stream; +struct sctp_stream_out; #include @@ -380,6 +381,7 @@ struct sctp_sender_hb_info { int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp); +int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); @@ -1315,11 +1317,15 @@ struct sctp_inithdr_host { __u32 initial_tsn; }; +struct sctp_stream_out_ext { + __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; + __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; +}; + struct sctp_stream_out { __u16 ssn; __u8 state; - __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; - __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; + struct sctp_stream_out_ext *ext; }; struct sctp_stream_in { diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 3afac275ee82d..7b261afc47b9d 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -311,10 +311,10 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++; } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; - streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; + streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && @@ -323,7 +323,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 2966ff400755f..746b07b7937d8 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -366,7 +366,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; - streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; + streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (!chk->tsn_gap_acked) { if (chk->transport) @@ -404,7 +404,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_stream_out *streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; - streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } msg_len -= SCTP_DATA_SNDSIZE(chk) + diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d4730ada7f323..d207734326b08 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1927,6 +1927,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_free; } + /* Allocate sctp_stream_out_ext if not already done */ + if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) { + err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); + if (err) + goto out_free; + } + if (sctp_wspace(asoc) < msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); @@ -6645,7 +6652,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct sctp_stream_out *streamout; + struct sctp_stream_out_ext *streamoute; struct sctp_association *asoc; struct sctp_prstatus params; int retval = -EINVAL; @@ -6668,21 +6675,29 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamout = &asoc->stream.out[params.sprstat_sid]; + streamoute = asoc->stream.out[params.sprstat_sid].ext; + if (!streamoute) { + /* Not allocated yet, means all stats are 0 */ + params.sprstat_abandoned_unsent = 0; + params.sprstat_abandoned_sent = 0; + retval = 0; + goto out; + } + if (policy == SCTP_PR_SCTP_NONE) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { params.sprstat_abandoned_unsent += - streamout->abandoned_unsent[policy]; + streamoute->abandoned_unsent[policy]; params.sprstat_abandoned_sent += - streamout->abandoned_sent[policy]; + streamoute->abandoned_sent[policy]; } } else { params.sprstat_abandoned_unsent = - streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)]; + streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)]; params.sprstat_abandoned_sent = - streamout->abandoned_sent[__SCTP_PR_INDEX(policy)]; + streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)]; } if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) { diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 952437d656cc7..055ca25bbc91b 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -121,8 +121,24 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, return 0; } +int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_stream_out_ext *soute; + + soute = kzalloc(sizeof(*soute), GFP_KERNEL); + if (!soute) + return -ENOMEM; + stream->out[sid].ext = soute; + + return 0; +} + void sctp_stream_free(struct sctp_stream *stream) { + int i; + + for (i = 0; i < stream->outcnt; i++) + kfree(stream->out[i].ext); kfree(stream->out); kfree(stream->in); } -- GitLab From 2fc019f790312e703efa1a44204c586112a430dc Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:12 -0300 Subject: [PATCH 0855/1507] sctp: introduce sctp_chunk_stream_no Add a helper to fetch the stream number from a given chunk. Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 9b2b30b3ba4df..c48f7999fe9b8 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -642,6 +642,11 @@ void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *, union sctp_addr *); const union sctp_addr *sctp_source(const struct sctp_chunk *chunk); +static inline __u16 sctp_chunk_stream_no(struct sctp_chunk *ch) +{ + return ntohs(ch->subh.data_hdr->stream); +} + enum { SCTP_ADDR_NEW, /* new address added to assoc/ep */ SCTP_ADDR_SRC, /* address can be used as source */ -- GitLab From 5bbbbe32a43199c2b9ea5ea66fab6241c64beb51 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:13 -0300 Subject: [PATCH 0856/1507] sctp: introduce stream scheduler foundations This patch introduces the hooks necessary to do stream scheduling, as per RFC Draft ndata. It also introduces the first scheduler, which is what we do today but now factored out: first come first served (FCFS). With stream scheduling now we have to track which chunk was enqueued on which stream and be able to select another other than the in front of the main outqueue. So we introduce a list on sctp_stream_out_ext structure for this purpose. We reuse sctp_chunk->transmitted_list space for the list above, as the chunk cannot belong to the two lists at the same time. By using the union in there, we can have distinct names for these moments. sctp_sched_ops are the operations expected to be implemented by each scheduler. The dequeueing is a bit particular to this implementation but it is to match how we dequeue packets today. We first dequeue and then check if it fits the packet and if not, we requeue it at head. Thus why we don't have a peek operation but have dequeue_done instead, which is called once the chunk can be safely considered as transmitted. The check removed from sctp_outq_flush is now performed by sctp_stream_outq_migrate, which is only called during assoc setup. (sctp_sendmsg() also checks for it) The only operation that is foreseen but not yet added here is a way to signalize that a new packet is starting or that the packet is done, for round robin scheduler per packet, but is intentionally left to the patch that actually implements it. Support for I-DATA chunks, also described in this RFC, with user message interleaving is straightforward as it just requires the schedulers to probe for the feature and ignore datamsg boundaries when dequeueing. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/stream_sched.h | 72 +++++++++ include/net/sctp/structs.h | 15 +- include/uapi/linux/sctp.h | 6 + net/sctp/Makefile | 2 +- net/sctp/outqueue.c | 59 +++---- net/sctp/sm_sideeffect.c | 3 + net/sctp/stream.c | 88 ++++++++++- net/sctp/stream_sched.c | 270 ++++++++++++++++++++++++++++++++ 8 files changed, 477 insertions(+), 38 deletions(-) create mode 100644 include/net/sctp/stream_sched.h create mode 100644 net/sctp/stream_sched.c diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h new file mode 100644 index 0000000000000..c676550a4c7dd --- /dev/null +++ b/include/net/sctp/stream_sched.h @@ -0,0 +1,72 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * These are definitions used by the stream schedulers, defined in RFC + * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11) + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresses: + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#ifndef __sctp_stream_sched_h__ +#define __sctp_stream_sched_h__ + +struct sctp_sched_ops { + /* Property handling for a given stream */ + int (*set)(struct sctp_stream *stream, __u16 sid, __u16 value, + gfp_t gfp); + int (*get)(struct sctp_stream *stream, __u16 sid, __u16 *value); + + /* Init the specific scheduler */ + int (*init)(struct sctp_stream *stream); + /* Init a stream */ + int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp); + /* Frees the entire thing */ + void (*free)(struct sctp_stream *stream); + + /* Enqueue a chunk */ + void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg); + /* Dequeue a chunk */ + struct sctp_chunk *(*dequeue)(struct sctp_outq *q); + /* Called only if the chunk fit the packet */ + void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk); + /* Sched all chunks already enqueued */ + void (*sched_all)(struct sctp_stream *steam); + /* Unched all chunks already enqueued */ + void (*unsched_all)(struct sctp_stream *steam); +}; + +int sctp_sched_set_sched(struct sctp_association *asoc, + enum sctp_sched_type sched); +int sctp_sched_get_sched(struct sctp_association *asoc); +int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, + __u16 value, gfp_t gfp); +int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, + __u16 *value); +void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch); + +void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch); +int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp); +struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream); + +#endif /* __sctp_stream_sched_h__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index c48f7999fe9b8..3c22a30fd71b4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -84,7 +84,6 @@ struct sctp_ulpq; struct sctp_ep_common; struct crypto_shash; struct sctp_stream; -struct sctp_stream_out; #include @@ -531,8 +530,12 @@ struct sctp_chunk { /* How many times this chunk have been sent, for prsctp RTX policy */ int sent_count; - /* This is our link to the per-transport transmitted list. */ - struct list_head transmitted_list; + union { + /* This is our link to the per-transport transmitted list. */ + struct list_head transmitted_list; + /* List in specific stream outq */ + struct list_head stream_list; + }; /* This field is used by chunks that hold fragmented data. * For the first fragment this is the list that holds the rest of @@ -1019,6 +1022,9 @@ struct sctp_outq { /* Data pending that has never been transmitted. */ struct list_head out_chunk_list; + /* Stream scheduler being used */ + struct sctp_sched_ops *sched; + unsigned int out_qlen; /* Total length of queued data chunks. */ /* Error of send failed, may used in SCTP_SEND_FAILED event. */ @@ -1325,6 +1331,7 @@ struct sctp_inithdr_host { struct sctp_stream_out_ext { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; + struct list_head outq; /* chunks enqueued by this stream */ }; struct sctp_stream_out { @@ -1342,6 +1349,8 @@ struct sctp_stream { struct sctp_stream_in *in; __u16 outcnt; __u16 incnt; + /* Current stream being sent, if any */ + struct sctp_stream_out *out_curr; }; #define SCTP_STREAM_CLOSED 0x00 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1d..4487e7625ddbd 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1088,4 +1088,10 @@ struct sctp_add_streams { uint16_t sas_outstrms; }; +/* SCTP Stream schedulers */ +enum sctp_sched_type { + SCTP_SS_FCFS, + SCTP_SS_MAX = SCTP_SS_FCFS +}; + #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 70f1b570bab97..0f6e6d1d69fd3 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o + offload.o stream_sched.o sctp_probe-y := probe.o diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 746b07b7937d8..4db012aa25f7a 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -50,6 +50,7 @@ #include #include +#include /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -72,32 +73,38 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, - struct sctp_chunk *ch) + struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { - struct sctp_chunk *ch = NULL; - - if (!list_empty(&q->out_chunk_list)) { - struct list_head *entry = q->out_chunk_list.next; - - ch = list_entry(entry, struct sctp_chunk, list); - list_del_init(entry); - q->out_qlen -= ch->skb->len; - } - return ch; + return q->sched->dequeue(q); } + /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add_tail(&ch->stream_list, &oute->outq); } /* @@ -207,6 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + sctp_sched_set_sched(asoc, SCTP_SS_FCFS); } /* Free the outqueue structure and any related pending chunks. @@ -258,6 +266,7 @@ static void __sctp_outq_teardown(struct sctp_outq *q) /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { + sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); @@ -391,13 +400,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + q->sched->unsched_all(&asoc->stream); + list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) continue; - list_del_init(&chk->list); - q->out_qlen -= chk->skb->len; + sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { @@ -415,6 +425,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, break; } + q->sched->sched_all(&asoc->stream); + return msg_len; } @@ -1033,22 +1045,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); - /* RFC 2960 6.5 Every DATA chunk MUST carry a valid - * stream identifier. - */ - if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { - - /* Mark as failed send. */ - sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); - if (asoc->peer.prsctp_capable && - SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) - asoc->sent_cnt_removable--; - sctp_chunk_free(chunk); - continue; - } - /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1070,6 +1069,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) new_transport = asoc->peer.active_path; if (new_transport->state == SCTP_UNCONFIRMED) { WARN_ONCE(1, "Attempt to send packet on unconfirmed path."); + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1133,6 +1133,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) else asoc->stats.oodchunks++; + /* Only now it's safe to consider this + * chunk as sent, sched-wise. + */ + sctp_sched_dequeue_done(q, chunk); + break; default: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e6a2974e020e1..402bfbb888cda 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -50,6 +50,7 @@ #include #include #include +#include static int sctp_cmd_interpreter(enum sctp_event event_type, union sctp_subtype subtype, @@ -1089,6 +1090,8 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc, list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_outq_tail(&asoc->outqueue, chunk, gfp); + + asoc->outqueue.sched->enqueue(&asoc->outqueue, msg); } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 055ca25bbc91b..5ea33a2c453b4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -32,8 +32,61 @@ * Xin Long */ +#include #include #include +#include + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + struct sctp_association *asoc; + struct sctp_chunk *ch, *temp; + struct sctp_outq *outq; + int i; + + asoc = container_of(stream, struct sctp_association, stream); + outq = &asoc->outqueue; + + list_for_each_entry_safe(ch, temp, &outq->out_chunk_list, list) { + __u16 sid = sctp_chunk_stream_no(ch); + + if (sid < outcnt) + continue; + + sctp_sched_dequeue_common(outq, ch); + /* No need to call dequeue_done here because + * the chunks are not scheduled by now. + */ + + /* Mark as failed send. */ + sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM); + if (asoc->peer.prsctp_capable && + SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags)) + asoc->sent_cnt_removable--; + + sctp_chunk_free(ch); + } + + if (new) { + /* Here we actually move the old ext stuff into the new + * buffer, because we want to keep it. Then + * sctp_stream_update will swap ->out pointers. + */ + for (i = 0; i < outcnt; i++) { + kfree(new->out[i].ext); + new->out[i].ext = stream->out[i].ext; + stream->out[i].ext = NULL; + } + } + + for (i = outcnt; i < stream->outcnt; i++) + kfree(stream->out[i].ext); +} static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, gfp_t gfp) @@ -87,7 +140,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { - int i; + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + int i, ret = 0; gfp |= __GFP_NOWARN; @@ -97,6 +151,11 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, if (outcnt == stream->outcnt) goto in; + /* Filter out chunks queued on streams that won't exist anymore */ + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, NULL, outcnt); + sched->sched_all(stream); + i = sctp_stream_alloc_out(stream, outcnt, gfp); if (i) return i; @@ -105,20 +164,27 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; + sched->init(stream); + in: if (!incnt) - return 0; + goto out; i = sctp_stream_alloc_in(stream, incnt, gfp); if (i) { - kfree(stream->out); - stream->out = NULL; - return -ENOMEM; + ret = -ENOMEM; + goto free; } stream->incnt = incnt; + goto out; - return 0; +free: + sched->free(stream); + kfree(stream->out); + stream->out = NULL; +out: + return ret; } int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) @@ -130,13 +196,15 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) return -ENOMEM; stream->out[sid].ext = soute; - return 0; + return sctp_sched_init_sid(stream, sid, GFP_KERNEL); } void sctp_stream_free(struct sctp_stream *stream) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; + sched->free(stream); for (i = 0; i < stream->outcnt; i++) kfree(stream->out[i].ext); kfree(stream->out); @@ -156,6 +224,10 @@ void sctp_stream_clear(struct sctp_stream *stream) void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, new, new->outcnt); sctp_stream_free(stream); stream->out = new->out; @@ -163,6 +235,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) stream->outcnt = new->outcnt; stream->incnt = new->incnt; + sched->sched_all(stream); + new->out = NULL; new->in = NULL; } diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c new file mode 100644 index 0000000000000..40a9a9de2b98a --- /dev/null +++ b/net/sctp/stream_sched.c @@ -0,0 +1,270 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* First Come First Serve (a.k.a. FIFO) + * RFC DRAFT ndata Section 3.1 + */ +static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid, + __u16 value, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = 0; + return 0; +} + +static int sctp_sched_fcfs_init(struct sctp_stream *stream) +{ + return 0; +} + +static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + return 0; +} + +static void sctp_sched_fcfs_free(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ +} + +static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_chunk *ch = NULL; + struct list_head *entry; + + if (list_empty(&q->out_chunk_list)) + goto out; + + if (stream->out_curr) { + ch = list_entry(stream->out_curr->ext->outq.next, + struct sctp_chunk, stream_list); + } else { + entry = q->out_chunk_list.next; + ch = list_entry(entry, struct sctp_chunk, list); + } + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *chunk) +{ +} + +static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream) +{ +} + +static struct sctp_sched_ops sctp_sched_fcfs = { + .set = sctp_sched_fcfs_set, + .get = sctp_sched_fcfs_get, + .init = sctp_sched_fcfs_init, + .init_sid = sctp_sched_fcfs_init_sid, + .free = sctp_sched_fcfs_free, + .enqueue = sctp_sched_fcfs_enqueue, + .dequeue = sctp_sched_fcfs_dequeue, + .dequeue_done = sctp_sched_fcfs_dequeue_done, + .sched_all = sctp_sched_fcfs_sched_all, + .unsched_all = sctp_sched_fcfs_unsched_all, +}; + +/* API to other parts of the stack */ + +struct sctp_sched_ops *sctp_sched_ops[] = { + &sctp_sched_fcfs, +}; + +int sctp_sched_set_sched(struct sctp_association *asoc, + enum sctp_sched_type sched) +{ + struct sctp_sched_ops *n = sctp_sched_ops[sched]; + struct sctp_sched_ops *old = asoc->outqueue.sched; + struct sctp_datamsg *msg = NULL; + struct sctp_chunk *ch; + int i, ret = 0; + + if (old == n) + return ret; + + if (sched > SCTP_SS_MAX) + return -EINVAL; + + if (old) { + old->free(&asoc->stream); + + /* Give the next scheduler a clean slate. */ + for (i = 0; i < asoc->stream.outcnt; i++) { + void *p = asoc->stream.out[i].ext; + + if (!p) + continue; + + p += offsetofend(struct sctp_stream_out_ext, outq); + memset(p, 0, sizeof(struct sctp_stream_out_ext) - + offsetofend(struct sctp_stream_out_ext, outq)); + } + } + + asoc->outqueue.sched = n; + n->init(&asoc->stream); + for (i = 0; i < asoc->stream.outcnt; i++) { + if (!asoc->stream.out[i].ext) + continue; + + ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); + if (ret) + goto err; + } + + /* We have to requeue all chunks already queued. */ + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + if (ch->msg == msg) + continue; + msg = ch->msg; + n->enqueue(&asoc->outqueue, msg); + } + + return ret; + +err: + n->free(&asoc->stream); + asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */ + + return ret; +} + +int sctp_sched_get_sched(struct sctp_association *asoc) +{ + int i; + + for (i = 0; i <= SCTP_SS_MAX; i++) + if (asoc->outqueue.sched == sctp_sched_ops[i]) + return i; + + return 0; +} + +int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, + __u16 value, gfp_t gfp) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) { + int ret; + + ret = sctp_stream_init_ext(&asoc->stream, sid); + if (ret) + return ret; + } + + return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp); +} + +int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, + __u16 *value) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) + return 0; + + return asoc->outqueue.sched->get(&asoc->stream, sid, value); +} + +void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) +{ + if (!list_is_last(&ch->frag_list, &ch->msg->chunks)) { + struct sctp_stream_out *sout; + __u16 sid; + + /* datamsg is not finish, so save it as current one, + * in case application switch scheduler or a higher + * priority stream comes in. + */ + sid = sctp_chunk_stream_no(ch); + sout = &q->asoc->stream.out[sid]; + q->asoc->stream.out_curr = sout; + return; + } + + q->asoc->stream.out_curr = NULL; + q->sched->dequeue_done(q, ch); +} + +/* Auxiliary functions for the schedulers */ +void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) +{ + list_del_init(&ch->list); + list_del_init(&ch->stream_list); + q->out_qlen -= ch->skb->len; +} + +int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) +{ + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + INIT_LIST_HEAD(&stream->out[sid].ext->outq); + return sched->init_sid(stream, sid, gfp); +} + +struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + + asoc = container_of(stream, struct sctp_association, stream); + + return asoc->outqueue.sched; +} -- GitLab From 13aa8770fe42d246c6f3a8eb814b85bccb428011 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:14 -0300 Subject: [PATCH 0857/1507] sctp: add sockopt to get/set stream scheduler As defined per RFC Draft ndata Section 4.3.2, named as SCTP_STREAM_SCHEDULER. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 75 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 4487e7625ddbd..0050f10087d22 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -122,6 +122,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_RESET_ASSOC 120 #define SCTP_ADD_STREAMS 121 #define SCTP_SOCKOPT_PEELOFF_FLAGS 122 +#define SCTP_STREAM_SCHEDULER 123 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d207734326b08..ae35dbf2810f7 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -79,6 +79,7 @@ #include #include #include +#include /* Forward declarations for internal helper functions. */ static int sctp_writeable(struct sock *sk); @@ -3914,6 +3915,36 @@ static int sctp_setsockopt_add_streams(struct sock *sk, return retval; } +static int sctp_setsockopt_scheduler(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_assoc_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_value > SCTP_SS_MAX) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_sched(asoc, params.assoc_value); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4095,6 +4126,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_ADD_STREAMS: retval = sctp_setsockopt_add_streams(sk, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_setsockopt_scheduler(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6793,6 +6827,43 @@ static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, return retval; } +static int sctp_getsockopt_scheduler(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + params.assoc_value = sctp_sched_get_sched(asoc); + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -6975,6 +7046,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_getsockopt_scheduler(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; -- GitLab From 0ccdf3c7fdeda511b10def19505178a9d2d3fccd Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:15 -0300 Subject: [PATCH 0858/1507] sctp: add sockopt to get/set stream scheduler parameters As defined per RFC Draft ndata Section 4.3.3, named as SCTP_STREAM_SCHEDULER_VALUE. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 7 ++++ net/sctp/socket.c | 77 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 84 insertions(+) diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 0050f10087d22..00ac417d2c4f8 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -123,6 +123,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_ADD_STREAMS 121 #define SCTP_SOCKOPT_PEELOFF_FLAGS 122 #define SCTP_STREAM_SCHEDULER 123 +#define SCTP_STREAM_SCHEDULER_VALUE 124 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -815,6 +816,12 @@ struct sctp_assoc_value { uint32_t assoc_value; }; +struct sctp_stream_value { + sctp_assoc_t assoc_id; + uint16_t stream_id; + uint16_t stream_value; +}; + /* * 7.2.2 Peer Address Information * diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ae35dbf2810f7..88c28421ec151 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3945,6 +3945,34 @@ static int sctp_setsockopt_scheduler(struct sock *sk, return retval; } +static int sctp_setsockopt_scheduler_value(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_stream_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4129,6 +4157,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_STREAM_SCHEDULER: retval = sctp_setsockopt_scheduler(sk, optval, optlen); break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_setsockopt_scheduler_value(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6864,6 +6895,48 @@ static int sctp_getsockopt_scheduler(struct sock *sk, int len, return retval; } +static int sctp_getsockopt_scheduler_value(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_stream_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + retval = sctp_sched_get_value(asoc, params.stream_id, + ¶ms.stream_value); + if (retval) + goto out; + + if (put_user(len, optlen)) { + retval = -EFAULT; + goto out; + } + + if (copy_to_user(optval, ¶ms, len)) { + retval = -EFAULT; + goto out; + } + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -7050,6 +7123,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_scheduler(sk, len, optval, optlen); break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_getsockopt_scheduler_value(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; -- GitLab From 637784ade221a3c8a7ecd0f583eddd95d6276b9a Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:16 -0300 Subject: [PATCH 0859/1507] sctp: introduce priority based stream scheduler This patch introduces RFC Draft ndata section 3.4 Priority Based Scheduler (SCTP_SS_PRIO). It works by having a struct sctp_stream_priority for each priority configured. This struct is then enlisted on a queue ordered per priority if, and only if, there is a stream with data queued, so that dequeueing is very straightforward: either finish current datamsg or simply dequeue from the highest priority queued, which is the next stream pointed, and that's it. If there are multiple streams assigned with the same priority and with data queued, it will do round robin amongst them while respecting datamsgs boundaries (when not using idata chunks), to be reasonably fair. We intentionally don't maintain a list of priorities nor a list of all streams with the same priority to save memory. The first would mean at least 2 other pointers per priority (which, for 1000 priorities, that can mean 16kB) and the second would also mean 2 other pointers but per stream. As SCTP supports up to 65535 streams on a given asoc, that's 1MB. This impacts when giving a priority to some stream, as we have to find out if the new priority is already being used and if we can free the old one, and also when tearing down. The new fields in struct sctp_stream_out_ext and sctp_stream are added under a union because that memory is to be shared with other schedulers. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 24 +++ include/uapi/linux/sctp.h | 3 +- net/sctp/Makefile | 2 +- net/sctp/stream_sched.c | 3 + net/sctp/stream_sched_prio.c | 347 +++++++++++++++++++++++++++++++++++ 5 files changed, 377 insertions(+), 2 deletions(-) create mode 100644 net/sctp/stream_sched_prio.c diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 3c22a30fd71b4..40eb8d66a37c3 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1328,10 +1328,27 @@ struct sctp_inithdr_host { __u32 initial_tsn; }; +struct sctp_stream_priorities { + /* List of priorities scheduled */ + struct list_head prio_sched; + /* List of streams scheduled */ + struct list_head active; + /* The next stream stream in line */ + struct sctp_stream_out_ext *next; + __u16 prio; +}; + struct sctp_stream_out_ext { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; struct list_head outq; /* chunks enqueued by this stream */ + union { + struct { + /* Scheduled streams list */ + struct list_head prio_list; + struct sctp_stream_priorities *prio_head; + }; + }; }; struct sctp_stream_out { @@ -1351,6 +1368,13 @@ struct sctp_stream { __u16 incnt; /* Current stream being sent, if any */ struct sctp_stream_out *out_curr; + union { + /* Fields used by priority scheduler */ + struct { + /* List of priorities scheduled */ + struct list_head prio_list; + }; + }; }; #define SCTP_STREAM_CLOSED 0x00 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 00ac417d2c4f8..850fa8b29d7e8 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1099,7 +1099,8 @@ struct sctp_add_streams { /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, - SCTP_SS_MAX = SCTP_SS_FCFS + SCTP_SS_PRIO, + SCTP_SS_MAX = SCTP_SS_PRIO }; #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 0f6e6d1d69fd3..647c9cfd4e95b 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o stream_sched.o + offload.o stream_sched.o stream_sched_prio.o sctp_probe-y := probe.o diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 40a9a9de2b98a..115ddb7651695 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -121,8 +121,11 @@ static struct sctp_sched_ops sctp_sched_fcfs = { /* API to other parts of the stack */ +extern struct sctp_sched_ops sctp_sched_prio; + struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, + &sctp_sched_prio, }; int sctp_sched_set_sched(struct sctp_association *asoc, diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c new file mode 100644 index 0000000000000..384dbf3c87609 --- /dev/null +++ b/net/sctp/stream_sched_prio.c @@ -0,0 +1,347 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* Priority handling + * RFC DRAFT ndata section 3.4 + */ + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); + +static struct sctp_stream_priorities *sctp_sched_prio_new_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + + p = kmalloc(sizeof(*p), gfp); + if (!p) + return NULL; + + INIT_LIST_HEAD(&p->prio_sched); + INIT_LIST_HEAD(&p->active); + p->next = NULL; + p->prio = prio; + + return p; +} + +static struct sctp_stream_priorities *sctp_sched_prio_get_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + int i; + + /* Look into scheduled priorities first, as they are sorted and + * we can find it fast IF it's scheduled. + */ + list_for_each_entry(p, &stream->prio_list, prio_sched) { + if (p->prio == prio) + return p; + if (p->prio > prio) + break; + } + + /* No luck. So we search on all streams now. */ + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + + p = stream->out[i].ext->prio_head; + if (!p) + /* Means all other streams won't be initialized + * as well. + */ + break; + if (p->prio == prio) + return p; + } + + /* If not even there, allocate a new one. */ + return sctp_sched_prio_new_head(stream, prio, gfp); +} + +static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p) +{ + struct list_head *pos; + + pos = p->next->prio_list.next; + if (pos == &p->active) + pos = pos->next; + p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list); +} + +static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute) +{ + bool scheduled = false; + + if (!list_empty(&soute->prio_list)) { + struct sctp_stream_priorities *prio_head = soute->prio_head; + + /* Scheduled */ + scheduled = true; + + if (prio_head->next == soute) + /* Try to move to the next stream */ + sctp_sched_prio_next_stream(prio_head); + + list_del_init(&soute->prio_list); + + /* Also unsched the priority if this was the last stream */ + if (list_empty(&prio_head->active)) { + list_del_init(&prio_head->prio_sched); + /* If there is no stream left, clear next */ + prio_head->next = NULL; + } + } + + return scheduled; +} + +static void sctp_sched_prio_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + struct sctp_stream_priorities *prio, *prio_head; + + prio_head = soute->prio_head; + + /* Nothing to do if already scheduled */ + if (!list_empty(&soute->prio_list)) + return; + + /* Schedule the stream. If there is a next, we schedule the new + * one before it, so it's the last in round robin order. + * If there isn't, we also have to schedule the priority. + */ + if (prio_head->next) { + list_add(&soute->prio_list, prio_head->next->prio_list.prev); + return; + } + + list_add(&soute->prio_list, &prio_head->active); + prio_head->next = soute; + + list_for_each_entry(prio, &stream->prio_list, prio_sched) { + if (prio->prio > prio_head->prio) { + list_add(&prio_head->prio_sched, prio->prio_sched.prev); + return; + } + } + + list_add_tail(&prio_head->prio_sched, &stream->prio_list); +} + +static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + struct sctp_stream_out *sout = &stream->out[sid]; + struct sctp_stream_out_ext *soute = sout->ext; + struct sctp_stream_priorities *prio_head, *old; + bool reschedule = false; + int i; + + prio_head = sctp_sched_prio_get_head(stream, prio, gfp); + if (!prio_head) + return -ENOMEM; + + reschedule = sctp_sched_prio_unsched(soute); + old = soute->prio_head; + soute->prio_head = prio_head; + if (reschedule) + sctp_sched_prio_sched(stream, soute); + + if (!old) + /* Happens when we set the priority for the first time */ + return 0; + + for (i = 0; i < stream->outcnt; i++) { + soute = stream->out[i].ext; + if (soute && soute->prio_head == old) + /* It's still in use, nothing else to do here. */ + return 0; + } + + /* No hits, we are good to free it. */ + kfree(old); + + return 0; +} + +static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = stream->out[sid].ext->prio_head->prio; + return 0; +} + +static int sctp_sched_prio_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->prio_list); + + return 0; +} + +static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->prio_list); + return sctp_sched_prio_set(stream, sid, 0, gfp); +} + +static void sctp_sched_prio_free(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *prio, *n; + LIST_HEAD(list); + int i; + + /* As we don't keep a list of priorities, to avoid multiple + * frees we have to do it in 3 steps: + * 1. unsched everyone, so the lists are free to use in 2. + * 2. build the list of the priorities + * 3. free the list + */ + sctp_sched_prio_unsched_all(stream); + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + prio = stream->out[i].ext->prio_head; + if (prio && list_empty(&prio->prio_sched)) + list_add(&prio->prio_sched, &list); + } + list_for_each_entry_safe(prio, n, &list, prio_sched) { + list_del_init(&prio->prio_sched); + kfree(prio); + } +} + +static void sctp_sched_prio_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_prio_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next. It's easy, it's either the current + * one or the first chunk on the next active stream. + */ + if (stream->out_curr) { + soute = stream->out_curr->ext; + } else { + prio = list_entry(stream->prio_list.next, + struct sctp_stream_priorities, prio_sched); + soute = prio->next; + } + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream on + * this priority. + */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + prio = soute->prio_head; + + sctp_sched_prio_next_stream(prio); + + if (list_empty(&soute->outq)) + sctp_sched_prio_unsched(soute); +} + +static void sctp_sched_prio_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out *sout; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + sout = &stream->out[sid]; + if (sout->ext) + sctp_sched_prio_sched(stream, sout->ext); + } +} + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *p, *tmp; + struct sctp_stream_out_ext *soute, *souttmp; + + list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched) + list_for_each_entry_safe(soute, souttmp, &p->active, prio_list) + sctp_sched_prio_unsched(soute); +} + +struct sctp_sched_ops sctp_sched_prio = { + .set = sctp_sched_prio_set, + .get = sctp_sched_prio_get, + .init = sctp_sched_prio_init, + .init_sid = sctp_sched_prio_init_sid, + .free = sctp_sched_prio_free, + .enqueue = sctp_sched_prio_enqueue, + .dequeue = sctp_sched_prio_dequeue, + .dequeue_done = sctp_sched_prio_dequeue_done, + .sched_all = sctp_sched_prio_sched_all, + .unsched_all = sctp_sched_prio_unsched_all, +}; -- GitLab From ac1ed8b82cd60ba8e7d84103ac1414b8c577c485 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:17 -0300 Subject: [PATCH 0860/1507] sctp: introduce round robin stream scheduler This patch introduces RFC Draft ndata section 3.2 Priority Based Scheduler (SCTP_SS_RR). Works by maintaining a list of enqueued streams and tracking the last one used to send data. When the datamsg is done, it switches to the next stream. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 11 ++ include/uapi/linux/sctp.h | 3 +- net/sctp/Makefile | 3 +- net/sctp/stream_sched.c | 2 + net/sctp/stream_sched_rr.c | 201 +++++++++++++++++++++++++++++++++++++ 5 files changed, 218 insertions(+), 2 deletions(-) create mode 100644 net/sctp/stream_sched_rr.c diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 40eb8d66a37c3..16f949eef52fd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1348,6 +1348,10 @@ struct sctp_stream_out_ext { struct list_head prio_list; struct sctp_stream_priorities *prio_head; }; + /* Fields used by RR scheduler */ + struct { + struct list_head rr_list; + }; }; }; @@ -1374,6 +1378,13 @@ struct sctp_stream { /* List of priorities scheduled */ struct list_head prio_list; }; + /* Fields used by RR scheduler */ + struct { + /* List of streams scheduled */ + struct list_head rr_list; + /* The next stream stream in line */ + struct sctp_stream_out_ext *rr_next; + }; }; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 850fa8b29d7e8..6cd7d416ca406 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1100,7 +1100,8 @@ struct sctp_add_streams { enum sctp_sched_type { SCTP_SS_FCFS, SCTP_SS_PRIO, - SCTP_SS_MAX = SCTP_SS_PRIO + SCTP_SS_RR, + SCTP_SS_MAX = SCTP_SS_RR }; #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 647c9cfd4e95b..bf90c53977190 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o stream_sched.o stream_sched_prio.o + offload.o stream_sched.o stream_sched_prio.o \ + stream_sched_rr.o sctp_probe-y := probe.o diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 115ddb7651695..03513a9fa110b 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -122,10 +122,12 @@ static struct sctp_sched_ops sctp_sched_fcfs = { /* API to other parts of the stack */ extern struct sctp_sched_ops sctp_sched_prio; +extern struct sctp_sched_ops sctp_sched_rr; struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, &sctp_sched_prio, + &sctp_sched_rr, }; int sctp_sched_set_sched(struct sctp_association *asoc, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c new file mode 100644 index 0000000000000..7612a438c5b93 --- /dev/null +++ b/net/sctp/stream_sched_rr.c @@ -0,0 +1,201 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* Priority handling + * RFC DRAFT ndata section 3.2 + */ +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream); + +static void sctp_sched_rr_next_stream(struct sctp_stream *stream) +{ + struct list_head *pos; + + pos = stream->rr_next->rr_list.next; + if (pos == &stream->rr_list) + pos = pos->next; + stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list); +} + +static void sctp_sched_rr_unsched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (stream->rr_next == soute) + /* Try to move to the next stream */ + sctp_sched_rr_next_stream(stream); + + list_del_init(&soute->rr_list); + + /* If we have no other stream queued, clear next */ + if (list_empty(&stream->rr_list)) + stream->rr_next = NULL; +} + +static void sctp_sched_rr_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (!list_empty(&soute->rr_list)) + /* Already scheduled. */ + return; + + /* Schedule the stream */ + list_add_tail(&soute->rr_list, &stream->rr_list); + + if (!stream->rr_next) + stream->rr_next = soute; +} + +static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + return 0; +} + +static int sctp_sched_rr_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->rr_list); + stream->rr_next = NULL; + + return 0; +} + +static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->rr_list); + + return 0; +} + +static void sctp_sched_rr_free(struct sctp_stream *stream) +{ + sctp_sched_rr_unsched_all(stream); +} + +static void sctp_sched_rr_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_rr_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next */ + if (stream->out_curr) + soute = stream->out_curr->ext; + else + soute = stream->rr_next; + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_rr_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + + sctp_sched_rr_next_stream(&q->asoc->stream); + + if (list_empty(&soute->outq)) + sctp_sched_rr_unsched(&q->asoc->stream, soute); +} + +static void sctp_sched_rr_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + soute = stream->out[sid].ext; + if (soute) + sctp_sched_rr_sched(stream, soute); + } +} + +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_out_ext *soute, *tmp; + + list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list) + sctp_sched_rr_unsched(stream, soute); +} + +struct sctp_sched_ops sctp_sched_rr = { + .set = sctp_sched_rr_set, + .get = sctp_sched_rr_get, + .init = sctp_sched_rr_init, + .init_sid = sctp_sched_rr_init_sid, + .free = sctp_sched_rr_free, + .enqueue = sctp_sched_rr_enqueue, + .dequeue = sctp_sched_rr_dequeue, + .dequeue_done = sctp_sched_rr_dequeue_done, + .sched_all = sctp_sched_rr_sched_all, + .unsched_all = sctp_sched_rr_unsched_all, +}; -- GitLab From 8ee912dab95f1483156b6e994004bfcc3158d798 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 3 Oct 2017 16:14:15 -0700 Subject: [PATCH 0861/1507] alpha: fix build failures The build of alpha allmodconfig is giving error: arch/alpha/include/asm/mmu_context.h: In function 'ev5_switch_mm': arch/alpha/include/asm/mmu_context.h:160:2: error: implicit declaration of function 'task_thread_info'; did you mean 'init_thread_info'? [-Werror=implicit-function-declaration] The file 'mmu_context.h' needed an extra header file. Link: http://lkml.kernel.org/r/1505668810-7497-1-git-send-email-sudipm.mukherjee@gmail.com Signed-off-by: Sudip Mukherjee Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/mmu_context.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h index 384bd47b51871..45c020a0fe761 100644 --- a/arch/alpha/include/asm/mmu_context.h +++ b/arch/alpha/include/asm/mmu_context.h @@ -8,6 +8,7 @@ */ #include +#include #include #include -- GitLab From 630cc2b30a42c70628368a412beb4a5e5dd71abe Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Oct 2017 16:14:18 -0700 Subject: [PATCH 0862/1507] kernel/params.c: align add_sysfs_param documentation with code This parameter is named kp, so the documentation should use that. Fixes: 9b473de87209 ("param: Fix duplicate module prefixes") Link: http://lkml.kernel.org/r/20170919142656.64aea59e@endymion Signed-off-by: Jean Delvare Acked-by: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/params.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355f..1cd8f1a895a89 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -600,7 +600,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and -- GitLab From e00e5a26e3d37b47ce8ca59611db1e6135790ef8 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 3 Oct 2017 16:14:21 -0700 Subject: [PATCH 0863/1507] scripts/spelling.txt: add more spelling mistakes to spelling.txt Here are some of the more spelling mistakes and typos that I've found while fixing up spelling mistakes in kernel error message text over the past eight weeks. [akpm@linux-foundation.org: s/|/||/, per Joe] Link: http://lkml.kernel.org/r/20170919090818.5989-1-colin.king@canonical.com Signed-off-by: Colin Ian King Acked-by: Kees Cook Cc: Masahiro Yamada Cc: Stephen Boyd Cc: Joe Perches Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/spelling.txt | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 400ef35169c54..aa0cc49ad1adc 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -53,6 +53,7 @@ acumulator||accumulator adapater||adapter addional||additional additionaly||additionally +additonal||additional addres||address adddress||address addreses||addresses @@ -67,6 +68,8 @@ adviced||advised afecting||affecting againt||against agaist||against +aggreataon||aggregation +aggreation||aggregation albumns||albums alegorical||allegorical algined||aligned @@ -80,6 +83,8 @@ aligment||alignment alignement||alignment allign||align alligned||aligned +alllocate||allocate +alloated||allocated allocatote||allocate allocatrd||allocated allocte||allocate @@ -171,6 +176,7 @@ availale||available availavility||availability availble||available availiable||available +availible||available avalable||available avaliable||available aysnc||async @@ -203,6 +209,7 @@ broadcat||broadcast cacluated||calculated caculation||calculation calender||calendar +calescing||coalescing calle||called callibration||calibration calucate||calculate @@ -210,6 +217,7 @@ calulate||calculate cancelation||cancellation cancle||cancel capabilites||capabilities +capabilty||capability capabitilies||capabilities capatibilities||capabilities capapbilities||capabilities @@ -302,6 +310,7 @@ containts||contains contaisn||contains contant||contact contence||contents +continious||continuous continous||continuous continously||continuously continueing||continuing @@ -393,6 +402,7 @@ differrence||difference diffrent||different diffrentiate||differentiate difinition||definition +dimesions||dimensions diplay||display direectly||directly disassocation||disassociation @@ -449,6 +459,7 @@ equiped||equipped equivelant||equivalent equivilant||equivalent eror||error +errorr||error estbalishment||establishment etsablishment||establishment etsbalishment||establishment @@ -481,6 +492,7 @@ failied||failed faillure||failure failue||failure failuer||failure +failng||failing faireness||fairness falied||failed faliure||failure @@ -493,6 +505,7 @@ fetaure||feature fetaures||features fileystem||filesystem fimware||firmware +firware||firmware finanize||finalize findn||find finilizes||finalizes @@ -502,6 +515,7 @@ folloing||following followign||following followings||following follwing||following +fonud||found forseeable||foreseeable forse||force fortan||fortran @@ -532,6 +546,7 @@ grabing||grabbing grahical||graphical grahpical||graphical grapic||graphic +grranted||granted guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -543,6 +558,7 @@ happend||happened harware||hardware heirarchically||hierarchically helpfull||helpful +hybernate||hibernate hierachy||hierarchy hierarchie||hierarchy howver||however @@ -565,16 +581,19 @@ implemenation||implementation implementaiton||implementation implementated||implemented implemention||implementation +implementd||implemented implemetation||implementation implemntation||implementation implentation||implementation implmentation||implementation implmenting||implementing +incative||inactive incomming||incoming incompatabilities||incompatibilities incompatable||incompatible inconsistant||inconsistent increas||increase +incremeted||incremented incrment||increment indendation||indentation indended||intended @@ -619,6 +638,7 @@ interger||integer intermittant||intermittent internel||internal interoprability||interoperability +interuupt||interrupt interrface||interface interrrupt||interrupt interrup||interrupt @@ -638,8 +658,10 @@ intrrupt||interrupt intterrupt||interrupt intuative||intuitive invaid||invalid +invald||invalid invalde||invalid invalide||invalid +invalidiate||invalidate invalud||invalid invididual||individual invokation||invocation @@ -713,6 +735,7 @@ misformed||malformed mispelled||misspelled mispelt||misspelt mising||missing +mismactch||mismatch missmanaged||mismanaged missmatch||mismatch miximum||maximum @@ -731,6 +754,7 @@ multidimensionnal||multidimensional multple||multiple mumber||number muticast||multicast +mutilcast||multicast mutiple||multiple mutli||multi nams||names @@ -834,6 +858,7 @@ posible||possible positon||position possibilites||possibilities powerfull||powerful +preample||preamble preapre||prepare preceeded||preceded preceeding||preceding @@ -1059,6 +1084,7 @@ sturcture||structure subdirectoires||subdirectories suble||subtle substract||subtract +submition||submission succesfully||successfully succesful||successful successed||succeeded @@ -1078,6 +1104,7 @@ suppoted||supported suppported||supported suppport||support supress||suppress +surpressed||suppressed surpresses||suppresses susbsystem||subsystem suspeneded||suspended @@ -1091,6 +1118,7 @@ swithced||switched swithcing||switching swithed||switched swithing||switching +swtich||switch symetric||symmetric synax||syntax synchonized||synchronized @@ -1111,7 +1139,9 @@ therfore||therefore thier||their threds||threads threshhold||threshold +thresold||threshold throught||through +troughput||throughput thses||these tiggered||triggered tipically||typically @@ -1120,6 +1150,7 @@ tmis||this torerable||tolerable tramsmitted||transmitted tramsmit||transmit +tranasction||transaction tranfer||transfer transciever||transceiver transferd||transferred @@ -1133,6 +1164,7 @@ trasmission||transmission treshold||threshold trigerring||triggering trun||turn +tunning||tuning ture||true tyep||type udpate||update @@ -1199,6 +1231,7 @@ visiters||visitors vitual||virtual wakeus||wakeups wating||waiting +wiat||wait wether||whether whataver||whatever whcih||which -- GitLab From fa87b91c94a8fd2c8502b6761be2d08a8e9bcf55 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 3 Oct 2017 16:14:24 -0700 Subject: [PATCH 0864/1507] include/linux/mm.h: fix typo in VM_MPX definition There's a typo in recent change of VM_MPX definition. We want it to be VM_HIGH_ARCH_4, not VM_HIGH_ARCH_BIT_4. This bug does cause visible regressions. In arch_vma_name the vmflags are tested against VM_MPX. With the incorrect value of VM_MPX, a number of vmas (such as the stack) test positive and end up being marked as "[mpx]" in /proc/N/maps instead of their correct names. This confuses tools like rr which expect to be able to find familiar vmas. Fixes: df3735c5b40f ("x86,mpx: make mpx depend on x86-64 to free up VMA flag") Link: http://lkml.kernel.org/r/20170918140253.36856-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Rik van Riel Cc: Dave Hansen Cc: Kyle Huey Cc: [4.14+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index f8c10d336e42e..065d99deb847e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -240,7 +240,7 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_BIT_4 +# define VM_MPX VM_HIGH_ARCH_4 #else # define VM_MPX VM_NONE #endif -- GitLab From 4b22927f0cbd58303aac689e378d20bf56267a39 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 3 Oct 2017 16:14:27 -0700 Subject: [PATCH 0865/1507] ksm: fix unlocked iteration over vmas in cmp_and_merge_page() In this place mm is unlocked, so vmas or list may change. Down read mmap_sem to protect them from modifications. Link: http://lkml.kernel.org/r/150512788393.10691.8868381099691121308.stgit@localhost.localdomain Fixes: e86c59b1b12d ("mm/ksm: improve deduplication of zero pages with colouring") Signed-off-by: Kirill Tkhai Acked-by: Michal Hocko Reviewed-by: Andrea Arcangeli Cc: Minchan Kim Cc: zhong jiang Cc: Ingo Molnar Cc: Claudio Imbrenda Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/ksm.c b/mm/ksm.c index 15dd7415f7b3f..6cb60f46cce55 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1990,6 +1990,7 @@ static void stable_tree_append(struct rmap_item *rmap_item, */ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) { + struct mm_struct *mm = rmap_item->mm; struct rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct stable_node *stable_node; @@ -2062,9 +2063,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) if (ksm_use_zero_pages && (checksum == zero_checksum)) { struct vm_area_struct *vma; - vma = find_mergeable_vma(rmap_item->mm, rmap_item->address); + down_read(&mm->mmap_sem); + vma = find_mergeable_vma(mm, rmap_item->address); err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); + up_read(&mm->mmap_sem); /* * In case of failure, the page was not really empty, so we * need to continue. Otherwise we're done. -- GitLab From 19bfbe22f59a207417b2679e7e83c180419c9ec5 Mon Sep 17 00:00:00 2001 From: Alexandru Moise <00moses.alexander00@gmail.com> Date: Tue, 3 Oct 2017 16:14:31 -0700 Subject: [PATCH 0866/1507] mm, hugetlb, soft_offline: save compound page order before page migration This fixes a bug in madvise() where if you'd try to soft offline a hugepage via madvise(), while walking the address range you'd end up, using the wrong page offset due to attempting to get the compound order of a former but presently not compound page, due to dissolving the huge page (since commit c3114a84f7f9: "mm: hugetlb: soft-offline: dissolve source hugepage after successful migration"). As a result I ended up with all my free pages except one being offlined. Link: http://lkml.kernel.org/r/20170912204306.GA12053@gmail.com Fixes: c3114a84f7f9 ("mm: hugetlb: soft-offline: dissolve source hugepage after successful migration") Signed-off-by: Alexandru Moise <00moses.alexander00@gmail.com> Cc: Anshuman Khandual Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Minchan Kim Cc: Hillf Danton Cc: Shaohua Li Cc: Mike Rapoport Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: David Rientjes Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/madvise.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index 21261ff0466fb..25bade36e9caa 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -625,18 +625,26 @@ static int madvise_inject_error(int behavior, { struct page *page; struct zone *zone; + unsigned int order; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE << - compound_order(compound_head(page))) { + + for (; start < end; start += PAGE_SIZE << order) { int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; + /* + * When soft offlining hugepages, after migrating the page + * we dissolve it, therefore in the second loop "page" will + * no longer be a compound page, and order will be 0. + */ + order = compound_order(compound_head(page)); + if (PageHWPoison(page)) { put_page(page); continue; -- GitLab From b78412b8300a8453b78d2c1b0b925b66493bb011 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 3 Oct 2017 16:14:34 -0700 Subject: [PATCH 0867/1507] sh: sh7722: remove nonexistent GPIO_PTQ7 to fix pinctrl registration Patch series "sh: sh7722/sh7757i/sh7264/sh7269: Fix pinctrl registration", v2. Magnus Damm reported that on sh7722/Migo-R, pinctrl registration fails with: sh-pfc pfc-sh7722: pin 0 already registered sh-pfc pfc-sh7722: error during pin registration sh-pfc pfc-sh7722: could not register: -22 sh-pfc: probe of pfc-sh7722 failed with error -22 pinmux_pins[] is initialized through PINMUX_GPIO(), using designated array initializers, where the GPIO_* enums serve as indices. Apparently GPIO_PTQ7 was defined in the enum, but never used. If enum values are defined, but never used, pinmux_pins[] contains (zero-filled) holes. Hence such entries are treated as pin zero, which was registered before, and pinctrl registration fails. I can't see how this ever worked, as at the time of commit f5e25ae52fef ("sh-pfc: Add sh7722 pinmux support"), pinmux_gpios[] in drivers/pinctrl/sh-pfc/pfc-sh7722.c already had the hole, and drivers/pinctrl/core.c already had the check. Some scripting revealed a few more broken drivers: - sh7757 has four holes, due to nonexistent GPIO_PT[JLNQ]7_RESV. - sh7264 and sh7269 define GPIO_PH[0-7], but don't use it with PINMUX_GPIO(). Patch 1 fixes the issue on sh7722, and was tested. Patches 3-4 should fix the issue on the other 3 SoCs, but was untested due to lack of hardware. This patch (of 4): On sh7722/Migo-R, pinctrl registration fails with: sh-pfc pfc-sh7722: pin 0 already registered sh-pfc pfc-sh7722: error during pin registration sh-pfc pfc-sh7722: could not register: -22 sh-pfc: probe of pfc-sh7722 failed with error -22 pinmux_pins[] is initialized through PINMUX_GPIO(), using designated array initializers, where the GPIO_* enums serve as indices. As GPIO_PTQ7 is defined in the enum, but never used, pinmux_pins[] contains a (zero-filled) hole. Hence this entry is treated as pin zero, which was registered before, and pinctrl registration fails. According to the datasheet, port PTQ7 does not exist. Hence remove GPIO_PTQ7 from the enum to fix this. Link: http://lkml.kernel.org/r/1505205657-18012-2-git-send-email-geert+renesas@glider.be Fixes: 8d7b5b0af7e070b9 ("sh: Add sh7722 pinmux code") Signed-off-by: Geert Uytterhoeven Reported-by: Magnus Damm Reviewed-by: Laurent Pinchart Tested-by: Jacopo Mondi Cc: Rich Felker Cc: Yoshihiro Shimoda Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/cpu-sh4/cpu/sh7722.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h index 3bb74e534d0f8..78961ab78a5a9 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7722.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h @@ -67,7 +67,7 @@ enum { GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0, /* PTQ */ - GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, + GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0, /* PTR */ -- GitLab From d8ce38f69843a56da044e56b6c16aecfbc3c6e39 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 3 Oct 2017 16:14:37 -0700 Subject: [PATCH 0868/1507] sh: sh7757: remove nonexistent GPIO_PT[JLNQ]7_RESV to fix pinctrl registration Commit 3810e96056ff ("sh: modify pinmux for SH7757 2nd cut") renamed GPIO_PT[JLNQ]7 to GPIO_PT[JLNQ]7_RESV, and removed the existing users from the pinmux_pins[] array. However, pinmux_pins[] is initialized through PINMUX_GPIO(), using designated array initializers, where the GPIO_* enums serve as indices. Hence entries were not really removed, but replaced by (zero-filled) holes. Such entries are treated as pin zero, which was registered before, thus leading to pinctrl registration failures, as seen on sh7722: sh-pfc pfc-sh7722: pin 0 already registered sh-pfc pfc-sh7722: error during pin registration sh-pfc pfc-sh7722: could not register: -22 sh-pfc: probe of pfc-sh7722 failed with error -22 Remove GPIO_PT[JLNQ]7_RESV from the enum to fix this. Link: http://lkml.kernel.org/r/1505205657-18012-3-git-send-email-geert+renesas@glider.be Fixes: 3810e96056ffddf6 ("sh: modify pinmux for SH7757 2nd cut") Signed-off-by: Geert Uytterhoeven Reviewed-by: Laurent Pinchart Cc: Jacopo Mondi Cc: Magnus Damm Cc: Rich Felker Cc: Yoshihiro Shimoda Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/cpu-sh4/cpu/sh7757.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h index 5340f3bc1863c..b40fb541e72a7 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7757.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h @@ -40,7 +40,7 @@ enum { /* PTJ */ GPIO_PTJ0, GPIO_PTJ1, GPIO_PTJ2, GPIO_PTJ3, - GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, GPIO_PTJ7_RESV, + GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, /* PTK */ GPIO_PTK0, GPIO_PTK1, GPIO_PTK2, GPIO_PTK3, @@ -48,7 +48,7 @@ enum { /* PTL */ GPIO_PTL0, GPIO_PTL1, GPIO_PTL2, GPIO_PTL3, - GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, GPIO_PTL7_RESV, + GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, /* PTM */ GPIO_PTM0, GPIO_PTM1, GPIO_PTM2, GPIO_PTM3, @@ -56,7 +56,7 @@ enum { /* PTN */ GPIO_PTN0, GPIO_PTN1, GPIO_PTN2, GPIO_PTN3, - GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, GPIO_PTN7_RESV, + GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, /* PTO */ GPIO_PTO0, GPIO_PTO1, GPIO_PTO2, GPIO_PTO3, @@ -68,7 +68,7 @@ enum { /* PTQ */ GPIO_PTQ0, GPIO_PTQ1, GPIO_PTQ2, GPIO_PTQ3, - GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, GPIO_PTQ7_RESV, + GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, /* PTR */ GPIO_PTR0, GPIO_PTR1, GPIO_PTR2, GPIO_PTR3, -- GitLab From eae3df7e82318d798f45dedf111e241805ec7a4a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 3 Oct 2017 16:14:41 -0700 Subject: [PATCH 0869/1507] sh: sh7264: remove nonexistent GPIO_PH[0-7] to fix pinctrl registration Pinmux_pins[] is initialized through PINMUX_GPIO(), using designated array initializers, where the GPIO_* enums serve as indices. If enum values are defined, but never used, pinmux_pins[] contains (zero-filled) holes. Such entries are treated as pin zero, which was registered before, thus leading to pinctrl registration failures, as seen on sh7722: sh-pfc pfc-sh7722: pin 0 already registered sh-pfc pfc-sh7722: error during pin registration sh-pfc pfc-sh7722: could not register: -22 sh-pfc: probe of pfc-sh7722 failed with error -22 Remove GPIO_PH[0-7] from the enum to fix this. Link: http://lkml.kernel.org/r/1505205657-18012-4-git-send-email-geert+renesas@glider.be Fixes: 41797f75486d8ca3 ("sh: Add pinmux for sh7264") Signed-off-by: Geert Uytterhoeven Reviewed-by: Laurent Pinchart Cc: Jacopo Mondi Cc: Magnus Damm Cc: Rich Felker Cc: Yoshihiro Shimoda Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/cpu-sh2a/cpu/sh7264.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7264.h b/arch/sh/include/cpu-sh2a/cpu/sh7264.h index 4d1ef6d74bd60..2ae0e938b657a 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7264.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7264.h @@ -43,9 +43,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ -- GitLab From d9d73e81fe82fdf4ee65a48c26531edc04108349 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 3 Oct 2017 16:14:44 -0700 Subject: [PATCH 0870/1507] sh: sh7269: remove nonexistent GPIO_PH[0-7] to fix pinctrl registration Pinmux_pins[] is initialized through PINMUX_GPIO(), using designated array initializers, where the GPIO_* enums serve as indices. If enum values are defined, but never used, pinmux_pins[] contains (zero-filled) holes. Such entries are treated as pin zero, which was registered before, thus leading to pinctrl registration failures, as seen on sh7722: sh-pfc pfc-sh7722: pin 0 already registered sh-pfc pfc-sh7722: error during pin registration sh-pfc pfc-sh7722: could not register: -22 sh-pfc: probe of pfc-sh7722 failed with error -22 Remove GPIO_PH[0-7] from the enum to fix this. Link: http://lkml.kernel.org/r/1505205657-18012-5-git-send-email-geert+renesas@glider.be Fixes: ef0fa5331a73e479 ("sh: Add pinmux for sh7269") Signed-off-by: Geert Uytterhoeven Reviewed-by: Laurent Pinchart Cc: Yoshinori Sato Cc: Rich Felker Cc: Magnus Damm Cc: Yoshihiro Shimoda Cc: Jacopo Mondi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/cpu-sh2a/cpu/sh7269.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h index 2a0ca8780f0d8..13c495a9fc000 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h @@ -45,9 +45,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ -- GitLab From d5567c9df1ef001b2a7e6684b3b3498371ee4cae Mon Sep 17 00:00:00 2001 From: Vitaly Wool Date: Tue, 3 Oct 2017 16:14:47 -0700 Subject: [PATCH 0871/1507] z3fold: fix potential race in z3fold_reclaim_page It is possible that on a (partially) unsuccessful page reclaim, kref_put() called in z3fold_reclaim_page() does not yield page release, but the page is released shortly afterwards by another thread. Then z3fold_reclaim_page() would try to list_add() that (released) page again which is obviously a bug. To avoid that, spin_lock() has to be taken earlier, before the kref_put() call mentioned earlier. Link: http://lkml.kernel.org/r/20170913162937.bfff21c7d12b12a5f47639fd@gmail.com Signed-off-by: Vitaly Wool Cc: Dan Streetman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/z3fold.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/z3fold.c b/mm/z3fold.c index 486550df32be8..b04fa3ba1bf26 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -875,16 +875,18 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: + spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { + spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { atomic64_dec(&pool->pages_nr); + spin_unlock(&pool->lock); return 0; } - spin_lock(&pool->lock); /* * Add to the beginning of LRU. -- GitLab From 4d4bbd8526a8fbeb2c090ea360211fceff952383 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 3 Oct 2017 16:14:50 -0700 Subject: [PATCH 0872/1507] mm, oom_reaper: skip mm structs with mmu notifiers Andrea has noticed that the oom_reaper doesn't invalidate the range via mmu notifiers (mmu_notifier_invalidate_range_start/end) and that can corrupt the memory of the kvm guest for example. tlb_flush_mmu_tlbonly already invokes mmu notifiers but that is not sufficient as per Andrea: "mmu_notifier_invalidate_range cannot be used in replacement of mmu_notifier_invalidate_range_start/end. For KVM mmu_notifier_invalidate_range is a noop and rightfully so. A MMU notifier implementation has to implement either ->invalidate_range method or the invalidate_range_start/end methods, not both. And if you implement invalidate_range_start/end like KVM is forced to do, calling mmu_notifier_invalidate_range in common code is a noop for KVM. For those MMU notifiers that can get away only implementing ->invalidate_range, the ->invalidate_range is implicitly called by mmu_notifier_invalidate_range_end(). And only those secondary MMUs that share the same pagetable with the primary MMU (like AMD iommuv2) can get away only implementing ->invalidate_range" As the callback is allowed to sleep and the implementation is out of hand of the MM it is safer to simply bail out if there is an mmu notifier registered. In order to not fail too early make the mm_has_notifiers check under the oom_lock and have a little nap before failing to give the current oom victim some more time to exit. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170913113427.2291-1-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko Reported-by: Andrea Arcangeli Reviewed-by: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 5 +++++ mm/oom_kill.c | 16 ++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 7b2e31b1745aa..6866e8126982e 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -400,6 +400,11 @@ extern void mmu_notifier_synchronize(void); #else /* CONFIG_MMU_NOTIFIER */ +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return 0; +} + static inline void mmu_notifier_release(struct mm_struct *mm) { } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 99736e026712c..dee0f75c30133 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include "internal.h" @@ -494,6 +495,21 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) goto unlock_oom; } + /* + * If the mm has notifiers then we would need to invalidate them around + * unmap_page_range and that is risky because notifiers can sleep and + * what they do is basically undeterministic. So let's have a short + * sleep to give the oom victim some more time. + * TODO: we really want to get rid of this ugly hack and make sure that + * notifiers cannot block for unbounded amount of time and add + * mmu_notifier_invalidate_range_{start,end} around unmap_page_range + */ + if (mm_has_notifiers(mm)) { + up_read(&mm->mmap_sem); + schedule_timeout_idle(HZ); + goto unlock_oom; + } + /* * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't * work on the mm anymore. The check for MMF_OOM_SKIP must run -- GitLab From 72f0184c8a00c70179cfed6266e2e06b4d400065 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 3 Oct 2017 16:14:53 -0700 Subject: [PATCH 0873/1507] mm, memcg: remove hotplug locking from try_charge The following lockdep splat has been noticed during LTP testing ====================================================== WARNING: possible circular locking dependency detected 4.13.0-rc3-next-20170807 #12 Not tainted ------------------------------------------------------ a.out/4771 is trying to acquire lock: (cpu_hotplug_lock.rw_sem){++++++}, at: [] drain_all_stock.part.35+0x18/0x140 but task is already holding lock: (&mm->mmap_sem){++++++}, at: [] __do_page_fault+0x175/0x530 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){++++++}: lock_acquire+0xc9/0x230 __might_fault+0x70/0xa0 _copy_to_user+0x23/0x70 filldir+0xa7/0x110 xfs_dir2_sf_getdents.isra.10+0x20c/0x2c0 [xfs] xfs_readdir+0x1fa/0x2c0 [xfs] xfs_file_readdir+0x30/0x40 [xfs] iterate_dir+0x17a/0x1a0 SyS_getdents+0xb0/0x160 entry_SYSCALL_64_fastpath+0x1f/0xbe -> #2 (&type->i_mutex_dir_key#3){++++++}: lock_acquire+0xc9/0x230 down_read+0x51/0xb0 lookup_slow+0xde/0x210 walk_component+0x160/0x250 link_path_walk+0x1a6/0x610 path_openat+0xe4/0xd50 do_filp_open+0x91/0x100 file_open_name+0xf5/0x130 filp_open+0x33/0x50 kernel_read_file_from_path+0x39/0x80 _request_firmware+0x39f/0x880 request_firmware_direct+0x37/0x50 request_microcode_fw+0x64/0xe0 reload_store+0xf7/0x180 dev_attr_store+0x18/0x30 sysfs_kf_write+0x44/0x60 kernfs_fop_write+0x113/0x1a0 __vfs_write+0x37/0x170 vfs_write+0xc7/0x1c0 SyS_write+0x58/0xc0 do_syscall_64+0x6c/0x1f0 return_from_SYSCALL_64+0x0/0x7a -> #1 (microcode_mutex){+.+.+.}: lock_acquire+0xc9/0x230 __mutex_lock+0x88/0x960 mutex_lock_nested+0x1b/0x20 microcode_init+0xbb/0x208 do_one_initcall+0x51/0x1a9 kernel_init_freeable+0x208/0x2a7 kernel_init+0xe/0x104 ret_from_fork+0x2a/0x40 -> #0 (cpu_hotplug_lock.rw_sem){++++++}: __lock_acquire+0x153c/0x1550 lock_acquire+0xc9/0x230 cpus_read_lock+0x4b/0x90 drain_all_stock.part.35+0x18/0x140 try_charge+0x3ab/0x6e0 mem_cgroup_try_charge+0x7f/0x2c0 shmem_getpage_gfp+0x25f/0x1050 shmem_fault+0x96/0x200 __do_fault+0x1e/0xa0 __handle_mm_fault+0x9c3/0xe00 handle_mm_fault+0x16e/0x380 __do_page_fault+0x24a/0x530 do_page_fault+0x30/0x80 page_fault+0x28/0x30 other info that might help us debug this: Chain exists of: cpu_hotplug_lock.rw_sem --> &type->i_mutex_dir_key#3 --> &mm->mmap_sem Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(&type->i_mutex_dir_key#3); lock(&mm->mmap_sem); lock(cpu_hotplug_lock.rw_sem); *** DEADLOCK *** 2 locks held by a.out/4771: #0: (&mm->mmap_sem){++++++}, at: [] __do_page_fault+0x175/0x530 #1: (percpu_charge_mutex){+.+...}, at: [] try_charge+0x397/0x6e0 The problem is very similar to the one fixed by commit a459eeb7b852 ("mm, page_alloc: do not depend on cpu hotplug locks inside the allocator"). We are taking hotplug locks while we can be sitting on top of basically arbitrary locks. This just calls for problems. We can get rid of {get,put}_online_cpus, fortunately. We do not have to be worried about races with memory hotplug because drain_local_stock, which is called from both the WQ draining and the memory hotplug contexts, is always operating on the local cpu stock with IRQs disabled. The only thing to be careful about is that the target memcg doesn't vanish while we are still in drain_all_stock so take a reference on it. Link: http://lkml.kernel.org/r/20170913090023.28322-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Artem Savkov Tested-by: Artem Savkov Cc: Johannes Weiner Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 15af3da5af02f..696c6529e9000 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1777,6 +1777,10 @@ static void drain_local_stock(struct work_struct *dummy) struct memcg_stock_pcp *stock; unsigned long flags; + /* + * The only protection from memory hotplug vs. drain_stock races is + * that we always operate on local CPU stock here with IRQ disabled + */ local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); @@ -1821,27 +1825,33 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) /* If someone's already draining, avoid adding running more workers. */ if (!mutex_trylock(&percpu_charge_mutex)) return; - /* Notify other cpus that system-wide "drain" is running */ - get_online_cpus(); + /* + * Notify other cpus that system-wide "drain" is running + * We do not care about races with the cpu hotplug because cpu down + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; memcg = stock->cached; - if (!memcg || !stock->nr_pages) + if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css)) continue; - if (!mem_cgroup_is_descendant(memcg, root_memcg)) + if (!mem_cgroup_is_descendant(memcg, root_memcg)) { + css_put(&memcg->css); continue; + } if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); else schedule_work_on(cpu, &stock->work); } + css_put(&memcg->css); } put_cpu(); - put_online_cpus(); mutex_unlock(&percpu_charge_mutex); } -- GitLab From 3f2eb0287ebd62ec8d6d544f830285302279e6bf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Tue, 3 Oct 2017 16:14:57 -0700 Subject: [PATCH 0874/1507] mm/memcg: avoid page count check for zone device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix for 4.14, zone device page always have an elevated refcount of one and thus page count sanity check in uncharge_page() is inappropriate for them. [mhocko@suse.com: nano-optimize VM_BUG_ON in uncharge_page] Link: http://lkml.kernel.org/r/20170914190011.5217-1-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Michal Hocko Reported-by: Evgeny Baskakov Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 696c6529e9000..d5f3a62887cf9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5658,7 +5658,8 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page); + VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && + !PageHWPoison(page) , page); if (!page->mem_cgroup) return; -- GitLab From a1b2289cef92ef0e9a92afcd2e1ea71d5bcaaf64 Mon Sep 17 00:00:00 2001 From: Sherry Yang Date: Tue, 3 Oct 2017 16:15:00 -0700 Subject: [PATCH 0875/1507] android: binder: drop lru lock in isolate callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the global lru lock in isolate callback before calling zap_page_range which calls cond_resched, and re-acquire the global lru lock before returning. Also change return code to LRU_REMOVED_RETRY. Use mmput_async when fail to acquire mmap sem in an atomic context. Fix "BUG: sleeping function called from invalid context" errors when CONFIG_DEBUG_ATOMIC_SLEEP is enabled. Also restore mmput_async, which was initially introduced in commit ec8d7c14ea14 ("mm, oom_reaper: do not mmput synchronously from the oom reaper context"), and was removed in commit 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently"). Link: http://lkml.kernel.org/r/20170914182231.90908-1-sherryy@android.com Fixes: f2517eb76f1f2 ("android: binder: Add global lru shrinker to binder") Signed-off-by: Sherry Yang Signed-off-by: Greg Kroah-Hartman Reported-by: Kyle Yan Acked-by: Arve Hjønnevåg Acked-by: Michal Hocko Cc: Martijn Coenen Cc: Todd Kjos Cc: Riley Andrews Cc: Ingo Molnar Cc: Vlastimil Babka Cc: Hillf Danton Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Oleg Nesterov Cc: Hoeun Ryu Cc: Christopher Lameter Cc: Vegard Nossum Cc: Frederic Weisbecker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/android/binder_alloc.c | 18 ++++++++++++------ include/linux/sched/mm.h | 6 ++++++ kernel/fork.c | 18 ++++++++++++++++++ 3 files changed, 36 insertions(+), 6 deletions(-) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 8fe165844e470..064f5e31ec552 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -913,6 +913,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, struct binder_alloc *alloc; uintptr_t page_addr; size_t index; + struct vm_area_struct *vma; alloc = page->alloc; if (!mutex_trylock(&alloc->mutex)) @@ -923,16 +924,22 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - if (alloc->vma) { + vma = alloc->vma; + if (vma) { mm = get_task_mm(alloc->tsk); if (!mm) goto err_get_task_mm_failed; if (!down_write_trylock(&mm->mmap_sem)) goto err_down_write_mmap_sem_failed; + } + + list_lru_isolate(lru, item); + spin_unlock(lock); + if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(alloc->vma, + zap_page_range(vma, page_addr + alloc->user_buffer_offset, PAGE_SIZE); @@ -950,13 +957,12 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_kernel_end(alloc, index); - list_lru_isolate(lru, item); - + spin_lock(lock); mutex_unlock(&alloc->mutex); - return LRU_REMOVED; + return LRU_REMOVED_RETRY; err_down_write_mmap_sem_failed: - mmput(mm); + mmput_async(mm); err_get_task_mm_failed: err_page_already_freed: mutex_unlock(&alloc->mutex); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3a19c253bdb1c..ae53e413fb131 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,6 +84,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +void mmput_async(struct mm_struct *); +#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440fa..e702cb9ffbd85 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -946,6 +946,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * -- GitLab From 6818600ff094ca255a7fe31838ad50c29656c3c5 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 3 Oct 2017 16:15:03 -0700 Subject: [PATCH 0876/1507] mm,compaction: serialize waitqueue_active() checks (for real) Andrea brought to my attention that the L->{L,S} guarantees are completely bogus for this case. I was looking at the diagram, from the offending commit, when that _is_ the race, we had the load reordered already. What we need is at least S->L semantics, thus simply use wq_has_sleeper() to serialize the call for good. Link: http://lkml.kernel.org/r/20170914175313.GB811@linux-80c1.suse Fixes: 46acef048a6 (mm,compaction: serialize waitqueue_active() checks) Signed-off-by: Davidlohr Bueso Reported-by: Andrea Parri Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/compaction.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index fb548e4c7bd4b..03d31a8753416 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1999,17 +1999,14 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; - /* - * Pairs with implicit barrier in wait_event_freezable() - * such that wakeups are not missed in the lockless - * waitqueue_active() call. - */ - smp_acquire__after_ctrl_dep(); - if (pgdat->kcompactd_classzone_idx > classzone_idx) pgdat->kcompactd_classzone_idx = classzone_idx; - if (!waitqueue_active(&pgdat->kcompactd_wait)) + /* + * Pairs with implicit barrier in wait_event_freezable() + * such that wakeups are not missed. + */ + if (!wq_has_sleeper(&pgdat->kcompactd_wait)) return; if (!kcompactd_node_suitable(pgdat)) -- GitLab From 3552935742e0d5f0dafd823736f45bdaa7ba672c Mon Sep 17 00:00:00 2001 From: Vitaly Wool Date: Tue, 3 Oct 2017 16:15:06 -0700 Subject: [PATCH 0877/1507] z3fold: fix stale list handling Fix the situation when clear_bit() is called for page->private before the page pointer is actually assigned. While at it, remove work_busy() check because it is costly and does not give 100% guarantee anyway. Signed-off-by: Vitaly Wool Cc: Dan Streetman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/z3fold.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/mm/z3fold.c b/mm/z3fold.c index b04fa3ba1bf26..b2ba2ba585f3c 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -250,6 +250,7 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) WARN_ON(!list_empty(&zhdr->buddy)); set_bit(PAGE_STALE, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); spin_lock(&pool->lock); if (!list_empty(&page->lru)) list_del(&page->lru); @@ -303,7 +304,6 @@ static void free_pages_work(struct work_struct *w) list_del(&zhdr->buddy); if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) continue; - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); cancel_work_sync(&zhdr->work); free_z3fold_page(page); @@ -624,10 +624,8 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, * stale pages list. cancel_work_sync() can sleep so we must make * sure it won't be called in case we're in atomic context. */ - if (zhdr && (can_sleep || !work_pending(&zhdr->work) || - !unlikely(work_busy(&zhdr->work)))) { + if (zhdr && (can_sleep || !work_pending(&zhdr->work))) { list_del(&zhdr->buddy); - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); if (can_sleep) cancel_work_sync(&zhdr->work); -- GitLab From 57148a64e823bb1f49112fa52a92a7f372cda892 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Oct 2017 16:15:10 -0700 Subject: [PATCH 0878/1507] mm: meminit: mark init_reserved_page as __meminit The function is called from __meminit context and calls other __meminit functions but isn't it self mark as such today: WARNING: vmlinux.o(.text.unlikely+0x4516): Section mismatch in reference from the function init_reserved_page() to the function .meminit.text:early_pfn_to_nid() The function init_reserved_page() references the function __meminit early_pfn_to_nid(). This is often because init_reserved_page lacks a __meminit annotation or the annotation of early_pfn_to_nid is wrong. On most compilers, we don't notice this because the function gets inlined all the time. Adding __meminit here fixes the harmless warning for the old versions and is generally the correct annotation. Link: http://lkml.kernel.org/r/20170915193149.901180-1-arnd@arndb.de Fixes: 7e18adb4f80b ("mm: meminit: initialise remaining struct pages in parallel with kswapd") Signed-off-by: Arnd Bergmann Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c841af88836ad..38d165a87860f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1190,7 +1190,7 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void init_reserved_page(unsigned long pfn) +static void __meminit init_reserved_page(unsigned long pfn) { pg_data_t *pgdat; int nid, zid; -- GitLab From 31d1e130f4a0f8f629a460167569577cac9b17c1 Mon Sep 17 00:00:00 2001 From: Ioan Nicu Date: Tue, 3 Oct 2017 16:15:13 -0700 Subject: [PATCH 0879/1507] rapidio: remove global irq spinlocks from the subsystem Locking of config and doorbell operations should be done only if the underlying hardware requires it. This patch removes the global spinlocks from the rapidio subsystem and moves them to the mport drivers (fsl_rio and tsi721), only to the necessary places. For example, local config space read and write operations (lcread/lcwrite) are atomic in all existing drivers, so there should be no need for locking, while the cread/cwrite operations which generate maintenance transactions need to be synchronized with a lock. Later, each driver could chose to use a per-port lock instead of a global one, or even more granular locking. Link: http://lkml.kernel.org/r/20170824113023.GD50104@nokia.com Signed-off-by: Ioan Nicu Signed-off-by: Frank Kunz Acked-by: Alexandre Bounine Cc: Matt Porter Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/sysdev/fsl_rio.c | 17 ++++++++++++-- arch/powerpc/sysdev/fsl_rmu.c | 8 +++++++ drivers/rapidio/devices/tsi721.c | 7 ++++++ drivers/rapidio/rio-access.c | 40 ++++---------------------------- 4 files changed, 35 insertions(+), 37 deletions(-) diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 9234be1e66f55..5011ffea4e4b3 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -71,6 +71,8 @@ #define RIWAR_WRTYP_ALLOC 0x00006000 #define RIWAR_SIZE_MASK 0x0000003F +static DEFINE_SPINLOCK(fsl_rio_config_lock); + #define __fsl_read_rio_config(x, addr, err, op) \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ @@ -184,6 +186,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 *val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; u32 rval, err = 0; @@ -197,6 +200,8 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -213,6 +218,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, __fsl_read_rio_config(rval, data, err, "lwz"); break; default: + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); return -EINVAL; } @@ -221,6 +227,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, err, destid, hopcount, offset); } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); *val = rval; return err; @@ -244,7 +251,10 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; + int ret = 0; + pr_debug ("fsl_rio_config_write:" " index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n", @@ -255,6 +265,8 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -271,10 +283,11 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, out_be32((u32 *) data, val); break; default: - return -EINVAL; + ret = -EINVAL; } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); - return 0; + return ret; } static void fsl_rio_inbound_mem_init(struct rio_priv *priv) diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index ab7a74c75be8f..88b35a3dcdc59 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -104,6 +104,8 @@ #define DOORBELL_MESSAGE_SIZE 0x08 +static DEFINE_SPINLOCK(fsl_rio_doorbell_lock); + struct rio_msg_regs { u32 omr; u32 osr; @@ -626,9 +628,13 @@ int fsl_rio_port_write_init(struct fsl_rio_pw *pw) int fsl_rio_doorbell_send(struct rio_mport *mport, int index, u16 destid, u16 data) { + unsigned long flags; + pr_debug("fsl_doorbell_send: index %d destid %4.4x data %4.4x\n", index, destid, data); + spin_lock_irqsave(&fsl_rio_doorbell_lock, flags); + /* In the serial version silicons, such as MPC8548, MPC8641, * below operations is must be. */ @@ -638,6 +644,8 @@ int fsl_rio_doorbell_send(struct rio_mport *mport, out_be32(&dbell->dbell_regs->oddatr, (index << 20) | data); out_be32(&dbell->dbell_regs->odmr, 0x00000001); + spin_unlock_irqrestore(&fsl_rio_doorbell_lock, flags); + return 0; } diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 315a4be8dc1e6..9a68914100ad6 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -51,6 +51,8 @@ module_param(mbox_sel, byte, S_IRUGO); MODULE_PARM_DESC(mbox_sel, "RIO Messaging MBOX Selection Mask (default: 0x0f = all)"); +static DEFINE_SPINLOCK(tsi721_maint_lock); + static void tsi721_omsg_handler(struct tsi721_device *priv, int ch); static void tsi721_imsg_handler(struct tsi721_device *priv, int ch); @@ -124,12 +126,15 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, void __iomem *regs = priv->regs + TSI721_DMAC_BASE(priv->mdma.ch_id); struct tsi721_dma_desc *bd_ptr; u32 rd_count, swr_ptr, ch_stat; + unsigned long flags; int i, err = 0; u32 op = do_wr ? MAINT_WR : MAINT_RD; if (offset > (RIO_MAINT_SPACE_SZ - len) || (len != sizeof(u32))) return -EINVAL; + spin_lock_irqsave(&tsi721_maint_lock, flags); + bd_ptr = priv->mdma.bd_base; rd_count = ioread32(regs + TSI721_DMAC_DRDCNT); @@ -197,7 +202,9 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, */ swr_ptr = ioread32(regs + TSI721_DMAC_DSWP); iowrite32(swr_ptr, regs + TSI721_DMAC_DSRP); + err_out: + spin_unlock_irqrestore(&tsi721_maint_lock, flags); return err; } diff --git a/drivers/rapidio/rio-access.c b/drivers/rapidio/rio-access.c index a3824baca2e51..3ee9af83b6384 100644 --- a/drivers/rapidio/rio-access.c +++ b/drivers/rapidio/rio-access.c @@ -13,17 +13,9 @@ #include #include -/* - * These interrupt-safe spinlocks protect all accesses to RIO - * configuration space and doorbell access. - */ -static DEFINE_SPINLOCK(rio_config_lock); -static DEFINE_SPINLOCK(rio_doorbell_lock); - /* * Wrappers for all RIO configuration access functions. They just check - * alignment, do locking and call the low-level functions pointed to - * by rio_mport->ops. + * alignment and call the low-level functions pointed to by rio_mport->ops. */ #define RIO_8_BAD 0 @@ -44,13 +36,10 @@ int __rio_local_read_config_##size \ (struct rio_mport *mport, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->lcread(mport, mport->id, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -67,13 +56,8 @@ int __rio_local_read_config_##size \ int __rio_local_write_config_##size \ (struct rio_mport *mport, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->lcwrite(mport, mport->id, offset, len, value);\ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->lcwrite(mport, mport->id, offset, len, value);\ } RIO_LOP_READ(8, u8, 1) @@ -104,13 +88,10 @@ int rio_mport_read_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -127,13 +108,9 @@ int rio_mport_read_config_##size \ int rio_mport_write_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->cwrite(mport, mport->id, destid, hopcount, offset, len, value); \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->cwrite(mport, mport->id, destid, hopcount, \ + offset, len, value); \ } RIO_OP_READ(8, u8, 1) @@ -162,14 +139,7 @@ EXPORT_SYMBOL_GPL(rio_mport_write_config_32); */ int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data) { - int res; - unsigned long flags; - - spin_lock_irqsave(&rio_doorbell_lock, flags); - res = mport->ops->dsend(mport, mport->id, destid, data); - spin_unlock_irqrestore(&rio_doorbell_lock, flags); - - return res; + return mport->ops->dsend(mport, mport->id, destid, data); } EXPORT_SYMBOL_GPL(rio_mport_send_doorbell); -- GitLab From a872eb2131e91ce7c89a8888974a5e22a272b12f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 3 Oct 2017 16:15:16 -0700 Subject: [PATCH 0880/1507] mm: fix RODATA_TEST failure "rodata_test: test data was not read only" On powerpc, RODATA_TEST fails with message the following messages: Freeing unused kernel memory: 528K rodata_test: test data was not read only This is because GCC allocates it to .data section: c0695034 g O .data 00000004 rodata_test_data Since commit 056b9d8a7692 ("mm: remove rodata_test_data export, add pr_fmt"), rodata_test_data is used only inside rodata_test.c By declaring it static, it gets properly allocated into .rodata section instead of .data: c04df710 l O .rodata 00000004 rodata_test_data Fixes: 056b9d8a7692 ("mm: remove rodata_test_data export, add pr_fmt") Link: http://lkml.kernel.org/r/20170921093729.1080368AC1@po15668-vm-win7.idsi0.si.c-s.fr Signed-off-by: Christophe Leroy Cc: Kees Cook Cc: Jinbum Park Cc: Segher Boessenkool Cc: David Laight Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/rodata_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 6bb4deb12e78b..d908c8769b484 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -14,7 +14,7 @@ #include #include -const int rodata_test_data = 0xC3; +static const int rodata_test_data = 0xC3; void rodata_test(void) { -- GitLab From ae94264ed4b0cf7cd887947650db4c69acb62072 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 3 Oct 2017 16:15:19 -0700 Subject: [PATCH 0881/1507] zram: fix null dereference of handle In testing I found handle passed to zs_map_object in __zram_bvec_read is NULL so eh kernel goes oops in pin_object(). The reason is there is no routine to check the slot's freeing after getting the slot's lock. This patch fixes it. [minchan@kernel.org: v2] Link: http://lkml.kernel.org/r/1505887347-10881-1-git-send-email-minchan@kernel.org Link: http://lkml.kernel.org/r/1505788488-26723-1-git-send-email-minchan@kernel.org Fixes: 1f7319c74275 ("zram: partial IO refactoring") Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 36 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 24 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2981c27d3aae3..f149d3e612341 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -766,27 +766,6 @@ static void zram_slot_unlock(struct zram *zram, u32 index) bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value); } -static bool zram_same_page_read(struct zram *zram, u32 index, - struct page *page, - unsigned int offset, unsigned int len) -{ - zram_slot_lock(zram, index); - if (unlikely(!zram_get_handle(zram, index) || - zram_test_flag(zram, index, ZRAM_SAME))) { - void *mem; - - zram_slot_unlock(zram, index); - mem = kmap_atomic(page); - zram_fill_page(mem + offset, len, - zram_get_element(zram, index)); - kunmap_atomic(mem); - return true; - } - zram_slot_unlock(zram, index); - - return false; -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -884,11 +863,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, zram_slot_unlock(zram, index); } - if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE)) - return 0; - zram_slot_lock(zram, index); handle = zram_get_handle(zram, index); + if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { + unsigned long value; + void *mem; + + value = handle ? zram_get_element(zram, index) : 0; + mem = kmap_atomic(page); + zram_fill_page(mem, PAGE_SIZE, value); + kunmap_atomic(mem); + zram_slot_unlock(zram, index); + return 0; + } + size = zram_get_obj_size(zram, index); src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); -- GitLab From 5bdfca6435b8294490ffb5b7c8b7d8eac3814b06 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 3 Oct 2017 16:15:23 -0700 Subject: [PATCH 0882/1507] m32r: define CPU_BIG_ENDIAN The build of m32r allmodconfig is giving lots of build warnings about: include/linux/byteorder/big_endian.h:7:2: warning: #warning inconsistent configuration, needs CONFIG_CPU_BIG_ENDIAN [-Wcpp] #warning inconsistent configuration, needs CONFIG_CPU_BIG_ENDIAN Define CPU_BIG_ENDIAN like the way CPU_LITTLE_ENDIAN is defined. Link: http://lkml.kernel.org/r/1505678083-10320-1-git-send-email-sudipm.mukherjee@gmail.com Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 87cde1e4b38ca..0777f3a8a1f37 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -194,6 +194,10 @@ config TIMER_DIVIDE int "Timer divider (integer)" default "128" +config CPU_BIG_ENDIAN + bool "Generate big endian code" + default n + config CPU_LITTLE_ENDIAN bool "Generate little endian code" default n -- GitLab From f4e222c56c83b2aed7cc2b329fca7435508eefa1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 3 Oct 2017 16:15:25 -0700 Subject: [PATCH 0883/1507] mm: have filemap_check_and_advance_wb_err clear AS_EIO/AS_ENOSPC Eryu noticed that he could sometimes get a leftover error reported when it shouldn't be on fsync with ext2 and non-journalled ext4. The problem is that writeback_single_inode still uses filemap_fdatawait. That picks up a previously set AS_EIO flag, which would ordinarily have been cleared before. Since we're mostly using this function as a replacement for filemap_check_errors, have filemap_check_and_advance_wb_err clear AS_EIO and AS_ENOSPC when reporting an error. That should allow the new function to better emulate the behavior of the old with respect to these flags. Link: http://lkml.kernel.org/r/20170922133331.28812-1-jlayton@kernel.org Signed-off-by: Jeff Layton Reported-by: Eryu Guan Reviewed-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/filemap.c b/mm/filemap.c index db250d0e05655..594d73fef8b43 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -620,6 +620,14 @@ int file_check_and_advance_wb_err(struct file *file) trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } + + /* + * We're mostly using this function as a drop in replacement for + * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect + * that the legacy code would have had on these flags. + */ + clear_bit(AS_EIO, &mapping->flags); + clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); -- GitLab From 24c92eb7dce0a299b8e1a8c5fa585844a53bf7f0 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Tue, 3 Oct 2017 16:15:29 -0700 Subject: [PATCH 0884/1507] mm: avoid marking swap cached page as lazyfree MADV_FREE clears pte dirty bit and then marks the page lazyfree (clear SwapBacked). There is no lock to prevent the page is added to swap cache between these two steps by page reclaim. Page reclaim could add the page to swap cache and unmap the page. After page reclaim, the page is added back to lru. At that time, we probably start draining per-cpu pagevec and mark the page lazyfree. So the page could be in a state with SwapBacked cleared and PG_swapcache set. Next time there is a refault in the virtual address, do_swap_page can find the page from swap cache but the page has PageSwapCache false because SwapBacked isn't set, so do_swap_page will bail out and do nothing. The task will keep running into fault handler. Fixes: 802a3a92ad7a ("mm: reclaim MADV_FREE pages") Link: http://lkml.kernel.org/r/6537ef3814398c0073630b03f176263bc81f0902.1506446061.git.shli@fb.com Signed-off-by: Shaohua Li Reported-by: Artem Savkov Tested-by: Artem Savkov Reviewed-by: Rik van Riel Acked-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: Minchan Kim Cc: Hillf Danton Cc: Hugh Dickins Cc: Mel Gorman Cc: [4.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index 9295ae960d668..a77d68f2c1b61 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -575,7 +575,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); del_page_from_lru_list(page, lruvec, @@ -665,7 +665,7 @@ void deactivate_file_page(struct page *page) void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); get_page(page); -- GitLab From 9625456cc76391b7f3f2809579126542a8ed4d39 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Tue, 3 Oct 2017 16:15:32 -0700 Subject: [PATCH 0885/1507] mm: fix data corruption caused by lazyfree page MADV_FREE clears pte dirty bit and then marks the page lazyfree (clear SwapBacked). There is no lock to prevent the page is added to swap cache between these two steps by page reclaim. If page reclaim finds such page, it will simply add the page to swap cache without pageout the page to swap because the page is marked as clean. Next time, page fault will read data from the swap slot which doesn't have the original data, so we have a data corruption. To fix issue, we mark the page dirty and pageout the page. However, we shouldn't dirty all pages which is clean and in swap cache. swapin page is swap cache and clean too. So we only dirty page which is added into swap cache in page reclaim, which shouldn't be swapin page. As Minchan suggested, simply dirty the page in add_to_swap can do the job. Fixes: 802a3a92ad7a ("mm: reclaim MADV_FREE pages") Link: http://lkml.kernel.org/r/08c84256b007bf3f63c91d94383bd9eb6fee2daa.1506446061.git.shli@fb.com Signed-off-by: Shaohua Li Reported-by: Artem Savkov Acked-by: Michal Hocko Acked-by: Minchan Kim Cc: Johannes Weiner Cc: Hillf Danton Cc: Hugh Dickins Cc: Rik van Riel Cc: Mel Gorman Cc: [4.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap_state.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/mm/swap_state.c b/mm/swap_state.c index 71ce2d1ccbf73..ed91091d1e688 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -242,6 +242,17 @@ int add_to_swap(struct page *page) * clear SWAP_HAS_CACHE flag. */ goto fail; + /* + * Normally the page will be dirtied in unmap because its pte should be + * dirty. A special case is MADV_FREE page. The page'e pte could have + * dirty bit cleared but the page's SwapBacked bit is still set because + * clearing the dirty bit and SwapBacked bit has no lock protected. For + * such page, unmap will not set dirty bit for it, so page reclaim will + * not write the page out. This can cause data corruption when the page + * is swap in later. Always setting the dirty bit for the page solves + * the problem. + */ + set_page_dirty(page); return 1; -- GitLab From 7d790d2da386a52cfebcf0c898ba927bece9d4ab Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Tue, 3 Oct 2017 16:15:35 -0700 Subject: [PATCH 0886/1507] mm/device-public-memory: fix edge case in _vm_normal_page() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With device public pages at the end of my memory space, I'm getting output from _vm_normal_page(): BUG: Bad page map in process migrate_pages pte:c0800001ffff0d06 pmd:f95d3000 addr:00007fff89330000 vm_flags:00100073 anon_vma:c0000000fa899320 mapping: (null) index:7fff8933 file: (null) fault: (null) mmap: (null) readpage: (null) CPU: 0 PID: 13963 Comm: migrate_pages Tainted: P B OE 4.14.0-rc1-wip #155 Call Trace: dump_stack+0xb0/0xf4 (unreliable) print_bad_pte+0x28c/0x340 _vm_normal_page+0xc0/0x140 zap_pte_range+0x664/0xc10 unmap_page_range+0x318/0x670 unmap_vmas+0x74/0xe0 exit_mmap+0xe8/0x1f0 mmput+0xac/0x1f0 do_exit+0x348/0xcd0 do_group_exit+0x5c/0xf0 SyS_exit_group+0x1c/0x20 system_call+0x58/0x6c The pfn causing this is the very last one. Correct the bounds check accordingly. Fixes: df6ad69838fc ("mm/device-public-memory: device memory cache coherent with CPU") Link: http://lkml.kernel.org/r/1506092178-20351-1-git-send-email-arbab@linux.vnet.ibm.com Signed-off-by: Reza Arbab Reviewed-by: Jérôme Glisse Reviewed-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index ec4e154949016..a728bed16c206 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -845,7 +845,7 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, * vm_normal_page() so that we do not have to special case all * call site of vm_normal_page(). */ - if (likely(pfn < highest_memmap_pfn)) { + if (likely(pfn <= highest_memmap_pfn)) { struct page *page = pfn_to_page(pfn); if (is_device_public_page(page)) { -- GitLab From 384632e67e0829deb8015ee6ad916b180049d252 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 3 Oct 2017 16:15:38 -0700 Subject: [PATCH 0887/1507] userfaultfd: non-cooperative: fix fork use after free When reading the event from the uffd, we put it on a temporary fork_event list to detect if we can still access it after releasing and retaking the event_wqh.lock. If fork aborts and removes the event from the fork_event all is fine as long as we're still in the userfault read context and fork_event head is still alive. We've to put the event allocated in the fork kernel stack, back from fork_event list-head to the event_wqh head, before returning from userfaultfd_ctx_read, because the fork_event head lifetime is limited to the userfaultfd_ctx_read stack lifetime. Forgetting to move the event back to its event_wqh place then results in __remove_wait_queue(&ctx->event_wqh, &ewq->wq); in userfaultfd_event_wait_completion to remove it from a head that has been already freed from the reader stack. This could only happen if resolve_userfault_fork failed (for example if there are no file descriptors available to allocate the fork uffd). If it succeeded it was put back correctly. Furthermore, after find_userfault_evt receives a fork event, the forked userfault context in fork_nctx and uwq->msg.arg.reserved.reserved1 can be released by the fork thread as soon as the event_wqh.lock is released. Taking a reference on the fork_nctx before dropping the lock prevents an use after free in resolve_userfault_fork(). If the fork side aborted and it already released everything, we still try to succeed resolve_userfault_fork(), if possible. Fixes: 893e26e61d04eac9 ("userfaultfd: non-cooperative: Add fork() event") Link: http://lkml.kernel.org/r/20170920180413.26713-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: Mark Rutland Tested-by: Mark Rutland Cc: Pavel Emelyanov Cc: Mike Rapoport Cc: "Dr. David Alan Gilbert" Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 66 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 56 insertions(+), 10 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ef4b48d1ea427..1c713fd5b3e67 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -588,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { + /* + * &ewq->wq may be queued in fork_event, but + * __remove_wait_queue ignores the head + * parameter. It would be a problem if it + * didn't. + */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; @@ -1061,6 +1067,12 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); + /* + * fork_nctx can be freed as soon as + * we drop the lock, unless we take a + * reference on it. + */ + userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; @@ -1091,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(ctx, fork_nctx, msg); + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + /* + * The fork thread didn't abort, so we can + * drop the temporary refcount. + */ + userfaultfd_ctx_put(fork_nctx); + + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.entry); + /* + * If fork_event list wasn't empty and in turn + * the event wasn't already released by fork + * (the event is allocated on fork kernel + * stack), put the event back to its place in + * the event_wq. fork_event head will be freed + * as soon as we return so the event cannot + * stay queued there no matter the current + * "ret" value. + */ + list_del(&uwq->wq.entry); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); - if (!ret) { - spin_lock(&ctx->event_wqh.lock); - if (!list_empty(&fork_event)) { - uwq = list_first_entry(&fork_event, - typeof(*uwq), - wq.entry); - list_del(&uwq->wq.entry); - __add_wait_queue(&ctx->event_wqh, &uwq->wq); + /* + * Leave the event in the waitqueue and report + * error to userland if we failed to resolve + * the userfault fork. + */ + if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); - } - spin_unlock(&ctx->event_wqh.lock); + } else { + /* + * Here the fork thread aborted and the + * refcount from the fork thread on fork_nctx + * has already been released. We still hold + * the reference we took before releasing the + * lock above. If resolve_userfault_fork + * failed we've to drop it because the + * fork_nctx has to be freed in such case. If + * it succeeded we'll hold it because the new + * uffd references it. + */ + if (ret) + userfaultfd_ctx_put(fork_nctx); } + spin_unlock(&ctx->event_wqh.lock); } return ret; -- GitLab From c2315c187fa0d3ab363fdebe22718170b40473e3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:42 -0700 Subject: [PATCH 0888/1507] exec: load_script: kill the onstack interp[BINPRM_BUF_SIZE] array Patch series "exec: binfmt_misc: fix use-after-free, kill iname[BINPRM_BUF_SIZE]". It looks like this code was always wrong, then commit 948b701a607f ("binfmt_misc: add persistent opened binary handler for containers") added more problems. This patch (of 6): load_script() can simply use i_name instead, it points into bprm->buf[] and nobody can change this memory until we call prepare_binprm(). The only complication is that we need to also change the signature of bprm_change_interp() but this change looks good too. While at it, do whitespace/style cleanups. NOTE: the real motivation for this change is that people want to increase BINPRM_BUF_SIZE, we need to change load_misc_binary() too but this looks more complicated because afaics it is very buggy. Link: http://lkml.kernel.org/r/20170918163446.GA26793@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Travis Gummels Cc: Ben Woodard Cc: Jim Foraker Cc: Cc: Al Viro Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_script.c | 17 +++++++++-------- fs/exec.c | 2 +- include/linux/binfmts.h | 2 +- 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index afdf4e3cafc2a..7cde3f46ad263 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm) const char *i_arg, *i_name; char *cp; struct file *file; - char interp[BINPRM_BUF_SIZE]; int retval; if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) @@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm) break; } for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++); - if (*cp == '\0') + if (*cp == '\0') return -ENOEXEC; /* No interpreter name found */ i_name = cp; i_arg = NULL; @@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm) *cp++ = '\0'; if (*cp) i_arg = cp; - strcpy (interp, i_name); /* * OK, we've parsed out the interpreter name and * (optional) argument. @@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm) if (retval) return retval; retval = copy_strings_kernel(1, &bprm->interp, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; if (i_arg) { retval = copy_strings_kernel(1, &i_arg, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; } retval = copy_strings_kernel(1, &i_name, bprm); - if (retval) return retval; + if (retval) + return retval; bprm->argc++; - retval = bprm_change_interp(interp, bprm); + retval = bprm_change_interp(i_name, bprm); if (retval < 0) return retval; /* * OK, now restart the process with the interpreter's dentry. */ - file = open_exec(interp); + file = open_exec(i_name); if (IS_ERR(file)) return PTR_ERR(file); diff --git a/fs/exec.c b/fs/exec.c index ac34d97246848..5470d3c1892af 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1410,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm) kfree(bprm); } -int bprm_change_interp(char *interp, struct linux_binprm *bprm) +int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fb44d6180ca0e..18d05b5491f34 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -131,7 +131,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); -extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); +extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); -- GitLab From baba1b29731c79d605100087b8f02f9e1cf5a344 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:45 -0700 Subject: [PATCH 0889/1507] exec: binfmt_misc: don't nullify Node->dentry in kill_node() kill_node() nullifies/checks Node->dentry to avoid double free. This complicates the next changes and this is very confusing: - we do not need to check dentry != NULL under entries_lock, kill_node() is always called under inode_lock(d_inode(root)) and we rely on this inode_lock() anyway, without this lock the MISC_FMT_OPEN_FILE cleanup could race with itself. - if kill_inode() was already called and ->dentry == NULL we should not even try to close e->interp_file. We can change bm_entry_write() to simply check !list_empty(list) before kill_node. Again, we rely on inode_lock(), in particular it saves us from the race with bm_status_write(), another caller of kill_node(). Link: http://lkml.kernel.org/r/20170922143641.GA17210@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Ben Woodard Cc: James Bottomley Cc: Jim Foraker Cc: Cc: Travis Gummels Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ce7181ea60fa9..6451e7520e053 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -603,11 +603,7 @@ static void kill_node(Node *e) struct dentry *dentry; write_lock(&entries_lock); - dentry = e->dentry; - if (dentry) { - list_del_init(&e->list); - e->dentry = NULL; - } + list_del_init(&e->list); write_unlock(&entries_lock); if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) { @@ -615,12 +611,11 @@ static void kill_node(Node *e) e->interp_file = NULL; } - if (dentry) { - drop_nlink(d_inode(dentry)); - d_drop(dentry); - dput(dentry); - simple_release_fs(&bm_mnt, &entry_count); - } + dentry = e->dentry; + drop_nlink(d_inode(dentry)); + d_drop(dentry); + dput(dentry); + simple_release_fs(&bm_mnt, &entry_count); } /* / */ @@ -665,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, root = file_inode(file)->i_sb->s_root; inode_lock(d_inode(root)); - kill_node(e); + if (!list_empty(&e->list)) + kill_node(e); inode_unlock(d_inode(root)); break; @@ -794,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, inode_lock(d_inode(root)); while (!list_empty(&entries)) - kill_node(list_entry(entries.next, Node, list)); + kill_node(list_first_entry(&entries, Node, list)); inode_unlock(d_inode(root)); break; -- GitLab From 83f918274e4b841d6fb817861ea0c896fba0c179 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:48 -0700 Subject: [PATCH 0890/1507] exec: binfmt_misc: shift filp_close(interp_file) from kill_node() to bm_evict_inode() To ensure that load_misc_binary() can't use the partially destroyed Node, see also the next patch. The current logic looks wrong in any case, once we close interp_file it doesn't make any sense to delay kfree(inode->i_private), this Node is no longer valid. Even if the MISC_FMT_OPEN_FILE/interp_file checks were not racy (they are), load_misc_binary() should not try to reopen ->interpreter if MISC_FMT_OPEN_FILE is set but ->interp_file is NULL. And I can't understand why do we use filp_close(), not fput(). Link: http://lkml.kernel.org/r/20170922143644.GA17216@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Ben Woodard Cc: James Bottomley Cc: Jim Foraker Cc: Cc: Travis Gummels Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 6451e7520e053..203598ccb40ad 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -594,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_evict_inode(struct inode *inode) { + Node *e = inode->i_private; + + if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) + filp_close(e->interp_file, NULL); + clear_inode(inode); - kfree(inode->i_private); + kfree(e); } static void kill_node(Node *e) @@ -606,11 +611,6 @@ static void kill_node(Node *e) list_del_init(&e->list); write_unlock(&entries_lock); - if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) { - filp_close(e->interp_file, NULL); - e->interp_file = NULL; - } - dentry = e->dentry; drop_nlink(d_inode(dentry)); d_drop(dentry); -- GitLab From eb23aa0317eb1f08e8d9d36b8753d42f03b32764 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:51 -0700 Subject: [PATCH 0891/1507] exec: binfmt_misc: remove the confusing e->interp_file != NULL checks If MISC_FMT_OPEN_FILE flag is set e->interp_file must be valid or we have a bug which should not be silently ignored. Link: http://lkml.kernel.org/r/20170922143647.GA17222@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Ben Woodard Cc: James Bottomley Cc: Jim Foraker Cc: Cc: Travis Gummels Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 203598ccb40ad..babfe7bd56f06 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm) if (retval < 0) goto error; - if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) { + if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = filp_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); @@ -596,7 +596,7 @@ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; - if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) + if (e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); clear_inode(inode); -- GitLab From 43a4f2619038002f48c78698c42c05692d4b4eb2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:55 -0700 Subject: [PATCH 0892/1507] exec: binfmt_misc: fix race between load_misc_binary() and kill_node() load_misc_binary() makes a local copy of fmt->interpreter under entries_lock to avoid the race with kill_node() but this is not enough; the whole Node can be freed after we drop entries_lock, not only the ->interpreter string. Add dget/dput(fmt->dentry) to ensure bm_evict_inode() can't destroy/free this Node. Link: http://lkml.kernel.org/r/20170922143650.GA17227@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Ben Woodard Cc: James Bottomley Cc: Jim Foraker Cc: Travis Gummels Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index babfe7bd56f06..f5f8c25417904 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -138,20 +138,23 @@ static int load_misc_binary(struct linux_binprm *bprm) retval = -ENOEXEC; if (!enabled) - goto ret; + return retval; /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); - if (fmt) + if (fmt) { + dget(fmt->dentry); strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE); + } read_unlock(&entries_lock); if (!fmt) - goto ret; + return retval; /* Need to be able to load the file after exec */ + retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; + goto ret; if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { retval = remove_arg_zero(bprm); @@ -238,6 +241,7 @@ static int load_misc_binary(struct linux_binprm *bprm) goto error; ret: + dput(fmt->dentry); return retval; error: if (fd_binary > 0) -- GitLab From 50097f74934e3ec8fb1e6f3087568b958972817d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 3 Oct 2017 16:15:58 -0700 Subject: [PATCH 0893/1507] exec: binfmt_misc: kill the onstack iname[BINPRM_BUF_SIZE] array After the previous change "fmt" can't go away, we can kill iname/iname_addr and use fmt->interpreter. Link: http://lkml.kernel.org/r/20170922143653.GA17232@redhat.com Signed-off-by: Oleg Nesterov Acked-by: Kees Cook Cc: Al Viro Cc: Ben Woodard Cc: James Bottomley Cc: Jim Foraker Cc: Cc: Travis Gummels Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_misc.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index f5f8c25417904..2a46762def315 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -54,7 +54,7 @@ typedef struct { int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ - char *interpreter; /* filename of interpreter */ + const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; @@ -131,8 +131,6 @@ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; - char iname[BINPRM_BUF_SIZE]; - const char *iname_addr = iname; int retval; int fd_binary = -1; @@ -143,10 +141,8 @@ static int load_misc_binary(struct linux_binprm *bprm) /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); - if (fmt) { + if (fmt) dget(fmt->dentry); - strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE); - } read_unlock(&entries_lock); if (!fmt) return retval; @@ -198,13 +194,13 @@ static int load_misc_binary(struct linux_binprm *bprm) bprm->argc++; /* add the interp as argv[0] */ - retval = copy_strings_kernel(1, &iname_addr, bprm); + retval = copy_strings_kernel(1, &fmt->interpreter, bprm); if (retval < 0) goto error; bprm->argc++; /* Update interp in case binfmt_script needs it. */ - retval = bprm_change_interp(iname, bprm); + retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto error; @@ -213,7 +209,7 @@ static int load_misc_binary(struct linux_binprm *bprm) if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { - interp_file = open_exec(iname); + interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) -- GitLab From 8cb5d7482810b7eb1bb05bf4f71bc93ce35e5896 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 3 Oct 2017 16:16:01 -0700 Subject: [PATCH 0894/1507] lib/lz4: make arrays static const, reduces object code size Don't populate the read-only arrays dec32table and dec64table on the stack, instead make them both static const. Makes the object code smaller by over 10K bytes: Before: text data bss dec hex filename 31500 0 0 31500 7b0c lib/lz4/lz4_decompress.o After: text data bss dec hex filename 20237 176 0 20413 4fbd lib/lz4/lz4_decompress.o (gcc version 7.2.0 x86_64) Link: http://lkml.kernel.org/r/20170921221939.20820-1-colin.king@canonical.com Signed-off-by: Colin Ian King Cc: Christophe JAILLET Cc: Sven Schmidt <4sschmid@informatik.uni-hamburg.de> Cc: Arnd Bergmann Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/lz4/lz4_decompress.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index bd3574312b827..141734d255e4b 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -85,8 +85,8 @@ static FORCE_INLINE int LZ4_decompress_generic( const BYTE * const lowLimit = lowPrefix - dictSize; const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize; - const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; - const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; + static const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; + static const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; const int safeDecode = (endOnInput == endOnInputSize); const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB))); -- GitLab From 7240767450d6d8380fb153e2998a1bb4ede7b029 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 3 Oct 2017 16:16:04 -0700 Subject: [PATCH 0895/1507] include/linux/bitfield.h: remove 32bit from FIELD_GET comment block I do not see anything that restricts this macro to 32 bit width. Link: http://lkml.kernel.org/r/1505921975-23379-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Jakub Kicinski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitfield.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 8b9d6fff002db..f2deb71958b2d 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -92,7 +92,7 @@ /** * FIELD_GET() - extract a bitfield element * @_mask: shifted mask defining the field's length and position - * @_reg: 32bit value of entire bitfield + * @_reg: value of entire bitfield * * FIELD_GET() extracts the field specified by @_mask from the * bitfield passed in as @_reg by masking and shifting it down. -- GitLab From 3181c38e4df257852a0c0a53552fd5c869402886 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Tue, 3 Oct 2017 16:16:07 -0700 Subject: [PATCH 0896/1507] kernel/sysctl.c: remove duplicate UINT_MAX check on do_proc_douintvec_conv() do_proc_douintvec_conv() has two UINT_MAX checks, we can remove one. This has no functional changes other than fixing a compiler warning: kernel/sysctl.c:2190]: (warning) Identical condition '*lvalp>UINT_MAX', second condition is always false Fixes: 4f2fec00afa60 ("sysctl: simplify unsigned int support") Link: http://lkml.kernel.org/r/20170919072918.12066-1-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Reported-by: David Binderman Acked-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 423554ad36102..4da9e622471f6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2186,8 +2186,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, int write, void *data) { if (write) { - if (*lvalp > UINT_MAX) - return -EINVAL; if (*lvalp > UINT_MAX) return -EINVAL; *valp = *lvalp; -- GitLab From f80c7dab95a1f0f968acbafe4426ee9525b6f6ab Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 3 Oct 2017 16:16:10 -0700 Subject: [PATCH 0897/1507] mm: memcontrol: use vmalloc fallback for large kmem memcg arrays For quick per-memcg indexing, slab caches and list_lru structures maintain linear arrays of descriptors. As the number of concurrent memory cgroups in the system goes up, this requires large contiguous allocations (8k cgroups = order-5, 16k cgroups = order-6 etc.) for every existing slab cache and list_lru, which can easily fail on loaded systems. E.g.: mkdir: page allocation failure: order:5, mode:0x14040c0(GFP_KERNEL|__GFP_COMP), nodemask=(null) CPU: 1 PID: 6399 Comm: mkdir Not tainted 4.13.0-mm1-00065-g720bbe532b7c-dirty #481 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-20170228_101828-anatol 04/01/2014 Call Trace: ? __alloc_pages_direct_compact+0x4c/0x110 __alloc_pages_nodemask+0xf50/0x1430 alloc_pages_current+0x60/0xc0 kmalloc_order_trace+0x29/0x1b0 __kmalloc+0x1f4/0x320 memcg_update_all_list_lrus+0xca/0x2e0 mem_cgroup_css_alloc+0x612/0x670 cgroup_apply_control_enable+0x19e/0x360 cgroup_mkdir+0x322/0x490 kernfs_iop_mkdir+0x55/0x80 vfs_mkdir+0xd0/0x120 SyS_mkdirat+0x6c/0xe0 SyS_mkdir+0x14/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Mem-Info: active_anon:2965 inactive_anon:19 isolated_anon:0 active_file:100270 inactive_file:98846 isolated_file:0 unevictable:0 dirty:0 writeback:0 unstable:0 slab_reclaimable:7328 slab_unreclaimable:16402 mapped:771 shmem:52 pagetables:278 bounce:0 free:13718 free_pcp:0 free_cma:0 This output is from an artificial reproducer, but we have repeatedly observed order-7 failures in production in the Facebook fleet. These systems become useless as they cannot run more jobs, even though there is plenty of memory to allocate 128 individual pages. Use kvmalloc and kvzalloc to fall back to vmalloc space if these arrays prove too large for allocating them physically contiguous. Link: http://lkml.kernel.org/r/20170918184919.20644-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Josef Bacik Acked-by: Michal Hocko Acked-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/list_lru.c | 12 ++++++------ mm/slab_common.c | 22 +++++++++++++++------- 2 files changed, 21 insertions(+), 13 deletions(-) diff --git a/mm/list_lru.c b/mm/list_lru.c index 7a40fa2be858a..f141f0c80ff33 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -325,12 +325,12 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) { int size = memcg_nr_cache_ids; - nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL); + nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL); if (!nlru->memcg_lrus) return -ENOMEM; if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) { - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); return -ENOMEM; } @@ -340,7 +340,7 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) { __memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids); - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); } static int memcg_update_list_lru_node(struct list_lru_node *nlru, @@ -351,12 +351,12 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, BUG_ON(old_size > new_size); old = nlru->memcg_lrus; - new = kmalloc(new_size * sizeof(void *), GFP_KERNEL); + new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; if (__memcg_init_list_lru_node(new, old_size, new_size)) { - kfree(new); + kvfree(new); return -ENOMEM; } @@ -373,7 +373,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, nlru->memcg_lrus = new; spin_unlock_irq(&nlru->lock); - kfree(old); + kvfree(old); return 0; } diff --git a/mm/slab_common.c b/mm/slab_common.c index 904a83be82de8..80164599ca5d1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -165,9 +165,9 @@ static int init_memcg_params(struct kmem_cache *s, if (!memcg_nr_cache_ids) return 0; - arr = kzalloc(sizeof(struct memcg_cache_array) + - memcg_nr_cache_ids * sizeof(void *), - GFP_KERNEL); + arr = kvzalloc(sizeof(struct memcg_cache_array) + + memcg_nr_cache_ids * sizeof(void *), + GFP_KERNEL); if (!arr) return -ENOMEM; @@ -178,15 +178,23 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { if (is_root_cache(s)) - kfree(rcu_access_pointer(s->memcg_params.memcg_caches)); + kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); +} + +static void free_memcg_params(struct rcu_head *rcu) +{ + struct memcg_cache_array *old; + + old = container_of(rcu, struct memcg_cache_array, rcu); + kvfree(old); } static int update_memcg_params(struct kmem_cache *s, int new_array_size) { struct memcg_cache_array *old, *new; - new = kzalloc(sizeof(struct memcg_cache_array) + - new_array_size * sizeof(void *), GFP_KERNEL); + new = kvzalloc(sizeof(struct memcg_cache_array) + + new_array_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; @@ -198,7 +206,7 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size) rcu_assign_pointer(s->memcg_params.memcg_caches, new); if (old) - kfree_rcu(old, rcu); + call_rcu(&old->rcu, free_memcg_params); return 0; } -- GitLab From a70e43a59de9316e6fbad3b65557d0a24c099aca Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 3 Oct 2017 16:16:13 -0700 Subject: [PATCH 0898/1507] lib/idr.c: fix comment for idr_replace() idr_replace() returns the old value on success, not 0. Link: http://lkml.kernel.org/r/20170918162642.37511-1-ebiggers3@gmail.com Signed-off-by: Eric Biggers Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/idr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/idr.c b/lib/idr.c index f9adf4805fd74..edd9b2be1651f 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -146,8 +146,8 @@ EXPORT_SYMBOL(idr_get_next_ext); * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * - * Returns: 0 on success. %-ENOENT indicates that @id was not found. - * %-EINVAL indicates that @id or @ptr were not valid. + * Returns: the old value on success. %-ENOENT indicates that @id was not + * found. %-EINVAL indicates that @id or @ptr were not valid. */ void *idr_replace(struct idr *idr, void *ptr, int id) { -- GitLab From f64ac5e6e30668216cf489d73ba8a96e372d78c6 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 3 Oct 2017 16:16:16 -0700 Subject: [PATCH 0899/1507] mm, memory_hotplug: add scheduling point to __add_pages Patch series "mm, memory_hotplug: fix few soft lockups in memory hotadd". Johannes has noticed few soft lockups when adding a large nvdimm device. All of them were caused by a long loop without any explicit cond_resched which is a problem for !PREEMPT kernels. The fix is quite straightforward. Just make sure that cond_resched gets called from time to time. This patch (of 3): __add_pages gets a pfn range to add and there is no upper bound for a single call. This is usually a memory block aligned size for the regular memory hotplug - smaller sizes are usual for memory balloning drivers, or the whole NUMA node for physical memory online. There is no explicit scheduling point in that code path though. This can lead to long latencies while __add_pages is executed and we have even seen a soft lockup report during nvdimm initialization with !PREEMPT kernel NMI watchdog: BUG: soft lockup - CPU#11 stuck for 23s! [kworker/u641:3:832] [...] Workqueue: events_unbound async_run_entry_fn task: ffff881809270f40 ti: ffff881809274000 task.ti: ffff881809274000 RIP: _raw_spin_unlock_irqrestore+0x11/0x20 RSP: 0018:ffff881809277b10 EFLAGS: 00000286 [...] Call Trace: sparse_add_one_section+0x13d/0x18e __add_pages+0x10a/0x1d0 arch_add_memory+0x4a/0xc0 devm_memremap_pages+0x29d/0x430 pmem_attach_disk+0x2fd/0x3f0 [nd_pmem] nvdimm_bus_probe+0x64/0x110 [libnvdimm] driver_probe_device+0x1f7/0x420 bus_for_each_drv+0x52/0x80 __device_attach+0xb0/0x130 bus_probe_device+0x87/0xa0 device_add+0x3fc/0x5f0 nd_async_device_register+0xe/0x40 [libnvdimm] async_run_entry_fn+0x43/0x150 process_one_work+0x14e/0x410 worker_thread+0x116/0x490 kthread+0xc7/0xe0 ret_from_fork+0x3f/0x70 DWARF2 unwinder stuck at ret_from_fork+0x3f/0x70 Fix this by adding cond_resched once per each memory section in the given pfn range. Each section is constant amount of work which itself is not too expensive but many of them will just add up. Link: http://lkml.kernel.org/r/20170918121410.24466-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Johannes Thumshirn Tested-by: Johannes Thumshirn Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e882cb6da9942..23d5bd9689501 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -328,6 +328,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn, if (err && (err != -EEXIST)) break; err = 0; + cond_resched(); } vmemmap_populate_print_last(); out: -- GitLab From 9b6e63cbf85b89b2dbffa4955dbf2df8250e5375 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 3 Oct 2017 16:16:19 -0700 Subject: [PATCH 0900/1507] mm, page_alloc: add scheduling point to memmap_init_zone memmap_init_zone gets a pfn range to initialize and it can be really large resulting in a soft lockup on non-preemptible kernels NMI watchdog: BUG: soft lockup - CPU#31 stuck for 23s! [kworker/u642:5:1720] [...] task: ffff88ecd7e902c0 ti: ffff88eca4e50000 task.ti: ffff88eca4e50000 RIP: move_pfn_range_to_zone+0x185/0x1d0 [...] Call Trace: devm_memremap_pages+0x2c7/0x430 pmem_attach_disk+0x2fd/0x3f0 [nd_pmem] nvdimm_bus_probe+0x64/0x110 [libnvdimm] driver_probe_device+0x1f7/0x420 bus_for_each_drv+0x52/0x80 __device_attach+0xb0/0x130 bus_probe_device+0x87/0xa0 device_add+0x3fc/0x5f0 nd_async_device_register+0xe/0x40 [libnvdimm] async_run_entry_fn+0x43/0x150 process_one_work+0x14e/0x410 worker_thread+0x116/0x490 kthread+0xc7/0xe0 ret_from_fork+0x3f/0x70 Fix this by adding a scheduling point once per page block. Link: http://lkml.kernel.org/r/20170918121410.24466-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Johannes Thumshirn Tested-by: Johannes Thumshirn Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 38d165a87860f..77e4d3c5c57b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5367,6 +5367,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, __init_single_page(page, pfn, zone, nid); set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); } else { __init_single_pfn(pfn, zone, nid); } -- GitLab From 1fdcce6e16c54facc4f0688630d3b9ecfcaa411f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 3 Oct 2017 16:16:23 -0700 Subject: [PATCH 0901/1507] memremap: add scheduling point to devm_memremap_pages devm_memremap_pages is initializing struct pages in for_each_device_pfn and that can take quite some time. We have even seen a soft lockup triggering on a non preemptive kernel NMI watchdog: BUG: soft lockup - CPU#61 stuck for 22s! [kworker/u641:11:1808] [...] RIP: 0010:[] [] devm_memremap_pages+0x327/0x430 [...] Call Trace: pmem_attach_disk+0x2fd/0x3f0 [nd_pmem] nvdimm_bus_probe+0x64/0x110 [libnvdimm] driver_probe_device+0x1f7/0x420 bus_for_each_drv+0x52/0x80 __device_attach+0xb0/0x130 bus_probe_device+0x87/0xa0 device_add+0x3fc/0x5f0 nd_async_device_register+0xe/0x40 [libnvdimm] async_run_entry_fn+0x43/0x150 process_one_work+0x14e/0x410 worker_thread+0x116/0x490 kthread+0xc7/0xe0 ret_from_fork+0x3f/0x70 fix this by adding cond_resched every 1024 pages. Link: http://lkml.kernel.org/r/20170918121410.24466-4-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Johannes Thumshirn Tested-by: Johannes Thumshirn Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/memremap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fdf..403ab9cdb949a 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); -- GitLab From c9653850c90d6050197bc76ba672e00a7771aea5 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Tue, 3 Oct 2017 16:16:26 -0700 Subject: [PATCH 0902/1507] kernel/kcmp.c: drop branch leftover typo The else branch been left over and escaped the source code refresh. Not a problem but better clean it up. Fixes: 0791e3644e5e ("kcmp: add KCMP_EPOLL_TFD mode to compare epoll target files") Link: http://lkml.kernel.org/r/20170917165838.GA1887@uranus.lan Reported-by: Eugene Syromiatnikov Signed-off-by: Cyrill Gorcunov Acked-by: Andrei Vagin Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kcmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb9529..055bb2962a0b6 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); -- GitLab From 1dd2bfc86818ddbc95f98e312e7704350223fd7d Mon Sep 17 00:00:00 2001 From: YASUAKI ISHIMATSU Date: Tue, 3 Oct 2017 16:16:29 -0700 Subject: [PATCH 0903/1507] mm/memory_hotplug: change pfn_to_section_nr/section_nr_to_pfn macro to inline function pfn_to_section_nr() and section_nr_to_pfn() are defined as macro. pfn_to_section_nr() has no issue even if it is defined as macro. But section_nr_to_pfn() has overflow issue if sec is defined as int. section_nr_to_pfn() just shifts sec by PFN_SECTION_SHIFT. If sec is defined as unsigned long, section_nr_to_pfn() returns pfn as 64 bit value. But if sec is defined as int, section_nr_to_pfn() returns pfn as 32 bit value. __remove_section() calculates start_pfn using section_nr_to_pfn() and scn_nr defined as int. So if hot-removed memory address is over 16TB, overflow issue occurs and section_nr_to_pfn() does not calculate correct pfn. To make callers use proper arg, the patch changes the macros to inline functions. Fixes: 815121d2b5cd ("memory_hotplug: clear zone when removing the memory") Link: http://lkml.kernel.org/r/e643a387-e573-6bbf-d418-c60c8ee3d15e@gmail.com Signed-off-by: Yasuaki Ishimatsu Acked-by: Michal Hocko Cc: Xishi Qiu Cc: Reza Arbab Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++-- mm/memory_hotplug.c | 2 +- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 356a814e7c8eb..c8f89417740bb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1094,8 +1094,14 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif -#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) -#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) +static inline unsigned long pfn_to_section_nr(unsigned long pfn) +{ + return pfn >> PFN_SECTION_SHIFT; +} +static inline unsigned long section_nr_to_pfn(unsigned long sec) +{ + return sec << PFN_SECTION_SHIFT; +} #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 23d5bd9689501..efd1ad37bb574 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -551,7 +551,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms, return ret; scn_nr = __section_nr(ms); - start_pfn = section_nr_to_pfn(scn_nr); + start_pfn = section_nr_to_pfn((unsigned long)scn_nr); __remove_zone(zone, start_pfn); sparse_remove_one_section(zone, ms, map_offset); -- GitLab From d09b0137d204bebeaafed672bc5a244e9ac92edb Mon Sep 17 00:00:00 2001 From: YASUAKI ISHIMATSU Date: Tue, 3 Oct 2017 16:16:32 -0700 Subject: [PATCH 0904/1507] mm/memory_hotplug: define find_{smallest|biggest}_section_pfn as unsigned long find_{smallest|biggest}_section_pfn()s find the smallest/biggest section and return the pfn of the section. But the functions are defined as int. So the functions always return 0x00000000 - 0xffffffff. It means if memory address is over 16TB, the functions does not work correctly. To handle 64 bit value, the patch defines find_{smallest|biggest}_section_pfn() as unsigned long. Fixes: 815121d2b5cd ("memory_hotplug: clear zone when removing the memory") Link: http://lkml.kernel.org/r/d9d5593a-d0a4-c4be-ab08-493df59a85c6@gmail.com Signed-off-by: Yasuaki Ishimatsu Acked-by: Michal Hocko Cc: Xishi Qiu Cc: Reza Arbab Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index efd1ad37bb574..d4b5f29906b96 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -338,7 +338,7 @@ EXPORT_SYMBOL_GPL(__add_pages); #ifdef CONFIG_MEMORY_HOTREMOVE /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ -static int find_smallest_section_pfn(int nid, struct zone *zone, +static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { @@ -363,7 +363,7 @@ static int find_smallest_section_pfn(int nid, struct zone *zone, } /* find the biggest valid pfn in the range [start_pfn, end_pfn). */ -static int find_biggest_section_pfn(int nid, struct zone *zone, +static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { -- GitLab From 90ceb2a3ad868f800eb1c9f4ede650daddd94b77 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Oct 2017 16:16:35 -0700 Subject: [PATCH 0905/1507] kernel/params.c: fix the maximum length in param_get_string The length parameter of strlcpy() is supposed to reflect the size of the target buffer, not of the source string. Harmless in this case as the buffer is PAGE_SIZE long and the source string is always much shorter than this, but conceptually wrong, so let's fix it. Link: http://lkml.kernel.org/r/20170928162515.24846b4f@endymion Signed-off-by: Jean Delvare Acked-by: Ingo Molnar Cc: Baoquan He Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/params.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/params.c b/kernel/params.c index 1cd8f1a895a89..8283ba045f4f3 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -507,7 +507,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return strlcpy(buffer, kps->string, PAGE_SIZE); } EXPORT_SYMBOL(param_get_string); -- GitLab From 96802e6b1dbf29d3012b39503c5dd6d9d8e82955 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Oct 2017 16:16:38 -0700 Subject: [PATCH 0906/1507] kernel/params.c: fix an overflow in param_attr_show Function param_attr_show could overflow the buffer it is operating on. The buffer size is PAGE_SIZE, and the string returned by attribute->param->ops->get is generated by scnprintf(buffer, PAGE_SIZE, ...) so it could be PAGE_SIZE - 1 long, with the terminating '\0' at the very end of the buffer. Calling strcat(..., "\n") on this isn't safe, as the '\0' will be replaced by '\n' (OK) and then another '\0' will be added past the end of the buffer (not OK.) Simply add the trailing '\n' when writing the attribute contents to the buffer originally. This is safe, and also faster. Credits to Teradata for discovering this issue. Link: http://lkml.kernel.org/r/20170928162602.60c379c7@endymion Signed-off-by: Jean Delvare Acked-by: Ingo Molnar Cc: Baoquan He Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/params.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/kernel/params.c b/kernel/params.c index 8283ba045f4f3..0cca488263dd3 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, PAGE_SIZE); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } -- GitLab From e0596c80f442d1e1221c17dbb71b2aed43909221 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Oct 2017 16:16:41 -0700 Subject: [PATCH 0907/1507] kernel/params.c: improve STANDARD_PARAM_DEF readability Align the parameters passed to STANDARD_PARAM_DEF for clarity. Link: http://lkml.kernel.org/r/20170928162728.756143cc@endymion Signed-off-by: Jean Delvare Suggested-by: Ingo Molnar Acked-by: Ingo Molnar Cc: Baoquan He Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/params.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/kernel/params.c b/kernel/params.c index 0cca488263dd3..cc9108c2a1fde 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { -- GitLab From 656d61ce9666209c4c4a13c71902d3ee70d1ff6f Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Tue, 3 Oct 2017 16:16:45 -0700 Subject: [PATCH 0908/1507] lib/ratelimit.c: use deferred printk() version printk_ratelimit() invokes ___ratelimit() which may invoke a normal printk() (pr_warn() in this particular case) to warn about suppressed output. Given that printk_ratelimit() may be called from anywhere, that pr_warn() is dangerous - it may end up deadlocking the system. Fix ___ratelimit() by using deferred printk(). Sasha reported the following lockdep error: : Unregister pv shared memory for cpu 8 : select_fallback_rq: 3 callbacks suppressed : process 8583 (trinity-c78) no longer affine to cpu8 : : ====================================================== : WARNING: possible circular locking dependency detected : 4.14.0-rc2-next-20170927+ #252 Not tainted : ------------------------------------------------------ : migration/8/62 is trying to acquire lock: : (&port_lock_key){-.-.}, at: serial8250_console_write() : : but task is already holding lock: : (&rq->lock){-.-.}, at: sched_cpu_dying() : : which lock already depends on the new lock. : : : the existing dependency chain (in reverse order) is: : : -> #3 (&rq->lock){-.-.}: : __lock_acquire() : lock_acquire() : _raw_spin_lock() : task_fork_fair() : sched_fork() : copy_process.part.31() : _do_fork() : kernel_thread() : rest_init() : start_kernel() : x86_64_start_reservations() : x86_64_start_kernel() : verify_cpu() : : -> #2 (&p->pi_lock){-.-.}: : __lock_acquire() : lock_acquire() : _raw_spin_lock_irqsave() : try_to_wake_up() : default_wake_function() : woken_wake_function() : __wake_up_common() : __wake_up_common_lock() : __wake_up() : tty_wakeup() : tty_port_default_wakeup() : tty_port_tty_wakeup() : uart_write_wakeup() : serial8250_tx_chars() : serial8250_handle_irq.part.25() : serial8250_default_handle_irq() : serial8250_interrupt() : __handle_irq_event_percpu() : handle_irq_event_percpu() : handle_irq_event() : handle_level_irq() : handle_irq() : do_IRQ() : ret_from_intr() : native_safe_halt() : default_idle() : arch_cpu_idle() : default_idle_call() : do_idle() : cpu_startup_entry() : rest_init() : start_kernel() : x86_64_start_reservations() : x86_64_start_kernel() : verify_cpu() : : -> #1 (&tty->write_wait){-.-.}: : __lock_acquire() : lock_acquire() : _raw_spin_lock_irqsave() : __wake_up_common_lock() : __wake_up() : tty_wakeup() : tty_port_default_wakeup() : tty_port_tty_wakeup() : uart_write_wakeup() : serial8250_tx_chars() : serial8250_handle_irq.part.25() : serial8250_default_handle_irq() : serial8250_interrupt() : __handle_irq_event_percpu() : handle_irq_event_percpu() : handle_irq_event() : handle_level_irq() : handle_irq() : do_IRQ() : ret_from_intr() : native_safe_halt() : default_idle() : arch_cpu_idle() : default_idle_call() : do_idle() : cpu_startup_entry() : rest_init() : start_kernel() : x86_64_start_reservations() : x86_64_start_kernel() : verify_cpu() : : -> #0 (&port_lock_key){-.-.}: : check_prev_add() : __lock_acquire() : lock_acquire() : _raw_spin_lock_irqsave() : serial8250_console_write() : univ8250_console_write() : console_unlock() : vprintk_emit() : vprintk_default() : vprintk_func() : printk() : ___ratelimit() : __printk_ratelimit() : select_fallback_rq() : sched_cpu_dying() : cpuhp_invoke_callback() : take_cpu_down() : multi_cpu_stop() : cpu_stopper_thread() : smpboot_thread_fn() : kthread() : ret_from_fork() : : other info that might help us debug this: : : Chain exists of: : &port_lock_key --> &p->pi_lock --> &rq->lock : : Possible unsafe locking scenario: : : CPU0 CPU1 : ---- ---- : lock(&rq->lock); : lock(&p->pi_lock); : lock(&rq->lock); : lock(&port_lock_key); : : *** DEADLOCK *** : : 4 locks held by migration/8/62: : #0: (&p->pi_lock){-.-.}, at: sched_cpu_dying() : #1: (&rq->lock){-.-.}, at: sched_cpu_dying() : #2: (printk_ratelimit_state.lock){....}, at: ___ratelimit() : #3: (console_lock){+.+.}, at: vprintk_emit() : : stack backtrace: : CPU: 8 PID: 62 Comm: migration/8 Not tainted 4.14.0-rc2-next-20170927+ #252 : Call Trace: : dump_stack() : print_circular_bug() : check_prev_add() : ? add_lock_to_list.isra.26() : ? check_usage() : ? kvm_clock_read() : ? kvm_sched_clock_read() : ? sched_clock() : ? check_preemption_disabled() : __lock_acquire() : ? __lock_acquire() : ? add_lock_to_list.isra.26() : ? debug_check_no_locks_freed() : ? memcpy() : lock_acquire() : ? serial8250_console_write() : _raw_spin_lock_irqsave() : ? serial8250_console_write() : serial8250_console_write() : ? serial8250_start_tx() : ? lock_acquire() : ? memcpy() : univ8250_console_write() : console_unlock() : ? __down_trylock_console_sem() : vprintk_emit() : vprintk_default() : vprintk_func() : printk() : ? show_regs_print_info() : ? lock_acquire() : ___ratelimit() : __printk_ratelimit() : select_fallback_rq() : sched_cpu_dying() : ? sched_cpu_starting() : ? rcutree_dying_cpu() : ? sched_cpu_starting() : cpuhp_invoke_callback() : ? cpu_disable_common() : take_cpu_down() : ? trace_hardirqs_off_caller() : ? cpuhp_invoke_callback() : multi_cpu_stop() : ? __this_cpu_preempt_check() : ? cpu_stop_queue_work() : cpu_stopper_thread() : ? cpu_stop_create() : smpboot_thread_fn() : ? sort_range() : ? schedule() : ? __kthread_parkme() : kthread() : ? sort_range() : ? kthread_create_on_node() : ret_from_fork() : process 9121 (trinity-c78) no longer affine to cpu8 : smpboot: CPU 8 is now offline Link: http://lkml.kernel.org/r/20170928120405.18273-1-sergey.senozhatsky@gmail.com Fixes: 6b1d174b0c27b ("ratelimit: extend to print suppressed messages on release") Signed-off-by: Sergey Senozhatsky Reported-by: Sasha Levin Reviewed-by: Petr Mladek Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Steven Rostedt Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ratelimit.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 08f8043cac619..d01f471352390 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -48,7 +48,9 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) if (time_is_before_jiffies(rs->begin + rs->interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { - pr_warn("%s: %d callbacks suppressed\n", func, rs->missed); + printk_deferred(KERN_WARNING + "%s: %d callbacks suppressed\n", + func, rs->missed); rs->missed = 0; } } -- GitLab From d22e3d69ee1a3f83ff7cc943af63de48b6156dcf Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 3 Oct 2017 16:16:49 -0700 Subject: [PATCH 0909/1507] m32r: fix build failure The allmodconfig build of m32r is failing with the error: lib/mpi/mpih-div.o: In function 'mpihelp_divrem': mpih-div.c:(.text+0x40): undefined reference to 'abort' mpih-div.c:(.text+0x40): relocation truncated to fit: R_M32R_26_PCREL_RELA against undefined symbol 'abort' The function 'abort' was never defined for the m32r architecture. Create 'abort' as is done in other arch like 'arm' and 'unicore32'. Link: http://lkml.kernel.org/r/1506727220-6108-1-git-send-email-sudip.mukherjee@codethink.co.uk Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/kernel/traps.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index 647dd94a0c399..72b96f282689a 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -114,6 +114,15 @@ static void set_eit_vector_entries(void) _flush_cache_copyback_all(); } +void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} +EXPORT_SYMBOL(abort); + void __init trap_init(void) { set_eit_vector_entries(); -- GitLab From a08ffbef4ab799351d0610bbdbeaa1ee746b9065 Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Tue, 3 Oct 2017 16:16:51 -0700 Subject: [PATCH 0910/1507] checkpatch: fix ignoring cover-letter logic Currently running checkpatch on a directory with a cover-letter.patch file reports the following error: ----------------------------------------- patches/smp-v2/v2-0000-cover-letter.patch ----------------------------------------- ERROR: Does not appear to be a unified-diff format patch The logic to suppress the unified-diff check for cover letters is there but is checking $file instead of $filename. Fix the variable to use the correct one. Link: http://lkml.kernel.org/r/20170909090406.31523-1-shorne@gmail.com Signed-off-by: Stafford Horne Acked-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index dd2c262aebbf2..8b80bac055e49 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6390,7 +6390,7 @@ sub process { exit(0); } - if (!$is_patch && $file !~ /cover-letter\.patch$/) { + if (!$is_patch && $filename !~ /cover-letter\.patch$/) { ERROR("NOT_UNIFIED_DIFF", "Does not appear to be a unified-diff format patch\n"); } -- GitLab From 32e57c29e3c038ac802b7cc214a8795a4234055f Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 3 Oct 2017 16:16:54 -0700 Subject: [PATCH 0911/1507] include/linux/fs.h: fix comment about struct address_space Before commit 9c5d760b8d22 ("mm: split gfp_mask and mapping flags into separate fields") the private_* fields of struct adrress_space were grouped together and using "ditto" in comments describing the last fields was correct. With introduction of gpf_mask between private_lock and private_list "ditto" references the wrong description. Fix it by using the elaborate description. Link: http://lkml.kernel.org/r/1507009987-8746-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e736..13dab191a23e6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,7 +403,7 @@ struct address_space { unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* ditto */ + struct list_head private_list; /* for use by the address_space */ void *private_data; /* ditto */ errseq_t wb_err; } __attribute__((aligned(sizeof(long)))) __randomize_layout; -- GitLab From e4c77f8b9b213c6315faba109c03b0db873db200 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 18 Sep 2017 17:47:50 +0200 Subject: [PATCH 0912/1507] ARM: defconfig: FRAMEBUFFER_CONSOLE can no longer be =m It is no longer possible to load this at runtime, so let's change the few remaining users to have it built-in all the time. arch/arm/configs/zeus_defconfig:115:warning: symbol value 'm' invalid for FRAMEBUFFER_CONSOLE arch/arm/configs/viper_defconfig:116:warning: symbol value 'm' invalid for FRAMEBUFFER_CONSOLE arch/arm/configs/pxa_defconfig:474:warning: symbol value 'm' invalid for FRAMEBUFFER_CONSOLE Reported-by: kernelci.org bot Fixes: 6104c37094e7 ("fbcon: Make fbcon a built-time depency for fbdev") Signed-off-by: Arnd Bergmann Signed-off-by: Olof Johansson --- arch/arm/configs/pxa_defconfig | 2 +- arch/arm/configs/viper_defconfig | 2 +- arch/arm/configs/zeus_defconfig | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 64e3a2a8cedec..d5e1370ec303d 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -471,7 +471,7 @@ CONFIG_LCD_PLATFORM=m CONFIG_LCD_TOSA=m CONFIG_BACKLIGHT_PWM=m CONFIG_BACKLIGHT_TOSA=m -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y CONFIG_SOUND=m diff --git a/arch/arm/configs/viper_defconfig b/arch/arm/configs/viper_defconfig index 44d4fa57ba0a3..070e5074f1ee5 100644 --- a/arch/arm/configs/viper_defconfig +++ b/arch/arm/configs/viper_defconfig @@ -113,7 +113,7 @@ CONFIG_FB_PXA_PARAMETERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_BACKLIGHT_PWM=m # CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig index 8d4c0c926c344..09e7050d56532 100644 --- a/arch/arm/configs/zeus_defconfig +++ b/arch/arm/configs/zeus_defconfig @@ -112,7 +112,7 @@ CONFIG_FB_PXA=m CONFIG_FB_PXA_PARAMETERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y # CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=m +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m -- GitLab From 0694b2ee87ee1a6d83acf1a66b92c8e64ceb38f2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 17 Sep 2017 16:26:18 +0200 Subject: [PATCH 0913/1507] ARM: defconfig: update Gemini defconfig This updates the Gemini defconfig with drivers merged for v4.13 or v4.14: - ATA driver is merged - DMA driver is merged - RTC driver gets selected from default Kconfig Signed-off-by: Linus Walleij Signed-off-by: Olof Johansson --- arch/arm/configs/gemini_defconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index d2d75fa664a64..2a63fa10c8130 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -32,6 +32,7 @@ CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_ATA=y +CONFIG_PATA_FTIDE010=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -55,8 +56,8 @@ CONFIG_LEDS_GPIO=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_GEMINI=y CONFIG_DMADEVICES=y +CONFIG_AMBA_PL08X=y # CONFIG_DNOTIFY is not set CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y -- GitLab From 043d1e729b0fbaf2b69386fe45290b8a9a18a6a9 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Wed, 6 Sep 2017 21:21:08 +0300 Subject: [PATCH 0914/1507] ARC: [plat-axs103] Add temporary quirk to reset ethernet IP DW ethernet controller on AXS10x hangs sometimes after SW reset, so add temporary quirk to reset DW ethernet controller IP core. This quirk can be removed after axs10x reset driver (see http://patchwork.ozlabs.org/patch/800273/) or simple reset driver (see https://patchwork.kernel.org/patch/9903375/) will be available in upstream. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/plat-axs10x/axs10x.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c index f1ac6790da5fe..cf14ebc36916a 100644 --- a/arch/arc/plat-axs10x/axs10x.c +++ b/arch/arc/plat-axs10x/axs10x.c @@ -111,6 +111,13 @@ static void __init axs10x_early_init(void) axs10x_enable_gpio_intc_wire(); + /* + * Reset ethernet IP core. + * TODO: get rid of this quirk after axs10x reset driver (or simple + * reset driver) will be available in upstream. + */ + iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET); + scnprintf(mb, 32, "MainBoard v%d", mb_rev); axs10x_print_board_ver(CREG_MB_VER, mb); } -- GitLab From 6afa3bcf1f919c374d4606a7ed8078d3f67dfa90 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 8 Sep 2017 21:42:33 +0300 Subject: [PATCH 0915/1507] ARC: [plat-hsdk] sdio: Temporary fix of sdio ciu frequency DW sdio controller has external ciu clock divider controlled via register in SDIO IP. Due to its unexpected default value (it should divide by 1 but it divides by 8) SDIO IP uses wrong ciu clock and works unstable So add temporary fix and change clock frequency from 100000000 to 12500000 Hz until we fix dw sdio driver itself. Fixes SNPS STAR 9001204800 Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/hsdk.dts | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 229d13adbce42..daeef4ab2df91 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -120,7 +120,17 @@ gmacclk: gmacclk { mmcclk_ciu: mmcclk-ciu { compatible = "fixed-clock"; - clock-frequency = <100000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. Due to its + * unexpected default value (it should devide by 1 + * but it devides by 8) SDIO IP uses wrong clock and + * works unstable (see STAR 9001204800) + * So add temporary fix and change clock frequency + * from 100000000 to 12500000 Hz until we fix dw sdio + * driver itself. + */ + clock-frequency = <12500000>; #clock-cells = <0>; }; -- GitLab From 976e78a5226598cb582fe9ef98a72861adbc0e9c Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Tue, 12 Sep 2017 21:20:45 +0300 Subject: [PATCH 0916/1507] ARC: [plat-axs10x] sdio: Temporary fix of sdio ciu frequency DW sdio controller has external ciu clock divider controlled via register in SDIO IP. It divides sdio_ref_clk (which comes from CGU) by 16 for default. So default mmcclk clock (which comes to sdk_in) is 25000000 Hz. So fix wrong current value (50000000 Hz) to actual 25000000 Hz. Note this is a preventive fix, in line with similar change for HSDK where this was actually needed. see: http://lists.infradead.org/pipermail/linux-snps-arc/2017-September/002924.html Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/axs10x_mb.dtsi | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 2367a67c5f10b..e114000a84f56 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -44,7 +44,14 @@ apbclk: apbclk { mmcclk: mmcclk { compatible = "fixed-clock"; - clock-frequency = <50000000>; + /* + * DW sdio controller has external ciu clock divider + * controlled via register in SDIO IP. It divides + * sdio_ref_clk (which comes from CGU) by 16 for + * default. So default mmcclk clock (which comes + * to sdk_in) is 25000000 Hz. + */ + clock-frequency = <25000000>; #clock-cells = <0>; }; -- GitLab From 9583833e9e3628177661e815e5ce80dd3955d82f Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Fri, 8 Sep 2017 23:12:59 +0300 Subject: [PATCH 0917/1507] ARC: [*defconfig] Reenable soft lock-up detector Commit 92e5aae45778 "kernel/watchdog: split up config options" introduced SOFTLOCKUP_DETECTOR which selects LOCKUP_DETECTOR instead of the latter to be selected itself. We need to adjust our defconfigs accordingly. Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/configs/axs101_defconfig | 2 +- arch/arc/configs/axs103_defconfig | 2 +- arch/arc/configs/axs103_smp_defconfig | 2 +- arch/arc/configs/haps_hs_smp_defconfig | 2 +- arch/arc/configs/hsdk_defconfig | 2 +- arch/arc/configs/vdk_hs38_defconfig | 2 +- arch/arc/configs/vdk_hs38_smp_defconfig | 2 +- 7 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 6980b966a3640..ec7c849a5c8e9 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -105,7 +105,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 2233f5777a71f..63d3cf69e0b02 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -104,7 +104,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 30a3d4cf53d20..f613ecac14a75 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -107,7 +107,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 821a2e562f3f1..3507be2af6fe3 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -84,5 +84,5 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9a3fcf4463882..7b8f8faf8a243 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -72,7 +72,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index c0d6a010751a9..4fcf4f2503f61 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -94,7 +94,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 5c0971787acf4..7b71464f6c2f2 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -98,7 +98,7 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_SHIRQ=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10 # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set -- GitLab From ef833eab1ddec06982ea620086b03d67ef4ddf9b Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Mon, 4 Sep 2017 12:48:43 +0300 Subject: [PATCH 0918/1507] ARC: [plat-hsdk] use actual clk driver to manage cpu clk With corresponding clk driver now merged upstream, switch to it. - core_clk now represent the PLL (vs. fixed clk before) - input_clk represent the clk signal src for PLL (basically xtal) Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/hsdk.dts | 11 +++++++++-- arch/arc/plat-hsdk/Kconfig | 3 ++- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index daeef4ab2df91..b922f3faf5549 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -57,10 +57,10 @@ cpu@3 { }; }; - core_clk: core-clk { + input_clk: input-clk { #clock-cells = <0>; compatible = "fixed-clock"; - clock-frequency = <500000000>; + clock-frequency = <33333333>; }; cpu_intc: cpu-interrupt-controller { @@ -102,6 +102,13 @@ soc { ranges = <0x00000000 0xf0000000 0x10000000>; + core_clk: core-clk@0 { + compatible = "snps,hsdk-core-pll-clock"; + reg = <0x00 0x10>, <0x14B8 0x4>; + #clock-cells = <0>; + clocks = <&input_clk>; + }; + serial: serial@5000 { compatible = "snps,dw-apb-uart"; reg = <0x5000 0x100>; diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 5a6ed5afb009a..bd08de4be75e7 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -6,4 +6,5 @@ # menuconfig ARC_SOC_HSDK - bool "ARC HS Development Kit SOC" + bool "ARC HS Development Kit SOC" + select CLK_HSDK -- GitLab From bd6d3588c834e3087ad0229ff0da651bbccf5e24 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 11 Sep 2017 09:48:46 -0700 Subject: [PATCH 0919/1507] ARC: [plat-eznps] Update platform maintainer as Noam left Signed-off-by: Vineet Gupta --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 65b0c88d5ee0d..42bfa57673ed0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5259,7 +5259,8 @@ S: Maintained F: drivers/iommu/exynos-iommu.c EZchip NPS platform support -M: Noam Camus +M: Elad Kanfi +M: Vineet Gupta S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts -- GitLab From d9bc84a808572451f95fb1dde80cb8d12be05665 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 20 Sep 2017 20:25:30 +0900 Subject: [PATCH 0920/1507] arc: remove redundant UTS_MACHINE define in arch/arc/Makefile The top-level Makefile sets the default of UTS_MACHINE to $(ARCH). If ARCH and UTS_MACHINE match, arch/$(ARCH)/Makefile need not specify UTS_MACHINE explicitly. Signed-off-by: Masahiro Yamada Signed-off-by: Vineet Gupta --- arch/arc/Makefile | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 3a4b52b7e09d6..d37f49d6a27f4 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,8 +6,6 @@ # published by the Free Software Foundation. # -UTS_MACHINE := arc - ifeq ($(CROSS_COMPILE),) ifndef CONFIG_CPU_BIG_ENDIAN CROSS_COMPILE := arc-linux- -- GitLab From 010a8c98884f4ca42a167c9b51470c624daa2932 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 21 Sep 2017 17:46:38 -0700 Subject: [PATCH 0921/1507] ARC: boot log: decontaminate ARCv2 ISA_CONFIG register ARCv2 ISA_CONFIG and ARC700_BUILD build config registers are not compatible. cpuinfo_arc had isa info placeholder which was mashup of bits form both. Untangle this by defining it off of ARCv2 ISA info and it is fine even for ARC700 since former is a super set of latter (ARC700 buildonly has 2 bits for atomics and stack check). At runtime, we treat ARCv2 ISA info as a generic placeholder but populate it correctly depending on ARC700 or HS. This paves way for adding more HS specific bits in isa info which was colliding with the extra bits for arc700. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 8 ++++---- arch/arc/kernel/setup.c | 15 +++++++++++---- 2 files changed, 15 insertions(+), 8 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index ba8e802dba80b..b71d84873f7dc 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -135,12 +135,12 @@ struct bcr_identity { #endif }; -struct bcr_isa { +struct bcr_isa_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1, - pad1:11, atomic1:1, ver:8; + pad1:12, ver:8; #else - unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1, + unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1, ldd:1, pad2:4, div_rem:4; #endif }; @@ -263,7 +263,7 @@ struct cpuinfo_arc { struct cpuinfo_arc_mmu mmu; struct cpuinfo_arc_bpu bpu; struct bcr_identity core; - struct bcr_isa isa; + struct bcr_isa_arcv2 isa; const char *details, *name; unsigned int vec_base; struct cpuinfo_arc_ccm iccm, dccm; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 877cec8f5ea21..228593a964f83 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -119,11 +119,11 @@ static void read_arc_build_cfg_regs(void) struct bcr_generic bcr; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; const struct id_to_str *tbl; + struct bcr_isa_arcv2 isa; FIX_PTR(cpu); READ_BCR(AUX_IDENTITY, cpu->core); - READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa); for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) { if (cpu->core.family == tbl->id) { @@ -205,18 +205,25 @@ static void read_arc_build_cfg_regs(void) cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt; + READ_BCR(ARC_REG_ISA_CFG_BCR, isa); + /* some hacks for lack of feature BCR info in old ARC700 cores */ if (is_isa_arcompact()) { - if (!cpu->isa.ver) /* ISA BCR absent, use Kconfig info */ + if (!isa.ver) /* ISA BCR absent, use Kconfig info */ cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC); - else - cpu->isa.atomic = cpu->isa.atomic1; + else { + /* ARC700_BUILD only has 2 bits of isa info */ + struct bcr_generic bcr = *(struct bcr_generic *)&isa; + cpu->isa.atomic = bcr.info & 1; + } cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); /* there's no direct way to distinguish 750 vs. 770 */ if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3)) cpu->name = "ARC750"; + } else { + cpu->isa = isa; } } -- GitLab From dea8252059a3210340f255bf69d67225b9af552d Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 21 Sep 2017 18:02:44 -0700 Subject: [PATCH 0922/1507] ARCv2: boot log: identify HS48 cores (dual issue) Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 3 ++- arch/arc/kernel/setup.c | 17 ++++++++++++++--- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index b71d84873f7dc..b1c56d35f2a93 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -98,6 +98,7 @@ /* Auxiliary registers */ #define AUX_IDENTITY 4 +#define AUX_EXEC_CTRL 8 #define AUX_INTR_VEC_BASE 0x25 #define AUX_VOL 0x5e @@ -269,7 +270,7 @@ struct cpuinfo_arc { struct cpuinfo_arc_ccm iccm, dccm; struct { unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2, - fpu_sp:1, fpu_dp:1, pad2:6, + fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4, debug:1, ap:1, smart:1, rtt:1, pad3:4, timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4; } extn; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 228593a964f83..fb83844daeea3 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,6 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, + { 0x54, "R4.0" }, #endif { 0x00, NULL } }; @@ -62,6 +63,7 @@ static const struct id_to_str arc_cpu_nm[] = { #else { 0x40, "ARC EM" }, { 0x50, "ARC HS38" }, + { 0x54, "ARC HS48" }, #endif { 0x00, "Unknown" } }; @@ -133,7 +135,7 @@ static void read_arc_build_cfg_regs(void) } for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) { - if ((cpu->core.family & 0xF0) == tbl->id) + if ((cpu->core.family & 0xF4) == tbl->id) break; } cpu->name = tbl->str; @@ -192,6 +194,14 @@ static void read_arc_build_cfg_regs(void) cpu->bpu.full = bpu.ft; cpu->bpu.num_cache = 256 << bpu.bce; cpu->bpu.num_pred = 2048 << bpu.pte; + + if (cpu->core.family >= 0x54) { + unsigned int exec_ctrl; + + READ_BCR(AUX_EXEC_CTRL, exec_ctrl); + cpu->extn.dual_iss_exist = 1; + cpu->extn.dual_iss_enb = exec_ctrl & 1; + } } READ_BCR(ARC_REG_AP_BCR, bcr); @@ -239,10 +249,11 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n", core->family, core->cpu_id, core->chip_id); - n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n", + n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n", cpu_id, cpu->name, cpu->details, is_isa_arcompact() ? "ARCompact" : "ARCv2", - IS_AVAIL1(cpu->isa.be, "[Big-Endian]")); + IS_AVAIL1(cpu->isa.be, "[Big-Endian]"), + IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue")); n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ", IS_AVAIL1(cpu->extn.timer0, "Timer0 "), -- GitLab From 5464d03d92601ac2977ef605b0cbb33276567daf Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 29 Sep 2017 14:46:50 -0700 Subject: [PATCH 0923/1507] ARC: fix allnoconfig build warning Reported-by: Dmitrii Kolesnichenko Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index a598641eed98e..c84e67fdea095 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -24,7 +24,7 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_FUTEX_CMPXCHG + select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES -- GitLab From edb40d74c08edfd049cbba15479dadd9aeb7d307 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Thu, 28 Sep 2017 17:33:29 +0300 Subject: [PATCH 0924/1507] ARC: [plat-hsdk]: Temporary fix to set CPU frequency to 1GHz Add temporary fix to HSDK platform code to setup CPU frequency to 1GHz on early boot. We can remove this fix when smart hsdk pll driver will be introduced, see discussion: https://www.mail-archive.com/linux-snps-arc@lists.infradead.org/msg02689.html Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/plat-hsdk/platform.c | 42 +++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index a2e7fd17e36d3..744e62e587889 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -38,6 +38,42 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define CREG_PAE (CREG_BASE + 0x180) #define CREG_PAE_UPDATE (CREG_BASE + 0x194) +#define CREG_CORE_IF_CLK_DIV (CREG_BASE + 0x4B8) +#define CREG_CORE_IF_CLK_DIV_2 0x1 +#define CGU_BASE ARC_PERIPHERAL_BASE +#define CGU_PLL_STATUS (ARC_PERIPHERAL_BASE + 0x4) +#define CGU_PLL_CTRL (ARC_PERIPHERAL_BASE + 0x0) +#define CGU_PLL_STATUS_LOCK BIT(0) +#define CGU_PLL_STATUS_ERR BIT(1) +#define CGU_PLL_CTRL_1GHZ 0x3A10 +#define HSDK_PLL_LOCK_TIMEOUT 500 + +#define HSDK_PLL_LOCKED() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK) + +#define HSDK_PLL_ERR() \ + !!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR) + +static void __init hsdk_set_cpu_freq_1ghz(void) +{ + u32 timeout = HSDK_PLL_LOCK_TIMEOUT; + + /* + * As we set cpu clock which exceeds 500MHz, the divider for the interface + * clock must be programmed to div-by-2. + */ + iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV); + + /* Set cpu clock to 1GHz */ + iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL); + + while (!HSDK_PLL_LOCKED() && timeout--) + cpu_relax(); + + if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR()) + pr_err("Failed to setup CPU frequency to 1GHz!"); +} + static void __init hsdk_init_early(void) { /* @@ -52,6 +88,12 @@ static void __init hsdk_init_early(void) /* Really apply settings made above */ writel(1, (void __iomem *) CREG_PAE_UPDATE); + + /* + * Setup CPU frequency to 1GHz. + * TODO: remove it after smart hsdk pll driver will be introduced. + */ + hsdk_set_cpu_freq_1ghz(); } static const char *hsdk_compat[] __initconst = { -- GitLab From 52bfcdd7adbc26639bc7b2356ab9a3f5dad68ad6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 18 Sep 2017 09:41:18 -0700 Subject: [PATCH 0925/1507] xfs: always swap the cow forks when swapping extents Since the CoW fork exists as a secondary data structure to the data fork, we must always swap cow forks during swapext. We also need to swap the extent counts and reset the cowblocks tags. Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_bmap_util.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index bc6c6e10a9699..e9db7fc95b70b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -2122,11 +2122,31 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); -- GitLab From e12199f85d0ad1b04ce6c425ad93cd847fe930bb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Oct 2017 08:58:33 -0700 Subject: [PATCH 0926/1507] xfs: handle racy AIO in xfs_reflink_end_cow If we got two AIO writes into a COW area the second one might not have any COW extents left to convert. Handle that case gracefully instead of triggering an assert or accessing beyond the bounds of the extent list. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_reflink.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 3246815c24d65..37e603bf15913 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -736,7 +736,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_iext_get_extent(ifp, --idx, &got); } @@ -809,6 +815,7 @@ xfs_reflink_end_cow( out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: -- GitLab From acd669a8f67ed47f5edd385741486cc7a259a446 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Tue, 3 Oct 2017 11:10:53 +0530 Subject: [PATCH 0927/1507] cxgb4: add new T6 pci device id's Add 0x6085 T6 device id. Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 37d90d63e4a3f..633e9751a25e7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -202,6 +202,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x6082), /* Custom T6225-CR SFP28 */ CH_PCI_ID_TABLE_FENTRY(0x6083), /* Custom T62100-CR QSFP28 */ CH_PCI_ID_TABLE_FENTRY(0x6084), /* Custom T64100-CR QSFP28 */ + CH_PCI_ID_TABLE_FENTRY(0x6085), /* Custom T6240-SO */ CH_PCI_DEVICE_ID_TABLE_DEFINE_END; #endif /* __T4_PCI_ID_TBL_H__ */ -- GitLab From 57e7ba04d422c3d41c8426380303ec9b7533ded9 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Tue, 19 Sep 2017 09:39:08 -0700 Subject: [PATCH 0928/1507] lsm: fix smack_inode_removexattr and xattr_getsecurity memleak security_inode_getsecurity() provides the text string value of a security attribute. It does not provide a "secctx". The code in xattr_getsecurity() that calls security_inode_getsecurity() and then calls security_release_secctx() happened to work because SElinux and Smack treat the attribute and the secctx the same way. It fails for cap_inode_getsecurity(), because that module has no secctx that ever needs releasing. It turns out that Smack is the one that's doing things wrong by not allocating memory when instructed to do so by the "alloc" parameter. The fix is simple enough. Change the security_release_secctx() to kfree() because it isn't a secctx being returned by security_inode_getsecurity(). Change Smack to allocate the string when told to do so. Note: this also fixes memory leaks for LSMs which implement inode_getsecurity but not release_secctx, such as capabilities. Signed-off-by: Casey Schaufler Reported-by: Konstantin Khlebnikov Cc: stable@vger.kernel.org Signed-off-by: James Morris --- fs/xattr.c | 2 +- security/smack/smack_lsm.c | 55 +++++++++++++++++--------------------- 2 files changed, 26 insertions(+), 31 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index 4424f7fecf145..61cd28ba25f36 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -250,7 +250,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value, } memcpy(value, buffer, len); out: - security_release_secctx(buffer, len); + kfree(buffer); out_noalloc: return len; } diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 319add31b4a4e..286171a16ed25 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1473,7 +1473,7 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name) * @inode: the object * @name: attribute name * @buffer: where to put the result - * @alloc: unused + * @alloc: duplicate memory * * Returns the size of the attribute or an error code */ @@ -1486,43 +1486,38 @@ static int smack_inode_getsecurity(struct inode *inode, struct super_block *sbp; struct inode *ip = (struct inode *)inode; struct smack_known *isp; - int ilen; - int rc = 0; - if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) { + if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) isp = smk_of_inode(inode); - ilen = strlen(isp->smk_known); - *buffer = isp->smk_known; - return ilen; - } + else { + /* + * The rest of the Smack xattrs are only on sockets. + */ + sbp = ip->i_sb; + if (sbp->s_magic != SOCKFS_MAGIC) + return -EOPNOTSUPP; - /* - * The rest of the Smack xattrs are only on sockets. - */ - sbp = ip->i_sb; - if (sbp->s_magic != SOCKFS_MAGIC) - return -EOPNOTSUPP; + sock = SOCKET_I(ip); + if (sock == NULL || sock->sk == NULL) + return -EOPNOTSUPP; - sock = SOCKET_I(ip); - if (sock == NULL || sock->sk == NULL) - return -EOPNOTSUPP; - - ssp = sock->sk->sk_security; + ssp = sock->sk->sk_security; - if (strcmp(name, XATTR_SMACK_IPIN) == 0) - isp = ssp->smk_in; - else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) - isp = ssp->smk_out; - else - return -EOPNOTSUPP; + if (strcmp(name, XATTR_SMACK_IPIN) == 0) + isp = ssp->smk_in; + else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) + isp = ssp->smk_out; + else + return -EOPNOTSUPP; + } - ilen = strlen(isp->smk_known); - if (rc == 0) { - *buffer = isp->smk_known; - rc = ilen; + if (alloc) { + *buffer = kstrdup(isp->smk_known, GFP_KERNEL); + if (*buffer == NULL) + return -ENOMEM; } - return rc; + return strlen(isp->smk_known); } -- GitLab From de3ee99b097dd51938276e3af388cd4ad0f2750a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 20 Sep 2017 10:56:14 +0200 Subject: [PATCH 0929/1507] mmc: Delete bounce buffer handling In may, Steven sent a patch deleting the bounce buffer handling and the CONFIG_MMC_BLOCK_BOUNCE option. I chose the less invasive path of making it a runtime config option, and we merged that successfully for kernel v4.12. The code is however just standing in the way and taking up space for seemingly no gain on any systems in wide use today. Pierre says the code was there to improve speed on TI SDHCI controllers on certain HP laptops and possibly some Ricoh controllers as well. Early SDHCI controllers lacked the scatter-gather feature, which made software bounce buffers a significant speed boost. We are clearly talking about the list of SDHCI PCI-based MMC/SD card readers found in the pci_ids[] list in drivers/mmc/host/sdhci-pci-core.c. The TI SDHCI derivative is not supported by the upstream kernel. This leaves the Ricoh. What we can however notice is that the x86 defconfigs in the kernel did not enable CONFIG_MMC_BLOCK_BOUNCE option, which means that any such laptop would have to have a custom configured kernel to actually take advantage of this bounce buffer speed-up. It simply seems like there was a speed optimization for the Ricoh controllers that noone was using. (I have not checked the distro defconfigs but I am pretty sure the situation is the same there.) Bounce buffers increased performance on the OMAP HSMMC at one point, and was part of the original submission in commit a45c6cb81647 ("[ARM] 5369/1: omap mmc: Add new omap hsmmc controller for 2430 and 34xx, v3") This optimization was removed in commit 0ccd76d4c236 ("omap_hsmmc: Implement scatter-gather emulation") which found that scatter-gather emulation provided even better performance. The same was introduced for SDHCI in commit 2134a922c6e7 ("sdhci: scatter-gather (ADMA) support") I am pretty positively convinced that software scatter-gather emulation will do for any host controller what the bounce buffers were doing. Essentially, the bounce buffer was a reimplementation of software scatter-gather-emulation in the MMC subsystem, and it should be done away with. Cc: Pierre Ossman Cc: Juha Yrjola Cc: Steven J. Hill Cc: Shawn Lin Cc: Adrian Hunter Suggested-by: Steven J. Hill Suggested-by: Shawn Lin Signed-off-by: Linus Walleij Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 3 - drivers/mmc/core/queue.c | 125 +++----------------------------------- drivers/mmc/core/queue.h | 6 -- drivers/mmc/host/cavium.c | 2 +- drivers/mmc/host/pxamci.c | 6 +- include/linux/mmc/host.h | 2 +- 6 files changed, 12 insertions(+), 132 deletions(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 29fc1e662891d..2ad7b5c691569 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1634,8 +1634,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq, } mqrq->areq.mrq = &brq->mrq; - - mmc_queue_bounce_pre(mqrq); } static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, @@ -1829,7 +1827,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req) brq = &mq_rq->brq; old_req = mmc_queue_req_to_req(mq_rq); type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE; - mmc_queue_bounce_post(mq_rq); switch (status) { case MMC_BLK_SUCCESS: diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 74c663b1c0a74..0a4e77a5ba33f 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -23,8 +23,6 @@ #include "core.h" #include "card.h" -#define MMC_QUEUE_BOUNCESZ 65536 - /* * Prepare a MMC request. This just filters out odd stuff. */ @@ -150,26 +148,6 @@ static void mmc_queue_setup_discard(struct request_queue *q, queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q); } -static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host) -{ - unsigned int bouncesz = MMC_QUEUE_BOUNCESZ; - - if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF)) - return 0; - - if (bouncesz > host->max_req_size) - bouncesz = host->max_req_size; - if (bouncesz > host->max_seg_size) - bouncesz = host->max_seg_size; - if (bouncesz > host->max_blk_count * 512) - bouncesz = host->max_blk_count * 512; - - if (bouncesz <= 512) - return 0; - - return bouncesz; -} - /** * mmc_init_request() - initialize the MMC-specific per-request data * @q: the request queue @@ -184,26 +162,9 @@ static int mmc_init_request(struct request_queue *q, struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; - if (card->bouncesz) { - mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp); - if (!mq_rq->bounce_buf) - return -ENOMEM; - if (card->bouncesz > 512) { - mq_rq->sg = mmc_alloc_sg(1, gfp); - if (!mq_rq->sg) - return -ENOMEM; - mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512, - gfp); - if (!mq_rq->bounce_sg) - return -ENOMEM; - } - } else { - mq_rq->bounce_buf = NULL; - mq_rq->bounce_sg = NULL; - mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); - if (!mq_rq->sg) - return -ENOMEM; - } + mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp); + if (!mq_rq->sg) + return -ENOMEM; return 0; } @@ -212,13 +173,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req) { struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req); - /* It is OK to kfree(NULL) so this will be smooth */ - kfree(mq_rq->bounce_sg); - mq_rq->bounce_sg = NULL; - - kfree(mq_rq->bounce_buf); - mq_rq->bounce_buf = NULL; - kfree(mq_rq->sg); mq_rq->sg = NULL; } @@ -242,12 +196,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; - /* - * mmc_init_request() depends on card->bouncesz so it must be calculated - * before blk_init_allocated_queue() starts allocating requests. - */ - card->bouncesz = mmc_queue_calc_bouncesz(host); - mq->card = card; mq->queue = blk_alloc_queue(GFP_KERNEL); if (!mq->queue) @@ -271,17 +219,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, if (mmc_can_erase(card)) mmc_queue_setup_discard(mq->queue, card); - if (card->bouncesz) { - blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512); - blk_queue_max_segments(mq->queue, card->bouncesz / 512); - blk_queue_max_segment_size(mq->queue, card->bouncesz); - } else { - blk_queue_bounce_limit(mq->queue, limit); - blk_queue_max_hw_sectors(mq->queue, - min(host->max_blk_count, host->max_req_size / 512)); - blk_queue_max_segments(mq->queue, host->max_segs); - blk_queue_max_segment_size(mq->queue, host->max_seg_size); - } + blk_queue_bounce_limit(mq->queue, limit); + blk_queue_max_hw_sectors(mq->queue, + min(host->max_blk_count, host->max_req_size / 512)); + blk_queue_max_segments(mq->queue, host->max_segs); + blk_queue_max_segment_size(mq->queue, host->max_seg_size); sema_init(&mq->thread_sem, 1); @@ -370,56 +312,7 @@ void mmc_queue_resume(struct mmc_queue *mq) */ unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) { - unsigned int sg_len; - size_t buflen; - struct scatterlist *sg; struct request *req = mmc_queue_req_to_req(mqrq); - int i; - - if (!mqrq->bounce_buf) - return blk_rq_map_sg(mq->queue, req, mqrq->sg); - - sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg); - - mqrq->bounce_sg_len = sg_len; - - buflen = 0; - for_each_sg(mqrq->bounce_sg, sg, sg_len, i) - buflen += sg->length; - - sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen); - - return 1; -} - -/* - * If writing, bounce the data to the buffer before the request - * is sent to the host driver - */ -void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE) - return; - - sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); -} - -/* - * If reading, bounce the data from the buffer after the request - * has been handled by the host driver - */ -void mmc_queue_bounce_post(struct mmc_queue_req *mqrq) -{ - if (!mqrq->bounce_buf) - return; - - if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ) - return; - sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, - mqrq->bounce_buf, mqrq->sg[0].length); + return blk_rq_map_sg(mq->queue, req, mqrq->sg); } diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 04fc89360a7a1..f18d3f656baa5 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -49,9 +49,6 @@ enum mmc_drv_op { struct mmc_queue_req { struct mmc_blk_request brq; struct scatterlist *sg; - char *bounce_buf; - struct scatterlist *bounce_sg; - unsigned int bounce_sg_len; struct mmc_async_req areq; enum mmc_drv_op drv_op; int drv_op_result; @@ -81,11 +78,8 @@ extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); - extern unsigned int mmc_queue_map_sg(struct mmc_queue *, struct mmc_queue_req *); -extern void mmc_queue_bounce_pre(struct mmc_queue_req *); -extern void mmc_queue_bounce_post(struct mmc_queue_req *); extern int mmc_access_rpmb(struct mmc_queue *); diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c index 27fb625cbcf3f..fbd29f00fca05 100644 --- a/drivers/mmc/host/cavium.c +++ b/drivers/mmc/host/cavium.c @@ -1038,7 +1038,7 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host) */ mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD | - MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF; + MMC_CAP_3_3V_DDR; if (host->use_sg) mmc->max_segs = 16; diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 59ab194cb0099..c763b404510f3 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -702,11 +702,7 @@ static int pxamci_probe(struct platform_device *pdev) pxamci_init_ocr(host); - /* - * This architecture used to disable bounce buffers through its - * defconfig, now it is done at runtime as a host property. - */ - mmc->caps = MMC_CAP_NO_BOUNCE_BUFF; + mmc->caps = 0; host->cmdat = 0; if (!cpu_is_pxa25x()) { mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f3f2d07feb2a6..9a43763a68adb 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -316,7 +316,7 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 18) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 19) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 20) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_NO_BOUNCE_BUFF (1 << 21) /* Disable bounce buffers on host */ +/* (1 << 21) is free for reuse */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ -- GitLab From ca3dcd3ff5b13a31a09a0119dc484b97ec19c4c8 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Mon, 2 Oct 2017 14:27:41 +0200 Subject: [PATCH 0930/1507] mmc: meson-gx: make sure the clock is rounded down Using CLK_DIVIDER_ROUND_CLOSEST is unsafe as the mmc clock could be rounded to a rate higher the specified rate. Removing this flag ensure that, if the rate needs to be rounded, it will be rounded down. Fixes: 51c5d8447bd7 ("MMC: meson: initial support for GX platforms") Signed-off-by: Jerome Brunet Reviewed-by: Kevin Hilman Signed-off-by: Ulf Hansson --- drivers/mmc/host/meson-gx-mmc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index c885c2d4b9041..421c8719c2028 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -531,8 +531,7 @@ static int meson_mmc_clk_init(struct meson_host *host) div->shift = __ffs(CLK_DIV_MASK); div->width = __builtin_popcountl(CLK_DIV_MASK); div->hw.init = &init; - div->flags = (CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ROUND_CLOSEST); + div->flags = CLK_DIVIDER_ONE_BASED; clk = devm_clk_register(host->dev, &div->hw); if (WARN_ON(IS_ERR(clk))) -- GitLab From 3e2b0af411d4bf85bc0fbc385756fd5968adb9fd Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Mon, 2 Oct 2017 14:27:42 +0200 Subject: [PATCH 0931/1507] mmc: meson-gx: fix rx phase reset Resetting the phase when POWER_ON is set the set_ios() call means that the phase is reset almost every time the set_ios() is called, while the expected behavior was to reset the phase on a power cycle. This had gone unnoticed until now because in all mode (except hs400) the tuning is done after the last to set_ios(). In such case, the tuning result is used anyway. In HS400, there are a few calls to set_ios() after the tuning is done, overwriting the tuning result. Resetting the phase on POWER_UP instead of POWER_ON solve the problem. Fixes: d341ca88eead ("mmc: meson-gx: rework tuning function") Signed-off-by: Jerome Brunet Reviewed-by: Kevin Hilman Signed-off-by: Ulf Hansson --- drivers/mmc/host/meson-gx-mmc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 421c8719c2028..08a55c2e96e1b 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -745,6 +745,10 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_UP: if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); + + /* Reset rx phase */ + clk_set_phase(host->rx_clk, 0); + break; case MMC_POWER_ON: @@ -758,8 +762,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->vqmmc_enabled = true; } - /* Reset rx phase */ - clk_set_phase(host->rx_clk, 0); break; } -- GitLab From 0a44697627d17a66d7dc98f17aeca07ca79c5c20 Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Mon, 2 Oct 2017 14:27:43 +0200 Subject: [PATCH 0932/1507] mmc: meson-gx: include tx phase in the tuning process It has been reported that some platforms (odroid-c2) may require a different tx phase setting to operate at high speed (hs200 and hs400) To improve the situation, this patch includes tx phase in the tuning process. Fixes: d341ca88eead ("mmc: meson-gx: rework tuning function") Reported-by: Heiner Kallweit Signed-off-by: Jerome Brunet Reviewed-by: Kevin Hilman Signed-off-by: Ulf Hansson --- drivers/mmc/host/meson-gx-mmc.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 08a55c2e96e1b..85745ef179e22 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -716,6 +716,22 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode, static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct meson_host *host = mmc_priv(mmc); + int ret; + + /* + * If this is the initial tuning, try to get a sane Rx starting + * phase before doing the actual tuning. + */ + if (!mmc->doing_retune) { + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); + + if (ret) + return ret; + } + + ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk); + if (ret) + return ret; return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk); } @@ -746,8 +762,9 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (!IS_ERR(mmc->supply.vmmc)) mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd); - /* Reset rx phase */ + /* Reset phases */ clk_set_phase(host->rx_clk, 0); + clk_set_phase(host->tx_clk, 270); break; -- GitLab From bb16ea1742c8f35a9349b7508dc45d3a922db5f5 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Mon, 2 Oct 2017 16:58:52 +0200 Subject: [PATCH 0933/1507] mmc: sdhci-xenon: Fix clock resource by adding an optional bus clock On Armada 7K/8K we need to explicitly enable the bus clock. The bus clock is optional because not all the SoCs need them but at least for Armada 7K/8K it is actually mandatory. The binding documentation is updating accordingly. Without this patch the kernel hand during boot if the mvpp2.2 network driver was not present in the kernel. Indeed the clock needed by the xenon controller was set by the network driver. Fixes: 3a3748dba881 ("mmc: sdhci-xenon: Add Marvell Xenon SDHC core functionality)" CC: Stable Tested-by: Zhoujie Wu Signed-off-by: Gregory CLEMENT Signed-off-by: Ulf Hansson --- .../bindings/mmc/marvell,xenon-sdhci.txt | 12 ++++++---- drivers/mmc/host/sdhci-xenon.c | 24 +++++++++++++++---- drivers/mmc/host/sdhci-xenon.h | 1 + 3 files changed, 28 insertions(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt index b878a1e305af6..ed1456f5c94dd 100644 --- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt @@ -16,11 +16,13 @@ Required Properties: - clocks: Array of clocks required for SDHC. - Require at least input clock for Xenon IP core. + Require at least input clock for Xenon IP core. For Armada AP806 and + CP110, the AXI clock is also mandatory. - clock-names: Array of names corresponding to clocks property. The input clock for Xenon IP core should be named as "core". + The input clock for the AXI bus must be named as "axi". - reg: * For "marvell,armada-3700-sdhci", two register areas. @@ -106,8 +108,8 @@ Example: compatible = "marvell,armada-ap806-sdhci"; reg = <0xaa0000 0x1000>; interrupts = - clocks = <&emmc_clk>; - clock-names = "core"; + clocks = <&emmc_clk>,<&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-phy-slow-mode; marvell,xenon-tun-count = <11>; @@ -126,8 +128,8 @@ Example: interrupts = vqmmc-supply = <&sd_vqmmc_regulator>; vmmc-supply = <&sd_vmmc_regulator>; - clocks = <&sdclk>; - clock-names = "core"; + clocks = <&sdclk>, <&axi_clk>; + clock-names = "core", "axi"; bus-width = <4>; marvell,xenon-tun-count = <9>; }; diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 2eec2e652c53d..0842bbc2d7ad3 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -466,6 +466,7 @@ static int xenon_probe(struct platform_device *pdev) { struct sdhci_pltfm_host *pltfm_host; struct sdhci_host *host; + struct xenon_priv *priv; int err; host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata, @@ -474,6 +475,7 @@ static int xenon_probe(struct platform_device *pdev) return PTR_ERR(host); pltfm_host = sdhci_priv(host); + priv = sdhci_pltfm_priv(pltfm_host); /* * Link Xenon specific mmc_host_ops function, @@ -491,9 +493,20 @@ static int xenon_probe(struct platform_device *pdev) if (err) goto free_pltfm; + priv->axi_clk = devm_clk_get(&pdev->dev, "axi"); + if (IS_ERR(priv->axi_clk)) { + err = PTR_ERR(priv->axi_clk); + if (err == -EPROBE_DEFER) + goto err_clk; + } else { + err = clk_prepare_enable(priv->axi_clk); + if (err) + goto err_clk; + } + err = mmc_of_parse(host->mmc); if (err) - goto err_clk; + goto err_clk_axi; sdhci_get_of_property(pdev); @@ -502,11 +515,11 @@ static int xenon_probe(struct platform_device *pdev) /* Xenon specific dt parse */ err = xenon_probe_dt(pdev); if (err) - goto err_clk; + goto err_clk_axi; err = xenon_sdhc_prepare(host); if (err) - goto err_clk; + goto err_clk_axi; pm_runtime_get_noresume(&pdev->dev); pm_runtime_set_active(&pdev->dev); @@ -527,6 +540,8 @@ static int xenon_probe(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); xenon_sdhc_unprepare(host); +err_clk_axi: + clk_disable_unprepare(priv->axi_clk); err_clk: clk_disable_unprepare(pltfm_host->clk); free_pltfm: @@ -538,6 +553,7 @@ static int xenon_remove(struct platform_device *pdev) { struct sdhci_host *host = platform_get_drvdata(pdev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); pm_runtime_get_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); @@ -546,7 +562,7 @@ static int xenon_remove(struct platform_device *pdev) sdhci_remove_host(host, 0); xenon_sdhc_unprepare(host); - + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(pltfm_host->clk); sdhci_pltfm_free(pdev); diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h index 2bc0510c07696..9994995c7c568 100644 --- a/drivers/mmc/host/sdhci-xenon.h +++ b/drivers/mmc/host/sdhci-xenon.h @@ -83,6 +83,7 @@ struct xenon_priv { unsigned char bus_width; unsigned char timing; unsigned int clock; + struct clk *axi_clk; int phy_type; /* -- GitLab From 6b9dc4806b28214a4a260517e59439e0ac12a15e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 2 Oct 2017 12:34:50 +0200 Subject: [PATCH 0934/1507] watchdog/core, powerpc: Replace watchdog_nmi_reconfigure() The recent cleanup of the watchdog code split watchdog_nmi_reconfigure() into two stages. One to stop the NMI and one to restart it after reconfiguration. That was done by adding a boolean 'run' argument to the code, which is functionally correct but not necessarily a piece of art. Replace it by two explicit functions: watchdog_nmi_stop() and watchdog_nmi_start(). Fixes: 6592ad2fcc8f ("watchdog/core, powerpc: Make watchdog_nmi_reconfigure() two stage") Requested-by: Linus 'Nursing his pet-peeve' Torvalds Signed-off-by: Thomas 'Mopping up garbage' Gleixner Acked-by: Michael Ellerman Cc: Peter Zijlstra Cc: Don Zickus Cc: Benjamin Herrenschmidt Cc: Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1710021957480.2114@nanos --- arch/powerpc/kernel/watchdog.c | 23 ++++++++++++++--------- include/linux/nmi.h | 3 ++- kernel/watchdog.c | 33 ++++++++++++++++++--------------- 3 files changed, 34 insertions(+), 25 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index dfb0677644801..2673ec8bec008 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -355,19 +355,24 @@ static void watchdog_calc_timeouts(void) wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5; } -void watchdog_nmi_reconfigure(bool run) +void watchdog_nmi_stop(void) { int cpu; cpus_read_lock(); - if (!run) { - for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); - } else { - watchdog_calc_timeouts(); - for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); - } + for_each_cpu(cpu, &wd_cpus_enabled) + stop_wd_on_cpu(cpu); + cpus_read_unlock(); +} + +void watchdog_nmi_start(void) +{ + int cpu; + + cpus_read_lock(); + watchdog_calc_timeouts(); + for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) + start_wd_on_cpu(cpu); cpus_read_unlock(); } diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 89ba8b23c6fe1..0c9ed49fb21a2 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -109,7 +109,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } # endif #endif -void watchdog_nmi_reconfigure(bool run); +void watchdog_nmi_stop(void); +void watchdog_nmi_start(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f6ef163b72cdb..6ad6226535d0e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -123,24 +123,27 @@ int __weak __init watchdog_nmi_probe(void) } /** - * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs - * @run: If false stop the watchdogs on all enabled CPUs - * If true start the watchdogs on all enabled CPUs + * watchdog_nmi_stop - Stop the watchdog for reconfiguration * - * The core call order is: - * watchdog_nmi_reconfigure(false); + * The reconfiguration steps are: + * watchdog_nmi_stop(); * update_variables(); - * watchdog_nmi_reconfigure(true); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration * - * The second call which starts the watchdogs again guarantees that the - * following variables are stable across the call. + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - * After the call the variables can be changed again. */ -void __weak watchdog_nmi_reconfigure(bool run) { } +void __weak watchdog_nmi_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit @@ -551,13 +554,13 @@ static void softlockup_unpark_threads(void) static void softlockup_reconfigure_threads(void) { - watchdog_nmi_reconfigure(false); + watchdog_nmi_stop(); softlockup_park_all_threads(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_unpark_threads(); - watchdog_nmi_reconfigure(true); + watchdog_nmi_start(); } /* @@ -602,9 +605,9 @@ static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } static void softlockup_reconfigure_threads(void) { - watchdog_nmi_reconfigure(false); + watchdog_nmi_stop(); lockup_detector_update_enable(); - watchdog_nmi_reconfigure(true); + watchdog_nmi_start(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -- GitLab From e31d6883f21c1cdfe5bc64e28411f8a92b783fde Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Oct 2017 16:37:53 +0200 Subject: [PATCH 0935/1507] watchdog/core, powerpc: Lock cpus across reconfiguration Instead of dropping the cpu hotplug lock after stopping NMI watchdog and threads and reaquiring for restart, the code and the protection rules become more obvious when holding cpu hotplug lock across the full reconfiguration. Suggested-by: Linus Torvalds Signed-off-by: Thomas Gleixner Acked-by: Michael Ellerman Cc: Peter Zijlstra Cc: Don Zickus Cc: Benjamin Herrenschmidt Cc: Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1710022105570.2114@nanos --- arch/powerpc/kernel/watchdog.c | 4 ---- kernel/smpboot.c | 3 +-- kernel/watchdog.c | 10 +++++++++- 3 files changed, 10 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 2673ec8bec008..f9b4c6352d24a 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -359,21 +359,17 @@ void watchdog_nmi_stop(void) { int cpu; - cpus_read_lock(); for_each_cpu(cpu, &wd_cpus_enabled) stop_wd_on_cpu(cpu); - cpus_read_unlock(); } void watchdog_nmi_start(void) { int cpu; - cpus_read_lock(); watchdog_calc_timeouts(); for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) start_wd_on_cpu(cpu); - cpus_read_unlock(); } /* diff --git a/kernel/smpboot.c b/kernel/smpboot.c index ed7507b69b480..5043e7433f4b1 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -351,7 +351,7 @@ void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread static struct cpumask tmp; unsigned int cpu; - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ @@ -367,7 +367,6 @@ void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); } static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6ad6226535d0e..fff90fe100071 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -535,7 +535,6 @@ static void softlockup_update_smpboot_threads(void) smpboot_update_cpumask_percpu_thread(&watchdog_threads, &watchdog_allowed_mask); - __lockup_detector_cleanup(); } /* Temporarily park all watchdog threads */ @@ -554,6 +553,7 @@ static void softlockup_unpark_threads(void) static void softlockup_reconfigure_threads(void) { + cpus_read_lock(); watchdog_nmi_stop(); softlockup_park_all_threads(); set_sample_period(); @@ -561,6 +561,12 @@ static void softlockup_reconfigure_threads(void) if (watchdog_enabled && watchdog_thresh) softlockup_unpark_threads(); watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } /* @@ -605,9 +611,11 @@ static inline void watchdog_disable_all_cpus(void) { } static inline void softlockup_init_threads(void) { } static void softlockup_reconfigure_threads(void) { + cpus_read_lock(); watchdog_nmi_stop(); lockup_detector_update_enable(); watchdog_nmi_start(); + cpus_read_unlock(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -- GitLab From 34ddaa3e5c0096fef52485186c7eb6cf56ddc686 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 3 Oct 2017 16:39:02 +0200 Subject: [PATCH 0936/1507] powerpc/watchdog: Make use of watchdog_nmi_probe() The rework of the core hotplug code triggers the WARN_ON in start_wd_cpu() on powerpc because it is called multiple times for the boot CPU. The first call is via: start_wd_on_cpu+0x80/0x2f0 watchdog_nmi_reconfigure+0x124/0x170 softlockup_reconfigure_threads+0x110/0x130 lockup_detector_init+0xbc/0xe0 kernel_init_freeable+0x18c/0x37c kernel_init+0x2c/0x160 ret_from_kernel_thread+0x5c/0xbc And then again via the CPU hotplug registration: start_wd_on_cpu+0x80/0x2f0 cpuhp_invoke_callback+0x194/0x620 cpuhp_thread_fun+0x7c/0x1b0 smpboot_thread_fn+0x290/0x2a0 kthread+0x168/0x1b0 ret_from_kernel_thread+0x5c/0xbc This can be avoided by setting up the cpu hotplug state with nocalls and move the initialization to the watchdog_nmi_probe() function. That initializes the hotplug callbacks without invoking the callback and the following core initialization function then configures the watchdog for the online CPUs (in this case CPU0) via softlockup_reconfigure_threads(). Reported-and-tested-by: Michael Ellerman Signed-off-by: Thomas Gleixner Acked-by: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Nicholas Piggin Cc: linuxppc-dev@lists.ozlabs.org --- arch/powerpc/kernel/watchdog.c | 17 ++++++++--------- include/linux/nmi.h | 1 + kernel/watchdog.c | 5 ++++- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index f9b4c6352d24a..c702a89814525 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -373,22 +373,21 @@ void watchdog_nmi_start(void) } /* - * This runs after lockup_detector_init() which sets up watchdog_cpumask. + * Invoked from core watchdog init. */ -static int __init powerpc_watchdog_init(void) +int __init watchdog_nmi_probe(void) { int err; - watchdog_calc_timeouts(); - - err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); - if (err < 0) + err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "powerpc/watchdog:online", + start_wd_on_cpu, stop_wd_on_cpu); + if (err < 0) { pr_warn("Watchdog could not be initialized"); - + return err; + } return 0; } -arch_initcall(powerpc_watchdog_init); static void handle_backtrace_ipi(struct pt_regs *regs) { diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0c9ed49fb21a2..27e249ed7c5c8 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -111,6 +111,7 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); +int watchdog_nmi_probe(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/kernel/watchdog.c b/kernel/watchdog.c index fff90fe100071..5c6fb7cd9ae8f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -608,7 +608,6 @@ static inline int watchdog_park_threads(void) { return 0; } static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } -static inline void softlockup_init_threads(void) { } static void softlockup_reconfigure_threads(void) { cpus_read_lock(); @@ -617,6 +616,10 @@ static void softlockup_reconfigure_threads(void) watchdog_nmi_start(); cpus_read_unlock(); } +static inline void softlockup_init_threads(void) +{ + softlockup_reconfigure_threads(); +} #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) -- GitLab From 5587185ddb4b9f413299dfec0a022ad0212513e8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 4 Oct 2017 10:03:04 +0200 Subject: [PATCH 0937/1507] watchdog/core: Rename some softlockup_* functions The function names made sense up to the point where the watchdog (re)configuration was unified to use softlockup_reconfigure_threads() for all configuration purposes. But that includes scenarios which solely configure the nmi watchdog. Rename softlockup_reconfigure_threads() and softlockup_init_threads() so the function names match the functionality. Signed-off-by: Thomas Gleixner Cc: Linus Torvalds Cc: Michael Ellerman Cc: Peter Zijlstra Cc: Don Zickus --- kernel/watchdog.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5c6fb7cd9ae8f..d241bd99cee1d 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -551,7 +551,7 @@ static void softlockup_unpark_threads(void) softlockup_update_smpboot_threads(); } -static void softlockup_reconfigure_threads(void) +static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); @@ -570,13 +570,13 @@ static void softlockup_reconfigure_threads(void) } /* - * Create the watchdog thread infrastructure. + * Create the watchdog thread infrastructure and configure the detector(s). * * The threads are not unparked as watchdog_allowed_mask is empty. When * the threads are sucessfully initialized, take the proper locks and * unpark the threads in the watchdog_cpumask if the watchdog is enabled. */ -static __init void softlockup_init_threads(void) +static __init void lockup_detector_setup(void) { int ret; @@ -599,7 +599,7 @@ static __init void softlockup_init_threads(void) mutex_lock(&watchdog_mutex); softlockup_threads_initialized = true; - softlockup_reconfigure_threads(); + lockup_detector_reconfigure(); mutex_unlock(&watchdog_mutex); } @@ -608,7 +608,7 @@ static inline int watchdog_park_threads(void) { return 0; } static inline void watchdog_unpark_threads(void) { } static inline int watchdog_enable_all_cpus(void) { return 0; } static inline void watchdog_disable_all_cpus(void) { } -static void softlockup_reconfigure_threads(void) +static void lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); @@ -616,9 +616,9 @@ static void softlockup_reconfigure_threads(void) watchdog_nmi_start(); cpus_read_unlock(); } -static inline void softlockup_init_threads(void) +static inline void lockup_detector_setup(void) { - softlockup_reconfigure_threads(); + lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ @@ -658,7 +658,7 @@ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); - softlockup_reconfigure_threads(); + lockup_detector_reconfigure(); } /* @@ -785,5 +785,5 @@ void __init lockup_detector_init(void) if (!watchdog_nmi_probe()) nmi_watchdog_available = true; - softlockup_init_threads(); + lockup_detector_setup(); } -- GitLab From 0b62bf862dc93a05fea97b6ca6ffca072e2f30c1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 2 Oct 2017 20:59:09 +0200 Subject: [PATCH 0938/1507] watchdog/core: Put softlockup_threads_initialized under ifdef guard The variable is unused when the softlockup detector is disabled in Kconfig. Signed-off-by: Thomas Gleixner --- kernel/watchdog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d241bd99cee1d..6bcb854909c0b 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -47,7 +47,6 @@ int __read_mostly watchdog_thresh = 10; int __read_mostly nmi_watchdog_available; struct cpumask watchdog_allowed_mask __read_mostly; -static bool softlockup_threads_initialized __read_mostly; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -168,6 +167,7 @@ static void lockup_detector_update_enable(void) unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); -- GitLab From 4edd8121e555acbee63578abeaf73026d055bbb4 Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Wed, 4 Oct 2017 11:42:00 +0200 Subject: [PATCH 0939/1507] ARM: dts: stm32: Fix STMPE1600 binding on stm32429i-eval board To declare gpio interrupt line for STMPE1600, 2 possibilities are offered: -use gpio binding (and then the gpiolib interface inside driver) -use interrupt binding as each gpio-controller are also interrupt controller on stm32f429. In STMPE 1600 node both (gpio and interrupt) bindings are defined. This patch fixes this issue and use only interrupt binding. Fixes: c04b2e72af8d ("ARM: dts: stm32: Enable STMPE1600 gpio expander of STM32F429-EVAL board") Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32429i-eval.dts | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/stm32429i-eval.dts b/arch/arm/boot/dts/stm32429i-eval.dts index 97b1c2321ba9d..5bdb90b2ae728 100644 --- a/arch/arm/boot/dts/stm32429i-eval.dts +++ b/arch/arm/boot/dts/stm32429i-eval.dts @@ -202,10 +202,8 @@ ov2640_0: endpoint { stmpe1600: stmpe1600@42 { compatible = "st,stmpe1600"; reg = <0x42>; - irq-gpio = <&gpioi 8 0>; - irq-trigger = <3>; interrupts = <8 3>; - interrupt-parent = <&exti>; + interrupt-parent = <&gpioi>; interrupt-controller; wakeup-source; -- GitLab From 8969f1f8291762c13147c1ba89d46238af01675b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 1 Oct 2017 09:37:35 +0200 Subject: [PATCH 0940/1507] nvme-pci: Use PCI bus address for data/queues in CMB Currently, NVMe PCI host driver is programming CMB dma address as I/O SQs addresses. This results in failures on systems where 1:1 outbound mapping is not used (example Broadcom iProc SOCs) because CMB BAR will be progammed with PCI bus address but NVMe PCI EP will try to access CMB using dma address. To have CMB working on systems without 1:1 outbound mapping, we program PCI bus address for I/O SQs instead of dma address. This approach will work on systems with/without 1:1 outbound mapping. Based on a report and previous patch from Abhishek Shah. Fixes: 8ffaadf7 ("NVMe: Use CMB for the IO SQes if available") Cc: stable@vger.kernel.org Reported-by: Abhishek Shah Tested-by: Abhishek Shah Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index cb73bc8cad3bd..3f5a04c586cef 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -94,7 +94,7 @@ struct nvme_dev { struct mutex shutdown_lock; bool subsystem; void __iomem *cmb; - dma_addr_t cmb_dma_addr; + pci_bus_addr_t cmb_bus_addr; u64 cmb_size; u32 cmbsz; u32 cmbloc; @@ -1226,7 +1226,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq, if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) { unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth), dev->ctrl.page_size); - nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset; + nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset; nvmeq->sq_cmds_io = dev->cmb + offset; } else { nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth), @@ -1527,7 +1527,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) resource_size_t bar_size; struct pci_dev *pdev = to_pci_dev(dev->dev); void __iomem *cmb; - dma_addr_t dma_addr; + int bar; dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!(NVME_CMB_SZ(dev->cmbsz))) @@ -1540,7 +1540,8 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz)); size = szu * NVME_CMB_SZ(dev->cmbsz); offset = szu * NVME_CMB_OFST(dev->cmbloc); - bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc)); + bar = NVME_CMB_BIR(dev->cmbloc); + bar_size = pci_resource_len(pdev, bar); if (offset > bar_size) return NULL; @@ -1553,12 +1554,11 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev) if (size > bar_size - offset) size = bar_size - offset; - dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset; - cmb = ioremap_wc(dma_addr, size); + cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size); if (!cmb) return NULL; - dev->cmb_dma_addr = dma_addr; + dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset; dev->cmb_size = size; return cmb; } -- GitLab From 74f1282114acc7d67e25745efe200f020f823c8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Wed, 4 Oct 2017 11:15:04 +0200 Subject: [PATCH 0941/1507] powerpc/xive: Fix IPI reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When resetting an IPI, hw_ipi should also be set to zero. Fixes: eac1e731b59e ("powerpc/xive: guest exploitation of the XIVE interrupt controller") Signed-off-by: Cédric Le Goater Signed-off-by: Michael Ellerman --- arch/powerpc/sysdev/xive/spapr.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index f24a70bc6855d..d9c4c93660491 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -431,7 +431,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) { + if (!xc->hw_ipi) + return; + xive_irq_bitmap_free(xc->hw_ipi); + xc->hw_ipi = 0; } #endif /* CONFIG_SMP */ -- GitLab From cc56939802fb4c9548be53563387a0700baeec82 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Wed, 4 Oct 2017 11:15:05 +0200 Subject: [PATCH 0942/1507] powerpc/xive: Clear XIVE internal structures when a CPU is removed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit eac1e731b59e ("powerpc/xive: guest exploitation of the XIVE interrupt controller") introduced support for the XIVE exploitation mode of the P9 interrupt controller on the pseries platform. At that time, support for CPU removal was not complete on PowerVM and CPU hot unplug remained untested. It appears that some cleanups of the XIVE internal structures are required before releasing the CPU, without which the kernel crashes in a RTAS call doing the CPU isolation. These changes fix the crash by deconfiguring the IPI interrupt source and clearing the event queues of the CPU when it is removed. Fixes: eac1e731b59e ("powerpc/xive: guest exploitation of the XIVE interrupt controller") Signed-off-by: Cédric Le Goater Signed-off-by: Michael Ellerman --- arch/powerpc/sysdev/xive/common.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f387318678b97..a3b8d7d1316eb 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1402,6 +1402,14 @@ void xive_teardown_cpu(void) if (xive_ops->teardown_cpu) xive_ops->teardown_cpu(cpu, xc); + +#ifdef CONFIG_SMP + /* Get rid of IPI */ + xive_cleanup_cpu_ipi(cpu, xc); +#endif + + /* Disable and free the queues */ + xive_cleanup_cpu_queues(cpu, xc); } void xive_kexec_teardown_cpu(int secondary) -- GitLab From 7c6a4f3b1641195119ddbb531200f4dc4cecbafa Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 24 Sep 2017 10:30:43 -0700 Subject: [PATCH 0943/1507] powerpc/mm: Call flush_tlb_kernel_range with interrupts enabled flush_tlb_kernel_range() may call smp_call_function_many() which expects interrupts to be enabled. This results in a traceback. WARNING: CPU: 0 PID: 1 at kernel/smp.c:416 smp_call_function_many+0xcc/0x2fc CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.14.0-rc1-00009-g0666f56 #1 task: cf830000 task.stack: cf82e000 NIP: c00a93c8 LR: c00a9634 CTR: 00000001 REGS: cf82fde0 TRAP: 0700 Not tainted (4.14.0-rc1-00009-g0666f56) MSR: 00021000 CR: 24000082 XER: 00000000 GPR00: c00a9634 cf82fe90 cf830000 c050ad3c c0015a54 00000000 00000001 00000001 GPR08: 00000001 00000000 00000000 cf82e000 24000084 00000000 c0003150 00000000 GPR16: 00000000 00000000 00000000 00000000 00000000 00000001 00000000 c0510000 GPR24: 00000000 c0015a54 00000000 c050ad3c c051823c c050ad3c 00000025 00000000 NIP [c00a93c8] smp_call_function_many+0xcc/0x2fc LR [c00a9634] smp_call_function+0x3c/0x50 Call Trace: [cf82fe90] [00000010] 0x10 (unreliable) [cf82fed0] [c00a9634] smp_call_function+0x3c/0x50 [cf82fee0] [c0015d2c] flush_tlb_kernel_range+0x20/0x38 [cf82fef0] [c001524c] mark_initmem_nx+0x154/0x16c [cf82ff20] [c001484c] free_initmem+0x20/0x4c [cf82ff30] [c000316c] kernel_init+0x1c/0x108 [cf82ff40] [c000f3a8] ret_from_kernel_thread+0x5c/0x64 Instruction dump: 7c0803a6 7d808120 38210040 4e800020 3d20c052 812981a0 2f890000 40beffac 3d20c051 8929ac64 2f890000 40beff9c <0fe00000> 4bffff94 7fc3f378 7f64db78 Fixes: 3184cc4b6f6a ("powerpc/mm: Fix kernel RAM protection after freeing ...") Fixes: e611939fc8ec ("powerpc/mm: Ensure change_page_attr() doesn't ...") Cc: Christophe Leroy Signed-off-by: Guenter Roeck Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman --- arch/powerpc/mm/pgtable_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 65eda1997c3f8..f6c7f54c05157 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -361,9 +361,9 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot) break; } wmb(); + local_irq_restore(flags); flush_tlb_kernel_range((unsigned long)page_address(start), (unsigned long)page_address(page)); - local_irq_restore(flags); return err; } -- GitLab From ad670233c9e1d5feb365d870e30083ef1b889177 Mon Sep 17 00:00:00 2001 From: Peng Xu Date: Tue, 3 Oct 2017 23:21:51 +0300 Subject: [PATCH 0944/1507] nl80211: Define policy for packet pattern attributes Define a policy for packet pattern attributes in order to fix a potential read over the end of the buffer during nla_get_u32() of the NL80211_PKTPAT_OFFSET attribute. Note that the data there can always be read due to SKB allocation (with alignment and struct skb_shared_info at the end), but the data might be uninitialized. This could be used to leak some data from uninitialized vmalloc() memory, but most drivers don't allow an offset (so you'd just get -EINVAL if the data is non-zero) or just allow it with a fixed value - 100 or 128 bytes, so anything above that would get -EINVAL. With brcmfmac the limit is 1500 so (at least) one byte could be obtained. Cc: stable@kernel.org Signed-off-by: Peng Xu Signed-off-by: Jouni Malinen [rewrite description based on SKB allocation knowledge] Signed-off-by: Johannes Berg --- net/wireless/nl80211.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 690874293cfc6..d396cb61a280d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -549,6 +549,14 @@ nl80211_nan_srf_policy[NL80211_NAN_SRF_ATTR_MAX + 1] = { [NL80211_NAN_SRF_MAC_ADDRS] = { .type = NLA_NESTED }, }; +/* policy for packet pattern attributes */ +static const struct nla_policy +nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = { + [NL80211_PKTPAT_MASK] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_PATTERN] = { .type = NLA_BINARY, }, + [NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -10532,7 +10540,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) u8 *mask_pat; nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - NULL, info->extack); + nl80211_packet_pattern_policy, + info->extack); err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -10781,7 +10790,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, NULL, NULL); + nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; -- GitLab From 2aaae13a9db7897a007c5d7bb46cacfb37dffacd Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Wed, 4 Oct 2017 15:34:48 +0200 Subject: [PATCH 0945/1507] ARM: dts: stm32: use right pinctrl compatible for stm32f469 Currently, same stm32f429-pinctrl driver is used for stm32f429 and stm32f469. As pin map is different between those 2 MCUs, a stm32f469-pinctrl driver has been recently added. This patch -allows to use stm32f469-pinctrl driver for stm32f469 boards -reworks stm32 devicetree files to fit with stm32f429 / stm32f469 In the same time it fixes an issue when only MACH_STM32F469 flag is selected in menuconfig. Fixes: d28bcd53fa90 ("ARM: stm32: Introduce MACH_STM32F469 flag") Reported-by: Nicolas Pitre Signed-off-by: Alexandre Torgue --- arch/arm/boot/dts/stm32429i-eval.dts | 1 + arch/arm/boot/dts/stm32f4-pinctrl.dtsi | 343 +++++++++++++++++++++++ arch/arm/boot/dts/stm32f429-disco.dts | 1 + arch/arm/boot/dts/stm32f429-pinctrl.dtsi | 95 +++++++ arch/arm/boot/dts/stm32f429.dtsi | 297 -------------------- arch/arm/boot/dts/stm32f469-disco.dts | 1 + arch/arm/boot/dts/stm32f469-pinctrl.dtsi | 96 +++++++ 7 files changed, 537 insertions(+), 297 deletions(-) create mode 100644 arch/arm/boot/dts/stm32f4-pinctrl.dtsi create mode 100644 arch/arm/boot/dts/stm32f429-pinctrl.dtsi create mode 100644 arch/arm/boot/dts/stm32f469-pinctrl.dtsi diff --git a/arch/arm/boot/dts/stm32429i-eval.dts b/arch/arm/boot/dts/stm32429i-eval.dts index 5bdb90b2ae728..293ecb9572271 100644 --- a/arch/arm/boot/dts/stm32429i-eval.dts +++ b/arch/arm/boot/dts/stm32429i-eval.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f429-pinctrl.dtsi" #include #include diff --git a/arch/arm/boot/dts/stm32f4-pinctrl.dtsi b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi new file mode 100644 index 0000000000000..7f3560c0211dd --- /dev/null +++ b/arch/arm/boot/dts/stm32f4-pinctrl.dtsi @@ -0,0 +1,343 @@ +/* + * Copyright 2017 - Alexandre Torgue + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include +#include + +/ { + soc { + pinctrl: pin-controller { + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x40020000 0x3000>; + interrupt-parent = <&exti>; + st,syscfg = <&syscfg 0x8>; + pins-are-numbered; + + gpioa: gpio@40020000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x0 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>; + st,bank-name = "GPIOA"; + }; + + gpiob: gpio@40020400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>; + st,bank-name = "GPIOB"; + }; + + gpioc: gpio@40020800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>; + st,bank-name = "GPIOC"; + }; + + gpiod: gpio@40020c00 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0xc00 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>; + st,bank-name = "GPIOD"; + }; + + gpioe: gpio@40021000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1000 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>; + st,bank-name = "GPIOE"; + }; + + gpiof: gpio@40021400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>; + st,bank-name = "GPIOF"; + }; + + gpiog: gpio@40021800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>; + st,bank-name = "GPIOG"; + }; + + gpioh: gpio@40021c00 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x1c00 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>; + st,bank-name = "GPIOH"; + }; + + gpioi: gpio@40022000 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2000 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>; + st,bank-name = "GPIOI"; + }; + + gpioj: gpio@40022400 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2400 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>; + st,bank-name = "GPIOJ"; + }; + + gpiok: gpio@40022800 { + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + reg = <0x2800 0x400>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>; + st,bank-name = "GPIOK"; + }; + + usart1_pins_a: usart1@0 { + pins1 { + pinmux = ; + bias-disable; + drive-push-pull; + slew-rate = <0>; + }; + pins2 { + pinmux = ; + bias-disable; + }; + }; + + usart3_pins_a: usart3@0 { + pins1 { + pinmux = ; + bias-disable; + drive-push-pull; + slew-rate = <0>; + }; + pins2 { + pinmux = ; + bias-disable; + }; + }; + + usbotg_fs_pins_a: usbotg_fs@0 { + pins { + pinmux = , + , + ; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + usbotg_fs_pins_b: usbotg_fs@1 { + pins { + pinmux = , + , + ; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + usbotg_hs_pins_a: usbotg_hs@0 { + pins { + pinmux = , + , + , + , + , + , + , + , + , + , + , + ; + bias-disable; + drive-push-pull; + slew-rate = <2>; + }; + }; + + ethernet_mii: mii@0 { + pins { + pinmux = , + , + , + , + , + , + , + , + , + , + , + , + , + ; + slew-rate = <2>; + }; + }; + + adc3_in8_pin: adc@200 { + pins { + pinmux = ; + }; + }; + + pwm1_pins: pwm@1 { + pins { + pinmux = , + , + ; + }; + }; + + pwm3_pins: pwm@3 { + pins { + pinmux = , + ; + }; + }; + + i2c1_pins: i2c1@0 { + pins { + pinmux = , + ; + bias-disable; + drive-open-drain; + slew-rate = <3>; + }; + }; + + ltdc_pins: ltdc@0 { + pins { + pinmux = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + slew-rate = <2>; + }; + }; + + dcmi_pins: dcmi@0 { + pins { + pinmux = , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + bias-disable; + drive-push-pull; + slew-rate = <3>; + }; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/stm32f429-disco.dts b/arch/arm/boot/dts/stm32f429-disco.dts index c66d617e4245b..5ceb2cf3777ff 100644 --- a/arch/arm/boot/dts/stm32f429-disco.dts +++ b/arch/arm/boot/dts/stm32f429-disco.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f429-pinctrl.dtsi" #include / { diff --git a/arch/arm/boot/dts/stm32f429-pinctrl.dtsi b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi new file mode 100644 index 0000000000000..3e7a17d9112e1 --- /dev/null +++ b/arch/arm/boot/dts/stm32f429-pinctrl.dtsi @@ -0,0 +1,95 @@ +/* + * Copyright 2017 - Alexandre Torgue + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "stm32f4-pinctrl.dtsi" + +/ { + soc { + pinctrl: pin-controller { + compatible = "st,stm32f429-pinctrl"; + + gpioa: gpio@40020000 { + gpio-ranges = <&pinctrl 0 0 16>; + }; + + gpiob: gpio@40020400 { + gpio-ranges = <&pinctrl 0 16 16>; + }; + + gpioc: gpio@40020800 { + gpio-ranges = <&pinctrl 0 32 16>; + }; + + gpiod: gpio@40020c00 { + gpio-ranges = <&pinctrl 0 48 16>; + }; + + gpioe: gpio@40021000 { + gpio-ranges = <&pinctrl 0 64 16>; + }; + + gpiof: gpio@40021400 { + gpio-ranges = <&pinctrl 0 80 16>; + }; + + gpiog: gpio@40021800 { + gpio-ranges = <&pinctrl 0 96 16>; + }; + + gpioh: gpio@40021c00 { + gpio-ranges = <&pinctrl 0 112 16>; + }; + + gpioi: gpio@40022000 { + gpio-ranges = <&pinctrl 0 128 16>; + }; + + gpioj: gpio@40022400 { + gpio-ranges = <&pinctrl 0 144 16>; + }; + + gpiok: gpio@40022800 { + gpio-ranges = <&pinctrl 0 160 8>; + }; + }; + }; +}; diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index dd7e99b1f43bc..5b36eb114ddc9 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -47,7 +47,6 @@ #include "skeleton.dtsi" #include "armv7-m.dtsi" -#include #include #include @@ -591,302 +590,6 @@ ltdc: display-controller@40016800 { status = "disabled"; }; - pinctrl: pin-controller { - #address-cells = <1>; - #size-cells = <1>; - compatible = "st,stm32f429-pinctrl"; - ranges = <0 0x40020000 0x3000>; - interrupt-parent = <&exti>; - st,syscfg = <&syscfg 0x8>; - pins-are-numbered; - - gpioa: gpio@40020000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x0 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>; - st,bank-name = "GPIOA"; - }; - - gpiob: gpio@40020400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>; - st,bank-name = "GPIOB"; - }; - - gpioc: gpio@40020800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>; - st,bank-name = "GPIOC"; - }; - - gpiod: gpio@40020c00 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0xc00 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOD)>; - st,bank-name = "GPIOD"; - }; - - gpioe: gpio@40021000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1000 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOE)>; - st,bank-name = "GPIOE"; - }; - - gpiof: gpio@40021400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOF)>; - st,bank-name = "GPIOF"; - }; - - gpiog: gpio@40021800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOG)>; - st,bank-name = "GPIOG"; - }; - - gpioh: gpio@40021c00 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x1c00 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOH)>; - st,bank-name = "GPIOH"; - }; - - gpioi: gpio@40022000 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2000 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOI)>; - st,bank-name = "GPIOI"; - }; - - gpioj: gpio@40022400 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2400 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOJ)>; - st,bank-name = "GPIOJ"; - }; - - gpiok: gpio@40022800 { - gpio-controller; - #gpio-cells = <2>; - interrupt-controller; - #interrupt-cells = <2>; - reg = <0x2800 0x400>; - clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOK)>; - st,bank-name = "GPIOK"; - }; - - usart1_pins_a: usart1@0 { - pins1 { - pinmux = ; - bias-disable; - drive-push-pull; - slew-rate = <0>; - }; - pins2 { - pinmux = ; - bias-disable; - }; - }; - - usart3_pins_a: usart3@0 { - pins1 { - pinmux = ; - bias-disable; - drive-push-pull; - slew-rate = <0>; - }; - pins2 { - pinmux = ; - bias-disable; - }; - }; - - usbotg_fs_pins_a: usbotg_fs@0 { - pins { - pinmux = , - , - ; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - usbotg_fs_pins_b: usbotg_fs@1 { - pins { - pinmux = , - , - ; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - usbotg_hs_pins_a: usbotg_hs@0 { - pins { - pinmux = , - , - , - , - , - , - , - , - , - , - , - ; - bias-disable; - drive-push-pull; - slew-rate = <2>; - }; - }; - - ethernet_mii: mii@0 { - pins { - pinmux = , - , - , - , - , - , - , - , - , - , - , - , - , - ; - slew-rate = <2>; - }; - }; - - adc3_in8_pin: adc@200 { - pins { - pinmux = ; - }; - }; - - pwm1_pins: pwm@1 { - pins { - pinmux = , - , - ; - }; - }; - - pwm3_pins: pwm@3 { - pins { - pinmux = , - ; - }; - }; - - i2c1_pins: i2c1@0 { - pins { - pinmux = , - ; - bias-disable; - drive-open-drain; - slew-rate = <3>; - }; - }; - - ltdc_pins: ltdc@0 { - pins { - pinmux = , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - , - ; - slew-rate = <2>; - }; - }; - - dcmi_pins: dcmi@0 { - pins { - pinmux = , - , - , - , - , - , - , - , - , - , - , - , - , - , - ; - bias-disable; - drive-push-pull; - slew-rate = <3>; - }; - }; - }; - crc: crc@40023000 { compatible = "st,stm32f4-crc"; reg = <0x40023000 0x400>; diff --git a/arch/arm/boot/dts/stm32f469-disco.dts b/arch/arm/boot/dts/stm32f469-disco.dts index 6ae1f037f3f0e..c18acbe4cf4e2 100644 --- a/arch/arm/boot/dts/stm32f469-disco.dts +++ b/arch/arm/boot/dts/stm32f469-disco.dts @@ -47,6 +47,7 @@ /dts-v1/; #include "stm32f429.dtsi" +#include "stm32f469-pinctrl.dtsi" / { model = "STMicroelectronics STM32F469i-DISCO board"; diff --git a/arch/arm/boot/dts/stm32f469-pinctrl.dtsi b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi new file mode 100644 index 0000000000000..fff542662eeaa --- /dev/null +++ b/arch/arm/boot/dts/stm32f469-pinctrl.dtsi @@ -0,0 +1,96 @@ +/* + * Copyright 2017 - Alexandre Torgue + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License, or (at your option) any later version. + * + * This file is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#include "stm32f4-pinctrl.dtsi" + +/ { + soc { + pinctrl: pin-controller { + compatible = "st,stm32f469-pinctrl"; + + gpioa: gpio@40020000 { + gpio-ranges = <&pinctrl 0 0 16>; + }; + + gpiob: gpio@40020400 { + gpio-ranges = <&pinctrl 0 16 16>; + }; + + gpioc: gpio@40020800 { + gpio-ranges = <&pinctrl 0 32 16>; + }; + + gpiod: gpio@40020c00 { + gpio-ranges = <&pinctrl 0 48 16>; + }; + + gpioe: gpio@40021000 { + gpio-ranges = <&pinctrl 0 64 16>; + }; + + gpiof: gpio@40021400 { + gpio-ranges = <&pinctrl 0 80 16>; + }; + + gpiog: gpio@40021800 { + gpio-ranges = <&pinctrl 0 96 16>; + }; + + gpioh: gpio@40021c00 { + gpio-ranges = <&pinctrl 0 112 16>; + }; + + gpioi: gpio@40022000 { + gpio-ranges = <&pinctrl 0 128 16>; + }; + + gpioj: gpio@40022400 { + gpio-ranges = <&pinctrl 0 144 6>, + <&pinctrl 12 156 4>; + }; + + gpiok: gpio@40022800 { + gpio-ranges = <&pinctrl 3 163 5>; + }; + }; + }; +}; -- GitLab From 2d8ce70a08fe033c904115d59276ad86adeaa337 Mon Sep 17 00:00:00 2001 From: Goffredo Baroncelli Date: Tue, 3 Oct 2017 19:31:10 +0200 Subject: [PATCH 0946/1507] btrfs: avoid overflow when sector_t is 32 bit Jean-Denis Girard noticed commit c821e7f3 "pass bytes to btrfs_bio_alloc" (https://patchwork.kernel.org/patch/9763081/) introduces a regression on 32 bit machines. When CONFIG_LBDAF is _not_ defined (CONFIG_LBDAF == Support for large (2TB+) block devices and files) sector_t is 32 bit on 32bit machines. In the function submit_extent_page, 'sector' (which is sector_t type) is multiplied by 512 to convert it from sectors to bytes, leading to an overflow when the disk is bigger than 4GB (!). I added a cast to u64 to avoid overflow. Fixes: c821e7f3 ("btrfs: pass bytes to btrfs_bio_alloc") CC: stable@vger.kernel.org # 4.13+ Signed-off-by: Goffredo Baroncelli Tested-by: Jean-Denis Girard Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3738d245518ca..8dfa181b1a927 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2801,7 +2801,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, } } - bio = btrfs_bio_alloc(bdev, sector << 9); + bio = btrfs_bio_alloc(bdev, (u64)sector << 9); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; -- GitLab From eab40cf336065e8d765e006b81ff48c5c114b365 Mon Sep 17 00:00:00 2001 From: Benjamin Block Date: Tue, 3 Oct 2017 12:48:37 +0200 Subject: [PATCH 0947/1507] bsg-lib: fix use-after-free under memory-pressure When under memory-pressure it is possible that the mempool which backs the 'struct request_queue' will make use of up to BLKDEV_MIN_RQ count emergency buffers - in case it can't get a regular allocation. These buffers are preallocated and once they are also used, they are re-supplied with old finished requests from the same request_queue (see mempool_free()). The bug is, when re-supplying the emergency pool, the old requests are not again ran through the callback mempool_t->alloc(), and thus also not through the callback bsg_init_rq(). Thus we skip initialization, and while the sense-buffer still should be good, scsi_request->cmd might have become to be an invalid pointer in the meantime. When the request is initialized in bsg.c, and the user's CDB is larger than BLK_MAX_CDB, bsg will replace it with a custom allocated buffer, which is freed when the user's command is finished, thus it dangles afterwards. When next a command is sent by the user that has a smaller/similar CDB as BLK_MAX_CDB, bsg will assume that scsi_request->cmd is backed by scsi_request->__cmd, will not make a custom allocation, and write into undefined memory. Fix this by splitting bsg_init_rq() into two functions: - bsg_init_rq() is changed to only do the allocation of the sense-buffer, which is used to back the bsg job's reply buffer. This pointer should never change during the lifetime of a scsi_request, so it doesn't need re-initialization. - bsg_initialize_rq() is a new function that makes use of 'struct request_queue's initialize_rq_fn callback (which was introduced in v4.12). This is always called before the request is given out via blk_get_request(). This function does the remaining initialization that was previously done in bsg_init_rq(), and will also do it when the request is taken from the emergency-pool of the backing mempool. Fixes: 50b4d485528d ("bsg-lib: fix kernel panic resulting from missing allocation of reply-buffer") Cc: # 4.11+ Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Benjamin Block Signed-off-by: Jens Axboe --- block/bsg-lib.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) diff --git a/block/bsg-lib.c b/block/bsg-lib.c index dbddff8174e57..15d25ccd51a5c 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -207,20 +207,34 @@ static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp) struct bsg_job *job = blk_mq_rq_to_pdu(req); struct scsi_request *sreq = &job->sreq; + /* called right after the request is allocated for the request_queue */ + + sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp); + if (!sreq->sense) + return -ENOMEM; + + return 0; +} + +static void bsg_initialize_rq(struct request *req) +{ + struct bsg_job *job = blk_mq_rq_to_pdu(req); + struct scsi_request *sreq = &job->sreq; + void *sense = sreq->sense; + + /* called right before the request is given to the request_queue user */ + memset(job, 0, sizeof(*job)); scsi_req_init(sreq); + + sreq->sense = sense; sreq->sense_len = SCSI_SENSE_BUFFERSIZE; - sreq->sense = kzalloc(sreq->sense_len, gfp); - if (!sreq->sense) - return -ENOMEM; job->req = req; - job->reply = sreq->sense; + job->reply = sense; job->reply_len = sreq->sense_len; job->dd_data = job + 1; - - return 0; } static void bsg_exit_rq(struct request_queue *q, struct request *req) @@ -251,6 +265,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->cmd_size = sizeof(struct bsg_job) + dd_job_size; q->init_rq_fn = bsg_init_rq; q->exit_rq_fn = bsg_exit_rq; + q->initialize_rq_fn = bsg_initialize_rq; q->request_fn = bsg_request_fn; ret = blk_init_allocated_queue(q); -- GitLab From 69ad59767d094752c23c0fc180a79532fde073d0 Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Wed, 4 Oct 2017 11:05:17 +0900 Subject: [PATCH 0948/1507] Btrfs: fix overlap of fs_info::flags values Because the values of BTRFS_FS_EXCL_OP and BTRFS_FS_QUOTA_OVERRIDE overlap, we should change the value. First, BTRFS_FS_EXCL_OP was set to 14. commit 171938e52807 ("btrfs: track exclusive filesystem operation in flags") Next, the value of BTRFS_FS_QUOTA_OVERRIDE was set to 14. commit f29efe292198 ("btrfs: add quota override flag to enable quota override for CAP_SYS_RESOURCE") As a result, the value 14 overlapped, by accident. This problem is solved by defining the value of BTRFS_FS_EXCL_OP as 16, the flags are internal. Fixes: f29efe292198 ("btrfs: add quota override flag to enable quota override for CAP_SYS_RESOURCE") CC: stable@vger.kernel.org # 4.13+ Signed-off-by: Tsutomu Itoh Reviewed-by: David Sterba [ minimize the change, update only BTRFS_FS_EXCL_OP ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7ccfcc01732b..aff3248beb908 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -721,7 +721,7 @@ struct btrfs_delayed_root; * Indicate that a whole-filesystem exclusive operation is running * (device replace, resize, device add/delete, balance) */ -#define BTRFS_FS_EXCL_OP 14 +#define BTRFS_FS_EXCL_OP 16 struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; -- GitLab From 783874b050768d361239e444ba0fa396bb6d463f Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Wed, 13 Sep 2017 15:45:56 +0200 Subject: [PATCH 0949/1507] dm crypt: reject sector_size feature if device length is not aligned to it If a crypt mapping uses optional sector_size feature, additional restrictions to mapped device segment size must be applied in constructor, otherwise the device activation will fail later. Fixes: 8f0009a225 ("dm crypt: optionally support larger encryption sector size") Cc: stable@vger.kernel.org # 4.12+ Signed-off-by: Milan Broz Signed-off-by: Mike Snitzer --- drivers/md/dm-crypt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 75341fdca4b6b..96ab46512e1fd 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2585,6 +2585,10 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar ti->error = "Invalid feature value for sector_size"; return -EINVAL; } + if (ti->len & ((cc->sector_size >> SECTOR_SHIFT) - 1)) { + ti->error = "Device size is not multiple of sector_size feature"; + return -EINVAL; + } cc->sector_shift = __ffs(cc->sector_size) - SECTOR_SHIFT; } else if (!strcasecmp(opt_string, "iv_large_sectors")) set_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); -- GitLab From 5dcbeca615ef12047a5f4097b91030cbf995b1d2 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 19 Sep 2017 12:01:08 +0200 Subject: [PATCH 0950/1507] clk: samsung: exynos4: Enable VPLL and EPLL clocks for suspend/resume cycle Commit 6edfa11cb396 ("clk: samsung: Add enable/disable operation for PLL36XX clocks") added enable/disable operations to PLL clocks. Prior that VPLL and EPPL clocks were always enabled because the enable bit was never touched. Those clocks have to be enabled during suspend/resume cycle, because otherwise board fails to enter sleep mode. This patch enables them unconditionally before entering system suspend state. System restore function will set them to the previous state saved in the register cache done before that unconditional enable. Fixes: 6edfa11cb396 ("clk: samsung: Add enable/disable operation for PLL36XX clocks") CC: stable@vger.kernel.org # v4.13 Signed-off-by: Marek Szyprowski Reviewed-by: Chanwoo Choi Reviewed-by: Krzysztof Kozlowski Acked-by: Sylwester Nawrocki Signed-off-by: Stephen Boyd --- drivers/clk/samsung/clk-exynos4.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index e40b77583c476..d8d3cb67b4029 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -294,6 +294,18 @@ static const struct samsung_clk_reg_dump src_mask_suspend_e4210[] = { #define PLL_ENABLED (1 << 31) #define PLL_LOCKED (1 << 29) +static void exynos4_clk_enable_pll(u32 reg) +{ + u32 pll_con = readl(reg_base + reg); + pll_con |= PLL_ENABLED; + writel(pll_con, reg_base + reg); + + while (!(pll_con & PLL_LOCKED)) { + cpu_relax(); + pll_con = readl(reg_base + reg); + } +} + static void exynos4_clk_wait_for_pll(u32 reg) { u32 pll_con; @@ -315,6 +327,9 @@ static int exynos4_clk_suspend(void) samsung_clk_save(reg_base, exynos4_save_pll, ARRAY_SIZE(exynos4_clk_pll_regs)); + exynos4_clk_enable_pll(EPLL_CON0); + exynos4_clk_enable_pll(VPLL_CON0); + if (exynos4_soc == EXYNOS4210) { samsung_clk_save(reg_base, exynos4_save_soc, ARRAY_SIZE(exynos4210_clk_save)); -- GitLab From a2b7861bb33b2538420bb5d8554153484d3f961f Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 3 Oct 2017 21:36:51 +0800 Subject: [PATCH 0951/1507] kvm/x86: Avoid async PF preempting the kernel incorrectly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, in PREEMPT_COUNT=n kernel, kvm_async_pf_task_wait() could call schedule() to reschedule in some cases. This could result in accidentally ending the current RCU read-side critical section early, causing random memory corruption in the guest, or otherwise preempting the currently running task inside between preempt_disable and preempt_enable. The difficulty to handle this well is because we don't know whether an async PF delivered in a preemptible section or RCU read-side critical section for PREEMPT_COUNT=n, since preempt_disable()/enable() and rcu_read_lock/unlock() are both no-ops in that case. To cure this, we treat any async PF interrupting a kernel context as one that cannot be preempted, preventing kvm_async_pf_task_wait() from choosing the schedule() path in that case. To do so, a second parameter for kvm_async_pf_task_wait() is introduced, so that we know whether it's called from a context interrupting the kernel, and the parameter is set properly in all the callsites. Cc: "Paul E. McKenney" Cc: Peter Zijlstra Cc: Wanpeng Li Cc: stable@vger.kernel.org Signed-off-by: Boqun Feng Signed-off-by: Radim Krčmář --- arch/x86/include/asm/kvm_para.h | 4 ++-- arch/x86/kernel/kvm.c | 14 ++++++++++---- arch/x86/kvm/mmu.c | 2 +- 3 files changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index bc62e7cbf1b1f..59ad3d1323532 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); void __init kvm_guest_init(void); -void kvm_async_pf_task_wait(u32 token); +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); @@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void) #else /* CONFIG_KVM_GUEST */ #define kvm_guest_init() do {} while (0) -#define kvm_async_pf_task_wait(T) do {} while(0) +#define kvm_async_pf_task_wait(T, I) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) static inline bool kvm_para_available(void) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e675704fa6f7d..8bb9594d07616 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -void kvm_async_pf_task_wait(u32 token) +/* + * @interrupt_kernel: Is this called from a routine which interrupts the kernel + * (other than user space)? + */ +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; @@ -140,8 +144,10 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1 || - rcu_preempt_depth(); + n.halted = is_idle_task(current) || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) + ? preempt_count() > 1 || rcu_preempt_depth() + : interrupt_kernel); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); @@ -269,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2()); + kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca30c1eb1d97..106d4a029a8a9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, case KVM_PV_REASON_PAGE_NOT_PRESENT: vcpu->arch.apf.host_apf_reason = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address); + kvm_async_pf_task_wait(fault_address, 0); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: -- GitLab From 37f6b42e9c2966b08c7df5cfddc0d73c39cead4a Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 2 Oct 2017 18:28:44 +0100 Subject: [PATCH 0952/1507] ACPI/IORT: Fix PCI ACS enablement commit f6810c15cf97 ("iommu/arm-smmu: Clean up early-probing workarounds") removed kernel code that was allowing to initialize and probe the SMMU devices early (ie earlier than PCI devices, through linker script callback entries) in the boot process because it was not needed any longer in that the SMMU devices/drivers now support deferred probing. Since the SMMUs probe routines are also in charge of requesting global PCI ACS kernel enablement, commit f6810c15cf97 ("iommu/arm-smmu: Clean up early-probing workarounds") also postponed PCI ACS enablement to SMMUs devices probe time, which is too late given that PCI devices needs to detect if PCI ACS is enabled to init the respective capability through the following call path: pci_device_add() -> pci_init_capabilities() -> pci_enable_acs() Add code in the ACPI IORT SMMU platform devices initialization path (that is called before ACPI PCI enumeration) to detect if there exists firmware mappings to map root complexes ids to SMMU ids and if so enable ACS for the system. Fixes: f6810c15cf97 ("iommu/arm-smmu: Clean up early-probing workarounds") Reviewed-by: Robin Murphy Tested-by: Nate Watterson Signed-off-by: Lorenzo Pieralisi Cc: Will Deacon Cc: Hanjun Guo Cc: Sudeep Holla Cc: Zhou Wang Cc: Alex Williamson Signed-off-by: Catalin Marinas --- drivers/acpi/arm64/iort.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9565d572f8dd2..de56394dd161f 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1178,12 +1178,44 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node) return ret; } +static bool __init iort_enable_acs(struct acpi_iort_node *iort_node) +{ + if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) { + struct acpi_iort_node *parent; + struct acpi_iort_id_mapping *map; + int i; + + map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node, + iort_node->mapping_offset); + + for (i = 0; i < iort_node->mapping_count; i++, map++) { + if (!map->output_reference) + continue; + + parent = ACPI_ADD_PTR(struct acpi_iort_node, + iort_table, map->output_reference); + /* + * If we detect a RC->SMMU mapping, make sure + * we enable ACS on the system. + */ + if ((parent->type == ACPI_IORT_NODE_SMMU) || + (parent->type == ACPI_IORT_NODE_SMMU_V3)) { + pci_request_acs(); + return true; + } + } + } + + return false; +} + static void __init iort_init_platform_devices(void) { struct acpi_iort_node *iort_node, *iort_end; struct acpi_table_iort *iort; struct fwnode_handle *fwnode; int i, ret; + bool acs_enabled = false; /* * iort_table and iort both point to the start of IORT table, but @@ -1203,6 +1235,9 @@ static void __init iort_init_platform_devices(void) return; } + if (!acs_enabled) + acs_enabled = iort_enable_acs(iort_node); + if ((iort_node->type == ACPI_IORT_NODE_SMMU) || (iort_node->type == ACPI_IORT_NODE_SMMU_V3)) { -- GitLab From b02faed15d86f846b0f23f47b92e0782baa873ed Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 3 Oct 2017 18:25:46 +0100 Subject: [PATCH 0953/1507] arm64: Use larger stacks when KASAN is selected AddressSanitizer instrumentation can significantly bloat the stack, and with GCC 7 this can result in stack overflows at boot time in some configurations. We can avoid this by doubling our stack size when KASAN is in use, as is already done on x86 (and has been since KASAN was introduced). Regardless of other patches to decrease KASAN's stack utilization, kernels built with KASAN will always require more stack space than those built without, and we should take this into account. Signed-off-by: Mark Rutland Cc: Will Deacon Cc: Suzuki K Poulose Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/memory.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 3585a5e261510..f7c4d2146aed0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -95,16 +95,19 @@ #define KERNEL_END _end /* - * The size of the KASAN shadow region. This should be 1/8th of the - * size of the entire kernel virtual address space. + * KASAN requires 1/8th of the kernel virtual address space for the shadow + * region. KASAN can bloat the stack significantly, so double the (minimum) + * stack size when KASAN is in use. */ #ifdef CONFIG_KASAN #define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - 3)) +#define KASAN_THREAD_SHIFT 1 #else #define KASAN_SHADOW_SIZE (0) +#define KASAN_THREAD_SHIFT 0 #endif -#define MIN_THREAD_SHIFT 14 +#define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such -- GitLab From 4d86d38186271438ef002c5ae6e04836f01bf8bf Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 4 Oct 2017 09:54:27 +0200 Subject: [PATCH 0954/1507] ravb: RX checksum offload Add support for RX checksum offload. This is enabled by default and may be disabled and re-enabled using ethtool: # ethtool -K eth0 rx off # ethtool -K eth0 rx on The RAVB provides a simple checksumming scheme which appears to be completely compatible with CHECKSUM_COMPLETE: sum of all packet data after the L2 header is appended to packet data; this may be trivially read by the driver and used to update the skb accordingly. In terms of performance throughput is close to gigabit line-rate both with and without RX checksum offload enabled. Perf output, however, appears to indicate that significantly less time is spent in do_csum(). This is as expected. Test results with RX checksum offload enabled: # /usr/bin/perf_3.16 record -o /run/perf.data -a netperf -t TCP_MAERTS -H 10.4.3.162 MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.4.3.162 () port 0 AF_INET : demo enable_enobufs failed: getprotobyname Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 937.54 Summary of output of perf report: 18.28% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 10.34% ksoftirqd/0 [kernel.kallsyms] [k] __pi_memcpy 9.83% ksoftirqd/0 [kernel.kallsyms] [k] ravb_poll 7.89% ksoftirqd/0 [kernel.kallsyms] [k] skb_put 4.01% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive 3.37% netperf [kernel.kallsyms] [k] __arch_copy_to_user 3.17% swapper [kernel.kallsyms] [k] arch_cpu_idle 2.55% swapper [kernel.kallsyms] [k] tick_nohz_idle_enter 2.04% ksoftirqd/0 [kernel.kallsyms] [k] __pi___inval_dcache_area 2.03% swapper [kernel.kallsyms] [k] _raw_spin_unlock_irq 1.96% ksoftirqd/0 [kernel.kallsyms] [k] __netdev_alloc_skb 1.59% ksoftirqd/0 [kernel.kallsyms] [k] __slab_alloc.isra.83 Test results without RX checksum offload enabled: # /usr/bin/perf_3.16 record -o /run/perf.data -a netperf -t TCP_MAERTS -H 10.4.3.162 MIGRATED TCP MAERTS TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.4.3.162 () port 0 AF_INET : demo enable_enobufs failed: getprotobyname Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 940.20 Summary of output of perf report: 17.10% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 10.99% ksoftirqd/0 [kernel.kallsyms] [k] __pi_memcpy 8.87% ksoftirqd/0 [kernel.kallsyms] [k] ravb_poll 8.16% ksoftirqd/0 [kernel.kallsyms] [k] skb_put 7.42% ksoftirqd/0 [kernel.kallsyms] [k] do_csum 3.91% ksoftirqd/0 [kernel.kallsyms] [k] dev_gro_receive 2.31% swapper [kernel.kallsyms] [k] arch_cpu_idle 2.16% ksoftirqd/0 [kernel.kallsyms] [k] __pi___inval_dcache_area 2.14% ksoftirqd/0 [kernel.kallsyms] [k] __netdev_alloc_skb 1.93% netperf [kernel.kallsyms] [k] __arch_copy_to_user 1.79% swapper [kernel.kallsyms] [k] tick_nohz_idle_enter 1.63% ksoftirqd/0 [kernel.kallsyms] [k] __slab_alloc.isra.83 Above results collected on an R-Car Gen 3 Salvator-X/r8a7796 ES1.0. Also tested on a R-Car Gen 3 Salvator-X/r8a7795 ES1.0. By inspection this also appears to be compatible with the ravb found on R-Car Gen 2 SoCs, however, this patch is currently untested on such hardware. Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 55 +++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index fdf30bfa403bf..a8822a756e083 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -403,8 +403,9 @@ static void ravb_emac_init(struct net_device *ndev) /* Receive frame limit set register */ ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR); - /* PAUSE prohibition */ + /* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */ ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) | + (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) | ECMR_TE | ECMR_RE, ECMR); ravb_set_rate(ndev); @@ -520,6 +521,19 @@ static void ravb_get_tx_tstamp(struct net_device *ndev) } } +static void ravb_rx_csum(struct sk_buff *skb) +{ + u8 *hw_csum; + + /* The hardware checksum is 2 bytes appended to packet data */ + if (unlikely(skb->len < 2)) + return; + hw_csum = skb_tail_pointer(skb) - 2; + skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum)); + skb->ip_summed = CHECKSUM_COMPLETE; + skb_trim(skb, skb->len - 2); +} + /* Packet receive function for Ethernet AVB */ static bool ravb_rx(struct net_device *ndev, int *quota, int q) { @@ -587,8 +601,11 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) ts.tv_nsec = le32_to_cpu(desc->ts_n); shhwtstamps->hwtstamp = timespec64_to_ktime(ts); } + skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); + if (ndev->features & NETIF_F_RXCSUM) + ravb_rx_csum(skb); napi_gro_receive(&priv->napi[q], skb); stats->rx_packets++; stats->rx_bytes += pkt_len; @@ -1842,6 +1859,38 @@ static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) return phy_mii_ioctl(phydev, req, cmd); } +static void ravb_set_rx_csum(struct net_device *ndev, bool enable) +{ + struct ravb_private *priv = netdev_priv(ndev); + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + /* Disable TX and RX */ + ravb_rcv_snd_disable(ndev); + + /* Modify RX Checksum setting */ + ravb_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0); + + /* Enable TX and RX */ + ravb_rcv_snd_enable(ndev); + + spin_unlock_irqrestore(&priv->lock, flags); +} + +static int ravb_set_features(struct net_device *ndev, + netdev_features_t features) +{ + netdev_features_t changed = ndev->features ^ features; + + if (changed & NETIF_F_RXCSUM) + ravb_set_rx_csum(ndev, features & NETIF_F_RXCSUM); + + ndev->features = features; + + return 0; +} + static const struct net_device_ops ravb_netdev_ops = { .ndo_open = ravb_open, .ndo_stop = ravb_close, @@ -1853,6 +1902,7 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_do_ioctl = ravb_do_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_set_features = ravb_set_features, }; /* MDIO bus init function */ @@ -2004,6 +2054,9 @@ static int ravb_probe(struct platform_device *pdev) if (!ndev) return -ENOMEM; + ndev->features = NETIF_F_RXCSUM; + ndev->hw_features = NETIF_F_RXCSUM; + pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); -- GitLab From 20e883204f0268b423799781e5efed786f8a11ba Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Oct 2017 13:56:50 +0200 Subject: [PATCH 0955/1507] net: core: fix kerneldoc comment net/core/dev.c:1306: warning: No description found for parameter 'name' net/core/dev.c:1306: warning: Excess function parameter 'alias' description in 'dev_get_alias' Fixes: 6c5570016b97 ("net: core: decouple ifalias get/set from rtnl lock") Reported-by: kbuild test robot Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 1770097cfd86b..454f054415466 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1295,7 +1295,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) /** * dev_get_alias - get ifalias of a device * @dev: device - * @alias: buffer to store name of ifalias + * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go -- GitLab From ebf6b13142f947be576b40edce214788dfe1d3e3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 4 Oct 2017 14:20:37 +0100 Subject: [PATCH 0956/1507] cxgb4vf: make a couple of functions static The functions t4vf_link_down_rc_str and t4vf_handle_get_port_info are local to the source and do not need to be in global scope, so make them static. Cleans up sparse warnings: symbol 't4vf_link_down_rc_str' was not declared. Should it be static? symbol 't4vf_handle_get_port_info' was not declared. Should it be static? Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index a8d94963b4d07..67aec59a14e6d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -1812,7 +1812,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid) * * Returns a string representation of the Link Down Reason Code. */ -const char *t4vf_link_down_rc_str(unsigned char link_down_rc) +static const char *t4vf_link_down_rc_str(unsigned char link_down_rc) { static const char * const reason[] = { "Link Down", @@ -1838,8 +1838,8 @@ const char *t4vf_link_down_rc_str(unsigned char link_down_rc) * * Processes a GET_PORT_INFO FW reply message. */ -void t4vf_handle_get_port_info(struct port_info *pi, - const struct fw_port_cmd *cmd) +static void t4vf_handle_get_port_info(struct port_info *pi, + const struct fw_port_cmd *cmd) { int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); struct adapter *adapter = pi->adapter; -- GitLab From e774d96b7d2c3489bfb5bbdc2b65ed41cd68d3d5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Oct 2017 15:55:29 +0200 Subject: [PATCH 0957/1507] rtnetlink: remove slave_validate callback no users in the tree. Signed-off-by: Florian Westphal Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 --- net/core/rtnetlink.c | 6 ------ 2 files changed, 9 deletions(-) diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 21837ca68ecc1..6520993ff449e 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -93,9 +93,6 @@ struct rtnl_link_ops { int slave_maxtype; const struct nla_policy *slave_policy; - int (*slave_validate)(struct nlattr *tb[], - struct nlattr *data[], - struct netlink_ext_ack *extack); int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3961f87cdc760..b63c5759641f2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2631,12 +2631,6 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, return err; slave_data = slave_attr; } - if (m_ops->slave_validate) { - err = m_ops->slave_validate(tb, slave_data, - extack); - if (err < 0) - return err; - } } if (dev) { -- GitLab From 5c45121dc39026ab2139910e57cf933fd57d30f2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Oct 2017 15:58:49 +0200 Subject: [PATCH 0958/1507] rtnetlink: remove __rtnl_af_unregister switch the only caller to rtnl_af_unregister. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 2 -- net/core/rtnetlink.c | 14 +------------- net/ipv6/addrconf.c | 4 ++-- 3 files changed, 3 insertions(+), 17 deletions(-) diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 6520993ff449e..e3ca8e2e31033 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -151,8 +151,6 @@ struct rtnl_af_ops { size_t (*get_stats_af_size)(const struct net_device *dev); }; -void __rtnl_af_unregister(struct rtnl_af_ops *ops); - void rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b63c5759641f2..3fb1ca33cba43 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -475,18 +475,6 @@ void rtnl_af_register(struct rtnl_af_ops *ops) } EXPORT_SYMBOL_GPL(rtnl_af_register); -/** - * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. - * @ops: struct rtnl_af_ops * to unregister - * - * The caller must hold the rtnl_mutex. - */ -void __rtnl_af_unregister(struct rtnl_af_ops *ops) -{ - list_del(&ops->list); -} -EXPORT_SYMBOL_GPL(__rtnl_af_unregister); - /** * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. * @ops: struct rtnl_af_ops * to unregister @@ -494,7 +482,7 @@ EXPORT_SYMBOL_GPL(__rtnl_af_unregister); void rtnl_af_unregister(struct rtnl_af_ops *ops) { rtnl_lock(); - __rtnl_af_unregister(ops); + list_del(&ops->list); rtnl_unlock(); } EXPORT_SYMBOL_GPL(rtnl_af_unregister); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f553f72d0bee7..837418ff2d4bf 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6618,9 +6618,9 @@ void addrconf_cleanup(void) unregister_pernet_subsys(&addrconf_ops); ipv6_addr_label_cleanup(); - rtnl_lock(); + rtnl_af_unregister(&inet6_ops); - __rtnl_af_unregister(&inet6_ops); + rtnl_lock(); /* clean dev list */ for_each_netdev(&init_net, dev) { -- GitLab From e9b871ee098dfb91780e13bfc6e91e82c7b4ad73 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 4 Oct 2017 16:22:59 +0200 Subject: [PATCH 0959/1507] selftests: rtnetlink: try concurrent change of ifalias to make sure this is serialized correctly. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 62c87da927708..e8c86c416ed04 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -278,6 +278,12 @@ kci_test_ifalias() ip link show "$devdummy" | grep -q "alias $namewant" check_fail $? + for i in $(seq 1 100); do + uuidgen > "$syspathname" & + done + + wait + # re-add the alias -- kernel should free mem when dummy dev is removed ip link set dev "$devdummy" alias "$namewant" check_err $? -- GitLab From e8fa33a6f6c7688591542db955794b69b8cecc55 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 4 Oct 2017 13:49:12 -0400 Subject: [PATCH 0960/1507] NFSv4/pnfs: Fix an infinite layoutget loop Since we can now use a lock stateid or a delegation stateid, that differs from the context stateid, we need to change the test in nfs4_layoutget_handle_exception() to take this into account. This fixes an infinite layoutget loop in the NFS client whereby it keeps retrying the initial layoutget using the same broken stateid. Fixes: 70d2f7b1ea19b ("pNFS: Use the standard I/O stateid when...") Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6c61e2b996351..f90090e8c959b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8399,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, lo = NFS_I(inode)->layout; /* If the open stateid was bad, then recover it. */ if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) || - nfs4_stateid_match_other(&lgp->args.stateid, - &lgp->args.ctx->state->stateid)) { + !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) { spin_unlock(&inode->i_lock); exception->state = lgp->args.ctx->state; exception->stateid = &lgp->args.stateid; -- GitLab From c818fa9e288be5be7e360c33cf4f5e30f9fa206e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 4 Oct 2017 10:48:35 -0700 Subject: [PATCH 0961/1507] net: cache skb_shinfo() in skb_try_coalesce() Compiler does not really know that skb_shinfo(to|from) are constants in skb_try_coalesce(), lets cache their values to shrink code. We might even take care of skb_zcopy() calls later. $ size net/core/skbuff.o.before net/core/skbuff.o text data bss dec hex filename 40727 1298 0 42025 a429 net/core/skbuff.o.before 40631 1298 0 41929 a3c9 net/core/skbuff.o Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d98c2e3ce2bfd..822a90e56aea2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4767,6 +4767,7 @@ EXPORT_SYMBOL(kfree_skb_partial); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) { + struct skb_shared_info *to_shinfo, *from_shinfo; int i, delta, len = from->len; *fragstolen = false; @@ -4781,7 +4782,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, return true; } - if (skb_has_frag_list(to) || skb_has_frag_list(from)) + to_shinfo = skb_shinfo(to); + from_shinfo = skb_shinfo(from); + if (to_shinfo->frag_list || from_shinfo->frag_list) return false; if (skb_zcopy(to) || skb_zcopy(from)) return false; @@ -4790,8 +4793,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct page *page; unsigned int offset; - if (skb_shinfo(to)->nr_frags + - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + if (to_shinfo->nr_frags + + from_shinfo->nr_frags >= MAX_SKB_FRAGS) return false; if (skb_head_is_locked(from)) @@ -4802,12 +4805,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); - skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + skb_fill_page_desc(to, to_shinfo->nr_frags, page, offset, skb_headlen(from)); *fragstolen = true; } else { - if (skb_shinfo(to)->nr_frags + - skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + if (to_shinfo->nr_frags + + from_shinfo->nr_frags > MAX_SKB_FRAGS) return false; delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); @@ -4815,19 +4818,19 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, WARN_ON_ONCE(delta < len); - memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, - skb_shinfo(from)->frags, - skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); - skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + memcpy(to_shinfo->frags + to_shinfo->nr_frags, + from_shinfo->frags, + from_shinfo->nr_frags * sizeof(skb_frag_t)); + to_shinfo->nr_frags += from_shinfo->nr_frags; if (!skb_cloned(from)) - skb_shinfo(from)->nr_frags = 0; + from_shinfo->nr_frags = 0; /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ - for (i = 0; i < skb_shinfo(from)->nr_frags; i++) - skb_frag_ref(from, i); + for (i = 0; i < from_shinfo->nr_frags; i++) + __skb_frag_ref(&from_shinfo->frags[i]); to->truesize += delta; to->len += len; -- GitLab From e19cd282ebedb801e572efae5df2f88d573932ce Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Sun, 1 Oct 2017 09:54:35 +0300 Subject: [PATCH 0962/1507] IB/mlx5: Fix label order in error path handling When UAR get_page fails, it needs to continue to cleanup debugfs for congestion control parameters. Labels for error path were incorrectly ordered. This patch fixes to do correct cleanup on debugfs init failure and uar get page failure. Fixes: 4a2da0b8c078 ("IB/mlx5: Add debug control parameters for congestion control") Signed-off-by: Parav Pandit Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index d6fbad8f34aa7..552f7bd4ecc38 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4174,9 +4174,9 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) err_uar_page: mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar); -err_cnt: - mlx5_ib_cleanup_cong_debugfs(dev); err_cong: + mlx5_ib_cleanup_cong_debugfs(dev); +err_cnt: if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) mlx5_ib_dealloc_counters(dev); -- GitLab From efe63c220e57ce74e240670399912e609ac125d9 Mon Sep 17 00:00:00 2001 From: "Amrani, Ram" Date: Tue, 3 Oct 2017 14:47:26 +0300 Subject: [PATCH 0963/1507] RDMA/qedr: Parse VLAN ID correctly and ignore the value of zero Rename vlan_id field name to vlan as it contains more than the vlan_id. Mask out non vlan id fields from vlan tag of the QED LL2 RX GSI vlan output. As it is expected to be vlan id only. Ignore vlan_id with value of zero. Fixes: abd49676c707 ("qed: Add RoCE ll2 & GSI support") Signed-off-by: Ram Amrani Signed-off-by: Michal Kalderon Signed-off-by: Doug Ledford --- drivers/infiniband/hw/qedr/qedr.h | 2 +- drivers/infiniband/hw/qedr/qedr_cm.c | 10 +++++++--- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index b2bb42e2805dd..254083b524bd9 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -387,7 +387,7 @@ struct qedr_qp { u8 wqe_size; u8 smac[ETH_ALEN]; - u16 vlan_id; + u16 vlan; int rc; } *rqe_wr_id; diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 4689e802b3326..5ebbe49523864 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -105,7 +105,7 @@ void qedr_ll2_complete_rx_packet(void *cxt, qp->rqe_wr_id[qp->rq.gsi_cons].rc = data->u.data_length_error ? -EINVAL : 0; - qp->rqe_wr_id[qp->rq.gsi_cons].vlan_id = data->vlan; + qp->rqe_wr_id[qp->rq.gsi_cons].vlan = data->vlan; /* note: length stands for data length i.e. GRH is excluded */ qp->rqe_wr_id[qp->rq.gsi_cons].sg_list[0].length = data->length.data_length; @@ -694,6 +694,7 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) struct qedr_cq *cq = get_qedr_cq(ibcq); struct qedr_qp *qp = dev->gsi_qp; unsigned long flags; + u16 vlan_id; int i = 0; spin_lock_irqsave(&cq->cq_lock, flags); @@ -712,9 +713,12 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) wc[i].wc_flags |= IB_WC_GRH | IB_WC_IP_CSUM_OK; ether_addr_copy(wc[i].smac, qp->rqe_wr_id[qp->rq.cons].smac); wc[i].wc_flags |= IB_WC_WITH_SMAC; - if (qp->rqe_wr_id[qp->rq.cons].vlan_id) { + + vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan & + VLAN_VID_MASK; + if (vlan_id) { wc[i].wc_flags |= IB_WC_WITH_VLAN; - wc[i].vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan_id; + wc[i].vlan_id = vlan_id; } qedr_inc_sw_cons(&qp->rq); -- GitLab From 1736b4c99d1c53abec042d41b702aeabeb65d86a Mon Sep 17 00:00:00 2001 From: "Amrani, Ram" Date: Tue, 3 Oct 2017 14:47:27 +0300 Subject: [PATCH 0964/1507] RDMA/qedr: Parse vlan priority as sl Parse the vlan priority from the vlan tag and configure it to the WC's sl field. Fixes: abd49676c707 ("qed: Add RoCE ll2 & GSI support") Signed-off-by: Ram Amrani Signed-off-by: Michal Kalderon Signed-off-by: Doug Ledford --- drivers/infiniband/hw/qedr/qedr_cm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c index 5ebbe49523864..ad8965397cf76 100644 --- a/drivers/infiniband/hw/qedr/qedr_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_cm.c @@ -719,6 +719,8 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) if (vlan_id) { wc[i].wc_flags |= IB_WC_WITH_VLAN; wc[i].vlan_id = vlan_id; + wc[i].sl = (qp->rqe_wr_id[qp->rq.cons].vlan & + VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } qedr_inc_sw_cons(&qp->rq); -- GitLab From 43bfc24ec1d69853d706cb3ebfdb9088846b9b50 Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Tue, 3 Oct 2017 11:11:49 -0500 Subject: [PATCH 0965/1507] i40iw: Add missing memory barriers Remove duplicate set_64bit_val call to offset 24. Replace some instances of set_64bit_val with i40iw_insert_wqe_hdr as valid bit needs a write barrier and should be the last write operation for the WQE. Fixes: 786c6adb3a94 ("i40iw: add puda code") Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_ctrl.c | 2 +- drivers/infiniband/hw/i40iw/i40iw_p.h | 2 ++ drivers/infiniband/hw/i40iw/i40iw_puda.c | 11 ++++------- 3 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index d1f5345f04f08..42ca5346777dd 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -48,7 +48,7 @@ * @wqe: cqp wqe for header * @header: header for the cqp wqe */ -static inline void i40iw_insert_wqe_hdr(u64 *wqe, u64 header) +void i40iw_insert_wqe_hdr(u64 *wqe, u64 header) { wmb(); /* make sure WQE is populated before polarity is set */ set_64bit_val(wqe, 24, header); diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h index e217a1259f570..5498ad01c280f 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_p.h +++ b/drivers/infiniband/hw/i40iw/i40iw_p.h @@ -59,6 +59,8 @@ enum i40iw_status_code i40iw_sc_mr_fast_register(struct i40iw_sc_qp *qp, struct i40iw_fast_reg_stag_info *info, bool post_sq); +void i40iw_insert_wqe_hdr(u64 *wqe, u64 header); + /* HMC/FPM functions */ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev, u8 hmc_fn_id); diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index c2cab20c4bc5d..59f70676f0e03 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -123,12 +123,11 @@ static void i40iw_puda_post_recvbuf(struct i40iw_puda_rsrc *rsrc, u32 wqe_idx, get_64bit_val(wqe, 24, &offset24); offset24 = (offset24) ? 0 : LS_64(1, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, offset24); set_64bit_val(wqe, 0, buf->mem.pa); set_64bit_val(wqe, 8, LS_64(buf->mem.size, I40IWQPSQ_FRAG_LEN)); - set_64bit_val(wqe, 24, offset24); + i40iw_insert_wqe_hdr(wqe, offset24); } /** @@ -409,9 +408,7 @@ enum i40iw_status_code i40iw_puda_send(struct i40iw_sc_qp *qp, set_64bit_val(wqe, 8, LS_64(info->len, I40IWQPSQ_FRAG_LEN)); set_64bit_val(wqe, 16, header[0]); - /* Ensure all data is written before writing valid bit */ - wmb(); - set_64bit_val(wqe, 24, header[1]); + i40iw_insert_wqe_hdr(wqe, header[1]); i40iw_debug_buf(qp->dev, I40IW_DEBUG_PUDA, "PUDA SEND WQE", wqe, 32); i40iw_qp_post_wr(&qp->qp_uk); @@ -539,7 +536,7 @@ static enum i40iw_status_code i40iw_puda_qp_wqe(struct i40iw_sc_dev *dev, struct LS_64(2, I40IW_CQPSQ_QP_NEXTIWSTATE) | LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID); - set_64bit_val(wqe, 24, header); + i40iw_insert_wqe_hdr(wqe, header); i40iw_debug_buf(cqp->dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, 32); i40iw_sc_cqp_post_sq(cqp); @@ -655,7 +652,7 @@ static enum i40iw_status_code i40iw_puda_cq_wqe(struct i40iw_sc_dev *dev, struct LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) | LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) | LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID); - set_64bit_val(wqe, 24, header); + i40iw_insert_wqe_hdr(wqe, header); i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, I40IW_CQP_WQE_SIZE * 8); -- GitLab From 789f903fd75036f937409a9a1616a5a5e5cc5bae Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Tue, 3 Oct 2017 11:11:50 -0500 Subject: [PATCH 0966/1507] i40iw: Fix port number for query QP Port number 0 is an invalid port number. Set it to 1 as there is one port per i40iw device. Fixes: d37498417947 ("i40iw: add files for iwarp interface") Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Doug Ledford --- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 28b3d02d511b3..62be0a41ad0b2 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -826,12 +826,14 @@ static int i40iw_query_qp(struct ib_qp *ibqp, attr->cap.max_inline_data = I40IW_MAX_INLINE_DATA_SIZE; attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT; attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT; + attr->port_num = 1; init_attr->event_handler = iwqp->ibqp.event_handler; init_attr->qp_context = iwqp->ibqp.qp_context; init_attr->send_cq = iwqp->ibqp.send_cq; init_attr->recv_cq = iwqp->ibqp.recv_cq; init_attr->srq = iwqp->ibqp.srq; init_attr->cap = attr->cap; + init_attr->port_num = 1; return 0; } -- GitLab From 2a8408e5372503fe4df9b5bbb49fb3af0c212c67 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 3 Oct 2017 12:51:58 +0300 Subject: [PATCH 0967/1507] drm/i915/cnl: Reprogram DMC firmware after S3/S4 resume The DMC firmware program memory is lost after S3/S4 system suspend, so we need to reprogram it during resume. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103070 Fixes: cebfcead63de ("drm/i915/DMC/CNL: Load DMC on CNL") Cc: Anusha Srivatsa Cc: Animesh Manna Cc: Rodrigo Vivi Signed-off-by: Imre Deak Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20171003095159.711-1-imre.deak@intel.com (cherry picked from commit 57522c4c87de20d8f7ad4e142a3a4334066d55ff) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_runtime_pm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index b66d8e136aa37..b3a087cb0860d 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -2782,6 +2782,9 @@ static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume /* 6. Enable DBUF */ gen9_dbuf_enable(dev_priv); + + if (resume && dev_priv->csr.dmc_payload) + intel_csr_load_program(dev_priv); } #undef CNL_PROCMON_IDX -- GitLab From 069d40f5834ad26a58f269225a7e13af17019062 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 3 Oct 2017 12:51:59 +0300 Subject: [PATCH 0968/1507] drm/i915/glk: Fix DMC/DC state idleness calculation According to BSpec GLK like BXT needs to ignore the idle state of cores before starting the DMC firmware's DC state handler. Fixes: dbb28b5c3d3c ("drm/i915/DMC/GLK: Load DMC on GLK") Cc: Anusha Srivatsa Cc: Rodrigo Vivi Signed-off-by: Imre Deak Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20171003095159.711-2-imre.deak@intel.com (cherry picked from commit b7208a3f3e52791571df064fb96025ad48edd1bf) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/intel_csr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 965988f79a558..92c1f8e166dc5 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -216,7 +216,7 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) mask = DC_STATE_DEBUG_MASK_MEMORY_UP; - if (IS_BROXTON(dev_priv)) + if (IS_GEN9_LP(dev_priv)) mask |= DC_STATE_DEBUG_MASK_CORES; /* The below bit doesn't need to be cleared ever afterwards */ -- GitLab From 324bda9e6c5add86ba2e1066476481c48132aca0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:21 -0700 Subject: [PATCH 0969/1507] bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 46 ++-- include/linux/bpf.h | 32 +++ include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 42 +++- kernel/bpf/cgroup.c | 467 ++++++++++++++++++++++++++----------- kernel/bpf/core.c | 31 +++ kernel/bpf/syscall.c | 37 ++- kernel/cgroup/cgroup.c | 28 ++- 8 files changed, 516 insertions(+), 169 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d41d40ac3efdb..102e56fbb6dea 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -14,27 +14,42 @@ struct bpf_sock_ops_kern; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_prog_list { + struct list_head node; + struct bpf_prog *prog; +}; + +struct bpf_prog_array; + struct cgroup_bpf { - /* - * Store two sets of bpf_prog pointers, one for programs that are - * pinned directly to this cgroup, and one for those that are effective - * when this cgroup is accessed. + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; - bool disallow_override[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_BPF_ATTACH_TYPE]; + u32 flags[MAX_BPF_ATTACH_TYPE]; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array __rcu *inactive; }; void cgroup_bpf_put(struct cgroup *cgrp); -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); +int cgroup_bpf_inherit(struct cgroup *cgrp); -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool overridable); +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); -/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable); +/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -96,8 +111,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} -static inline void cgroup_bpf_inherit(struct cgroup *cgrp, - struct cgroup *parent) {} +static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 252f4bc9eb258..a6964b75f0706 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -241,6 +241,38 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +/* an array of programs to be executed under rcu_lock. + * + * Typical usage: + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * + * the structure returned by bpf_prog_array_alloc() should be populated + * with program pointers and the last pointer must be NULL. + * The user has to keep refcnt on the program and make sure the program + * is removed from the array before bpf_prog_put(). + * The 'struct bpf_prog_array *' should only be replaced with xchg() + * since other cpus are walking the array of pointers in parallel. + */ +struct bpf_prog_array { + struct rcu_head rcu; + struct bpf_prog *progs[0]; +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); + +#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog **_prog; \ + u32 _ret = 1; \ + rcu_read_lock(); \ + _prog = rcu_dereference(array)->progs; \ + for (; *_prog; _prog++) \ + _ret &= func(*_prog, ctx); \ + rcu_read_unlock(); \ + _ret; \ + }) + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/linux/filter.h b/include/linux/filter.h index 911d454af1078..2d2db394b0ca7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -481,7 +481,7 @@ struct sk_filter { struct bpf_prog *prog; }; -#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi) #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6d2137b4cf380..762f74bc6c479 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,11 +143,47 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command - * to the given target_fd cgroup the descendent cgroup will be able to - * override effective bpf program that was inherited from this cgroup +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 546113430049d..6b7500bbdb537 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -27,129 +27,361 @@ void cgroup_bpf_put(struct cgroup *cgrp) { unsigned int type; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) { - struct bpf_prog *prog = cgrp->bpf.prog[type]; - - if (prog) { - bpf_prog_put(prog); + for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog_list *pl, *tmp; + + list_for_each_entry_safe(pl, tmp, progs, node) { + list_del(&pl->node); + bpf_prog_put(pl->prog); + kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } + bpf_prog_array_free(cgrp->bpf.effective[type]); + } +} + +/* count number of elements in the list. + * it's slow but the list cannot be long + */ +static u32 prog_list_length(struct list_head *head) +{ + struct bpf_prog_list *pl; + u32 cnt = 0; + + list_for_each_entry(pl, head, node) { + if (!pl->prog) + continue; + cnt++; } + return cnt; +} + +/* if parent has non-overridable prog attached, + * disallow attaching new programs to the descendent cgroup. + * if parent has overridable or multi-prog, allow attaching + */ +static bool hierarchy_allows_attach(struct cgroup *cgrp, + enum bpf_attach_type type, + u32 new_flags) +{ + struct cgroup *p; + + p = cgroup_parent(cgrp); + if (!p) + return true; + do { + u32 flags = p->bpf.flags[type]; + u32 cnt; + + if (flags & BPF_F_ALLOW_MULTI) + return true; + cnt = prog_list_length(&p->bpf.progs[type]); + WARN_ON_ONCE(cnt > 1); + if (cnt == 1) + return !!(flags & BPF_F_ALLOW_OVERRIDE); + p = cgroup_parent(p); + } while (p); + return true; +} + +/* compute a chain of effective programs for a given cgroup: + * start from the list of programs in this cgroup and add + * all parent programs. + * Note that parent's F_ALLOW_OVERRIDE-type program is yielding + * to programs in this cgroup + */ +static int compute_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu **array) +{ + struct bpf_prog_array __rcu *progs; + struct bpf_prog_list *pl; + struct cgroup *p = cgrp; + int cnt = 0; + + /* count number of effective programs by walking parents */ + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[type]); + p = cgroup_parent(p); + } while (p); + + progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!progs) + return -ENOMEM; + + /* populate the array with effective progs */ + cnt = 0; + p = cgrp; + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + list_for_each_entry(pl, + &p->bpf.progs[type], node) { + if (!pl->prog) + continue; + rcu_dereference_protected(progs, 1)-> + progs[cnt++] = pl->prog; + } + p = cgroup_parent(p); + } while (p); + + *array = progs; + return 0; +} + +static void activate_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu *array) +{ + struct bpf_prog_array __rcu *old_array; + + old_array = xchg(&cgrp->bpf.effective[type], array); + /* free prog array after grace period, since __cgroup_bpf_run_*() + * might be still walking the array + */ + bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify - * @parent: the parent to inherit from */ -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) +int cgroup_bpf_inherit(struct cgroup *cgrp) { - unsigned int type; +/* has to use marco instead of const int, since compiler thinks + * that array below is variable length + */ +#define NR ARRAY_SIZE(cgrp->bpf.effective) + struct bpf_prog_array __rcu *arrays[NR] = {}; + int i; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) { - struct bpf_prog *e; + for (i = 0; i < NR; i++) + INIT_LIST_HEAD(&cgrp->bpf.progs[i]); - e = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - rcu_assign_pointer(cgrp->bpf.effective[type], e); - cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; - } + for (i = 0; i < NR; i++) + if (compute_effective_progs(cgrp, i, &arrays[i])) + goto cleanup; + + for (i = 0; i < NR; i++) + activate_effective_progs(cgrp, i, arrays[i]); + + return 0; +cleanup: + for (i = 0; i < NR; i++) + bpf_prog_array_free(arrays[i]); + return -ENOMEM; } +#define BPF_CGROUP_MAX_PROGS 64 + /** - * __cgroup_bpf_update() - Update the pinned program of a cgroup, and + * __cgroup_bpf_attach() - Attach the program to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse - * @parent: The parent of @cgrp, or %NULL if @cgrp is the root - * @prog: A new program to pin - * @type: Type of pinning operation (ingress/egress) - * - * Each cgroup has a set of two pointers for bpf programs; one for eBPF - * programs it owns, and which is effective for execution. - * - * If @prog is not %NULL, this function attaches a new program to the cgroup - * and releases the one that is currently attached, if any. @prog is then made - * the effective program of type @type in that cgroup. - * - * If @prog is %NULL, the currently attached program of type @type is released, - * and the effective program of the parent cgroup (if any) is inherited to - * @cgrp. - * - * Then, the descendants of @cgrp are walked and the effective program for - * each of them is set to the effective program of @cgrp unless the - * descendant has its own program attached, in which case the subbranch is - * skipped. This ensures that delegated subcgroups with own programs are left - * untouched. + * @prog: A program to attach + * @type: Type of attach operation * * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool new_overridable) +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct bpf_prog *old_prog, *effective = NULL; - struct cgroup_subsys_state *pos; - bool overridable = true; - - if (parent) { - overridable = !parent->bpf.disallow_override[type]; - effective = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - } - - if (prog && effective && !overridable) - /* if parent has non-overridable prog attached, disallow - * attaching new programs to descendent cgroup - */ + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + bool pl_was_allocated; + u32 old_flags; + int err; + + if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + /* invalid combination */ + return -EINVAL; + + if (!hierarchy_allows_attach(cgrp, type, flags)) return -EPERM; - if (prog && effective && overridable != new_overridable) - /* if parent has overridable prog attached, only - * allow overridable programs in descendent cgroup + if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + /* Disallow attaching non-overridable on top + * of existing overridable in this cgroup. + * Disallow attaching multi-prog if overridable or none */ return -EPERM; - old_prog = cgrp->bpf.prog[type]; - - if (prog) { - overridable = new_overridable; - effective = prog; - if (old_prog && - cgrp->bpf.disallow_override[type] == new_overridable) - /* disallow attaching non-overridable on top - * of existing overridable in this cgroup - * and vice versa - */ - return -EPERM; + if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + return -E2BIG; + + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + pl->prog = prog; + list_add_tail(&pl->node, progs); + } else { + if (list_empty(progs)) { + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + list_add_tail(&pl->node, progs); + } else { + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl_was_allocated = false; + } + pl->prog = prog; } - if (!prog && !old_prog) - /* report error when trying to detach and nothing is attached */ - return -ENOENT; + old_flags = cgrp->bpf.flags[type]; + cgrp->bpf.flags[type] = flags; - cgrp->bpf.prog[type] = prog; + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); - css_for_each_descendant_pre(pos, &cgrp->self) { - struct cgroup *desc = container_of(pos, struct cgroup, self); - - /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) { - pos = css_rightmost_descendant(pos); - } else { - rcu_assign_pointer(desc->bpf.effective[type], - effective); - desc->bpf.disallow_override[type] = !overridable; - } + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; } - if (prog) - static_branch_inc(&cgroup_bpf_enabled_key); + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + static_branch_inc(&cgroup_bpf_enabled_key); if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and cleanup the prog list */ + pl->prog = old_prog; + if (pl_was_allocated) { + list_del(&pl->node); + kfree(pl); + } + return err; +} + +/** + * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * propagate the change to descendants + * @cgrp: The cgroup which descendants to traverse + * @prog: A program to detach or NULL + * @type: Type of detach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 unused_flags) +{ + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + int err; + + if (flags & BPF_F_ALLOW_MULTI) { + if (!prog) + /* to detach MULTI prog the user has to specify valid FD + * of the program to be detached + */ + return -EINVAL; + } else { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + } + + if (flags & BPF_F_ALLOW_MULTI) { + /* find the prog and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog != prog) + continue; + old_prog = prog; + /* mark it deleted, so it's ignored while + * recomputing effective + */ + pl->prog = NULL; + break; + } + if (!old_prog) + return -ENOENT; + } else { + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) + */ + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl->prog = NULL; + } + + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; + } + + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* now can actually delete it from this cgroup list */ + list_del(&pl->node); + kfree(pl); + if (list_empty(progs)) + /* last program was detached, reset flags to zero */ + cgrp->bpf.flags[type] = 0; + + bpf_prog_put(old_prog); + static_branch_dec(&cgroup_bpf_enabled_key); + return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and restore back old_prog */ + pl->prog = old_prog; + return err; } /** @@ -171,36 +403,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type) { - struct bpf_prog *prog; + unsigned int offset = skb->data - skb_network_header(skb); + struct sock *save_sk; struct cgroup *cgrp; - int ret = 0; + int ret; if (!sk || !sk_fullsock(sk)) return 0; - if (sk->sk_family != AF_INET && - sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) { - unsigned int offset = skb->data - skb_network_header(skb); - struct sock *save_sk = skb->sk; - - skb->sk = sk; - __skb_push(skb, offset); - ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM; - __skb_pull(skb, offset); - skb->sk = save_sk; - } - - rcu_read_unlock(); - - return ret; + save_sk = skb->sk; + skb->sk = sk; + __skb_push(skb, offset); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, + bpf_prog_run_save_cb); + __skb_pull(skb, offset); + skb->sk = save_sk; + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); @@ -221,19 +443,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; + int ret; - rcu_read_unlock(); - - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -258,18 +471,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); + int ret; - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, + BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a940..6b49e1991ae7a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1381,6 +1381,37 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +static struct { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +} empty_prog_array = { + .null_prog = NULL, +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +{ + if (prog_cnt) + return kzalloc(sizeof(struct bpf_prog_array) + + sizeof(struct bpf_prog *) * (prog_cnt + 1), + flags); + + return &empty_prog_array.hdr; +} + +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) +{ + if (!progs || + progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + return; + kfree_rcu(progs, rcu); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b927da66f653f..51bee695d32c2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1168,6 +1168,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach) return 0; } +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; @@ -1181,7 +1184,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) return -EINVAL; switch (attr->attach_type) { @@ -1212,8 +1215,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, - attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); if (ret) bpf_prog_put(prog); cgroup_put(cgrp); @@ -1225,6 +1228,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; + struct bpf_prog *prog; struct cgroup *cgrp; int ret; @@ -1237,23 +1242,33 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: + ptype = BPF_PROG_TYPE_CGROUP_SKB; + break; case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; case BPF_CGROUP_SOCK_OPS: - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); - cgroup_put(cgrp); + ptype = BPF_PROG_TYPE_SOCK_OPS; break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ret = sockmap_get_from_fd(attr, false); - break; + return sockmap_get_from_fd(attr, false); default: return -EINVAL; } + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + cgroup_put(cgrp); return ret; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd452380..57eb866ae78d5 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) if (ret) goto destroy_root; + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + trace_cgroup_setup_root(root); /* @@ -4713,6 +4716,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_idr_free; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4747,13 +4753,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - if (parent) - cgroup_bpf_inherit(cgrp, parent); - cgroup_propagate_control(cgrp); return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5736,14 +5741,23 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable) +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct cgroup *parent = cgroup_parent(cgrp); int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); + ret = __cgroup_bpf_detach(cgrp, prog, type, flags); mutex_unlock(&cgroup_mutex); return ret; } -- GitLab From 468e2f64d220fe2dc11caa2bcb9b3a1e50fc7321 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:22 -0700 Subject: [PATCH 0970/1507] bpf: introduce BPF_PROG_QUERY command introduce BPF_PROG_QUERY command to retrieve a set of either attached programs to given cgroup or a set of effective programs that will execute for events within a cgroup Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 4 ++++ include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 13 +++++++++++ kernel/bpf/cgroup.c | 46 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 38 +++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 ++++++++++++++++++++++++++++ kernel/cgroup/cgroup.c | 10 +++++++++ 7 files changed, 148 insertions(+) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 102e56fbb6dea..359b6f5d3d90c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -44,12 +44,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a6964b75f0706..a67daea731ab8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -260,6 +260,9 @@ struct bpf_prog_array { struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt); #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ ({ \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 762f74bc6c479..cb2b9f95160aa 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -92,6 +92,7 @@ enum bpf_cmd { BPF_PROG_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, }; enum bpf_map_type { @@ -211,6 +212,9 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + #define BPF_OBJ_NAME_LEN 16U union bpf_attr { @@ -289,6 +293,15 @@ union bpf_attr { __u32 info_len; __aligned_u64 info; } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; } __attribute__((aligned(8))); /* BPF helper function descriptions: diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6b7500bbdb537..e88abc0865d50 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -384,6 +384,52 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, return err; } +/* Must be called with cgroup_mutex held to avoid races. */ +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + enum bpf_attach_type type = attr->query.attach_type; + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + int cnt, ret = 0, i; + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) + cnt = bpf_prog_array_length(cgrp->bpf.effective[type]); + else + cnt = prog_list_length(progs); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + return -EFAULT; + if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + /* return early if user requested only program count + flags */ + return 0; + if (attr->query.prog_cnt < cnt) { + cnt = attr->query.prog_cnt; + ret = -ENOSPC; + } + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type], + prog_ids, cnt); + } else { + struct bpf_prog_list *pl; + u32 id; + + i = 0; + list_for_each_entry(pl, progs, node) { + id = pl->prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + } + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6b49e1991ae7a..eba966c09053f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1412,6 +1412,44 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) kfree_rcu(progs, rcu); } +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) +{ + struct bpf_prog **prog; + u32 cnt = 0; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) + cnt++; + rcu_read_unlock(); + return cnt; +} + +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt) +{ + struct bpf_prog **prog; + u32 i = 0, id; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) { + id = (*prog)->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) { + rcu_read_unlock(); + return -EFAULT; + } + if (++i == cnt) { + prog++; + break; + } + } + rcu_read_unlock(); + if (*prog) + return -ENOSPC; + return 0; +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 51bee695d32c2..0048cb24ba7b4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1272,6 +1272,37 @@ static int bpf_prog_detach(const union bpf_attr *attr) return ret; } +#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt + +static int bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (CHECK_ATTR(BPF_PROG_QUERY)) + return -EINVAL; + if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) + return -EINVAL; + + switch (attr->query.attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: + break; + default: + return -EINVAL; + } + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + ret = cgroup_bpf_query(cgrp, attr, uattr); + cgroup_put(cgrp); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -1568,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; + case BPF_PROG_QUERY: + err = bpf_prog_query(&attr, uattr); + break; #endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 57eb866ae78d5..269512b94a947 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, mutex_unlock(&cgroup_mutex); return ret; } +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + mutex_unlock(&cgroup_mutex); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ -- GitLab From 390ee7e29fc8e6e90d3065b00afb047c4ee552f9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:23 -0700 Subject: [PATCH 0971/1507] bpf: enforce return code for cgroup-bpf programs with addition of tnum logic the verifier got smart enough and we can enforce return codes at program load time. For now do so for cgroup-bpf program types. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 40 ++++++++++++ tools/testing/selftests/bpf/test_verifier.c | 72 +++++++++++++++++++++ 2 files changed, 112 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cf9b72c59a06..52b022310f6ac 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3073,6 +3073,43 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static int check_return_code(struct bpf_verifier_env *env) +{ + struct bpf_reg_state *reg; + struct tnum range = tnum_range(0, 1); + + switch (env->prog->type) { + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_SOCK_OPS: + break; + default: + return 0; + } + + reg = &env->cur_state.regs[BPF_REG_0]; + if (reg->type != SCALAR_VALUE) { + verbose("At program exit the register R0 is not a known value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + + if (!tnum_in(range, reg->var_off)) { + verbose("At program exit the register R0 "); + if (!tnum_is_unknown(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose("has value %s", tn_buf); + } else { + verbose("has unknown scalar value"); + } + verbose(" should have been 0 or 1\n"); + return -EINVAL; + } + return 0; +} + /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered @@ -3863,6 +3900,9 @@ static int do_check(struct bpf_verifier_env *env) return -EACCES; } + err = check_return_code(env); + if (err) + return err; process_bpf_exit: insn_idx = pop_stack(env, &prev_insn_idx); if (insn_idx < 0) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 290d5056c1650..cc91d0159f436 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -6892,6 +6892,78 @@ static struct bpf_test tests[] = { .result = ACCEPT, .prog_type = BPF_PROG_TYPE_XDP, }, + { + "bpf_exit with invalid return code. test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x0; 0xffffffff)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x0; 0x3)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test5", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has value (0x2; 0x0)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test6", + .insns = { + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .errstr = "R0 is not a known value (ctx)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "bpf_exit with invalid return code. test7", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4), + BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .errstr = "R0 has unknown scalar value", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, }; static int probe_filter_length(const struct bpf_insn *fp) -- GitLab From 244d20efdb68c5c1a26c667baeb232ea163e2f69 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:24 -0700 Subject: [PATCH 0972/1507] libbpf: introduce bpf_prog_detach2() introduce bpf_prog_detach2() that takes one more argument prog_fd vs bpf_prog_detach() that takes only attach_fd and type. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/lib/bpf/bpf.c | 12 ++++++++++++ tools/lib/bpf/bpf.h | 1 + 2 files changed, 13 insertions(+) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index daf624e4c720e..d4b6ba8292eec 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -291,6 +291,18 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type) return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); } +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 118d00535a0d4..afd64727c9cff 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -66,6 +66,7 @@ int bpf_obj_get(const char *pathname); int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); -- GitLab From 39323e788cb672adba8709ca407bd6763aae577d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:25 -0700 Subject: [PATCH 0973/1507] samples/bpf: add multi-prog cgroup test case create 5 cgroups, attach 6 progs and check that progs are executed as: cgrp1 (MULTI progs A, B) -> cgrp2 (OVERRIDE prog C) -> cgrp3 (MULTI prog D) -> cgrp4 (OVERRIDE prog E) -> cgrp5 (NONE prog F) the event in cgrp5 triggers execution of F,D,A,B in that order. if prog F is detached, the execution is E,D,A,B if prog F and D are detached, the execution is E,A,B if prog F, E and D are detached, the execution is C,A,B Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/cgroup_helpers.c | 4 +- samples/bpf/test_cgrp2_attach2.c | 188 ++++++++++++++++++++++++++++++- 2 files changed, 185 insertions(+), 7 deletions(-) diff --git a/samples/bpf/cgroup_helpers.c b/samples/bpf/cgroup_helpers.c index 9d1be94264019..88bdcf4b1670b 100644 --- a/samples/bpf/cgroup_helpers.c +++ b/samples/bpf/cgroup_helpers.c @@ -56,7 +56,7 @@ int setup_cgroup_environment(void) return 1; } - if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL)) { + if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) { log_err("mount cgroup2"); return 1; } @@ -163,7 +163,7 @@ int create_and_get_cgroup(char *path) format_cgroup_path(cgroup_path, path); if (mkdir(cgroup_path, 0777) && errno != EEXIST) { - log_err("mkdiring cgroup"); + log_err("mkdiring cgroup %s .. %s", path, cgroup_path); return 0; } diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c index 3049b1f26267c..9a9f6836e5e97 100644 --- a/samples/bpf/test_cgrp2_attach2.c +++ b/samples/bpf/test_cgrp2_attach2.c @@ -30,7 +30,7 @@ #define FOO "/foo" #define BAR "/foo/bar/" -#define PING_CMD "ping -c1 -w1 127.0.0.1" +#define PING_CMD "ping -c1 -w1 127.0.0.1 > /dev/null" char bpf_log_buf[BPF_LOG_BUF_SIZE]; @@ -55,8 +55,7 @@ static int prog_load(int verdict) return ret; } - -int main(int argc, char **argv) +static int test_foo_bar(void) { int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0; @@ -189,8 +188,187 @@ int main(int argc, char **argv) close(bar); cleanup_cgroup_environment(); if (!rc) - printf("PASS\n"); + printf("### override:PASS\n"); + else + printf("### override:FAIL\n"); + return rc; +} + +static int map_fd = -1; + +static int prog_load_cnt(int verdict, int val) +{ + if (map_fd < 0) + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + struct bpf_insn prog[] = { + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + int ret; + + ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); + + if (ret < 0) { + log_err("Loading program"); + printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); + return 0; + } + return ret; +} + + +static int test_multiprog(void) +{ + int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; + int drop_prog, allow_prog[6] = {}, rc = 0; + unsigned long long value; + int i = 0; + + for (i = 0; i < 6; i++) { + allow_prog[i] = prog_load_cnt(1, 1 << i); + if (!allow_prog[i]) + goto err; + } + drop_prog = prog_load_cnt(0, 1); + if (!drop_prog) + goto err; + + if (setup_cgroup_environment()) + goto err; + + cg1 = create_and_get_cgroup("/cg1"); + if (!cg1) + goto err; + cg2 = create_and_get_cgroup("/cg1/cg2"); + if (!cg2) + goto err; + cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); + if (!cg3) + goto err; + cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); + if (!cg4) + goto err; + cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); + if (!cg5) + goto err; + + if (join_cgroup("/cg1/cg2/cg3/cg4/cg5")) + goto err; + + if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, 2)) { + log_err("Attaching prog to cg1"); + goto err; + } + if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, 2)) { + log_err("Unexpected success attaching the same prog to cg1"); + goto err; + } + if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, 2)) { + log_err("Attaching prog2 to cg1"); + goto err; + } + if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, 1)) { + log_err("Attaching prog to cg2"); + goto err; + } + if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, 2)) { + log_err("Attaching prog to cg3"); + goto err; + } + if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, 1)) { + log_err("Attaching prog to cg4"); + goto err; + } + if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) { + log_err("Attaching prog to cg5"); + goto err; + } + assert(system(PING_CMD) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); + assert(value == 1 + 2 + 8 + 32); + + /* detach bottom program and ping again */ + if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) { + log_err("Detaching prog from cg5"); + goto err; + } + value = 0; + assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); + assert(system(PING_CMD) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); + assert(value == 1 + 2 + 8 + 16); + + /* detach 3rd from bottom program and ping again */ + errno = 0; + if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) { + log_err("Unexpected success on detach from cg3"); + goto err; + } + if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) { + log_err("Detaching from cg3"); + goto err; + } + value = 0; + assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); + assert(system(PING_CMD) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); + assert(value == 1 + 2 + 16); + + /* detach 2nd from bottom program and ping again */ + if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) { + log_err("Detaching prog from cg4"); + goto err; + } + value = 0; + assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); + assert(system(PING_CMD) == 0); + assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); + assert(value == 1 + 2 + 4); + goto out; +err: + rc = 1; + +out: + for (i = 0; i < 6; i++) + if (allow_prog[i] > 0) + close(allow_prog[i]); + close(cg1); + close(cg2); + close(cg3); + close(cg4); + close(cg5); + cleanup_cgroup_environment(); + if (!rc) + printf("### multi:PASS\n"); else - printf("FAIL\n"); + printf("### multi:FAIL\n"); return rc; } + +int main(int argc, char **argv) +{ + int rc = 0; + + rc = test_foo_bar(); + if (rc) + return rc; + + return test_multiprog(); +} -- GitLab From defd9c476fa6b01b4eb5450452bfd202138decb7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:26 -0700 Subject: [PATCH 0974/1507] libbpf: sync bpf.h tools/include/uapi/linux/bpf.h got out of sync with actual kernel header. Update it. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/include/uapi/linux/bpf.h | 55 ++++++++++++++++++++++++++++++++-- 1 file changed, 52 insertions(+), 3 deletions(-) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6d2137b4cf380..cb2b9f95160aa 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -92,6 +92,7 @@ enum bpf_cmd { BPF_PROG_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, }; enum bpf_map_type { @@ -143,11 +144,47 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command - * to the given target_fd cgroup the descendent cgroup will be able to - * override effective bpf program that was inherited from this cgroup +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -175,6 +212,9 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + #define BPF_OBJ_NAME_LEN 16U union bpf_attr { @@ -253,6 +293,15 @@ union bpf_attr { __u32 info_len; __aligned_u64 info; } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; } __attribute__((aligned(8))); /* BPF helper function descriptions: -- GitLab From 5d0cbf9b6c11964bf2f4041a5b0b6f81cb169736 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:27 -0700 Subject: [PATCH 0975/1507] libbpf: add support for BPF_PROG_QUERY add support for BPF_PROG_QUERY command to libbpf Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/lib/bpf/bpf.c | 20 ++++++++++++++++++++ tools/lib/bpf/bpf.h | 3 ++- 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index d4b6ba8292eec..5128677e41179 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -303,6 +303,26 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); } +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +{ + union bpf_attr attr; + int ret; + + bzero(&attr, sizeof(attr)); + attr.query.target_fd = target_fd; + attr.query.attach_type = type; + attr.query.query_flags = query_flags; + attr.query.prog_cnt = *prog_cnt; + attr.query.prog_ids = ptr_to_u64(prog_ids); + + ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + if (attach_flags) + *attach_flags = attr.query.attach_flags; + *prog_cnt = attr.query.prog_cnt; + return ret; +} + int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index afd64727c9cff..6534889e2b2f1 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -75,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); int bpf_prog_get_fd_by_id(__u32 id); int bpf_map_get_fd_by_id(__u32 id); int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); - +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); #endif -- GitLab From dfc069998ebb010f910dfec379dab4f44d331980 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:28 -0700 Subject: [PATCH 0976/1507] samples/bpf: use bpf_prog_query() interface use BPF_PROG_QUERY command to strengthen test coverage Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/test_cgrp2_attach2.c | 36 ++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c index 9a9f6836e5e97..3e8232cc04a84 100644 --- a/samples/bpf/test_cgrp2_attach2.c +++ b/samples/bpf/test_cgrp2_attach2.c @@ -236,6 +236,7 @@ static int prog_load_cnt(int verdict, int val) static int test_multiprog(void) { + __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; int drop_prog, allow_prog[6] = {}, rc = 0; unsigned long long value; @@ -304,6 +305,32 @@ static int test_multiprog(void) assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); assert(value == 1 + 2 + 8 + 32); + /* query the number of effective progs in cg5 */ + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, + NULL, NULL, &prog_cnt) == 0); + assert(prog_cnt == 4); + /* retrieve prog_ids of effective progs in cg5 */ + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, + &attach_flags, prog_ids, &prog_cnt) == 0); + assert(prog_cnt == 4); + assert(attach_flags == 0); + saved_prog_id = prog_ids[0]; + /* check enospc handling */ + prog_ids[0] = 0; + prog_cnt = 2; + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, + &attach_flags, prog_ids, &prog_cnt) == -1 && + errno == ENOSPC); + assert(prog_cnt == 4); + /* check that prog_ids are returned even when buffer is too small */ + assert(prog_ids[0] == saved_prog_id); + /* retrieve prog_id of single attached prog in cg5 */ + prog_ids[0] = 0; + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, + NULL, prog_ids, &prog_cnt) == 0); + assert(prog_cnt == 1); + assert(prog_ids[0] == saved_prog_id); + /* detach bottom program and ping again */ if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) { log_err("Detaching prog from cg5"); @@ -341,6 +368,15 @@ static int test_multiprog(void) assert(system(PING_CMD) == 0); assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); assert(value == 1 + 2 + 4); + + prog_cnt = 4; + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, + &attach_flags, prog_ids, &prog_cnt) == 0); + assert(prog_cnt == 3); + assert(attach_flags == 0); + assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, + NULL, prog_ids, &prog_cnt) == 0); + assert(prog_cnt == 0); goto out; err: rc = 1; -- GitLab From e0a86312874e36033cd94fb977dd603a292875c8 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 4 Oct 2017 23:10:59 +0100 Subject: [PATCH 0977/1507] Update James Hogan's email address Update my imgtec.com and personal email address to my kernel.org one in a few places as MIPS will soon no longer be part of Imagination Technologies, and add mappings in .mailcap so get_maintainer.pl reports the right address. Signed-off-by: James Hogan Signed-off-by: Linus Torvalds --- .mailmap | 2 ++ Documentation/ABI/testing/sysfs-power | 2 +- MAINTAINERS | 6 +++--- drivers/i2c/busses/i2c-img-scb.c | 2 +- drivers/media/rc/ir-sharp-decoder.c | 2 +- 5 files changed, 8 insertions(+), 6 deletions(-) diff --git a/.mailmap b/.mailmap index 5273cfd70ad62..c7b10caecc4ee 100644 --- a/.mailmap +++ b/.mailmap @@ -68,6 +68,8 @@ Jacob Shin James Bottomley James Bottomley James E Wilson +James Hogan +James Hogan James Ketrenos Javi Merino diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 713cab1d5f12d..a1d1612f36519 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -127,7 +127,7 @@ Description: What; /sys/power/pm_trace_dev_match Date: October 2010 -Contact: James Hogan +Contact: James Hogan Description: The /sys/power/pm_trace_dev_match file contains the name of the device associated with the last PM event point saved in the RTC diff --git a/MAINTAINERS b/MAINTAINERS index 65b0c88d5ee0d..3f05fc6961ade 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6738,7 +6738,7 @@ F: Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt F: drivers/auxdisplay/img-ascii-lcd.c IMGTEC IR DECODER DRIVER -M: James Hogan +M: James Hogan S: Maintained F: drivers/media/rc/img-ir/ @@ -7562,7 +7562,7 @@ F: arch/arm64/include/asm/kvm* F: arch/arm64/kvm/ KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips) -M: James Hogan +M: James Hogan L: linux-mips@linux-mips.org S: Supported F: arch/mips/include/uapi/asm/kvm* @@ -8885,7 +8885,7 @@ F: Documentation/devicetree/bindings/media/meson-ao-cec.txt T: git git://linuxtv.org/media_tree.git METAG ARCHITECTURE -M: James Hogan +M: James Hogan L: linux-metag@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jhogan/metag.git S: Odd Fixes diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c index 84fb35f6837f0..eb1d91b986fde 100644 --- a/drivers/i2c/busses/i2c-img-scb.c +++ b/drivers/i2c/busses/i2c-img-scb.c @@ -1459,6 +1459,6 @@ static struct platform_driver img_scb_i2c_driver = { }; module_platform_driver(img_scb_i2c_driver); -MODULE_AUTHOR("James Hogan "); +MODULE_AUTHOR("James Hogan "); MODULE_DESCRIPTION("IMG host I2C driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c index ed43a4212479f..129b558acc921 100644 --- a/drivers/media/rc/ir-sharp-decoder.c +++ b/drivers/media/rc/ir-sharp-decoder.c @@ -245,5 +245,5 @@ module_init(ir_sharp_decode_init); module_exit(ir_sharp_decode_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("James Hogan "); +MODULE_AUTHOR("James Hogan "); MODULE_DESCRIPTION("Sharp IR protocol decoder"); -- GitLab From 6621dd29eb9b5e6774ec7a9a75161352fdea47fc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 3 Oct 2017 13:53:23 +0200 Subject: [PATCH 0978/1507] dev: advertise the new nsid when the netns iface changes x-netns interfaces are bound to two netns: the link netns and the upper netns. Usually, this kind of interfaces is created in the link netns and then moved to the upper netns. At the end, the interface is visible only in the upper netns. The link nsid is advertised via netlink in the upper netns, thus the user always knows where is the link part. There is no such mechanism in the link netns. When the interface is moved to another netns, the user cannot "follow" it. This patch adds a new netlink attribute which helps to follow an interface which moves to another netns. When the interface is unregistered, the new nsid is advertised. If the interface is a x-netns interface (ie rtnl_link_ops->get_link_net is defined), the nsid is allocated if needed. CC: Jason A. Donenfeld Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 +++- include/uapi/linux/if_link.h | 1 + net/core/dev.c | 11 ++++++++--- net/core/rtnetlink.c | 31 ++++++++++++++++++++++--------- 4 files changed, 34 insertions(+), 13 deletions(-) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index dea59c8eec54d..1251638e60d31 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -17,9 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, - gfp_t flags); + gfp_t flags, int *new_nsid); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ea87bd708ee9e..cd580fc0e58ff 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -158,6 +158,7 @@ enum { IFLA_PAD, IFLA_XDP, IFLA_EVENT, + IFLA_NEW_NETNSID, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index 454f054415466..bffc754291846 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -145,6 +145,7 @@ #include #include #include +#include #include "net-sysfs.h" @@ -7204,7 +7205,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL); + GFP_KERNEL, NULL); /* * Flush the unicast and multicast chains @@ -8291,7 +8292,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - int err; + int err, new_nsid; ASSERT_RTNL(); @@ -8347,7 +8348,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) + new_nsid = peernet2id_alloc(dev_net(dev), net); + else + new_nsid = peernet2id(dev_net(dev), net); + rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3fb1ca33cba43..1ee98b1369d57 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -915,6 +915,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + nla_total_size(4) /* IFLA_EVENT */ + + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1384,7 +1385,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, - u32 event) + u32 event, int *new_nsid) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1472,6 +1473,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_fill_link_netnsid(skb, dev)) goto nla_put_failure; + if (new_nsid && + nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) + goto nla_put_failure; + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) goto nla_put_failure; @@ -1701,7 +1706,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0); + ext_filter_mask, 0, NULL); if (err < 0) { if (likely(skb->len)) @@ -2808,7 +2813,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2893,7 +2898,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, - u32 event, gfp_t flags) + u32 event, gfp_t flags, int *new_nsid) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2904,7 +2909,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event, + new_nsid); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2927,14 +2933,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags) + gfp_t flags, int *new_nsid) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } @@ -2942,10 +2948,17 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags) { - rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags); + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL); } EXPORT_SYMBOL(rtmsg_ifinfo); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid) +{ + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, + new_nsid); +} + static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u16 vid, u32 pid, u32 seq, @@ -4321,7 +4334,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL); + GFP_KERNEL, NULL); break; default: break; -- GitLab From e769fcec6bc4bdd1b0e2cf817680148f9c40b1c4 Mon Sep 17 00:00:00 2001 From: Vishakha Narvekar Date: Tue, 3 Oct 2017 16:13:29 -0400 Subject: [PATCH 0979/1507] net: 8021q: skip packets if the vlan is down If the vlan is down, free the packet instead of proceeding with other processing, or counting it as received. If vlan interfaces are used as slaves for bonding, with arp monitoring for connectivity, if the rx counter is seen to be incrementing, then the bond device will not observe that the interface is down. CC: David S. Miller Signed-off-by: Vishakha Narvekar Signed-off-by: David S. Miller --- net/8021q/vlan_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index e2ed69850489b..0bc31de9071a2 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -21,6 +21,12 @@ bool vlan_do_receive(struct sk_buff **skbp) if (unlikely(!skb)) return false; + if (unlikely(!(vlan_dev->flags & IFF_UP))) { + kfree_skb(skb); + *skbp = NULL; + return false; + } + skb->dev = vlan_dev; if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. -- GitLab From 51d0c04795a4b5d9a188336884887a9d394a94b0 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:45 -0700 Subject: [PATCH 0980/1507] net: Add extack to netdev_notifier_info Add netlink_ext_ack to netdev_notifier_info to allow notifier handlers to return errors to userspace. Clean up the initialization in dev.c such that extack is easily added in subsequent patches where relevant. Specifically, remove the init call in call_netdevice_notifiers_info and have callers initalize on stack when info is declared. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++- net/core/dev.c | 79 +++++++++++++++++++++++---------------- 2 files changed, 56 insertions(+), 33 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d04424cfffbaa..05fcaba4b0d95 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2309,7 +2309,8 @@ int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); struct netdev_notifier_info { - struct net_device *dev; + struct net_device *dev; + struct netlink_ext_ack *extack; }; struct netdev_notifier_change_info { @@ -2334,6 +2335,7 @@ static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; + info->extack = NULL; } static inline struct net_device * @@ -2342,6 +2344,12 @@ netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) return info->dev; } +static inline struct netlink_ext_ack * +netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) +{ + return info->extack; +} + int call_netdevice_notifiers(unsigned long val, struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index bffc754291846..e27a6bc0ac4d0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -163,7 +163,6 @@ static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info); static struct napi_struct *napi_by_id(unsigned int napi_id); @@ -1339,10 +1338,11 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - struct netdev_notifier_change_info change_info; + struct netdev_notifier_change_info change_info = { + .info.dev = dev, + }; - change_info.flags_changed = 0; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } @@ -1563,9 +1563,10 @@ EXPORT_SYMBOL(dev_disable_lro); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - netdev_notifier_info_init(&info, dev); return nb->notifier_call(nb, val, &info); } @@ -1690,11 +1691,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); */ static int call_netdevice_notifiers_info(unsigned long val, - struct net_device *dev, struct netdev_notifier_info *info) { ASSERT_RTNL(); - netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -1709,9 +1708,11 @@ static int call_netdevice_notifiers_info(unsigned long val, int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - struct netdev_notifier_info info; + struct netdev_notifier_info info = { + .dev = dev, + }; - return call_netdevice_notifiers_info(val, dev, &info); + return call_netdevice_notifiers_info(val, &info); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -6278,7 +6279,15 @@ static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info) { - struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + }, + .upper_dev = upper_dev, + .master = master, + .linking = true, + .upper_info = upper_info, + }; int ret = 0; ASSERT_RTNL(); @@ -6296,12 +6305,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (master && netdev_master_upper_dev_get(dev)) return -EBUSY; - changeupper_info.upper_dev = upper_dev; - changeupper_info.master = master; - changeupper_info.linking = true; - changeupper_info.upper_info = upper_info; - - ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6312,7 +6316,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) return ret; - ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) @@ -6376,20 +6380,24 @@ EXPORT_SYMBOL(netdev_master_upper_dev_link); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { - struct netdev_notifier_changeupper_info changeupper_info; + struct netdev_notifier_changeupper_info changeupper_info = { + .info = { + .dev = dev, + }, + .upper_dev = upper_dev, + .linking = false, + }; ASSERT_RTNL(); - changeupper_info.upper_dev = upper_dev; changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; - changeupper_info.linking = false; - call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -6405,11 +6413,13 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink); void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { - struct netdev_notifier_bonding_info info; + struct netdev_notifier_bonding_info info = { + .info.dev = dev, + }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); - call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev, + call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); @@ -6535,11 +6545,13 @@ EXPORT_SYMBOL(dev_get_nest_level); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { - struct netdev_notifier_changelowerstate_info changelowerstate_info; + struct netdev_notifier_changelowerstate_info changelowerstate_info = { + .info.dev = lower_dev, + }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; - call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev, + call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); @@ -6830,11 +6842,14 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { - struct netdev_notifier_change_info change_info; - - change_info.flags_changed = changes; - call_netdevice_notifiers_info(NETDEV_CHANGE, dev, - &change_info.info); + struct netdev_notifier_change_info change_info = { + .info = { + .dev = dev, + }, + .flags_changed = changes, + }; + + call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } -- GitLab From 33eaf2a6eb48ebf00374aaaf4b1b43f9950dcbe4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:46 -0700 Subject: [PATCH 0981/1507] net: Add extack to ndo_add_slave Pass extack to do_set_master and down to ndo_add_slave Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 5 +++-- drivers/net/bonding/bond_options.c | 2 +- drivers/net/team/team.c | 3 ++- drivers/net/vrf.c | 3 ++- include/linux/netdevice.h | 3 ++- include/net/bonding.h | 3 ++- net/batman-adv/soft-interface.c | 3 ++- net/bridge/br_device.c | 3 ++- net/core/rtnetlink.c | 10 ++++++---- 9 files changed, 22 insertions(+), 13 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b19dc033fb369..78feb94a36db9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1328,7 +1328,8 @@ void bond_lower_state_changed(struct slave *slave) } /* enslave device to bond device */ -int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) +int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, + struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; @@ -3492,7 +3493,7 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd switch (cmd) { case BOND_ENSLAVE_OLD: case SIOCBONDENSLAVE: - res = bond_enslave(bond_dev, slave_dev); + res = bond_enslave(bond_dev, slave_dev, NULL); break; case BOND_RELEASE_OLD: case SIOCBONDRELEASE: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 5931aa2fe9974..8a9b085c2a983 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1383,7 +1383,7 @@ static int bond_option_slaves_set(struct bonding *bond, switch (command[0]) { case '+': netdev_dbg(bond->dev, "Adding slave %s\n", dev->name); - ret = bond_enslave(bond->dev, dev); + ret = bond_enslave(bond->dev, dev, NULL); break; case '-': diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ae53e899259f8..4359d45aa131a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1914,7 +1914,8 @@ static int team_netpoll_setup(struct net_device *dev, } #endif -static int team_add_slave(struct net_device *dev, struct net_device *port_dev) +static int team_add_slave(struct net_device *dev, struct net_device *port_dev, + struct netlink_ext_ack *extack) { struct team *team = netdev_priv(dev); int err; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index cc18b7b11612d..4a082ef535334 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -788,7 +788,8 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) return ret; } -static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) +static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, + struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev)) return -EINVAL; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 05fcaba4b0d95..368a5064a487d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1246,7 +1246,8 @@ struct net_device_ops { u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, - struct net_device *slave_dev); + struct net_device *slave_dev, + struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); netdev_features_t (*ndo_fix_features)(struct net_device *dev, diff --git a/include/net/bonding.h b/include/net/bonding.h index b2e68657a2162..2860cc66c2bb3 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -596,7 +596,8 @@ void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); -int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); +int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, + struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index c2c986746d0b6..e7d5fbb6ad53d 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -867,7 +867,8 @@ static int batadv_softif_init_late(struct net_device *dev) * Return: 0 if successful or error otherwise. */ static int batadv_softif_slave_add(struct net_device *dev, - struct net_device *slave_dev) + struct net_device *slave_dev, + struct netlink_ext_ack *extack) { struct batadv_hard_iface *hard_iface; struct net *net = dev_net(dev); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index f6b6a92f1c486..cb0131d70ab1e 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -320,7 +320,8 @@ void br_netpoll_disable(struct net_bridge_port *p) #endif -static int br_add_slave(struct net_device *dev, struct net_device *slave_dev) +static int br_add_slave(struct net_device *dev, struct net_device *slave_dev, + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee98b1369d57..c5ee429bcce97 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1957,7 +1957,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } -static int do_set_master(struct net_device *dev, int ifindex) +static int do_set_master(struct net_device *dev, int ifindex, + struct netlink_ext_ack *extack) { struct net_device *upper_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops; @@ -1982,7 +1983,7 @@ static int do_set_master(struct net_device *dev, int ifindex) return -EINVAL; ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { - err = ops->ndo_add_slave(upper_dev, dev); + err = ops->ndo_add_slave(upper_dev, dev, extack); if (err) return err; } else { @@ -2115,7 +2116,7 @@ static int do_setlink(const struct sk_buff *skb, } if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); if (err) goto errout; status |= DO_SETLINK_MODIFIED; @@ -2753,7 +2754,8 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto out_unregister; } if (tb[IFLA_MASTER]) { - err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), + extack); if (err) goto out_unregister; } -- GitLab From 42ab19ee90292993370a30ad242599d75a3b749e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:47 -0700 Subject: [PATCH 0982/1507] net: Add extack to upper device linking Add extack arg to netdev_upper_dev_link and netdev_master_upper_dev_link Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 ++++--- .../net/ethernet/qualcomm/rmnet/rmnet_config.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 2 +- drivers/net/macsec.c | 2 +- drivers/net/macvlan.c | 7 ++++--- drivers/net/macvtap.c | 2 +- drivers/net/team/team.c | 2 +- drivers/net/usb/qmi_wwan.c | 2 +- drivers/net/vrf.c | 7 ++++--- include/linux/if_macvlan.h | 3 ++- include/linux/netdevice.h | 6 ++++-- net/8021q/vlan.c | 6 +++--- net/8021q/vlan.h | 2 +- net/8021q/vlan_netlink.c | 2 +- net/batman-adv/hard-interface.c | 2 +- net/bridge/br_if.c | 2 +- net/core/dev.c | 15 ++++++++++----- net/openvswitch/vport-netdev.c | 3 ++- 19 files changed, 44 insertions(+), 32 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78feb94a36db9..bc92307c2082f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1217,14 +1217,15 @@ static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond) } } -static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave) +static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, + struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = bond_lag_tx_type(bond); err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, - &lag_upper_info); + &lag_upper_info, extack); if (err) return err; rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL); @@ -1710,7 +1711,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_detach; } - res = bond_master_upper_dev_link(bond, new_slave); + res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 98f22551eb455..1af326a60cbbf 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -178,7 +178,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; - err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL); + err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL, extack); if (err) goto err2; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f300ae61c6c6c..dfb986421ec6f 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1748,7 +1748,7 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto rx_handler_failed; } - ret = netdev_upper_dev_link(vf_netdev, ndev); + ret = netdev_upper_dev_link(vf_netdev, ndev, NULL); if (ret != 0) { netdev_err(vf_netdev, "can not set master device %s (err = %d)\n", diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index c74893c1e6200..57c3856bab055 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -584,7 +584,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, if (err < 0) goto remove_ida; - err = netdev_upper_dev_link(phy_dev, dev); + err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) { goto unregister_netdev; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 98e4deaa3a6a1..ccbe4eaffe4df 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3244,7 +3244,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev, &macsec_netdev_addr_lock_key, macsec_get_nest_level(dev)); - err = netdev_upper_dev_link(real_dev, dev); + err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) goto unregister; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 1ffe77e95d46c..858bd66511a27 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1344,7 +1344,8 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; @@ -1433,7 +1434,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; - err = netdev_upper_dev_link(lowerdev, dev); + err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; @@ -1456,7 +1457,7 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - return macvlan_common_newlink(src_net, dev, tb, data); + return macvlan_common_newlink(src_net, dev, tb, data, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index c2d0ea2fb0193..f62aea2fcfa9c 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = macvlan_common_newlink(src_net, dev, tb, data); + err = macvlan_common_newlink(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 4359d45aa131a..a468439969df7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1112,7 +1112,7 @@ static int team_upper_dev_link(struct team *team, struct team_port *port) lag_upper_info.tx_type = team->mode->lag_tx_type; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, - &lag_upper_info); + &lag_upper_info, NULL); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8c37336082710..db7279d5b250f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -221,7 +221,7 @@ static int qmimux_register_device(struct net_device *real_dev, u8 mux_id) /* Account for reference in struct qmimux_priv_priv */ dev_hold(real_dev); - err = netdev_upper_dev_link(real_dev, new_dev); + err = netdev_upper_dev_link(real_dev, new_dev, NULL); if (err) goto out_unregister_netdev; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4a082ef535334..77d0655a02506 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -764,7 +764,8 @@ static void cycle_netdev(struct net_device *dev) } } -static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) +static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, + struct netlink_ext_ack *extack) { int ret; @@ -775,7 +776,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) return -EOPNOTSUPP; port_dev->priv_flags |= IFF_L3MDEV_SLAVE; - ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL); + ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; @@ -794,7 +795,7 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev)) return -EINVAL; - return do_vrf_add_slave(dev, port_dev); + return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index c9ec1343d1879..10e319f41fb14 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -72,7 +72,8 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]); + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack); extern void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 368a5064a487d..31bb3010c69b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3919,10 +3919,12 @@ void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); -int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); +int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, + struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info); + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9649579b5b9f3..71c3e045505be 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -138,7 +138,7 @@ int vlan_check_real_dev(struct net_device *real_dev, return 0; } -int register_vlan_dev(struct net_device *dev) +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; @@ -174,7 +174,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - err = netdev_upper_dev_link(real_dev, dev); + err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; @@ -270,7 +270,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; - err = register_vlan_dev(new_dev); + err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index df8bd65dd370e..94f8eed9f9b36 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -107,7 +107,7 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id); void vlan_setup(struct net_device *dev); -int register_vlan_dev(struct net_device *dev); +int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 5e831de3103e2..6e7c5a6a7930a 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -160,7 +160,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - return register_vlan_dev(dev); + return register_vlan_dev(dev, extack); } static inline size_t vlan_qos_map_size(unsigned int n) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index e348f76ea8c15..f7b413b9297e7 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -738,7 +738,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, bat_priv = netdev_priv(hard_iface->soft_iface); ret = netdev_master_upper_dev_link(hard_iface->net_dev, - soft_iface, NULL, NULL); + soft_iface, NULL, NULL, NULL); if (ret) goto err_dev; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f3aef22931ab2..0a3fd727048de 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -540,7 +540,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev->priv_flags |= IFF_BRIDGE_PORT; - err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL); + err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, NULL); if (err) goto err5; diff --git a/net/core/dev.c b/net/core/dev.c index e27a6bc0ac4d0..fcddccb6be41e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6277,11 +6277,13 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, - void *upper_priv, void *upper_info) + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, + .extack = extack, }, .upper_dev = upper_dev, .master = master, @@ -6341,9 +6343,11 @@ static int __netdev_upper_dev_link(struct net_device *dev, * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + struct netlink_ext_ack *extack) { - return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL); + return __netdev_upper_dev_link(dev, upper_dev, false, + NULL, NULL, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -6362,10 +6366,11 @@ EXPORT_SYMBOL(netdev_upper_dev_link); */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv, void *upper_info) + void *upper_priv, void *upper_info, + struct netlink_ext_ack *extack) { return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info); + upper_priv, upper_info, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 0389398fa4ab8..2e5e7a41d8ef8 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -108,7 +108,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name) rtnl_lock(); err = netdev_master_upper_dev_link(vport->dev, - get_dpdev(vport->dp), NULL, NULL); + get_dpdev(vport->dp), + NULL, NULL, NULL); if (err) goto error_unlock; -- GitLab From de3baa3ed72f09f8d2ba797645d052cd5f5de27d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:48 -0700 Subject: [PATCH 0983/1507] net: vrf: Add extack messages for enslave errors Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 77d0655a02506..0b54f553228e9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -772,8 +772,11 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ - if (port_dev == dev_net(dev)->loopback_dev) + if (port_dev == dev_net(dev)->loopback_dev) { + NL_SET_ERR_MSG(extack, + "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; + } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); @@ -792,7 +795,13 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { - if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev)) + if (netif_is_l3_master(port_dev)) { + NL_SET_ERR_MSG(extack, + "Can not enslave an L3 master device to a VRF"); + return -EINVAL; + } + + if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); -- GitLab From 759088bda21f4887c645579418e8b478eb570d78 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:49 -0700 Subject: [PATCH 0984/1507] net: bonding: Add extack messages for some enslave failures A number of bond_enslave errors are logged using the netdev_err API. Return those messages to userspace via the extack facility. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index bc92307c2082f..172eeeb68152b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1348,12 +1348,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { + NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved"); netdev_err(bond_dev, "Error: Device is in use and cannot be enslaved\n"); return -EBUSY; } if (bond_dev == slave_dev) { + NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself."); netdev_err(bond_dev, "cannot enslave bond to itself.\n"); return -EPERM; } @@ -1364,6 +1366,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, netdev_dbg(bond_dev, "%s is NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); if (vlan_uses_dev(bond_dev)) { + NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); netdev_err(bond_dev, "Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n", slave_dev->name, bond_dev->name); return -EPERM; @@ -1383,6 +1386,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, * enslaving it; the old ifenslave will not. */ if (slave_dev->flags & IFF_UP) { + NL_SET_ERR_MSG(extack, "Device can not be enslaved while up"); netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n", slave_dev->name); return -EPERM; @@ -1423,6 +1427,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_dev); } } else if (bond_dev->type != slave_dev->type) { + NL_SET_ERR_MSG(extack, "Device type is different from other slaves"); netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n", slave_dev->name, slave_dev->type, bond_dev->type); return -EINVAL; @@ -1430,6 +1435,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { + NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves"); netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n", slave_dev->type); res = -EOPNOTSUPP; @@ -1445,6 +1451,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond->params.fail_over_mac = BOND_FOM_ACTIVE; netdev_warn(bond_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { + NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); netdev_err(bond_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n"); res = -EOPNOTSUPP; goto err_undo_flags; -- GitLab From ca752be006013ac6f19721280f44c91ef07ad3d1 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:50 -0700 Subject: [PATCH 0985/1507] net: bridge: Pass extack to down to netdev_master_upper_dev_link Pass extack arg to br_add_if. Add messages for a couple of failures and pass arg to netdev_master_upper_dev_link. Signed-off-by: David Ahern Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/bridge/br_device.c | 2 +- net/bridge/br_if.c | 15 +++++++++++---- net/bridge/br_ioctl.c | 2 +- net/bridge/br_private.h | 3 ++- 4 files changed, 15 insertions(+), 7 deletions(-) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index cb0131d70ab1e..7acb77c9bd65c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -326,7 +326,7 @@ static int br_add_slave(struct net_device *dev, struct net_device *slave_dev, { struct net_bridge *br = netdev_priv(dev); - return br_add_if(br, slave_dev); + return br_add_if(br, slave_dev, extack); } static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 0a3fd727048de..59a74a414e204 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -480,7 +480,8 @@ netdev_features_t br_features_recompute(struct net_bridge *br, } /* called with RTNL */ -int br_add_if(struct net_bridge *br, struct net_device *dev) +int br_add_if(struct net_bridge *br, struct net_device *dev, + struct netlink_ext_ack *extack) { struct net_bridge_port *p; int err = 0; @@ -500,16 +501,22 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) return -EINVAL; /* No bridging of bridges */ - if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) + if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) { + NL_SET_ERR_MSG(extack, + "Can not enslave a bridge to a bridge"); return -ELOOP; + } /* Device is already being bridged */ if (br_port_exists(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ - if (dev->priv_flags & IFF_DONT_BRIDGE) + if (dev->priv_flags & IFF_DONT_BRIDGE) { + NL_SET_ERR_MSG(extack, + "Device does not allow enslaving to a bridge"); return -EOPNOTSUPP; + } p = new_nbp(br, dev); if (IS_ERR(p)) @@ -540,7 +547,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev->priv_flags |= IFF_BRIDGE_PORT; - err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, NULL); + err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack); if (err) goto err5; diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 66cd987720518..8f29103935a3b 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -98,7 +98,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) return -EINVAL; if (isadd) - ret = br_add_if(br, dev); + ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 020c709a017f0..ab4df24f7bba5 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -566,7 +566,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, void br_port_carrier_check(struct net_bridge_port *p); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); -int br_add_if(struct net_bridge *br, struct net_device *dev); +int br_add_if(struct net_bridge *br, struct net_device *dev, + struct netlink_ext_ack *extack); int br_del_if(struct net_bridge *br, struct net_device *dev); int br_min_mtu(const struct net_bridge *br); netdev_features_t br_features_recompute(struct net_bridge *br, -- GitLab From e58376e1df2aaffbf12753959142a50f824c46ea Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 Oct 2017 17:48:51 -0700 Subject: [PATCH 0986/1507] mlxsw: spectrum: Add extack messages for enslave failures mlxsw fails device enslavement for a number of reasons. Use the extack facility to return an error message to the user stating why the enslave is failing. Messages are prefixed with "spectrum" so users know it is a constraint imposed by the hardware driver. For example: $ ip li add br0.11 link br0 type vlan id 11 $ ip li set swp11 master br0 Error: spectrum: Enslaving a port to a device that already has an upper device is not supported. Signed-off-by: David Ahern Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 47 +++++++++++++++---- 1 file changed, 37 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3adf237c951ad..5cd4df08ce975 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4019,14 +4019,21 @@ static int mlxsw_sp_lag_index_get(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp, struct net_device *lag_dev, - struct netdev_lag_upper_info *lag_upper_info) + struct netdev_lag_upper_info *lag_upper_info, + struct netlink_ext_ack *extack) { u16 lag_id; - if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) + if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0) { + NL_SET_ERR_MSG(extack, + "spectrum: Exceeded number of supported LAG devices"); return false; - if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) + } + if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + NL_SET_ERR_MSG(extack, + "spectrum: LAG device using unsupported Tx type"); return false; + } return true; } @@ -4231,6 +4238,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, { struct netdev_notifier_changeupper_info *info; struct mlxsw_sp_port *mlxsw_sp_port; + struct netlink_ext_ack *extack; struct net_device *upper_dev; struct mlxsw_sp *mlxsw_sp; int err = 0; @@ -4238,6 +4246,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, mlxsw_sp_port = netdev_priv(dev); mlxsw_sp = mlxsw_sp_port->mlxsw_sp; info = ptr; + extack = netdev_notifier_info_to_extack(&info->info); switch (event) { case NETDEV_PRECHANGEUPPER: @@ -4245,25 +4254,43 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, if (!is_vlan_dev(upper_dev) && !netif_is_lag_master(upper_dev) && !netif_is_bridge_master(upper_dev) && - !netif_is_ovs_master(upper_dev)) + !netif_is_ovs_master(upper_dev)) { + NL_SET_ERR_MSG(extack, + "spectrum: Unknown upper device type"); return -EINVAL; + } if (!info->linking) break; - if (netdev_has_any_upper_dev(upper_dev)) + if (netdev_has_any_upper_dev(upper_dev)) { + NL_SET_ERR_MSG(extack, + "spectrum: Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; + } if (netif_is_lag_master(upper_dev) && !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev, - info->upper_info)) + info->upper_info, extack)) return -EINVAL; - if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) + if (netif_is_lag_master(upper_dev) && vlan_uses_dev(dev)) { + NL_SET_ERR_MSG(extack, + "spectrum: Master device is a LAG master and this device has a VLAN"); return -EINVAL; + } if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) && - !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) + !netif_is_lag_master(vlan_dev_real_dev(upper_dev))) { + NL_SET_ERR_MSG(extack, + "spectrum: Can not put a VLAN on a LAG port"); return -EINVAL; - if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) + } + if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) { + NL_SET_ERR_MSG(extack, + "spectrum: Master device is an OVS master and this device has a VLAN"); return -EINVAL; - if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) + } + if (netif_is_ovs_port(dev) && is_vlan_dev(upper_dev)) { + NL_SET_ERR_MSG(extack, + "spectrum: Can not put a VLAN on an OVS port"); return -EINVAL; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; -- GitLab From a92bb546cff0b31d96d5919ebfeda9c678756b42 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 Oct 2017 20:10:03 -0700 Subject: [PATCH 0987/1507] tools: rename tools/net directory to tools/bpf We currently only have BPF tools in the tools/net directory. We are about to add more BPF tools there, not necessarily networking related, rename the directory and related Makefile targets to bpf. Suggested-by: Daniel Borkmann Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- MAINTAINERS | 3 +-- tools/Makefile | 14 +++++++------- tools/{net => bpf}/Makefile | 0 tools/{net => bpf}/bpf_asm.c | 0 tools/{net => bpf}/bpf_dbg.c | 0 tools/{net => bpf}/bpf_exp.l | 0 tools/{net => bpf}/bpf_exp.y | 0 tools/{net => bpf}/bpf_jit_disasm.c | 0 8 files changed, 8 insertions(+), 9 deletions(-) rename tools/{net => bpf}/Makefile (100%) rename tools/{net => bpf}/bpf_asm.c (100%) rename tools/{net => bpf}/bpf_dbg.c (100%) rename tools/{net => bpf}/bpf_exp.l (100%) rename tools/{net => bpf}/bpf_exp.y (100%) rename tools/{net => bpf}/bpf_jit_disasm.c (100%) diff --git a/MAINTAINERS b/MAINTAINERS index 5231392cf4bd7..004816a585b82 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2725,7 +2725,7 @@ F: net/core/filter.c F: net/sched/act_bpf.c F: net/sched/cls_bpf.c F: samples/bpf/ -F: tools/net/bpf* +F: tools/bpf/ F: tools/testing/selftests/bpf/ BROADCOM B44 10/100 ETHERNET DRIVER @@ -9416,7 +9416,6 @@ F: include/uapi/linux/in.h F: include/uapi/linux/net.h F: include/uapi/linux/netdevice.h F: include/uapi/linux/net_namespace.h -F: tools/net/ F: tools/testing/selftests/net/ F: lib/random32.c diff --git a/tools/Makefile b/tools/Makefile index 9dfede37c8ff8..df6fcb293fbc5 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -19,7 +19,7 @@ help: @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' @echo ' liblockdep - user-space wrapper for kernel locking-validator' - @echo ' net - misc networking tools' + @echo ' bpf - misc BPF tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' @echo ' spi - spi tools' @@ -57,7 +57,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup firewire hv guest spi usb virtio vm net iio gpio objtool leds: FORCE +cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds: FORCE $(call descend,$@) liblockdep: FORCE @@ -91,7 +91,7 @@ kvm_stat: FORCE all: acpi cgroup cpupower gpio hv firewire liblockdep \ perf selftests spi turbostat usb \ - virtio vm net x86_energy_perf_policy \ + virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat acpi_install: @@ -100,7 +100,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install net_install objtool_install: +cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install: $(call descend,$(@:_install=),install) liblockdep_install: @@ -124,7 +124,7 @@ kvm_stat_install: install: acpi_install cgroup_install cpupower_install gpio_install \ hv_install firewire_install iio_install liblockdep_install \ perf_install selftests_install turbostat_install usb_install \ - virtio_install vm_install net_install x86_energy_perf_policy_install \ + virtio_install vm_install bpf_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install acpi_clean: @@ -133,7 +133,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: +cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean: @@ -169,7 +169,7 @@ build_clean: clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ - vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ + vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ gpio_clean objtool_clean leds_clean diff --git a/tools/net/Makefile b/tools/bpf/Makefile similarity index 100% rename from tools/net/Makefile rename to tools/bpf/Makefile diff --git a/tools/net/bpf_asm.c b/tools/bpf/bpf_asm.c similarity index 100% rename from tools/net/bpf_asm.c rename to tools/bpf/bpf_asm.c diff --git a/tools/net/bpf_dbg.c b/tools/bpf/bpf_dbg.c similarity index 100% rename from tools/net/bpf_dbg.c rename to tools/bpf/bpf_dbg.c diff --git a/tools/net/bpf_exp.l b/tools/bpf/bpf_exp.l similarity index 100% rename from tools/net/bpf_exp.l rename to tools/bpf/bpf_exp.l diff --git a/tools/net/bpf_exp.y b/tools/bpf/bpf_exp.y similarity index 100% rename from tools/net/bpf_exp.y rename to tools/bpf/bpf_exp.y diff --git a/tools/net/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c similarity index 100% rename from tools/net/bpf_jit_disasm.c rename to tools/bpf/bpf_jit_disasm.c -- GitLab From 71bb428fe2c19512ac671d5ee16ef3e73e1b49a8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 Oct 2017 20:10:04 -0700 Subject: [PATCH 0988/1507] tools: bpf: add bpftool Add a simple tool for querying and updating BPF objects on the system. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- tools/bpf/Makefile | 18 +- tools/bpf/bpftool/Makefile | 80 ++++ tools/bpf/bpftool/common.c | 216 ++++++++++ tools/bpf/bpftool/jit_disasm.c | 87 ++++ tools/bpf/bpftool/main.c | 212 ++++++++++ tools/bpf/bpftool/main.h | 99 +++++ tools/bpf/bpftool/map.c | 744 +++++++++++++++++++++++++++++++++ tools/bpf/bpftool/prog.c | 456 ++++++++++++++++++++ 8 files changed, 1909 insertions(+), 3 deletions(-) create mode 100644 tools/bpf/bpftool/Makefile create mode 100644 tools/bpf/bpftool/common.c create mode 100644 tools/bpf/bpftool/jit_disasm.c create mode 100644 tools/bpf/bpftool/main.c create mode 100644 tools/bpf/bpftool/main.h create mode 100644 tools/bpf/bpftool/map.c create mode 100644 tools/bpf/bpftool/prog.c diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index ddf8880106524..325a35e1c28e8 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -3,6 +3,7 @@ prefix = /usr CC = gcc LEX = flex YACC = bison +MAKE = make CFLAGS += -Wall -O2 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include @@ -13,7 +14,7 @@ CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include %.lex.c: %.l $(LEX) -o $@ $< -all : bpf_jit_disasm bpf_dbg bpf_asm +all: bpf_jit_disasm bpf_dbg bpf_asm bpftool bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm' bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl @@ -26,10 +27,21 @@ bpf_asm : LDLIBS = bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o bpf_exp.lex.o : bpf_exp.yacc.c -clean : +clean: bpftool_clean rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.* -install : +install: bpftool_install install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm install bpf_dbg $(prefix)/bin/bpf_dbg install bpf_asm $(prefix)/bin/bpf_asm + +bpftool: + $(MAKE) -C bpftool + +bpftool_install: + $(MAKE) -C bpftool install + +bpftool_clean: + $(MAKE) -C bpftool clean + +.PHONY: bpftool FORCE diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile new file mode 100644 index 0000000000000..a7151f47fb409 --- /dev/null +++ b/tools/bpf/bpftool/Makefile @@ -0,0 +1,80 @@ +include ../../scripts/Makefile.include + +include ../../scripts/utilities.mak + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +ifneq ($(objtree),) +#$(info Determined 'objtree' to be $(objtree)) +endif + +ifneq ($(OUTPUT),) +#$(info Determined 'OUTPUT' to be $(OUTPUT)) +# Adding $(OUTPUT) as a directory to look for source files, +# because use generated output files as sources dependency +# for flex/bison parsers. +VPATH += $(OUTPUT) +export VPATH +endif + +ifeq ($(V),1) + Q = +else + Q = @ +endif + +BPF_DIR = $(srctree)/tools/lib/bpf/ + +ifneq ($(OUTPUT),) + BPF_PATH=$(OUTPUT) +else + BPF_PATH=$(BPF_DIR) +endif + +LIBBPF = $(BPF_PATH)libbpf.a + +$(LIBBPF): FORCE + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) + +$(LIBBPF)-clean: + $(call QUIET_CLEAN, libbpf) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) clean >/dev/null + +prefix = /usr + +CC = gcc + +CFLAGS += -O2 +CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf +LIBS = -lelf -lbfd -lopcodes $(LIBBPF) + +include $(wildcard *.d) + +all: $(OUTPUT)bpftool + +SRCS=$(wildcard *.c) +OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) + +$(OUTPUT)bpftool: $(OBJS) $(LIBBPF) + $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS) + +$(OUTPUT)%.o: %.c + $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< + +clean: $(LIBBPF)-clean + $(call QUIET_CLEAN, bpftool) + $(Q)rm -rf $(OUTPUT)bpftool $(OUTPUT)*.o $(OUTPUT)*.d + +install: + install $(OUTPUT)bpftool $(prefix)/sbin/bpftool + +FORCE: + +.PHONY: all clean FORCE +.DEFAULT_GOAL := all diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c new file mode 100644 index 0000000000000..df8396a0c4007 --- /dev/null +++ b/tools/bpf/bpftool/common.c @@ -0,0 +1,216 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* Author: Jakub Kicinski */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "main.h" + +static bool is_bpffs(char *path) +{ + struct statfs st_fs; + + if (statfs(path, &st_fs) < 0) + return false; + + return (unsigned long)st_fs.f_type == BPF_FS_MAGIC; +} + +int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) +{ + enum bpf_obj_type type; + int fd; + + fd = bpf_obj_get(path); + if (fd < 0) { + err("bpf obj get (%s): %s\n", path, + errno == EACCES && !is_bpffs(dirname(path)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); + return -1; + } + + type = get_fd_type(fd); + if (type < 0) { + close(fd); + return type; + } + if (type != exp_type) { + err("incorrect object type: %s\n", get_fd_type_name(type)); + close(fd); + return -1; + } + + return fd; +} + +int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) +{ + unsigned int id; + char *endptr; + int err; + int fd; + + if (!is_prefix(*argv, "id")) { + err("expected 'id' got %s\n", *argv); + return -1; + } + NEXT_ARG(); + + id = strtoul(*argv, &endptr, 0); + if (*endptr) { + err("can't parse %s as ID\n", *argv); + return -1; + } + NEXT_ARG(); + + if (argc != 1) + usage(); + + fd = get_fd_by_id(id); + if (fd < 0) { + err("can't get prog by id (%u): %s\n", id, strerror(errno)); + return -1; + } + + err = bpf_obj_pin(fd, *argv); + close(fd); + if (err) { + err("can't pin the object (%s): %s\n", *argv, + errno == EACCES && !is_bpffs(dirname(*argv)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); + return -1; + } + + return 0; +} + +const char *get_fd_type_name(enum bpf_obj_type type) +{ + static const char * const names[] = { + [BPF_OBJ_UNKNOWN] = "unknown", + [BPF_OBJ_PROG] = "prog", + [BPF_OBJ_MAP] = "map", + }; + + if (type < 0 || type >= ARRAY_SIZE(names) || !names[type]) + return names[BPF_OBJ_UNKNOWN]; + + return names[type]; +} + +int get_fd_type(int fd) +{ + char path[PATH_MAX]; + char buf[512]; + ssize_t n; + + snprintf(path, sizeof(path), "/proc/%d/fd/%d", getpid(), fd); + + n = readlink(path, buf, sizeof(buf)); + if (n < 0) { + err("can't read link type: %s\n", strerror(errno)); + return -1; + } + if (n == sizeof(path)) { + err("can't read link type: path too long!\n"); + return -1; + } + + if (strstr(buf, "bpf-map")) + return BPF_OBJ_MAP; + else if (strstr(buf, "bpf-prog")) + return BPF_OBJ_PROG; + + return BPF_OBJ_UNKNOWN; +} + +char *get_fdinfo(int fd, const char *key) +{ + char path[PATH_MAX]; + char *line = NULL; + size_t line_n = 0; + ssize_t n; + FILE *fdi; + + snprintf(path, sizeof(path), "/proc/%d/fdinfo/%d", getpid(), fd); + + fdi = fopen(path, "r"); + if (!fdi) { + err("can't open fdinfo: %s\n", strerror(errno)); + return NULL; + } + + while ((n = getline(&line, &line_n, fdi))) { + char *value; + int len; + + if (!strstr(line, key)) + continue; + + fclose(fdi); + + value = strchr(line, '\t'); + if (!value || !value[1]) { + err("malformed fdinfo!?\n"); + free(line); + return NULL; + } + value++; + + len = strlen(value); + memmove(line, value, len); + line[len - 1] = '\0'; + + return line; + } + + err("key '%s' not found in fdinfo\n", key); + free(line); + fclose(fdi); + return NULL; +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c new file mode 100644 index 0000000000000..70e480b59e9da --- /dev/null +++ b/tools/bpf/bpftool/jit_disasm.c @@ -0,0 +1,87 @@ +/* + * Based on: + * + * Minimal BPF JIT image disassembler + * + * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for + * debugging or verification purposes. + * + * Copyright 2013 Daniel Borkmann + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static void get_exec_path(char *tpath, size_t size) +{ + ssize_t len; + char *path; + + snprintf(tpath, size, "/proc/%d/exe", (int) getpid()); + tpath[size - 1] = 0; + + path = strdup(tpath); + assert(path); + + len = readlink(path, tpath, size - 1); + assert(len > 0); + tpath[len] = 0; + + free(path); +} + +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes) +{ + disassembler_ftype disassemble; + struct disassemble_info info; + int count, i, pc = 0; + char tpath[256]; + bfd *bfdf; + + if (!len) + return; + + memset(tpath, 0, sizeof(tpath)); + get_exec_path(tpath, sizeof(tpath)); + + bfdf = bfd_openr(tpath, NULL); + assert(bfdf); + assert(bfd_check_format(bfdf, bfd_object)); + + init_disassemble_info(&info, stdout, (fprintf_ftype) fprintf); + info.arch = bfd_get_arch(bfdf); + info.mach = bfd_get_mach(bfdf); + info.buffer = image; + info.buffer_length = len; + + disassemble_init_for_target(&info); + + disassemble = disassembler(bfdf); + assert(disassemble); + + do { + printf("%4x:\t", pc); + + count = disassemble(pc, &info); + + if (opcodes) { + printf("\n\t"); + for (i = 0; i < count; ++i) + printf("%02x ", (uint8_t) image[pc + i]); + } + printf("\n"); + + pc += count; + } while (count > 0 && pc < len); + + bfd_close(bfdf); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c new file mode 100644 index 0000000000000..e02d00d6e00b1 --- /dev/null +++ b/tools/bpf/bpftool/main.c @@ -0,0 +1,212 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* Author: Jakub Kicinski */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "main.h" + +const char *bin_name; +static int last_argc; +static char **last_argv; +static int (*last_do_help)(int argc, char **argv); + +void usage(void) +{ + last_do_help(last_argc - 1, last_argv + 1); + + exit(-1); +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s OBJECT { COMMAND | help }\n" + " %s batch file FILE\n" + "\n" + " OBJECT := { prog | map }\n", + bin_name, bin_name); + + return 0; +} + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)) +{ + unsigned int i; + + last_argc = argc; + last_argv = argv; + last_do_help = help; + + if (argc < 1 && cmds[0].func) + return cmds[0].func(argc, argv); + + for (i = 0; cmds[i].func; i++) + if (is_prefix(*argv, cmds[i].cmd)) + return cmds[i].func(argc - 1, argv + 1); + + help(argc - 1, argv + 1); + + return -1; +} + +bool is_prefix(const char *pfx, const char *str) +{ + if (!pfx) + return false; + if (strlen(str) < strlen(pfx)) + return false; + + return !memcmp(str, pfx, strlen(pfx)); +} + +void print_hex(void *arg, unsigned int n, const char *sep) +{ + unsigned char *data = arg; + unsigned int i; + + for (i = 0; i < n; i++) { + const char *pfx = ""; + + if (!i) + /* nothing */; + else if (!(i % 16)) + printf("\n"); + else if (!(i % 8)) + printf(" "); + else + pfx = sep; + + printf("%s%02hhx", i ? pfx : "", data[i]); + } +} + +static int do_batch(int argc, char **argv); + +static const struct cmd cmds[] = { + { "help", do_help }, + { "batch", do_batch }, + { "prog", do_prog }, + { "map", do_map }, + { 0 } +}; + +static int do_batch(int argc, char **argv) +{ + unsigned int lines = 0; + char *n_argv[4096]; + char buf[65536]; + int n_argc; + FILE *fp; + int err; + + if (argc < 2) { + err("too few parameters for batch\n"); + return -1; + } else if (!is_prefix(*argv, "file")) { + err("expected 'file', got: %s\n", *argv); + return -1; + } else if (argc > 2) { + err("too many parameters for batch\n"); + return -1; + } + NEXT_ARG(); + + fp = fopen(*argv, "r"); + if (!fp) { + err("Can't open file (%s): %s\n", *argv, strerror(errno)); + return -1; + } + + while (fgets(buf, sizeof(buf), fp)) { + if (strlen(buf) == sizeof(buf) - 1) { + errno = E2BIG; + break; + } + + n_argc = 0; + n_argv[n_argc] = strtok(buf, " \t\n"); + + while (n_argv[n_argc]) { + n_argc++; + if (n_argc == ARRAY_SIZE(n_argv)) { + err("line %d has too many arguments, skip\n", + lines); + n_argc = 0; + break; + } + n_argv[n_argc] = strtok(NULL, " \t\n"); + } + + if (!n_argc) + continue; + + err = cmd_select(cmds, n_argc, n_argv, do_help); + if (err) + goto err_close; + + lines++; + } + + if (errno && errno != ENOENT) { + perror("reading batch file failed"); + err = -1; + } else { + info("processed %d lines\n", lines); + err = 0; + } +err_close: + fclose(fp); + + return err; +} + +int main(int argc, char **argv) +{ + bin_name = argv[0]; + NEXT_ARG(); + + bfd_init(); + + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h new file mode 100644 index 0000000000000..85d2d7870a582 --- /dev/null +++ b/tools/bpf/bpftool/main.h @@ -0,0 +1,99 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* Author: Jakub Kicinski */ + +#ifndef __BPF_TOOL_H +#define __BPF_TOOL_H + +#include +#include +#include + +#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) + +#define err(msg...) fprintf(stderr, "Error: " msg) +#define warn(msg...) fprintf(stderr, "Warning: " msg) +#define info(msg...) fprintf(stderr, msg) + +#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) + +#define min(a, b) \ + ({ typeof(a) _a = (a); typeof(b) _b = (b); _a > _b ? _b : _a; }) +#define max(a, b) \ + ({ typeof(a) _a = (a); typeof(b) _b = (b); _a < _b ? _b : _a; }) + +#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) +#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) +#define BAD_ARG() ({ err("what is '%s'?\n", *argv); -1; }) + +#define BPF_TAG_FMT "%02hhx:%02hhx:%02hhx:%02hhx:" \ + "%02hhx:%02hhx:%02hhx:%02hhx" + +#define HELP_SPEC_PROGRAM \ + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" + +enum bpf_obj_type { + BPF_OBJ_UNKNOWN, + BPF_OBJ_PROG, + BPF_OBJ_MAP, +}; + +extern const char *bin_name; + +bool is_prefix(const char *pfx, const char *str); +void print_hex(void *arg, unsigned int n, const char *sep); +void usage(void) __attribute__((noreturn)); + +struct cmd { + const char *cmd; + int (*func)(int argc, char **argv); +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)); + +int get_fd_type(int fd); +const char *get_fd_type_name(enum bpf_obj_type type); +char *get_fdinfo(int fd, const char *key); +int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); +int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)); + +int do_prog(int argc, char **arg); +int do_map(int argc, char **arg); + +int prog_parse_fd(int *argc, char ***argv); + +void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes); + +#endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c new file mode 100644 index 0000000000000..0528a5379e6c3 --- /dev/null +++ b/tools/bpf/bpftool/map.c @@ -0,0 +1,744 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* Author: Jakub Kicinski */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "main.h" + +static const char * const map_type_name[] = { + [BPF_MAP_TYPE_UNSPEC] = "unspec", + [BPF_MAP_TYPE_HASH] = "hash", + [BPF_MAP_TYPE_ARRAY] = "array", + [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", + [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", + [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", + [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", + [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", + [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", + [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", + [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", + [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", + [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", + [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", + [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_SOCKMAP] = "sockmap", +}; + +static unsigned int get_possible_cpus(void) +{ + static unsigned int result; + char buf[128]; + long int n; + char *ptr; + int fd; + + if (result) + return result; + + fd = open("/sys/devices/system/cpu/possible", O_RDONLY); + if (fd < 0) { + err("can't open sysfs possible cpus\n"); + exit(-1); + } + + n = read(fd, buf, sizeof(buf)); + if (n < 2) { + err("can't read sysfs possible cpus\n"); + exit(-1); + } + close(fd); + + if (n == sizeof(buf)) { + err("read sysfs possible cpus overflow\n"); + exit(-1); + } + + ptr = buf; + n = 0; + while (*ptr && *ptr != '\n') { + unsigned int a, b; + + if (sscanf(ptr, "%u-%u", &a, &b) == 2) { + n += b - a + 1; + + ptr = strchr(ptr, '-') + 1; + } else if (sscanf(ptr, "%u", &a) == 1) { + n++; + } else { + assert(0); + } + + while (isdigit(*ptr)) + ptr++; + if (*ptr == ',') + ptr++; + } + + result = n; + + return result; +} + +static bool map_is_per_cpu(__u32 type) +{ + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH; +} + +static bool map_is_map_of_maps(__u32 type) +{ + return type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS; +} + +static bool map_is_map_of_progs(__u32 type) +{ + return type == BPF_MAP_TYPE_PROG_ARRAY; +} + +static void *alloc_value(struct bpf_map_info *info) +{ + if (map_is_per_cpu(info->type)) + return malloc(info->value_size * get_possible_cpus()); + else + return malloc(info->value_size); +} + +static int map_parse_fd(int *argc, char ***argv) +{ + int fd; + + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + err("can't parse %s as ID\n", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) + err("get map by id (%u): %s\n", id, strerror(errno)); + return fd; + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_MAP); + } + + err("expected 'id' or 'pinned', got: '%s'?\n", **argv); + return -1; +} + +static int +map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +{ + int err; + int fd; + + fd = map_parse_fd(argc, argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, info, info_len); + if (err) { + err("can't get map info: %s\n", strerror(errno)); + close(fd); + return err; + } + + return fd; +} + +static void print_entry(struct bpf_map_info *info, unsigned char *key, + unsigned char *value) +{ + if (!map_is_per_cpu(info->type)) { + bool single_line, break_names; + + break_names = info->key_size > 16 || info->value_size > 16; + single_line = info->key_size + info->value_size <= 24 && + !break_names; + + printf("key:%c", break_names ? '\n' : ' '); + print_hex(key, info->key_size, " "); + + printf(single_line ? " " : "\n"); + + printf("value:%c", break_names ? '\n' : ' '); + print_hex(value, info->value_size, " "); + + printf("\n"); + } else { + unsigned int i, n; + + n = get_possible_cpus(); + + printf("key:\n"); + print_hex(key, info->key_size, " "); + printf("\n"); + for (i = 0; i < n; i++) { + printf("value (CPU %02d):%c", + i, info->value_size > 16 ? '\n' : ' '); + print_hex(value + i * info->value_size, + info->value_size, " "); + printf("\n"); + } + } +} + +static char **parse_bytes(char **argv, const char *name, unsigned char *val, + unsigned int n) +{ + unsigned int i = 0; + char *endptr; + + while (i < n && argv[i]) { + val[i] = strtoul(argv[i], &endptr, 0); + if (*endptr) { + err("error parsing byte: %s\n", argv[i]); + break; + } + i++; + } + + if (i != n) { + err("%s expected %d bytes got %d\n", name, n, i); + return NULL; + } + + return argv + i; +} + +static int parse_elem(char **argv, struct bpf_map_info *info, + void *key, void *value, __u32 key_size, __u32 value_size, + __u32 *flags, __u32 **value_fd) +{ + if (!*argv) { + if (!key && !value) + return 0; + err("did not find %s\n", key ? "key" : "value"); + return -1; + } + + if (is_prefix(*argv, "key")) { + if (!key) { + if (key_size) + err("duplicate key\n"); + else + err("unnecessary key\n"); + return -1; + } + + argv = parse_bytes(argv + 1, "key", key, key_size); + if (!argv) + return -1; + + return parse_elem(argv, info, NULL, value, key_size, value_size, + flags, value_fd); + } else if (is_prefix(*argv, "value")) { + int fd; + + if (!value) { + if (value_size) + err("duplicate value\n"); + else + err("unnecessary value\n"); + return -1; + } + + argv++; + + if (map_is_map_of_maps(info->type)) { + int argc = 2; + + if (value_size != 4) { + err("value smaller than 4B for map in map?\n"); + return -1; + } + if (!argv[0] || !argv[1]) { + err("not enough value arguments for map in map\n"); + return -1; + } + + fd = map_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else if (map_is_map_of_progs(info->type)) { + int argc = 2; + + if (value_size != 4) { + err("value smaller than 4B for map of progs?\n"); + return -1; + } + if (!argv[0] || !argv[1]) { + err("not enough value arguments for map of progs\n"); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + *value_fd = value; + **value_fd = fd; + } else { + argv = parse_bytes(argv, "value", value, value_size); + if (!argv) + return -1; + } + + return parse_elem(argv, info, key, NULL, key_size, value_size, + flags, NULL); + } else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") || + is_prefix(*argv, "exist")) { + if (!flags) { + err("flags specified multiple times: %s\n", *argv); + return -1; + } + + if (is_prefix(*argv, "any")) + *flags = BPF_ANY; + else if (is_prefix(*argv, "noexist")) + *flags = BPF_NOEXIST; + else if (is_prefix(*argv, "exist")) + *flags = BPF_EXIST; + + return parse_elem(argv + 1, info, key, value, key_size, + value_size, NULL, value_fd); + } + + err("expected key or value, got: %s\n", *argv); + return -1; +} + +static int show_map_close(int fd, struct bpf_map_info *info) +{ + char *memlock; + + memlock = get_fdinfo(fd, "memlock"); + close(fd); + + printf("%u: ", info->id); + if (info->type < ARRAY_SIZE(map_type_name)) + printf("%s ", map_type_name[info->type]); + else + printf("type %u ", info->type); + + if (*info->name) + printf("name %s ", info->name); + + printf("flags 0x%x\n", info->map_flags); + printf("\tkey %uB value %uB max_entries %u", + info->key_size, info->value_size, info->max_entries); + + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + printf("\n"); + + return 0; +} + +static int do_show(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 id = 0; + int err; + int fd; + + if (argc == 2) { + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + return show_map_close(fd, &info); + } + + if (argc) + return BAD_ARG(); + + while (true) { + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + err("can't get next map: %s\n", strerror(errno)); + if (errno == EINVAL) + err("kernel too old?\n"); + return -1; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + err("can't get map by id (%u): %s\n", + id, strerror(errno)); + return -1; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err("can't get map info: %s\n", strerror(errno)); + close(fd); + return -1; + } + + show_map_close(fd, &info); + } + + return errno == ENOENT ? 0 : -1; +} + +static int do_dump(int argc, char **argv) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int err; + int fd; + + if (argc != 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) { + err("Dumping maps of maps and program maps not supported\n"); + close(fd); + return -1; + } + + key = malloc(info.key_size); + value = alloc_value(&info); + if (!key || !value) { + err("mem alloc failed\n"); + err = -1; + goto exit_free; + } + + prev_key = NULL; + while (true) { + err = bpf_map_get_next_key(fd, prev_key, key); + if (err) { + if (errno == ENOENT) + err = 0; + break; + } + + if (!bpf_map_lookup_elem(fd, key, value)) { + print_entry(&info, key, value); + } else { + info("can't lookup element with key: "); + print_hex(key, info.key_size, " "); + printf("\n"); + } + + prev_key = key; + num_elems++; + } + + printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); + +exit_free: + free(key); + free(value); + close(fd); + + return err; +} + +static int do_update(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + __u32 *value_fd = NULL; + __u32 flags = BPF_ANY; + void *key, *value; + int fd, err; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + value = alloc_value(&info); + if (!key || !value) { + err("mem alloc failed"); + err = -1; + goto exit_free; + } + + err = parse_elem(argv, &info, key, value, info.key_size, + info.value_size, &flags, &value_fd); + if (err) + goto exit_free; + + err = bpf_map_update_elem(fd, key, value, flags); + if (err) { + err("update failed: %s\n", strerror(errno)); + goto exit_free; + } + +exit_free: + if (value_fd) + close(*value_fd); + free(key); + free(value); + close(fd); + + return err; +} + +static int do_lookup(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *value; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + value = alloc_value(&info); + if (!key || !value) { + err("mem alloc failed"); + err = -1; + goto exit_free; + } + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + if (err) + goto exit_free; + + err = bpf_map_lookup_elem(fd, key, value); + if (!err) { + print_entry(&info, key, value); + } else if (errno == ENOENT) { + printf("key:\n"); + print_hex(key, info.key_size, " "); + printf("\n\nNot found\n"); + } else { + err("lookup failed: %s\n", strerror(errno)); + } + +exit_free: + free(key); + free(value); + close(fd); + + return err; +} + +static int do_getnext(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key, *nextkey; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + nextkey = malloc(info.key_size); + if (!key || !nextkey) { + err("mem alloc failed"); + err = -1; + goto exit_free; + } + + if (argc) { + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, + NULL, NULL); + if (err) + goto exit_free; + } else { + free(key); + key = NULL; + } + + err = bpf_map_get_next_key(fd, key, nextkey); + if (err) { + err("can't get next key: %s\n", strerror(errno)); + goto exit_free; + } + + if (key) { + printf("key:\n"); + print_hex(key, info.key_size, " "); + printf("\n"); + } else { + printf("key: None\n"); + } + + printf("next key:\n"); + print_hex(nextkey, info.key_size, " "); + printf("\n"); + +exit_free: + free(nextkey); + free(key); + close(fd); + + return err; +} + +static int do_delete(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + void *key; + int err; + int fd; + + if (argc < 2) + usage(); + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + key = malloc(info.key_size); + if (!key) { + err("mem alloc failed"); + err = -1; + goto exit_free; + } + + err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL); + if (err) + goto exit_free; + + err = bpf_map_delete_elem(fd, key); + if (err) + err("delete failed: %s\n", strerror(errno)); + +exit_free: + free(key); + close(fd); + + return err; +} + +static int do_pin(int argc, char **argv) +{ + return do_pin_any(argc, argv, bpf_map_get_fd_by_id); +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s show [MAP]\n" + " %s %s dump MAP\n" + " %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" + " %s %s lookup MAP key BYTES\n" + " %s %s getnext MAP [key BYTES]\n" + " %s %s delete MAP key BYTES\n" + " %s %s pin MAP FILE\n" + " %s %s help\n" + "\n" + " MAP := { id MAP_ID | pinned FILE }\n" + " " HELP_SPEC_PROGRAM "\n" + " VALUE := { BYTES | MAP | PROG }\n" + " UPDATE_FLAGS := { any | exist | noexist }\n" + "", + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2], bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "help", do_help }, + { "dump", do_dump }, + { "update", do_update }, + { "lookup", do_lookup }, + { "getnext", do_getnext }, + { "delete", do_delete }, + { "pin", do_pin }, + { 0 } +}; + +int do_map(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c new file mode 100644 index 0000000000000..421ba89ce86a8 --- /dev/null +++ b/tools/bpf/bpftool/prog.c @@ -0,0 +1,456 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* Author: Jakub Kicinski */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "main.h" + +static const char * const prog_type_name[] = { + [BPF_PROG_TYPE_UNSPEC] = "unspec", + [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", + [BPF_PROG_TYPE_KPROBE] = "kprobe", + [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", + [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", + [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", + [BPF_PROG_TYPE_XDP] = "xdp", + [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", + [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", + [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", + [BPF_PROG_TYPE_LWT_IN] = "lwt_in", + [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", + [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", + [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", + [BPF_PROG_TYPE_SK_SKB] = "sk_skb", +}; + +static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) +{ + struct timespec real_time_ts, boot_time_ts; + time_t wallclock_secs; + struct tm load_tm; + + buf[--size] = '\0'; + + if (clock_gettime(CLOCK_REALTIME, &real_time_ts) || + clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) { + perror("Can't read clocks"); + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) + + nsecs / 1000000000; + + if (!localtime_r(&wallclock_secs, &load_tm)) { + snprintf(buf, size, "%llu", nsecs / 1000000000); + return; + } + + strftime(buf, size, "%b %d/%H:%M", &load_tm); +} + +static int prog_fd_by_tag(unsigned char *tag) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + unsigned int id = 0; + int err; + int fd; + + while (true) { + err = bpf_prog_get_next_id(id, &id); + if (err) { + err("%s\n", strerror(errno)); + return -1; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + err("can't get prog by id (%u): %s\n", + id, strerror(errno)); + return -1; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err("can't get prog info (%u): %s\n", + id, strerror(errno)); + close(fd); + return -1; + } + + if (!memcmp(tag, info.tag, BPF_TAG_SIZE)) + return fd; + + close(fd); + } +} + +int prog_parse_fd(int *argc, char ***argv) +{ + int fd; + + if (is_prefix(**argv, "id")) { + unsigned int id; + char *endptr; + + NEXT_ARGP(); + + id = strtoul(**argv, &endptr, 0); + if (*endptr) { + err("can't parse %s as ID\n", **argv); + return -1; + } + NEXT_ARGP(); + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) + err("get by id (%u): %s\n", id, strerror(errno)); + return fd; + } else if (is_prefix(**argv, "tag")) { + unsigned char tag[BPF_TAG_SIZE]; + + NEXT_ARGP(); + + if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2, + tag + 3, tag + 4, tag + 5, tag + 6, tag + 7) + != BPF_TAG_SIZE) { + err("can't parse tag\n"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_tag(tag); + } else if (is_prefix(**argv, "pinned")) { + char *path; + + NEXT_ARGP(); + + path = **argv; + NEXT_ARGP(); + + return open_obj_pinned_any(path, BPF_OBJ_PROG); + } + + err("expected 'id', 'tag' or 'pinned', got: '%s'?\n", **argv); + return -1; +} + +static void show_prog_maps(int fd, u32 num_maps) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + __u32 map_ids[num_maps]; + unsigned int i; + int err; + + info.nr_map_ids = num_maps; + info.map_ids = ptr_to_u64(map_ids); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err || !info.nr_map_ids) + return; + + printf(" map_ids "); + for (i = 0; i < info.nr_map_ids; i++) + printf("%u%s", map_ids[i], + i == info.nr_map_ids - 1 ? "" : ","); +} + +static int show_prog(int fd) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + char *memlock; + int err; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err("can't get prog info: %s\n", strerror(errno)); + return -1; + } + + printf("%u: ", info.id); + if (info.type < ARRAY_SIZE(prog_type_name)) + printf("%s ", prog_type_name[info.type]); + else + printf("type %u ", info.type); + + if (*info.name) + printf("name %s ", info.name); + + printf("tag "); + print_hex(info.tag, BPF_TAG_SIZE, ":"); + printf("\n"); + + if (info.load_time) { + char buf[32]; + + print_boot_time(info.load_time, buf, sizeof(buf)); + + /* Piggy back on load_time, since 0 uid is a valid one */ + printf("\tloaded_at %s uid %u\n", buf, info.created_by_uid); + } + + printf("\txlated %uB", info.xlated_prog_len); + + if (info.jited_prog_len) + printf(" jited %uB", info.jited_prog_len); + else + printf(" not jited"); + + memlock = get_fdinfo(fd, "memlock"); + if (memlock) + printf(" memlock %sB", memlock); + free(memlock); + + if (info.nr_map_ids) + show_prog_maps(fd, info.nr_map_ids); + + printf("\n"); + + return 0; +} + +static int do_show(int argc, char **argv) +{ __u32 id = 0; + int err; + int fd; + + if (argc == 2) { + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + return show_prog(fd); + } + + if (argc) + return BAD_ARG(); + + while (true) { + err = bpf_prog_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + err("can't get next program: %s\n", strerror(errno)); + if (errno == EINVAL) + err("kernel too old?\n"); + return -1; + } + + fd = bpf_prog_get_fd_by_id(id); + if (fd < 0) { + err("can't get prog by id (%u): %s\n", + id, strerror(errno)); + return -1; + } + + err = show_prog(fd); + close(fd); + if (err) + return err; + } + + return 0; +} + +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + bool can_disasm = false; + unsigned int buf_size; + char *filepath = NULL; + bool opcodes = false; + unsigned char *buf; + __u32 *member_len; + __u64 *member_ptr; + ssize_t n; + int err; + int fd; + + if (is_prefix(*argv, "jited")) { + member_len = &info.jited_prog_len; + member_ptr = &info.jited_prog_insns; + can_disasm = true; + } else if (is_prefix(*argv, "xlated")) { + member_len = &info.xlated_prog_len; + member_ptr = &info.xlated_prog_insns; + } else { + err("expected 'xlated' or 'jited', got: %s\n", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + err("expected file path\n"); + return -1; + } + + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } + + if (!filepath && !can_disasm) { + err("expected 'file' got %s\n", *argv); + return -1; + } + if (argc) { + usage(); + return -1; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err("can't get prog info: %s\n", strerror(errno)); + return -1; + } + + if (!*member_len) { + info("no instructions returned\n"); + close(fd); + return 0; + } + + buf_size = *member_len; + + buf = malloc(buf_size); + if (!buf) { + err("mem alloc failed\n"); + close(fd); + return -1; + } + + memset(&info, 0, sizeof(info)); + + *member_ptr = ptr_to_u64(buf); + *member_len = buf_size; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + close(fd); + if (err) { + err("can't get prog info: %s\n", strerror(errno)); + goto err_free; + } + + if (*member_len > buf_size) { + info("too many instructions returned\n"); + goto err_free; + } + + if (filepath) { + fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600); + if (fd < 0) { + err("can't open file %s: %s\n", filepath, + strerror(errno)); + goto err_free; + } + + n = write(fd, buf, *member_len); + close(fd); + if (n != *member_len) { + err("error writing output file: %s\n", + n < 0 ? strerror(errno) : "short write"); + goto err_free; + } + } else { + disasm_print_insn(buf, *member_len, opcodes); + } + + free(buf); + + return 0; + +err_free: + free(buf); + return -1; +} + +static int do_pin(int argc, char **argv) +{ + return do_pin_any(argc, argv, bpf_prog_get_fd_by_id); +} + +static int do_help(int argc, char **argv) +{ + fprintf(stderr, + "Usage: %s %s show [PROG]\n" + " %s %s dump xlated PROG file FILE\n" + " %s %s dump jited PROG [file FILE] [opcodes]\n" + " %s %s pin PROG FILE\n" + " %s %s help\n" + "\n" + " " HELP_SPEC_PROGRAM "\n" + "", + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2], bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "dump", do_dump }, + { "pin", do_pin }, + { 0 } +}; + +int do_prog(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} -- GitLab From ff69c21a85a4ed3d8dcf79dd750a0a9eda4fca83 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 Oct 2017 20:10:05 -0700 Subject: [PATCH 0989/1507] tools: bpftool: add documentation Add documentation for bpftool. Separate files for each subcommand. Use rst format. Documentation is compiled into man pages using rst2man. Signed-off-by: David Beckett Signed-off-by: Jakub Kicinski Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/bpf/bpftool/Documentation/Makefile | 34 ++++++ .../bpf/bpftool/Documentation/bpftool-map.rst | 110 ++++++++++++++++++ .../bpftool/Documentation/bpftool-prog.rst | 79 +++++++++++++ tools/bpf/bpftool/Documentation/bpftool.rst | 34 ++++++ tools/bpf/bpftool/Makefile | 6 + 5 files changed, 263 insertions(+) create mode 100644 tools/bpf/bpftool/Documentation/Makefile create mode 100644 tools/bpf/bpftool/Documentation/bpftool-map.rst create mode 100644 tools/bpf/bpftool/Documentation/bpftool-prog.rst create mode 100644 tools/bpf/bpftool/Documentation/bpftool.rst diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile new file mode 100644 index 0000000000000..bde77d7c4390a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -0,0 +1,34 @@ +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +INSTALL ?= install +RM ?= rm -f + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR +prefix?=$(HOME) +endif +mandir ?= $(prefix)/share/man +man8dir = $(mandir)/man8 + +MAN8_RST = $(wildcard *.rst) + +_DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST)) +DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) + +man: man8 +man8: $(DOC_MAN8) + +$(OUTPUT)%.8: %.rst + rst2man $< > $@ + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(DOC_MAN8) + +install: man + $(call QUIET_INSTALL, Documentation-man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man8dir); \ + $(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir); + +.PHONY: man man8 clean install +.DEFAULT_GOAL := man diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst new file mode 100644 index 0000000000000..ff63e89e4b6c8 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -0,0 +1,110 @@ +================ +bpftool-map +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** **map** *COMMAND* + + *COMMANDS* := + { show | dump | update | lookup | getnext | delete | pin | help } + +MAP COMMANDS +============= + +| **bpftool** map show [*MAP*] +| **bpftool** map dump *MAP* +| **bpftool** map update *MAP* key *BYTES* value *VALUE* [*UPDATE_FLAGS*] +| **bpftool** map lookup *MAP* key *BYTES* +| **bpftool** map getnext *MAP* [key *BYTES*] +| **bpftool** map delete *MAP* key *BYTES* +| **bpftool** map pin *MAP* *FILE* +| **bpftool** map help +| +| *MAP* := { id MAP_ID | pinned FILE } +| *VALUE* := { BYTES | MAP | PROGRAM } +| *UPDATE_FLAGS* := { any | exist | noexist } + +DESCRIPTION +=========== + **bpftool map show** [*MAP*] + Show information about loaded maps. If *MAP* is specified + show information only about given map, otherwise list all + maps currently loaded on the system. + + Output will start with map ID followed by map type and + zero or more named attributes (depending on kernel version). + + **bpftool map dump** *MAP* + Dump all entries in a given *MAP*. + + **bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] + Update map entry for a given *KEY*. + + *UPDATE_FLAGS* can be one of: **any** update existing entry + or add if doesn't exit; **exist** update only if entry already + exists; **noexist** update only if entry doesn't exist. + + **bpftool map lookup** *MAP* **key** *BYTES* + Lookup **key** in the map. + + **bpftool map getnext** *MAP* [**key** *BYTES*] + Get next key. If *key* is not specified, get first key. + + **bpftool map delete** *MAP* **key** *BYTES* + Remove entry from the map. + + **bpftool map pin** *MAP* *FILE* + Pin map *MAP* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. + + **bpftool map help** + Print short help message. + +EXAMPLES +======== +**# bpftool map show** +:: + + 10: hash name some_map flags 0x0 + key 4B value 8B max_entries 2048 memlock 167936B + +**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** + +**# bpftool map lookup id 10 key 0 1 2 3** + +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + + +**# bpftool map dump id 10** +:: + + key: 00 01 02 03 value: 00 01 02 03 04 05 06 07 + key: 0d 00 07 00 value: 02 00 00 00 01 02 03 04 + Found 2 elements + +**# bpftool map getnext id 10 key 0 1 2 3** +:: + + key: + 00 01 02 03 + next key: + 0d 00 07 00 + +| +| **# mount -t bpf none /sys/fs/bpf/** +| **# bpftool map pin id 10 /sys/fs/bpf/map** +| **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00** + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-prog**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst new file mode 100644 index 0000000000000..57fc4b9924ea6 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -0,0 +1,79 @@ +================ +bpftool-prog +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF progs +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + +| **bpftool** prog show [*PROG*] +| **bpftool** prog dump xlated *PROG* file *FILE* +| **bpftool** prog dump jited *PROG* [file *FILE*] [opcodes] +| **bpftool** prog pin *PROG* *FILE* +| **bpftool** prog help +| +| *PROG* := { id *PROG_ID* | pinned *FILE* | tag *PROG_TAG* } + +DESCRIPTION +=========== + **bpftool prog show** [*PROG*] + Show information about loaded programs. If *PROG* is + specified show information only about given program, otherwise + list all programs currently loaded on the system. + + Output will start with program ID followed by program type and + zero or more named attributes (depending on kernel version). + + **bpftool prog dump xlated** *PROG* **file** *FILE* + Dump eBPF instructions of the program from the kernel to a + file. + + **bpftool prog dump jited** *PROG* [**file** *FILE*] [**opcodes**] + Dump jited image (host machine code) of the program. + If *FILE* is specified image will be written to a file, + otherwise it will be disassembled and printed to stdout. + + **opcodes** controls if raw opcodes will be printed. + + **bpftool prog pin** *PROG* *FILE* + Pin program *PROG* as *FILE*. + + Note: *FILE* must be located in *bpffs* mount. + + **bpftool prog help** + Print short help message. + +EXAMPLES +======== +**# bpftool prog show** +:: + + 10: xdp name some_prog tag 00:5a:3d:21:23:62:0c:8b + loaded_at Sep 29/20:11 uid 0 + xlated 528B jited 370B memlock 4096B map_ids 10 + +| +| **# bpftool prog dump xlated id 10 file /tmp/t** +| **# ls -l /tmp/t** +| -rw------- 1 root root 560 Jul 22 01:42 /tmp/t + +| +| **# bpftool prog dum jited pinned /sys/fs/bpf/prog** + +:: + + push %rbp + mov %rsp,%rbp + sub $0x228,%rsp + sub $0x28,%rbp + mov %rbx,0x0(%rbp) + + + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-map**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst new file mode 100644 index 0000000000000..f1df1893fb549 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -0,0 +1,34 @@ +================ +BPFTOOL +================ +------------------------------------------------------------------------------- +tool for inspection and simple manipulation of eBPF programs and maps +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** *OBJECT* { *COMMAND* | help } + + **bpftool** batch file *FILE* + + *OBJECT* := { **map** | **program** } + + *MAP-COMMANDS* := + { show | dump | update | lookup | getnext | delete | pin | help } + + *PROG-COMMANDS* := { show | dump jited | dump xlated | pin | help } + +DESCRIPTION +=========== + *bpftool* allows for inspection and simple modification of BPF objects + on the system. + + Note that format of the output of all tools is not guaranteed to be + stable and should not be depended upon. + +SEE ALSO +======== + **bpftool-map**\ (8), **bpftool-prog**\ (8) diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index a7151f47fb409..8705ee44664d8 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -74,6 +74,12 @@ clean: $(LIBBPF)-clean install: install $(OUTPUT)bpftool $(prefix)/sbin/bpftool +doc: + $(Q)$(MAKE) -C Documentation/ + +doc-install: + $(Q)$(MAKE) -C Documentation/ install + FORCE: .PHONY: all clean FORCE -- GitLab From 463a9215f3ca7600b5fff6d903913906ae4548a9 Mon Sep 17 00:00:00 2001 From: Pierre-Yves MORDRET Date: Thu, 21 Sep 2017 15:30:09 +0200 Subject: [PATCH 0990/1507] i2c: stm32f7: fix setup structure I2C drive setup structure is not properly allocated. Make it static instead of pointer to store driver data. Fixes: aeb068c5721485 ("i2c: i2c-stm32f7: add driver") Signed-off-by: Pierre-Yves MORDRET Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-stm32f7.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 47c67b0ca8960..42ebdb1665e1a 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -215,7 +215,7 @@ struct stm32f7_i2c_dev { unsigned int msg_num; unsigned int msg_id; struct stm32f7_i2c_msg f7_msg; - struct stm32f7_i2c_setup *setup; + struct stm32f7_i2c_setup setup; struct stm32f7_i2c_timings timing; }; @@ -537,7 +537,7 @@ static void stm32f7_i2c_hw_config(struct stm32f7_i2c_dev *i2c_dev) writel_relaxed(timing, i2c_dev->base + STM32F7_I2C_TIMINGR); /* Enable I2C */ - if (i2c_dev->setup->analog_filter) + if (i2c_dev->setup.analog_filter) stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1, STM32F7_I2C_CR1_ANFOFF); else @@ -887,22 +887,19 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) } setup = of_device_get_match_data(&pdev->dev); - i2c_dev->setup->rise_time = setup->rise_time; - i2c_dev->setup->fall_time = setup->fall_time; - i2c_dev->setup->dnf = setup->dnf; - i2c_dev->setup->analog_filter = setup->analog_filter; + i2c_dev->setup = *setup; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-rising-time-ns", &rise_time); if (!ret) - i2c_dev->setup->rise_time = rise_time; + i2c_dev->setup.rise_time = rise_time; ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-falling-time-ns", &fall_time); if (!ret) - i2c_dev->setup->fall_time = fall_time; + i2c_dev->setup.fall_time = fall_time; - ret = stm32f7_i2c_setup_timing(i2c_dev, i2c_dev->setup); + ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup); if (ret) goto clk_free; -- GitLab From cb09d943c70da7c8097006db1dc163b2d99338f6 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 21 Sep 2017 16:23:16 +0300 Subject: [PATCH 0991/1507] i2c: i801: Add support for Intel Cedar Fork Add PCI ID for Intel Cedar Fork PCH. Signed-off-by: Jarkko Nikula Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- Documentation/i2c/busses/i2c-i801 | 1 + drivers/i2c/busses/Kconfig | 1 + drivers/i2c/busses/i2c-i801.c | 4 ++++ 3 files changed, 6 insertions(+) diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index 0500193434cb2..d477024569269 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -36,6 +36,7 @@ Supported adapters: * Intel Gemini Lake (SOC) * Intel Cannon Lake-H (PCH) * Intel Cannon Lake-LP (PCH) + * Intel Cedar Fork (PCH) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index c06dce2c1da74..45a3f3ca29b38 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -131,6 +131,7 @@ config I2C_I801 Gemini Lake (SOC) Cannon Lake-H (PCH) Cannon Lake-LP (PCH) + Cedar Fork (PCH) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e114e4e00d297..9e12a53ef7b8c 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -68,6 +68,7 @@ * Gemini Lake (SOC) 0x31d4 32 hard yes yes yes * Cannon Lake-H (PCH) 0xa323 32 hard yes yes yes * Cannon Lake-LP (PCH) 0x9da3 32 hard yes yes yes + * Cedar Fork (PCH) 0x18df 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -204,6 +205,7 @@ /* Older devices have their ID defined in */ #define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS 0x0f12 +#define PCI_DEVICE_ID_INTEL_CDF_SMBUS 0x18df #define PCI_DEVICE_ID_INTEL_DNV_SMBUS 0x19df #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 @@ -1025,6 +1027,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BRASWELL_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) }, @@ -1513,6 +1516,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) case PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS: case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS: + case PCI_DEVICE_ID_INTEL_CDF_SMBUS: case PCI_DEVICE_ID_INTEL_DNV_SMBUS: case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; -- GitLab From a91aee523fb282f8868ba6b918f781679c3ea301 Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Thu, 21 Sep 2017 08:24:27 +0200 Subject: [PATCH 0992/1507] i2c: ensure termination of *_device_id tables Make sure (of/i2c/platform)_device_id tables are NULL terminated. Found by coccinelle spatch "misc/of_table.cocci" Signed-off-by: Thomas Meyer Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-sprd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c index 22e08ae1704f4..25fcc3c1e32bf 100644 --- a/drivers/i2c/busses/i2c-sprd.c +++ b/drivers/i2c/busses/i2c-sprd.c @@ -627,6 +627,7 @@ static const struct dev_pm_ops sprd_i2c_pm_ops = { static const struct of_device_id sprd_i2c_of_match[] = { { .compatible = "sprd,sc9860-i2c", }, + {}, }; static struct platform_driver sprd_i2c_driver = { -- GitLab From 25f2f440989c7079fdd8fccd54592cc077b63ae5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 18 Sep 2017 09:15:39 +0100 Subject: [PATCH 0993/1507] i2c: i2c-stm32f7: make structure stm32f7_setup static const The structure stm32f7_setup is local to the source and does not need to be in global scope, make it static const. Cleans up sparse warning: symbol 'stm32f7_setup' was not declared. Should it be static? Signed-off-by: Colin Ian King Acked-by: Pierre-Yves MORDRET Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-stm32f7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 42ebdb1665e1a..d4a6e9c2e9aae 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -265,7 +265,7 @@ static struct stm32f7_i2c_spec i2c_specs[] = { }, }; -struct stm32f7_i2c_setup stm32f7_setup = { +static const struct stm32f7_i2c_setup stm32f7_setup = { .rise_time = STM32F7_I2C_RISE_TIME_DEFAULT, .fall_time = STM32F7_I2C_FALL_TIME_DEFAULT, .dnf = STM32F7_I2C_DNF_DEFAULT, -- GitLab From f26e60167d8b5b1c67b3efd4cb5672da446bdb0e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 4 Oct 2017 10:39:05 -0500 Subject: [PATCH 0994/1507] x86/kvm: Move kvm_fastop_exception to .fixup section MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When compiling the kernel with the '-frecord-gcc-switches' flag, objtool complains: arch/x86/kvm/emulate.o: warning: objtool: .GCC.command.line+0x0: special: can't find new instruction And also the kernel fails to link. The problem is that the 'kvm_fastop_exception' code gets placed into the throwaway '.GCC.command.line' section instead of '.text'. Exception fixup code is conventionally placed in the '.fixup' section, so put it there where it belongs. Reported-and-tested-by: Guenter Roeck Signed-off-by: Josh Poimboeuf Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- arch/x86/kvm/emulate.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a36254cbf7765..d90cdc77e0773 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #op " %al \n\t" \ FOP_RET -asm(".global kvm_fastop_exception \n" - "kvm_fastop_exception: xor %esi, %esi; ret"); +asm(".pushsection .fixup, \"ax\"\n" + ".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret\n" + ".popsection"); FOP_START(setcc) FOP_SETCC(seto) -- GitLab From 954c736f865d6c0c68ae4263a2f3502ee7c447a3 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 18 Sep 2017 22:53:43 +0300 Subject: [PATCH 0995/1507] ovl: fix may_write_real() for overlayfs directories Overlayfs directory file_inode() is the overlay inode whether the real inode is upper or lower. This fixes a regression in xfstest generic/158. Fixes: 7c6893e3c9ab ("ovl: don't allow writing ioctl on lower layer") Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/namespace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/namespace.c b/fs/namespace.c index 54059b142d6ba..3b601f115b6cb 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -468,7 +468,9 @@ static inline int may_write_real(struct file *file) /* File refers to upper, writable layer? */ upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER); - if (upperdentry && file_inode(file) == d_inode(upperdentry)) + if (upperdentry && + (file_inode(file) == d_inode(upperdentry) || + file_inode(file) == d_inode(dentry))) return 0; /* Lower layer: can't write to real file, sorry... */ -- GitLab From e0082a0f04c432cb6d7128ef60d8e425e45ce025 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 24 Sep 2017 13:01:35 +0300 Subject: [PATCH 0996/1507] ovl: fix error value printed in ovl_lookup_index() Fixes: 359f392ca53e ("ovl: lookup index entry for copy up origin") Cc: # v4.13 Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/namei.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index c3addd1114f1f..654bea1a5ac9f 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -506,6 +506,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry, index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { + err = PTR_ERR(index); pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" "overlayfs: mount with '-o index=off' to disable inodes index.\n", d_inode(origin)->i_ino, name.len, name.name, -- GitLab From 9f4ec904dbd4eb1a2db10d5e7dc16eae386fe64d Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 24 Sep 2017 17:36:26 +0300 Subject: [PATCH 0997/1507] ovl: fix dput() of ERR_PTR in ovl_cleanup_index() Fixes: caf70cb2ba5d ("ovl: cleanup orphan index entries") Cc: # v4.13 Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/util.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 117794582f9fa..7ae33d225a67c 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -430,7 +430,7 @@ void ovl_inuse_unlock(struct dentry *dentry) } } -/* Called must hold OVL_I(inode)->oi_lock */ +/* Caller must hold OVL_I(inode)->lock */ static void ovl_cleanup_index(struct dentry *dentry) { struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode; @@ -469,6 +469,9 @@ static void ovl_cleanup_index(struct dentry *dentry) err = PTR_ERR(index); if (!IS_ERR(index)) err = ovl_cleanup(dir, index); + else + index = NULL; + inode_unlock(dir); if (err) goto fail; -- GitLab From dc7ab6773e8171e07f16fd0df0c5eea28c899503 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 24 Sep 2017 22:19:10 +0300 Subject: [PATCH 0998/1507] ovl: fix dentry leak in ovl_indexdir_cleanup() index dentry was not released when breaking out of the loop due to index verification error. Fixes: 415543d5c64f ("ovl: cleanup bad and stale index entries on mount") Cc: # v4.13 Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/readdir.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 62e9b22a2077a..0f85ee9c3268a 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -988,6 +988,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, struct path *lowerstack, unsigned int numlower) { int err; + struct dentry *index = NULL; struct inode *dir = dentry->d_inode; struct path path = { .mnt = mnt, .dentry = dentry }; LIST_HEAD(list); @@ -1007,8 +1008,6 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, inode_lock_nested(dir, I_MUTEX_PARENT); list_for_each_entry(p, &list, l_node) { - struct dentry *index; - if (p->name[0] == '.') { if (p->len == 1) continue; @@ -1018,6 +1017,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, index = lookup_one_len(p->name, dentry, p->len); if (IS_ERR(index)) { err = PTR_ERR(index); + index = NULL; break; } err = ovl_verify_index(index, lowerstack, numlower); @@ -1029,7 +1029,9 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, break; } dput(index); + index = NULL; } + dput(index); inode_unlock(dir); out: ovl_cache_free(&list); -- GitLab From 5820dc0888d302ac05f8b91ffdf7e4e53b4fbf53 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Sep 2017 16:39:55 +0300 Subject: [PATCH 0999/1507] ovl: fix missing unlock_rename() in ovl_do_copy_up() Use the ovl_lock_rename_workdir() helper which requires unlock_rename() only on lock success. Fixes: ("fd210b7d67ee ovl: move copy up lock out") Cc: # v4.13 Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/overlayfs/copy_up.c | 6 ++---- fs/overlayfs/dir.c | 20 -------------------- fs/overlayfs/overlayfs.h | 1 + fs/overlayfs/util.c | 19 +++++++++++++++++++ 4 files changed, 22 insertions(+), 24 deletions(-) diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index aad97b30d5e65..c441f9387a1ba 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -561,10 +561,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) c->tmpfile = true; err = ovl_copy_up_locked(c); } else { - err = -EIO; - if (lock_rename(c->workdir, c->destdir) != NULL) { - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - } else { + err = ovl_lock_rename_workdir(c->workdir, c->destdir); + if (!err) { err = ovl_copy_up_locked(c); unlock_rename(c->workdir, c->destdir); } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 3309b19122417..cc961a3bd3bde 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -216,26 +216,6 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode, return err; } -static int ovl_lock_rename_workdir(struct dentry *workdir, - struct dentry *upperdir) -{ - /* Workdir should not be the same as upperdir */ - if (workdir == upperdir) - goto err; - - /* Workdir should not be subdir of upperdir and vice versa */ - if (lock_rename(workdir, upperdir) != NULL) - goto err_unlock; - - return 0; - -err_unlock: - unlock_rename(workdir, upperdir); -err: - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - return -EIO; -} - static struct dentry *ovl_clear_empty(struct dentry *dentry, struct list_head *list) { diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index d4e8c1a08fb0f..c706a6f999288 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -235,6 +235,7 @@ bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry, bool *locked); void ovl_nlink_end(struct dentry *dentry, bool locked); +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); static inline bool ovl_is_impuredir(struct dentry *dentry) { diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 7ae33d225a67c..b9b239fa5cfd2 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -560,3 +560,22 @@ void ovl_nlink_end(struct dentry *dentry, bool locked) mutex_unlock(&OVL_I(d_inode(dentry))->lock); } } + +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} -- GitLab From 85fdee1eef1a9e48ad5716916677e0c5fbc781e3 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 29 Sep 2017 10:21:21 +0300 Subject: [PATCH 1000/1507] ovl: fix regression caused by exclusive upper/work dir protection Enforcing exclusive ownership on upper/work dirs caused a docker regression: https://github.com/moby/moby/issues/34672. Euan spotted the regression and pointed to the offending commit. Vivek has brought the regression to my attention and provided this reproducer: Terminal 1: mount -t overlay -o workdir=work,lowerdir=lower,upperdir=upper none merged/ Terminal 2: unshare -m Terminal 1: umount merged mount -t overlay -o workdir=work,lowerdir=lower,upperdir=upper none merged/ mount: /root/overlay-testing/merged: none already mounted or mount point busy To fix the regression, I replaced the error with an alarming warning. With index feature enabled, mount does fail, but logs a suggestion to override exclusive dir protection by disabling index. Note that index=off mount does take the inuse locks, so a concurrent index=off will issue the warning and a concurrent index=on mount will fail. Documentation was updated to reflect this change. Fixes: 2cac0c00a6cd ("ovl: get exclusive ownership on upper/work dirs") Cc: # v4.13 Reported-by: Euan Kemp Reported-by: Vivek Goyal Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- Documentation/filesystems/overlayfs.txt | 5 ++++- fs/overlayfs/ovl_entry.h | 3 +++ fs/overlayfs/super.c | 27 +++++++++++++++++-------- 3 files changed, 26 insertions(+), 9 deletions(-) diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 36f528a7fdd64..8caa60734647f 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -210,8 +210,11 @@ path as another overlay mount and it may use a lower layer path that is beneath or above the path of another overlay lower layer path. Using an upper layer path and/or a workdir path that are already used by -another overlay mount is not allowed and will fail with EBUSY. Using +another overlay mount is not allowed and may fail with EBUSY. Using partially overlapping paths is not allowed but will not fail with EBUSY. +If files are accessed from two overlayfs mounts which share or overlap the +upper layer and/or workdir path the behavior of the overlay is undefined, +though it will not result in a crash or deadlock. Mounting an overlay using an upper layer path, where the upper layer path was previously used by another mounted overlay in combination with a diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 878a750986dd7..25d9b5adcd429 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -37,6 +37,9 @@ struct ovl_fs { bool noxattr; /* sb common to all layers */ struct super_block *same_sb; + /* Did we take the inuse lock? */ + bool upperdir_locked; + bool workdir_locked; }; /* private information held for every overlayfs dentry */ diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fd5ea4facc622..092d150643c12 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -211,9 +211,10 @@ static void ovl_put_super(struct super_block *sb) dput(ufs->indexdir); dput(ufs->workdir); - ovl_inuse_unlock(ufs->workbasedir); + if (ufs->workdir_locked) + ovl_inuse_unlock(ufs->workbasedir); dput(ufs->workbasedir); - if (ufs->upper_mnt) + if (ufs->upper_mnt && ufs->upperdir_locked) ovl_inuse_unlock(ufs->upper_mnt->mnt_root); mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) @@ -881,9 +882,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_put_upperpath; err = -EBUSY; - if (!ovl_inuse_trylock(upperpath.dentry)) { - pr_err("overlayfs: upperdir is in-use by another mount\n"); + if (ovl_inuse_trylock(upperpath.dentry)) { + ufs->upperdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); goto out_put_upperpath; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } err = ovl_mount_dir(ufs->config.workdir, &workpath); @@ -901,9 +906,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } err = -EBUSY; - if (!ovl_inuse_trylock(workpath.dentry)) { - pr_err("overlayfs: workdir is in-use by another mount\n"); + if (ovl_inuse_trylock(workpath.dentry)) { + ufs->workdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); goto out_put_workpath; + } else { + pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } ufs->workbasedir = workpath.dentry; @@ -1156,11 +1165,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) out_free_lowertmp: kfree(lowertmp); out_unlock_workdentry: - ovl_inuse_unlock(workpath.dentry); + if (ufs->workdir_locked) + ovl_inuse_unlock(workpath.dentry); out_put_workpath: path_put(&workpath); out_unlock_upperdentry: - ovl_inuse_unlock(upperpath.dentry); + if (ufs->upperdir_locked) + ovl_inuse_unlock(upperpath.dentry); out_put_upperpath: path_put(&upperpath); out_free_config: -- GitLab From e42eef4ba38806b18c4a74f0c276fb2e0b548173 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 4 Oct 2017 12:28:18 +0200 Subject: [PATCH 1001/1507] KVM: add X86_LOCAL_APIC dependency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The rework of the posted interrupt handling broke building without support for the local APIC: ERROR: "boot_cpu_physical_apicid" [arch/x86/kvm/kvm-intel.ko] undefined! That configuration is probably not particularly useful anyway, so we can avoid the randconfig failures by adding a Kconfig dependency. Fixes: 8b306e2f3c41 ("KVM: VMX: avoid double list add with VT-d posted interrupts") Signed-off-by: Arnd Bergmann Signed-off-by: Radim Krčmář --- arch/x86/kvm/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3ea624452f932..3c48bc8bf08c7 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES -- GitLab From 41dcf197ad5373a7dd0a4b6572aec2e3ec6a0e49 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Mon, 2 Oct 2017 17:17:35 -0500 Subject: [PATCH 1002/1507] dm raid: fix incorrect status output at the end of a "recover" process There are three important fields that indicate the overall health and status of an array: dev_health, sync_ratio, and sync_action. They tell us the condition of the devices in the array, and the degree to which the array is synchronized. This commit fixes a condition that is reported incorrectly. When a member of the array is being rebuilt or a new device is added, the "recover" process is used to synchronize it with the rest of the array. When the process is complete, but the sync thread hasn't yet been reaped, it is possible for the state of MD to be: mddev->recovery = [ MD_RECOVERY_RUNNING MD_RECOVERY_RECOVER MD_RECOVERY_DONE ] curr_resync_completed = (but not MaxSector) and all rdevs to be In_sync. This causes the 'array_in_sync' output parameter that is passed to rs_get_progress() to be computed incorrectly and reported as 'false' -- or not in-sync. This in turn causes the dev_health status characters to be reported as all 'a', rather than the proper 'A'. This can cause erroneous output for several seconds at a time when tools will want to be checking the condition due to events that are raised at the end of a sync process. Fix this by properly calculating the 'array_in_sync' return parameter in rs_get_progress(). Also, remove an unnecessary intermediate 'recovery_cp' variable in rs_get_progress(). Signed-off-by: Jonathan Brassow Signed-off-by: Mike Snitzer --- Documentation/device-mapper/dm-raid.txt | 1 + drivers/md/dm-raid.c | 11 ++++++----- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 4a0a7469fdd7b..32df07e29f686 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -344,3 +344,4 @@ Version History (wrong raid10_copies/raid10_format sequence) 1.11.1 Add raid4/5/6 journal write-back support via journal_mode option 1.12.1 fix for MD deadlock between mddev_suspend() and md_write_start() available +1.13.0 Fix dev_health status at end of "recover" (was 'a', now 'A') diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285ea9d1c..43094ea89e37f 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3297,11 +3297,10 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev, static sector_t rs_get_progress(struct raid_set *rs, sector_t resync_max_sectors, bool *array_in_sync) { - sector_t r, recovery_cp, curr_resync_completed; + sector_t r, curr_resync_completed; struct mddev *mddev = &rs->md; curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp; - recovery_cp = mddev->recovery_cp; *array_in_sync = false; if (rs_is_raid0(rs)) { @@ -3330,9 +3329,11 @@ static sector_t rs_get_progress(struct raid_set *rs, } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) r = curr_resync_completed; else - r = recovery_cp; + r = mddev->recovery_cp; - if (r == MaxSector) { + if ((r == MaxSector) || + (test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + (mddev->curr_resync_completed == resync_max_sectors))) { /* * Sync complete. */ @@ -3892,7 +3893,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 12, 1}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, -- GitLab From 44f209807ee87a5eddf6c0432f3fb63cec27bad8 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:50 -0400 Subject: [PATCH 1003/1507] VSOCK: export socket tables for sock_diag interface The socket table symbols need to be exported from vsock.ko so that the vsock_diag.ko module will be able to traverse sockets. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/net/af_vsock.h | 5 +++++ net/vmw_vsock/af_vsock.c | 10 ++++++---- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index f9fb566e75cfd..30cba806e3447 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -27,6 +27,11 @@ #define LAST_RESERVED_PORT 1023 +#define VSOCK_HASH_SIZE 251 +extern struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; +extern struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; +extern spinlock_t vsock_table_lock; + #define vsock_sk(__sk) ((struct vsock_sock *)__sk) #define sk_vsock(__vsk) (&(__vsk)->sk) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index dfc8c51e4d74e..9afe4da8c67d5 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -153,7 +153,6 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function * mods with VSOCK_HASH_SIZE to ensure this. */ -#define VSOCK_HASH_SIZE 251 #define MAX_PORT_RETRIES 24 #define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE) @@ -168,9 +167,12 @@ EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); #define vsock_connected_sockets_vsk(vsk) \ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) -static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; -static struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; -static DEFINE_SPINLOCK(vsock_table_lock); +struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; +EXPORT_SYMBOL_GPL(vsock_bind_table); +struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; +EXPORT_SYMBOL_GPL(vsock_connected_table); +DEFINE_SPINLOCK(vsock_table_lock); +EXPORT_SYMBOL_GPL(vsock_table_lock); /* Autobind this socket to the local address if necessary. */ static int vsock_auto_bind(struct vsock_sock *vsk) -- GitLab From bf359b8127719535f88494adb3c2b73c06667dcd Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:51 -0400 Subject: [PATCH 1004/1507] VSOCK: move __vsock_in_bound/connected_table() to af_vsock.h The vsock_diag.ko module will need to check socket table membership. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/net/af_vsock.h | 12 ++++++++++++ net/vmw_vsock/af_vsock.c | 10 ---------- 2 files changed, 12 insertions(+), 10 deletions(-) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 30cba806e3447..3dd217718a2f1 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -180,6 +180,18 @@ const struct vsock_transport *vsock_core_get_transport(void); /**** UTILS ****/ +/* vsock_table_lock must be held */ +static inline bool __vsock_in_bound_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->bound_table); +} + +/* vsock_table_lock must be held */ +static inline bool __vsock_in_connected_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->connected_table); +} + void vsock_release_pending(struct sock *pending); void vsock_add_pending(struct sock *listener, struct sock *pending); void vsock_remove_pending(struct sock *listener, struct sock *pending); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9afe4da8c67d5..9b179a0081b3d 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -250,16 +250,6 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, return NULL; } -static bool __vsock_in_bound_table(struct vsock_sock *vsk) -{ - return !list_empty(&vsk->bound_table); -} - -static bool __vsock_in_connected_table(struct vsock_sock *vsk) -{ - return !list_empty(&vsk->connected_table); -} - static void vsock_insert_unbound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); -- GitLab From 3b4477d2dcf2709d0be89e2a8dced3d0f4a017f2 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:52 -0400 Subject: [PATCH 1005/1507] VSOCK: use TCP state constants for sk_state There are two state fields: socket->state and sock->sk_state. The socket->state field uses SS_UNCONNECTED, SS_CONNECTED, etc while the sock->sk_state typically uses values that match TCP state constants (TCP_CLOSE, TCP_ESTABLISHED). AF_VSOCK does not follow this convention and instead uses SS_* constants for both fields. The sk_state field will be exposed to userspace through the vsock_diag interface for ss(8), netstat(8), and other programs. This patch switches sk_state to TCP state constants so that the meaning of this field is consistent with other address families. Not just AF_INET and AF_INET6 use the TCP constants, AF_UNIX and others do too. The following mapping was used to convert the code: SS_FREE -> TCP_CLOSE SS_UNCONNECTED -> TCP_CLOSE SS_CONNECTING -> TCP_SYN_SENT SS_CONNECTED -> TCP_ESTABLISHED SS_DISCONNECTING -> TCP_CLOSING VSOCK_SS_LISTEN -> TCP_LISTEN In __vsock_create() the sk_state initialization was dropped because sock_init_data() already initializes sk_state to TCP_CLOSE. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/net/af_vsock.h | 3 -- net/vmw_vsock/af_vsock.c | 46 ++++++++++++-------- net/vmw_vsock/hyperv_transport.c | 12 ++--- net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 22 +++++----- net/vmw_vsock/vmci_transport.c | 34 +++++++-------- net/vmw_vsock/vmci_transport_notify.c | 2 +- net/vmw_vsock/vmci_transport_notify_qstate.c | 2 +- 8 files changed, 64 insertions(+), 59 deletions(-) diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3dd217718a2f1..9324ac2d9ff2d 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -22,9 +22,6 @@ #include "vsock_addr.h" -/* vsock-specific sock->sk_state constants */ -#define VSOCK_SS_LISTEN 255 - #define LAST_RESERVED_PORT 1023 #define VSOCK_HASH_SIZE 251 diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9b179a0081b3d..98359c19522f6 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -36,7 +36,7 @@ * not support simultaneous connects (two "client" sockets connecting). * * - "Server" sockets are referred to as listener sockets throughout this - * implementation because they are in the VSOCK_SS_LISTEN state. When a + * implementation because they are in the TCP_LISTEN state. When a * connection request is received (the second kind of socket mentioned above), * we create a new socket and refer to it as a pending socket. These pending * sockets are placed on the pending connection list of the listener socket. @@ -82,6 +82,15 @@ * argument, we must ensure the reference count is increased to ensure the * socket isn't freed before the function is run; the deferred function will * then drop the reference. + * + * - sk->sk_state uses the TCP state constants because they are widely used by + * other address families and exposed to userspace tools like ss(8): + * + * TCP_CLOSE - unconnected + * TCP_SYN_SENT - connecting + * TCP_ESTABLISHED - connected + * TCP_CLOSING - disconnecting + * TCP_LISTEN - listening */ #include @@ -477,7 +486,7 @@ void vsock_pending_work(struct work_struct *work) if (vsock_in_connected_table(vsk)) vsock_remove_connected(vsk); - sk->sk_state = SS_FREE; + sk->sk_state = TCP_CLOSE; out: release_sock(sk); @@ -617,7 +626,6 @@ struct sock *__vsock_create(struct net *net, sk->sk_destruct = vsock_sk_destruct; sk->sk_backlog_rcv = vsock_queue_rcv_skb; - sk->sk_state = 0; sock_reset_flag(sk, SOCK_DONE); INIT_LIST_HEAD(&vsk->bound_table); @@ -891,7 +899,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, /* Listening sockets that have connections in their accept * queue can be read. */ - if (sk->sk_state == VSOCK_SS_LISTEN + if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) mask |= POLLIN | POLLRDNORM; @@ -920,7 +928,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, } /* Connected sockets that can produce data can be written. */ - if (sk->sk_state == SS_CONNECTED) { + if (sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( @@ -942,7 +950,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock, * POLLOUT|POLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ - if (sk->sk_state == SS_UNCONNECTED) { + if (sk->sk_state == TCP_CLOSE) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= POLLOUT | POLLWRNORM; @@ -1112,9 +1120,9 @@ static void vsock_connect_timeout(struct work_struct *work) sk = sk_vsock(vsk); lock_sock(sk); - if (sk->sk_state == SS_CONNECTING && + if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; sk->sk_error_report(sk); cancel = 1; @@ -1160,7 +1168,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, err = -EALREADY; break; default: - if ((sk->sk_state == VSOCK_SS_LISTEN) || + if ((sk->sk_state == TCP_LISTEN) || vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { err = -EINVAL; goto out; @@ -1183,7 +1191,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - sk->sk_state = SS_CONNECTING; + sk->sk_state = TCP_SYN_SENT; err = transport->connect(vsk); if (err < 0) @@ -1203,7 +1211,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) { + while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection @@ -1226,13 +1234,13 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; } else if (timeout == 0) { err = -ETIMEDOUT; - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; @@ -1243,7 +1251,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (sk->sk_err) { err = -sk->sk_err; - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; } else { err = 0; @@ -1276,7 +1284,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, goto out; } - if (listener->sk_state != VSOCK_SS_LISTEN) { + if (listener->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } @@ -1366,7 +1374,7 @@ static int vsock_listen(struct socket *sock, int backlog) } sk->sk_max_ack_backlog = backlog; - sk->sk_state = VSOCK_SS_LISTEN; + sk->sk_state = TCP_LISTEN; err = 0; @@ -1546,7 +1554,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, /* Callers should not provide a destination with stream sockets. */ if (msg->msg_namelen) { - err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP; + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; } @@ -1557,7 +1565,7 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - if (sk->sk_state != SS_CONNECTED || + if (sk->sk_state != TCP_ESTABLISHED || !vsock_addr_bound(&vsk->local_addr)) { err = -ENOTCONN; goto out; @@ -1681,7 +1689,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, lock_sock(sk); - if (sk->sk_state != SS_CONNECTED) { + if (sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a * peer has not connected or a local shutdown occured with the diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 14ed5a344cdf3..bbac023e70d17 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -310,7 +310,7 @@ static void hvs_close_connection(struct vmbus_channel *chan) struct sock *sk = get_per_channel_state(chan); struct vsock_sock *vsk = vsock_sk(sk); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN; @@ -344,8 +344,8 @@ static void hvs_open_connection(struct vmbus_channel *chan) if (!sk) return; - if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) || - (!conn_from_host && sk->sk_state != SS_CONNECTING)) + if ((conn_from_host && sk->sk_state != TCP_LISTEN) || + (!conn_from_host && sk->sk_state != TCP_SYN_SENT)) goto out; if (conn_from_host) { @@ -357,7 +357,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) if (!new) goto out; - new->sk_state = SS_CONNECTING; + new->sk_state = TCP_SYN_SENT; vnew = vsock_sk(new); hvs_new = vnew->trans; hvs_new->chan = chan; @@ -384,7 +384,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vmbus_set_chn_rescind_callback(chan, hvs_close_connection); if (conn_from_host) { - new->sk_state = SS_CONNECTED; + new->sk_state = TCP_ESTABLISHED; sk->sk_ack_backlog++; hvs_addr_init(&vnew->local_addr, if_type); @@ -399,7 +399,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) vsock_enqueue_accept(sk, new); release_sock(sk); } else { - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsock_sk(sk)); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 403d86e80162e..8e03bd3f3668b 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -414,7 +414,7 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { lock_sock(sk); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk->sk_error_report(sk); release_sock(sk); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index edba7ab975639..3ae3a33da70ba 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -708,7 +708,7 @@ static void virtio_transport_do_close(struct vsock_sock *vsk, sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; if (vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); if (vsk->close_work_scheduled && @@ -748,8 +748,8 @@ static bool virtio_transport_close(struct vsock_sock *vsk) { struct sock *sk = &vsk->sk; - if (!(sk->sk_state == SS_CONNECTED || - sk->sk_state == SS_DISCONNECTING)) + if (!(sk->sk_state == TCP_ESTABLISHED || + sk->sk_state == TCP_CLOSING)) return true; /* Already received SHUTDOWN from peer, reply with RST */ @@ -801,7 +801,7 @@ virtio_transport_recv_connecting(struct sock *sk, switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RESPONSE: - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsk); sk->sk_state_change(sk); @@ -821,7 +821,7 @@ virtio_transport_recv_connecting(struct sock *sk, destroy: virtio_transport_reset(vsk, pkt); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk->sk_error_report(sk); return err; @@ -857,7 +857,7 @@ virtio_transport_recv_connected(struct sock *sk, vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); break; @@ -928,7 +928,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt) lock_sock_nested(child, SINGLE_DEPTH_NESTING); - child->sk_state = SS_CONNECTED; + child->sk_state = TCP_ESTABLISHED; vchild = vsock_sk(child); vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid), @@ -1016,18 +1016,18 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) sk->sk_write_space(sk); switch (sk->sk_state) { - case VSOCK_SS_LISTEN: + case TCP_LISTEN: virtio_transport_recv_listen(sk, pkt); virtio_transport_free_pkt(pkt); break; - case SS_CONNECTING: + case TCP_SYN_SENT: virtio_transport_recv_connecting(sk, pkt); virtio_transport_free_pkt(pkt); break; - case SS_CONNECTED: + case TCP_ESTABLISHED: virtio_transport_recv_connected(sk, pkt); break; - case SS_DISCONNECTING: + case TCP_CLOSING: virtio_transport_recv_disconnecting(sk, pkt); virtio_transport_free_pkt(pkt); break; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 0206155bff535..391775e3575c2 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -742,7 +742,7 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) /* The local context ID may be out of date, update it. */ vsk->local_addr.svm_cid = dst.svm_cid; - if (sk->sk_state == SS_CONNECTED) + if (sk->sk_state == TCP_ESTABLISHED) vmci_trans(vsk)->notify_ops->handle_notify_pkt( sk, pkt, true, &dst, &src, &bh_process_pkt); @@ -800,7 +800,9 @@ static void vmci_transport_handle_detach(struct sock *sk) * left in our consume queue. */ if (vsock_stream_has_data(vsk) <= 0) { - if (sk->sk_state == SS_CONNECTING) { + sk->sk_state = TCP_CLOSE; + + if (sk->sk_state == TCP_SYN_SENT) { /* The peer may detach from a queue pair while * we are still in the connecting state, i.e., * if the peer VM is killed after attaching to @@ -809,12 +811,10 @@ static void vmci_transport_handle_detach(struct sock *sk) * event like a reset. */ - sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; sk->sk_error_report(sk); return; } - sk->sk_state = SS_UNCONNECTED; } sk->sk_state_change(sk); } @@ -882,17 +882,17 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; switch (sk->sk_state) { - case VSOCK_SS_LISTEN: + case TCP_LISTEN: vmci_transport_recv_listen(sk, pkt); break; - case SS_CONNECTING: + case TCP_SYN_SENT: /* Processing of pending connections for servers goes through * the listening socket, so see vmci_transport_recv_listen() * for that path. */ vmci_transport_recv_connecting_client(sk, pkt); break; - case SS_CONNECTED: + case TCP_ESTABLISHED: vmci_transport_recv_connected(sk, pkt); break; default: @@ -941,7 +941,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context; switch (pending->sk_state) { - case SS_CONNECTING: + case TCP_SYN_SENT: err = vmci_transport_recv_connecting_server(sk, pending, pkt); @@ -1071,7 +1071,7 @@ static int vmci_transport_recv_listen(struct sock *sk, vsock_add_pending(sk, pending); sk->sk_ack_backlog++; - pending->sk_state = SS_CONNECTING; + pending->sk_state = TCP_SYN_SENT; vmci_trans(vpending)->produce_size = vmci_trans(vpending)->consume_size = qp_size; vmci_trans(vpending)->queue_pair_size = qp_size; @@ -1196,11 +1196,11 @@ vmci_transport_recv_connecting_server(struct sock *listener, * the socket will be valid until it is removed from the queue. * * If we fail sending the attach below, we remove the socket from the - * connected list and move the socket to SS_UNCONNECTED before + * connected list and move the socket to TCP_CLOSE before * releasing the lock, so a pending slow path processing of an incoming * packet will not see the socket in the connected state in that case. */ - pending->sk_state = SS_CONNECTED; + pending->sk_state = TCP_ESTABLISHED; vsock_insert_connected(vpending); @@ -1231,7 +1231,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, destroy: pending->sk_err = skerr; - pending->sk_state = SS_UNCONNECTED; + pending->sk_state = TCP_CLOSE; /* As long as we drop our reference, all necessary cleanup will handle * when the cleanup function drops its reference and our destruct * implementation is called. Note that since the listen handler will @@ -1269,7 +1269,7 @@ vmci_transport_recv_connecting_client(struct sock *sk, * accounting (it can already be found since it's in the bound * table). */ - sk->sk_state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; sk->sk_socket->state = SS_CONNECTED; vsock_insert_connected(vsk); sk->sk_state_change(sk); @@ -1337,7 +1337,7 @@ vmci_transport_recv_connecting_client(struct sock *sk, destroy: vmci_transport_send_reset(sk, pkt); - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; sk->sk_error_report(sk); return err; @@ -1525,7 +1525,7 @@ static int vmci_transport_recv_connected(struct sock *sk, sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; if (vsock_stream_has_data(vsk) <= 0) - sk->sk_state = SS_DISCONNECTING; + sk->sk_state = TCP_CLOSING; sk->sk_state_change(sk); break; @@ -1789,7 +1789,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) err = vmci_transport_send_conn_request( sk, vmci_trans(vsk)->queue_pair_size); if (err < 0) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; return err; } } else { @@ -1799,7 +1799,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) sk, vmci_trans(vsk)->queue_pair_size, supported_proto_versions); if (err < 0) { - sk->sk_state = SS_UNCONNECTED; + sk->sk_state = TCP_CLOSE; return err; } diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c index 1406db4d97d14..41fb427f150a2 100644 --- a/net/vmw_vsock/vmci_transport_notify.c +++ b/net/vmw_vsock/vmci_transport_notify.c @@ -355,7 +355,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk, * queue. Ask for notifications when there is something to * read. */ - if (sk->sk_state == SS_CONNECTED) { + if (sk->sk_state == TCP_ESTABLISHED) { if (!send_waiting_read(sk, 1)) return -1; diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c index f3a0afc462081..0cc84f2bb05e5 100644 --- a/net/vmw_vsock/vmci_transport_notify_qstate.c +++ b/net/vmw_vsock/vmci_transport_notify_qstate.c @@ -176,7 +176,7 @@ vmci_transport_notify_pkt_poll_in(struct sock *sk, * queue. Ask for notifications when there is something to * read. */ - if (sk->sk_state == SS_CONNECTED) + if (sk->sk_state == TCP_ESTABLISHED) vsock_block_update_write_window(sk); *data_ready_now = false; } -- GitLab From 413a4317aca7d6367d57a5971b0c461f03851207 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:53 -0400 Subject: [PATCH 1006/1507] VSOCK: add sock_diag interface This patch adds the sock_diag interface for querying sockets from userspace. Tools like ss(8) and netstat(8) can use this interface to list open sockets. The userspace ABI is defined in and includes netlink request and response structs. The request can query sockets based on their sk_state (e.g. listening sockets only) and the response contains socket information fields including the local/remote addresses, inode number, etc. This patch does not dump VMCI pending sockets because I have only tested the virtio transport, which does not use pending sockets. Support can be added later by extending vsock_diag_dump() if needed by VMCI users. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- MAINTAINERS | 2 + include/uapi/linux/vm_sockets_diag.h | 33 +++++ net/vmw_vsock/Kconfig | 10 ++ net/vmw_vsock/Makefile | 3 + net/vmw_vsock/diag.c | 186 +++++++++++++++++++++++++++ 5 files changed, 234 insertions(+) create mode 100644 include/uapi/linux/vm_sockets_diag.h create mode 100644 net/vmw_vsock/diag.c diff --git a/MAINTAINERS b/MAINTAINERS index d0cbb3d7a0ca8..0fd9121953bb2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14286,6 +14286,8 @@ S: Maintained F: include/linux/virtio_vsock.h F: include/uapi/linux/virtio_vsock.h F: include/uapi/linux/vsockmon.h +F: include/uapi/linux/vm_sockets_diag.h +F: net/vmw_vsock/diag.c F: net/vmw_vsock/af_vsock_tap.c F: net/vmw_vsock/virtio_transport_common.c F: net/vmw_vsock/virtio_transport.c diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h new file mode 100644 index 0000000000000..14cd7dc5a187c --- /dev/null +++ b/include/uapi/linux/vm_sockets_diag.h @@ -0,0 +1,33 @@ +/* AF_VSOCK sock_diag(7) interface for querying open sockets */ + +#ifndef _UAPI__VM_SOCKETS_DIAG_H__ +#define _UAPI__VM_SOCKETS_DIAG_H__ + +#include + +/* Request */ +struct vsock_diag_req { + __u8 sdiag_family; /* must be AF_VSOCK */ + __u8 sdiag_protocol; /* must be 0 */ + __u16 pad; /* must be 0 */ + __u32 vdiag_states; /* query bitmap (e.g. 1 << TCP_LISTEN) */ + __u32 vdiag_ino; /* must be 0 (reserved) */ + __u32 vdiag_show; /* must be 0 (reserved) */ + __u32 vdiag_cookie[2]; +}; + +/* Response */ +struct vsock_diag_msg { + __u8 vdiag_family; /* AF_VSOCK */ + __u8 vdiag_type; /* SOCK_STREAM or SOCK_DGRAM */ + __u8 vdiag_state; /* sk_state (e.g. TCP_LISTEN) */ + __u8 vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */ + __u32 vdiag_src_cid; + __u32 vdiag_src_port; + __u32 vdiag_dst_cid; + __u32 vdiag_dst_port; + __u32 vdiag_ino; + __u32 vdiag_cookie[2]; +}; + +#endif /* _UAPI__VM_SOCKETS_DIAG_H__ */ diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index a24369d175fd6..970f96489fe76 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -15,6 +15,16 @@ config VSOCKETS To compile this driver as a module, choose M here: the module will be called vsock. If unsure, say N. +config VSOCKETS_DIAG + tristate "Virtual Sockets monitoring interface" + depends on VSOCKETS + default y + help + Support for PF_VSOCK sockets monitoring interface used by the ss tool. + If unsure, say Y. + + Enable this module so userspace applications can query open sockets. + config VMWARE_VMCI_VSOCKETS tristate "VMware VMCI transport for Virtual Sockets" depends on VSOCKETS && VMWARE_VMCI diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index e63d574234a98..64afc06805da3 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_VSOCKETS) += vsock.o +obj-$(CONFIG_VSOCKETS_DIAG) += vsock_diag.o obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o @@ -6,6 +7,8 @@ obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o +vsock_diag-y += diag.o + vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ vmci_transport_notify_qstate.o diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c new file mode 100644 index 0000000000000..31b5676522503 --- /dev/null +++ b/net/vmw_vsock/diag.c @@ -0,0 +1,186 @@ +/* + * vsock sock_diag(7) module + * + * Copyright (C) 2017 Red Hat, Inc. + * Author: Stefan Hajnoczi + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + u32 portid, u32 seq, u32 flags) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_diag_msg *rep; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + flags); + if (!nlh) + return -EMSGSIZE; + + rep = nlmsg_data(nlh); + rep->vdiag_family = AF_VSOCK; + + /* Lock order dictates that sk_lock is acquired before + * vsock_table_lock, so we cannot lock here. Simply don't take + * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is + * held. + */ + rep->vdiag_type = sk->sk_type; + rep->vdiag_state = sk->sk_state; + rep->vdiag_shutdown = sk->sk_shutdown; + rep->vdiag_src_cid = vsk->local_addr.svm_cid; + rep->vdiag_src_port = vsk->local_addr.svm_port; + rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; + rep->vdiag_dst_port = vsk->remote_addr.svm_port; + rep->vdiag_ino = sock_i_ino(sk); + + sock_diag_save_cookie(sk, rep->vdiag_cookie); + + return 0; +} + +static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct vsock_diag_req *req; + struct vsock_sock *vsk; + unsigned int bucket; + unsigned int last_i; + unsigned int table; + struct net *net; + unsigned int i; + + req = nlmsg_data(cb->nlh); + net = sock_net(skb->sk); + + /* State saved between calls: */ + table = cb->args[0]; + bucket = cb->args[1]; + i = last_i = cb->args[2]; + + /* TODO VMCI pending sockets? */ + + spin_lock_bh(&vsock_table_lock); + + /* Bind table (locally created sockets) */ + if (table == 0) { + while (bucket < ARRAY_SIZE(vsock_bind_table)) { + struct list_head *head = &vsock_bind_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, bound_table) { + struct sock *sk = sk_vsock(vsk); + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_bind; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_bind; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_bind: + i++; + } + last_i = 0; + bucket++; + } + + table++; + bucket = 0; + } + + /* Connected table (accepted connections) */ + while (bucket < ARRAY_SIZE(vsock_connected_table)) { + struct list_head *head = &vsock_connected_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, connected_table) { + struct sock *sk = sk_vsock(vsk); + + /* Skip sockets we've already seen above */ + if (__vsock_in_bound_table(vsk)) + continue; + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_connected; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_connected; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_connected: + i++; + } + last_i = 0; + bucket++; + } + +done: + spin_unlock_bh(&vsock_table_lock); + + cb->args[0] = table; + cb->args[1] = bucket; + cb->args[2] = i; + + return skb->len; +} + +static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + int hdrlen = sizeof(struct vsock_diag_req); + struct net *net = sock_net(skb->sk); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = vsock_diag_dump, + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); + } + + return -EOPNOTSUPP; +} + +static const struct sock_diag_handler vsock_diag_handler = { + .family = AF_VSOCK, + .dump = vsock_diag_handler_dump, +}; + +static int __init vsock_diag_init(void) +{ + return sock_diag_register(&vsock_diag_handler); +} + +static void __exit vsock_diag_exit(void) +{ + sock_diag_unregister(&vsock_diag_handler); +} + +module_init(vsock_diag_init); +module_exit(vsock_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, + 40 /* AF_VSOCK */); -- GitLab From 0b02503384301e4c2db13f1045a1ddbaca2ba0ce Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:54 -0400 Subject: [PATCH 1007/1507] VSOCK: add tools/testing/vsock/vsock_diag_test This patch adds tests for the vsock_diag.ko module. These tests are not self-tests because they require manual set up of a KVM or VMware guest. Please see tools/testing/vsock/README for instructions. The control.h and timeout.h infrastructure can be used for additional AF_VSOCK tests in the future. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- MAINTAINERS | 1 + tools/testing/vsock/.gitignore | 2 + tools/testing/vsock/Makefile | 9 + tools/testing/vsock/README | 36 ++ tools/testing/vsock/control.c | 219 +++++++++ tools/testing/vsock/control.h | 13 + tools/testing/vsock/timeout.c | 64 +++ tools/testing/vsock/timeout.h | 14 + tools/testing/vsock/vsock_diag_test.c | 681 ++++++++++++++++++++++++++ 9 files changed, 1039 insertions(+) create mode 100644 tools/testing/vsock/.gitignore create mode 100644 tools/testing/vsock/Makefile create mode 100644 tools/testing/vsock/README create mode 100644 tools/testing/vsock/control.c create mode 100644 tools/testing/vsock/control.h create mode 100644 tools/testing/vsock/timeout.c create mode 100644 tools/testing/vsock/timeout.h create mode 100644 tools/testing/vsock/vsock_diag_test.c diff --git a/MAINTAINERS b/MAINTAINERS index 0fd9121953bb2..f0c37be4e04a6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14294,6 +14294,7 @@ F: net/vmw_vsock/virtio_transport.c F: drivers/net/vsockmon.c F: drivers/vhost/vsock.c F: drivers/vhost/vsock.h +F: tools/testing/vsock/ VIRTIO CONSOLE DRIVER M: Amit Shah diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore new file mode 100644 index 0000000000000..dc5f11faf5300 --- /dev/null +++ b/tools/testing/vsock/.gitignore @@ -0,0 +1,2 @@ +*.d +vsock_diag_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile new file mode 100644 index 0000000000000..66ba0924194df --- /dev/null +++ b/tools/testing/vsock/Makefile @@ -0,0 +1,9 @@ +all: test +test: vsock_diag_test +vsock_diag_test: vsock_diag_test.o timeout.o control.o + +CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE +.PHONY: all test clean +clean: + ${RM} *.o *.d vsock_diag_test +-include *.d diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README new file mode 100644 index 0000000000000..2cc6d7302db64 --- /dev/null +++ b/tools/testing/vsock/README @@ -0,0 +1,36 @@ +AF_VSOCK test suite +------------------- +These tests exercise net/vmw_vsock/ host<->guest sockets for VMware, KVM, and +Hyper-V. + +The following tests are available: + + * vsock_diag_test - vsock_diag.ko module for listing open sockets + +The following prerequisite steps are not automated and must be performed prior +to running tests: + +1. Build the kernel and these tests. +2. Install the kernel and tests on the host. +3. Install the kernel and tests inside the guest. +4. Boot the guest and ensure that the AF_VSOCK transport is enabled. + +Invoke test binaries in both directions as follows: + + # host=server, guest=client + (host)# $TEST_BINARY --mode=server \ + --control-port=1234 \ + --peer-cid=3 + (guest)# $TEST_BINARY --mode=client \ + --control-host=$HOST_IP \ + --control-port=1234 \ + --peer-cid=2 + + # host=client, guest=server + (guest)# $TEST_BINARY --mode=server \ + --control-port=1234 \ + --peer-cid=2 + (host)# $TEST_BINARY --mode=client \ + --control-port=$GUEST_IP \ + --control-port=1234 \ + --peer-cid=3 diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c new file mode 100644 index 0000000000000..90fd47f0e4227 --- /dev/null +++ b/tools/testing/vsock/control.c @@ -0,0 +1,219 @@ +/* Control socket for client/server test execution + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +/* The client and server may need to coordinate to avoid race conditions like + * the client attempting to connect to a socket that the server is not + * listening on yet. The control socket offers a communications channel for + * such coordination tasks. + * + * If the client calls control_expectln("LISTENING"), then it will block until + * the server calls control_writeln("LISTENING"). This provides a simple + * mechanism for coordinating between the client and the server. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "timeout.h" +#include "control.h" + +static int control_fd = -1; + +/* Open the control socket, either in server or client mode */ +void control_init(const char *control_host, + const char *control_port, + bool server) +{ + struct addrinfo hints = { + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *result = NULL; + struct addrinfo *ai; + int ret; + + ret = getaddrinfo(control_host, control_port, &hints, &result); + if (ret != 0) { + fprintf(stderr, "%s\n", gai_strerror(ret)); + exit(EXIT_FAILURE); + } + + for (ai = result; ai; ai = ai->ai_next) { + int fd; + int val = 1; + + fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol); + if (fd < 0) + continue; + + if (!server) { + if (connect(fd, ai->ai_addr, ai->ai_addrlen) < 0) + goto next; + control_fd = fd; + printf("Control socket connected to %s:%s.\n", + control_host, control_port); + break; + } + + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, + &val, sizeof(val)) < 0) { + perror("setsockopt"); + exit(EXIT_FAILURE); + } + + if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0) + goto next; + if (listen(fd, 1) < 0) + goto next; + + printf("Control socket listening on %s:%s\n", + control_host, control_port); + fflush(stdout); + + control_fd = accept(fd, NULL, 0); + close(fd); + + if (control_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + printf("Control socket connection accepted...\n"); + break; + +next: + close(fd); + } + + if (control_fd < 0) { + fprintf(stderr, "Control socket initialization failed. Invalid address %s:%s?\n", + control_host, control_port); + exit(EXIT_FAILURE); + } + + freeaddrinfo(result); +} + +/* Free resources */ +void control_cleanup(void) +{ + close(control_fd); + control_fd = -1; +} + +/* Write a line to the control socket */ +void control_writeln(const char *str) +{ + ssize_t len = strlen(str); + ssize_t ret; + + timeout_begin(TIMEOUT); + + do { + ret = send(control_fd, str, len, MSG_MORE); + timeout_check("send"); + } while (ret < 0 && errno == EINTR); + + if (ret != len) { + perror("send"); + exit(EXIT_FAILURE); + } + + do { + ret = send(control_fd, "\n", 1, 0); + timeout_check("send"); + } while (ret < 0 && errno == EINTR); + + if (ret != 1) { + perror("send"); + exit(EXIT_FAILURE); + } + + timeout_end(); +} + +/* Return the next line from the control socket (without the trailing newline). + * + * The program terminates if a timeout occurs. + * + * The caller must free() the returned string. + */ +char *control_readln(void) +{ + char *buf = NULL; + size_t idx = 0; + size_t buflen = 0; + + timeout_begin(TIMEOUT); + + for (;;) { + ssize_t ret; + + if (idx >= buflen) { + char *new_buf; + + new_buf = realloc(buf, buflen + 80); + if (!new_buf) { + perror("realloc"); + exit(EXIT_FAILURE); + } + + buf = new_buf; + buflen += 80; + } + + do { + ret = recv(control_fd, &buf[idx], 1, 0); + timeout_check("recv"); + } while (ret < 0 && errno == EINTR); + + if (ret == 0) { + fprintf(stderr, "unexpected EOF on control socket\n"); + exit(EXIT_FAILURE); + } + + if (ret != 1) { + perror("recv"); + exit(EXIT_FAILURE); + } + + if (buf[idx] == '\n') { + buf[idx] = '\0'; + break; + } + + idx++; + } + + timeout_end(); + + return buf; +} + +/* Wait until a given line is received or a timeout occurs */ +void control_expectln(const char *str) +{ + char *line; + + line = control_readln(); + if (strcmp(str, line) != 0) { + fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n", + str, line); + exit(EXIT_FAILURE); + } + + free(line); +} diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h new file mode 100644 index 0000000000000..54a07efd267c2 --- /dev/null +++ b/tools/testing/vsock/control.h @@ -0,0 +1,13 @@ +#ifndef CONTROL_H +#define CONTROL_H + +#include + +void control_init(const char *control_host, const char *control_port, + bool server); +void control_cleanup(void); +void control_writeln(const char *str); +char *control_readln(void); +void control_expectln(const char *str); + +#endif /* CONTROL_H */ diff --git a/tools/testing/vsock/timeout.c b/tools/testing/vsock/timeout.c new file mode 100644 index 0000000000000..c49b3003b2dba --- /dev/null +++ b/tools/testing/vsock/timeout.c @@ -0,0 +1,64 @@ +/* Timeout API for single-threaded programs that use blocking + * syscalls (read/write/send/recv/connect/accept). + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +/* Use the following pattern: + * + * timeout_begin(TIMEOUT); + * do { + * ret = accept(...); + * timeout_check("accept"); + * } while (ret < 0 && ret == EINTR); + * timeout_end(); + */ + +#include +#include +#include +#include +#include "timeout.h" + +static volatile bool timeout; + +/* SIGALRM handler function. Do not use sleep(2), alarm(2), or + * setitimer(2) while using this API - they may interfere with each + * other. + */ +void sigalrm(int signo) +{ + timeout = true; +} + +/* Start a timeout. Call timeout_check() to verify that the timeout hasn't + * expired. timeout_end() must be called to stop the timeout. Timeouts cannot + * be nested. + */ +void timeout_begin(unsigned int seconds) +{ + alarm(seconds); +} + +/* Exit with an error message if the timeout has expired */ +void timeout_check(const char *operation) +{ + if (timeout) { + fprintf(stderr, "%s timed out\n", operation); + exit(EXIT_FAILURE); + } +} + +/* Stop a timeout */ +void timeout_end(void) +{ + alarm(0); + timeout = false; +} diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h new file mode 100644 index 0000000000000..77db9ce9860a9 --- /dev/null +++ b/tools/testing/vsock/timeout.h @@ -0,0 +1,14 @@ +#ifndef TIMEOUT_H +#define TIMEOUT_H + +enum { + /* Default timeout */ + TIMEOUT = 10 /* seconds */ +}; + +void sigalrm(int signo); +void timeout_begin(unsigned int seconds); +void timeout_check(const char *operation); +void timeout_end(void); + +#endif /* TIMEOUT_H */ diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c new file mode 100644 index 0000000000000..e896a4af52f40 --- /dev/null +++ b/tools/testing/vsock/vsock_diag_test.c @@ -0,0 +1,681 @@ +/* + * vsock_diag_test - vsock_diag.ko test suite + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../../../include/uapi/linux/vm_sockets.h" +#include "../../../include/uapi/linux/vm_sockets_diag.h" + +#include "timeout.h" +#include "control.h" + +enum test_mode { + TEST_MODE_UNSET, + TEST_MODE_CLIENT, + TEST_MODE_SERVER +}; + +/* Per-socket status */ +struct vsock_stat { + struct list_head list; + struct vsock_diag_msg msg; +}; + +static const char *sock_type_str(int type) +{ + switch (type) { + case SOCK_DGRAM: + return "DGRAM"; + case SOCK_STREAM: + return "STREAM"; + default: + return "INVALID TYPE"; + } +} + +static const char *sock_state_str(int state) +{ + switch (state) { + case TCP_CLOSE: + return "UNCONNECTED"; + case TCP_SYN_SENT: + return "CONNECTING"; + case TCP_ESTABLISHED: + return "CONNECTED"; + case TCP_CLOSING: + return "DISCONNECTING"; + case TCP_LISTEN: + return "LISTEN"; + default: + return "INVALID STATE"; + } +} + +static const char *sock_shutdown_str(int shutdown) +{ + switch (shutdown) { + case 1: + return "RCV_SHUTDOWN"; + case 2: + return "SEND_SHUTDOWN"; + case 3: + return "RCV_SHUTDOWN | SEND_SHUTDOWN"; + default: + return "0"; + } +} + +static void print_vsock_addr(FILE *fp, unsigned int cid, unsigned int port) +{ + if (cid == VMADDR_CID_ANY) + fprintf(fp, "*:"); + else + fprintf(fp, "%u:", cid); + + if (port == VMADDR_PORT_ANY) + fprintf(fp, "*"); + else + fprintf(fp, "%u", port); +} + +static void print_vsock_stat(FILE *fp, struct vsock_stat *st) +{ + print_vsock_addr(fp, st->msg.vdiag_src_cid, st->msg.vdiag_src_port); + fprintf(fp, " "); + print_vsock_addr(fp, st->msg.vdiag_dst_cid, st->msg.vdiag_dst_port); + fprintf(fp, " %s %s %s %u\n", + sock_type_str(st->msg.vdiag_type), + sock_state_str(st->msg.vdiag_state), + sock_shutdown_str(st->msg.vdiag_shutdown), + st->msg.vdiag_ino); +} + +static void print_vsock_stats(FILE *fp, struct list_head *head) +{ + struct vsock_stat *st; + + list_for_each_entry(st, head, list) + print_vsock_stat(fp, st); +} + +static struct vsock_stat *find_vsock_stat(struct list_head *head, int fd) +{ + struct vsock_stat *st; + struct stat stat; + + if (fstat(fd, &stat) < 0) { + perror("fstat"); + exit(EXIT_FAILURE); + } + + list_for_each_entry(st, head, list) + if (st->msg.vdiag_ino == stat.st_ino) + return st; + + fprintf(stderr, "cannot find fd %d\n", fd); + exit(EXIT_FAILURE); +} + +static void check_no_sockets(struct list_head *head) +{ + if (!list_empty(head)) { + fprintf(stderr, "expected no sockets\n"); + print_vsock_stats(stderr, head); + exit(1); + } +} + +static void check_num_sockets(struct list_head *head, int expected) +{ + struct list_head *node; + int n = 0; + + list_for_each(node, head) + n++; + + if (n != expected) { + fprintf(stderr, "expected %d sockets, found %d\n", + expected, n); + print_vsock_stats(stderr, head); + exit(EXIT_FAILURE); + } +} + +static void check_socket_state(struct vsock_stat *st, __u8 state) +{ + if (st->msg.vdiag_state != state) { + fprintf(stderr, "expected socket state %#x, got %#x\n", + state, st->msg.vdiag_state); + exit(EXIT_FAILURE); + } +} + +static void send_req(int fd) +{ + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + }; + struct { + struct nlmsghdr nlh; + struct vsock_diag_req vreq; + } req = { + .nlh = { + .nlmsg_len = sizeof(req), + .nlmsg_type = SOCK_DIAG_BY_FAMILY, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_DUMP, + }, + .vreq = { + .sdiag_family = AF_VSOCK, + .vdiag_states = ~(__u32)0, + }, + }; + struct iovec iov = { + .iov_base = &req, + .iov_len = sizeof(req), + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + + for (;;) { + if (sendmsg(fd, &msg, 0) < 0) { + if (errno == EINTR) + continue; + + perror("sendmsg"); + exit(EXIT_FAILURE); + } + + return; + } +} + +static ssize_t recv_resp(int fd, void *buf, size_t len) +{ + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + }; + struct iovec iov = { + .iov_base = buf, + .iov_len = len, + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + ssize_t ret; + + do { + ret = recvmsg(fd, &msg, 0); + } while (ret < 0 && errno == EINTR); + + if (ret < 0) { + perror("recvmsg"); + exit(EXIT_FAILURE); + } + + return ret; +} + +static void add_vsock_stat(struct list_head *sockets, + const struct vsock_diag_msg *resp) +{ + struct vsock_stat *st; + + st = malloc(sizeof(*st)); + if (!st) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + st->msg = *resp; + list_add_tail(&st->list, sockets); +} + +/* + * Read vsock stats into a list. + */ +static void read_vsock_stat(struct list_head *sockets) +{ + long buf[8192 / sizeof(long)]; + int fd; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + send_req(fd); + + for (;;) { + const struct nlmsghdr *h; + ssize_t ret; + + ret = recv_resp(fd, buf, sizeof(buf)); + if (ret == 0) + goto done; + if (ret < sizeof(*h)) { + fprintf(stderr, "short read of %zd bytes\n", ret); + exit(EXIT_FAILURE); + } + + h = (struct nlmsghdr *)buf; + + while (NLMSG_OK(h, ret)) { + if (h->nlmsg_type == NLMSG_DONE) + goto done; + + if (h->nlmsg_type == NLMSG_ERROR) { + const struct nlmsgerr *err = NLMSG_DATA(h); + + if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + fprintf(stderr, "NLMSG_ERROR\n"); + else { + errno = -err->error; + perror("NLMSG_ERROR"); + } + + exit(EXIT_FAILURE); + } + + if (h->nlmsg_type != SOCK_DIAG_BY_FAMILY) { + fprintf(stderr, "unexpected nlmsg_type %#x\n", + h->nlmsg_type); + exit(EXIT_FAILURE); + } + if (h->nlmsg_len < + NLMSG_LENGTH(sizeof(struct vsock_diag_msg))) { + fprintf(stderr, "short vsock_diag_msg\n"); + exit(EXIT_FAILURE); + } + + add_vsock_stat(sockets, NLMSG_DATA(h)); + + h = NLMSG_NEXT(h, ret); + } + } + +done: + close(fd); +} + +static void free_sock_stat(struct list_head *sockets) +{ + struct vsock_stat *st; + struct vsock_stat *next; + + list_for_each_entry_safe(st, next, sockets, list) + free(st); +} + +static void test_no_sockets(unsigned int peer_cid) +{ + LIST_HEAD(sockets); + + read_vsock_stat(&sockets); + + check_no_sockets(&sockets); + + free_sock_stat(&sockets); +} + +static void test_listen_socket_server(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = VMADDR_CID_ANY, + }, + }; + LIST_HEAD(sockets); + struct vsock_stat *st; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 1); + st = find_vsock_stat(&sockets, fd); + check_socket_state(st, TCP_LISTEN); + + close(fd); + free_sock_stat(&sockets); +} + +static void test_connect_client(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = peer_cid, + }, + }; + int fd; + int ret; + LIST_HEAD(sockets); + struct vsock_stat *st; + + control_expectln("LISTENING"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 1); + st = find_vsock_stat(&sockets, fd); + check_socket_state(st, TCP_ESTABLISHED); + + control_expectln("DONE"); + control_writeln("DONE"); + + close(fd); + free_sock_stat(&sockets); +} + +static void test_connect_server(unsigned int peer_cid) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = VMADDR_CID_ANY, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + socklen_t clientaddr_len = sizeof(clientaddr.svm); + LIST_HEAD(sockets); + struct vsock_stat *st; + int fd; + int client_fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + if (clientaddr.sa.sa_family != AF_VSOCK) { + fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", + clientaddr.sa.sa_family); + exit(EXIT_FAILURE); + } + if (clientaddr.svm.svm_cid != peer_cid) { + fprintf(stderr, "expected peer CID %u from accept(2), got %u\n", + peer_cid, clientaddr.svm.svm_cid); + exit(EXIT_FAILURE); + } + + read_vsock_stat(&sockets); + + check_num_sockets(&sockets, 2); + find_vsock_stat(&sockets, fd); + st = find_vsock_stat(&sockets, client_fd); + check_socket_state(st, TCP_ESTABLISHED); + + control_writeln("DONE"); + control_expectln("DONE"); + + close(client_fd); + close(fd); + free_sock_stat(&sockets); +} + +static struct { + const char *name; + void (*run_client)(unsigned int peer_cid); + void (*run_server)(unsigned int peer_cid); +} test_cases[] = { + { + .name = "No sockets", + .run_server = test_no_sockets, + }, + { + .name = "Listen socket", + .run_server = test_listen_socket_server, + }, + { + .name = "Connect", + .run_client = test_connect_client, + .run_server = test_connect_server, + }, + {}, +}; + +static void init_signals(void) +{ + struct sigaction act = { + .sa_handler = sigalrm, + }; + + sigaction(SIGALRM, &act, NULL); + signal(SIGPIPE, SIG_IGN); +} + +static unsigned int parse_cid(const char *str) +{ + char *endptr = NULL; + unsigned long int n; + + errno = 0; + n = strtoul(str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed CID \"%s\"\n", str); + exit(EXIT_FAILURE); + } + return n; +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "control-host", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "control-port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "mode", + .has_arg = required_argument, + .val = 'm', + }, + { + .name = "peer-cid", + .has_arg = required_argument, + .val = 'p', + }, + { + .name = "help", + .has_arg = no_argument, + .val = '?', + }, + {}, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=] --control-port= --mode=client|server --peer-cid=\n" + "\n" + " Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n" + " Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" + "\n" + "Run vsock_diag.ko tests. Must be launched in both\n" + "guest and host. One side must use --mode=client and\n" + "the other side must use --mode=server.\n" + "\n" + "A TCP control socket connection is used to coordinate tests\n" + "between the client and the server. The server requires a\n" + "listen address and the client requires an address to\n" + "connect to.\n" + "\n" + "The CID of the other side must be given with --peer-cid=.\n"); + exit(EXIT_FAILURE); +} + +int main(int argc, char **argv) +{ + const char *control_host = NULL; + const char *control_port = NULL; + int mode = TEST_MODE_UNSET; + unsigned int peer_cid = VMADDR_CID_ANY; + int i; + + init_signals(); + + for (;;) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'H': + control_host = optarg; + break; + case 'm': + if (strcmp(optarg, "client") == 0) + mode = TEST_MODE_CLIENT; + else if (strcmp(optarg, "server") == 0) + mode = TEST_MODE_SERVER; + else { + fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); + return EXIT_FAILURE; + } + break; + case 'p': + peer_cid = parse_cid(optarg); + break; + case 'P': + control_port = optarg; + break; + case '?': + default: + usage(); + } + } + + if (!control_port) + usage(); + if (mode == TEST_MODE_UNSET) + usage(); + if (peer_cid == VMADDR_CID_ANY) + usage(); + + if (!control_host) { + if (mode != TEST_MODE_SERVER) + usage(); + control_host = "0.0.0.0"; + } + + control_init(control_host, control_port, mode == TEST_MODE_SERVER); + + for (i = 0; test_cases[i].name; i++) { + void (*run)(unsigned int peer_cid); + + printf("%s...", test_cases[i].name); + fflush(stdout); + + if (mode == TEST_MODE_CLIENT) + run = test_cases[i].run_client; + else + run = test_cases[i].run_server; + + if (run) + run(peer_cid); + + printf("ok\n"); + } + + control_cleanup(); + return EXIT_SUCCESS; +} -- GitLab From 27204aaa9dc67b833b77179fdac556288ec3a4bf Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 4 Oct 2017 10:03:44 -0700 Subject: [PATCH 1008/1507] tcp: uniform the set up of sockets after successful connection Currently in the TCP code, the initialization sequence for cached metrics, congestion control, BPF, etc, after successful connection is very inconsistent. This introduces inconsistent bevhavior and is prone to bugs. The current call sequence is as follows: (1) for active case (tcp_finish_connect() case): tcp_mtup_init(sk); icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); (2) for passive case (tcp_rcv_state_process() TCP_SYN_RECV case): icsk->icsk_af_ops->rebuild_header(sk); tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); tcp_mtup_init(sk); tcp_init_buffer_space(sk); tcp_init_metrics(sk); (3) for TFO passive case (tcp_fastopen_create_child()): inet_csk(child)->icsk_af_ops->rebuild_header(child); tcp_init_congestion_control(child); tcp_mtup_init(child); tcp_init_metrics(child); tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_buffer_space(child); This commit uniforms the above functions to have the following sequence: tcp_mtup_init(sk); icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE/PASSIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); tcp_init_buffer_space(sk); This sequence is the same as the (1) active case. We pick this sequence because this order correctly allows BPF to override the settings including congestion control module and initial cwnd, etc from the route, and then allows the CC module to see those settings. Suggested-by: Neal Cardwell Tested-by: Neal Cardwell Signed-off-by: Wei Wang Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp.c | 12 ++++++++++++ net/ipv4/tcp_fastopen.c | 7 +------ net/ipv4/tcp_input.c | 21 +++------------------ 4 files changed, 17 insertions(+), 24 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 7a3a8af56fd69..426c2e986016a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -416,6 +416,7 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_disable_fack(struct tcp_sock *tp); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); +void tcp_init_transfer(struct sock *sk, int bpf_op); unsigned int tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 23225c98d287b..c115e37ca6083 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -456,6 +456,18 @@ void tcp_init_sock(struct sock *sk) } EXPORT_SYMBOL(tcp_init_sock); +void tcp_init_transfer(struct sock *sk, int bpf_op) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + tcp_mtup_init(sk); + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_metrics(sk); + tcp_call_bpf(sk, bpf_op); + tcp_init_congestion_control(sk); + tcp_init_buffer_space(sk); +} + static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) { if (tsflags && skb) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index de470e7e586f4..29fff14d5a53d 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -236,12 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ - inet_csk(child)->icsk_af_ops->rebuild_header(child); - tcp_init_congestion_control(child); - tcp_mtup_init(child); - tcp_init_metrics(child); - tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_buffer_space(child); + tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index db9bb46b5776f..bd3a35f5dbf21 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5513,20 +5513,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) security_inet_conn_established(sk, skb); } - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ tp->lsndtime = tcp_jiffies32; - tcp_init_buffer_space(sk); - if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); @@ -5693,7 +5686,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tcp_is_sack(tp) && sysctl_tcp_fack) tcp_enable_fack(tp); - tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); @@ -5920,14 +5912,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); } else { - /* Make sure socket is routed, for correct metrics. */ - icsk->icsk_af_ops->rebuild_header(sk); - tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tcp_init_congestion_control(sk); - - tcp_mtup_init(sk); + tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->copied_seq = tp->rcv_nxt; - tcp_init_buffer_space(sk); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); @@ -5957,8 +5943,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * are sent out. */ tcp_rearm_rto(sk); - } else - tcp_init_metrics(sk); + } if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); -- GitLab From 6d05081e55a5a55b32ae6609f1902eca8277541d Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Wed, 4 Oct 2017 10:04:04 -0700 Subject: [PATCH 1009/1507] tcp: clean up TFO server's initial tcp_rearm_rto() call This commit does a cleanup and moves tcp_rearm_rto() call in the TFO server case into a previous spot in tcp_rcv_state_process() to make it more compact. This is only a cosmetic change. Suggested-by: Yuchung Cheng Signed-off-by: Wei Wang Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bd3a35f5dbf21..c5b8d61846c2f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5911,6 +5911,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (req) { inet_csk(sk)->icsk_retransmits = 0; reqsk_fastopen_remove(sk, req, false); + /* Re-arm the timer because data may have been sent out. + * This is similar to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more aggressive and + * retransmitting any data sooner based on when they + * are sent out. + */ + tcp_rearm_rto(sk); } else { tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->copied_seq = tp->rcv_nxt; @@ -5933,18 +5942,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - if (req) { - /* Re-arm the timer because data may have been sent out. - * This is similar to the regular data transmission case - * when new data has just been ack'ed. - * - * (TFO) - we could try to be more aggressive and - * retransmitting any data sooner based on when they - * are sent out. - */ - tcp_rearm_rto(sk); - } - if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); -- GitLab From 1bcdca3ffbbbed0d09b46cf4263ed2593a418375 Mon Sep 17 00:00:00 2001 From: Tim Hansen Date: Wed, 4 Oct 2017 15:59:49 -0400 Subject: [PATCH 1010/1507] net/ipv4: Remove unused variable in route.c int rc is unmodified after initalization in net/ipv4/route.c, this patch simply cleans up that variable and returns 0. This was found with coccicheck M=net/ipv4/ on linus' tree. Signed-off-by: Tim Hansen Signed-off-by: David S. Miller --- net/ipv4/route.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ac6fde5d45f14..1c7ed77968c99 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3038,7 +3038,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { - int rc = 0; int cpu; ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); @@ -3095,7 +3094,7 @@ int __init ip_rt_init(void) #endif register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); - return rc; + return 0; } #ifdef CONFIG_SYSCTL -- GitLab From 9dff9936f0ccfffba5106ee4217c71c7bcf95143 Mon Sep 17 00:00:00 2001 From: Avinash Repaka Date: Wed, 4 Oct 2017 12:10:43 -0700 Subject: [PATCH 1011/1507] RDS: IB: Limit the scope of has_fr/has_fmr variables This patch fixes the scope of has_fr and has_fmr variables as they are needed only in rds_ib_add_one(). Signed-off-by: Avinash Repaka Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/ib.c | 11 ++++++----- net/rds/ib.h | 2 -- 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/net/rds/ib.c b/net/rds/ib.c index a0954ace37744..36dd2099048a8 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -126,6 +126,7 @@ void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) static void rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; + bool has_fr, has_fmr; /* Only handle IB (no iWARP) devices */ if (device->node_type != RDMA_NODE_IB_CA) @@ -143,11 +144,11 @@ static void rds_ib_add_one(struct ib_device *device) rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_sge, RDS_IB_MAX_SGE); - rds_ibdev->has_fr = (device->attrs.device_cap_flags & - IB_DEVICE_MEM_MGT_EXTENSIONS); - rds_ibdev->has_fmr = (device->alloc_fmr && device->dealloc_fmr && - device->map_phys_fmr && device->unmap_fmr); - rds_ibdev->use_fastreg = (rds_ibdev->has_fr && !rds_ibdev->has_fmr); + has_fr = (device->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS); + has_fmr = (device->alloc_fmr && device->dealloc_fmr && + device->map_phys_fmr && device->unmap_fmr); + rds_ibdev->use_fastreg = (has_fr && !has_fmr); rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32; rds_ibdev->max_1m_mrs = device->attrs.max_mr ? diff --git a/net/rds/ib.h b/net/rds/ib.h index bf48224075670..6ea6a27891b03 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -215,8 +215,6 @@ struct rds_ib_device { struct list_head conn_list; struct ib_device *dev; struct ib_pd *pd; - bool has_fmr; - bool has_fr; bool use_fastreg; unsigned int max_mrs; -- GitLab From b1fb67fa501c4787035317f84db6caf013385581 Mon Sep 17 00:00:00 2001 From: Avinash Repaka Date: Wed, 4 Oct 2017 12:11:29 -0700 Subject: [PATCH 1012/1507] RDS: IB: Initialize max_items based on underlying device attributes Use max_1m_mrs/max_8k_mrs while setting max_items, as the former variables are set based on the underlying device attributes. Signed-off-by: Avinash Repaka Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/ib_rdma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 9a3c54e659e9e..e678699268a25 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -601,11 +601,11 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev, if (pool_type == RDS_IB_MR_1M_POOL) { /* +1 allows for unaligned MRs */ pool->fmr_attr.max_pages = RDS_MR_1M_MSG_SIZE + 1; - pool->max_items = RDS_MR_1M_POOL_SIZE; + pool->max_items = rds_ibdev->max_1m_mrs; } else { /* pool_type == RDS_IB_MR_8K_POOL */ pool->fmr_attr.max_pages = RDS_MR_8K_MSG_SIZE + 1; - pool->max_items = RDS_MR_8K_POOL_SIZE; + pool->max_items = rds_ibdev->max_8k_mrs; } pool->max_free_pinned = pool->max_items * pool->fmr_attr.max_pages / 4; -- GitLab From e2080072ed2d98a55ae69d95dea60ff7a17cddd5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 4 Oct 2017 12:59:58 -0700 Subject: [PATCH 1013/1507] tcp: new list for sent but unacked skbs for RACK recovery This patch adds a new queue (list) that tracks the sent but not yet acked or SACKed skbs for a TCP connection. The list is chronologically ordered by skb->skb_mstamp (the head is the oldest sent skb). This list will be used to optimize TCP Rack recovery, which checks an skb's timestamp to judge if it has been lost and needs to be retransmitted. Since TCP write queue is ordered by sequence instead of sent time, RACK has to scan over the write queue to catch all eligible packets to detect lost retransmission, and iterates through SACKed skbs repeatedly. Special cares for rare events: 1. TCP repair fakes skb transmission so the send queue needs adjusted 2. SACK reneging would require re-inserting SACKed skbs into the send queue. For now I believe it's not worth the complexity to make RACK work perfectly on SACK reneging, so we do nothing here. 3. Fast Open: currently for non-TFO, send-queue correctly queues the pure SYN packet. For TFO which queues a pure SYN and then a data packet, send-queue only queues the data packet but not the pure SYN due to the structure of TFO code. This is okay because the SYN receiver would never respond with a SACK on a missing SYN (i.e. SYN is never fast-retransmitted by SACK/RACK). In order to not grow sk_buff, we use an union for the new list and _skb_refdst/destructor fields. This is a bit complicated because we need to make sure _skb_refdst and destructor are properly zeroed before skb is cloned/copied at transmit, and before being freed. Signed-off-by: Eric Dumazet Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++-- include/linux/tcp.h | 1 + include/net/tcp.h | 24 ++++++++++++++++++++++- net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_input.c | 9 +++++++-- net/ipv4/tcp_minisocks.c | 1 + net/ipv4/tcp_output.c | 42 +++++++++++++++++++++++++++++----------- 7 files changed, 74 insertions(+), 16 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ada821466e883..01a9859378679 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -617,6 +617,7 @@ typedef unsigned char *sk_buff_data_t; * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function + * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on @@ -686,8 +687,14 @@ struct sk_buff { */ char cb[48] __aligned(8); - unsigned long _skb_refdst; - void (*destructor)(struct sk_buff *skb); + union { + struct { + unsigned long _skb_refdst; + void (*destructor)(struct sk_buff *skb); + }; + struct list_head tcp_tsorted_anchor; + }; + #ifdef CONFIG_XFRM struct sec_path *sp; #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4aa40ef02d32c..1d2c44e09e31e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -191,6 +191,7 @@ struct tcp_sock { u32 tsoffset; /* timestamp offset */ struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 426c2e986016a..3b16f353b539a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1589,14 +1589,34 @@ enum tcp_chrono { void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); +/* This helper is needed, because skb->tcp_tsorted_anchor uses + * the same memory storage than skb->destructor/_skb_refdst + */ +static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) +{ + skb->destructor = NULL; + skb->_skb_refdst = 0UL; +} + +#define tcp_skb_tsorted_save(skb) { \ + unsigned long _save = skb->_skb_refdst; \ + skb->_skb_refdst = 0UL; + +#define tcp_skb_tsorted_restore(skb) \ + skb->_skb_refdst = _save; \ +} + /* write queue abstraction */ static inline void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) + while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + tcp_skb_tsorted_anchor_cleanup(skb); sk_wmem_free_skb(sk, skb); + } + INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); } @@ -1711,6 +1731,8 @@ static inline void tcp_insert_write_queue_before(struct sk_buff *new, static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { + list_del(&skb->tcp_tsorted_anchor); + tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c115e37ca6083..8cf742fd4f99d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -415,6 +415,7 @@ void tcp_init_sock(struct sock *sk) tp->out_of_order_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); + INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -881,6 +882,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * available to the caller, no more, no less. */ skb->reserved_tailroom = skb->end - skb->tail - size; + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c5b8d61846c2f..fb0d7ed84b941 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1593,6 +1593,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, tcp_skb_pcount(skb), skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + list_del_init(&skb->tcp_tsorted_anchor); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -3054,8 +3056,11 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb, shinfo = skb_shinfo(skb); if (!before(shinfo->tskey, prior_snd_una) && - before(shinfo->tskey, tcp_sk(sk)->snd_una)) - __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + before(shinfo->tskey, tcp_sk(sk)->snd_una)) { + tcp_skb_tsorted_save(skb) { + __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK); + } tcp_skb_tsorted_restore(skb); + } } /* Remove acknowledged frames from the retransmission queue. If our packet diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 188a6f31356db..2341b9f857b60 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -446,6 +446,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; INIT_LIST_HEAD(&newtp->tsq_node); + INIT_LIST_HEAD(&newtp->tsorted_sent_queue); tcp_init_wl(newtp, treq->rcv_isn); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0bc9e46a53696..8162e28801784 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -971,6 +971,12 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) HRTIMER_MODE_ABS_PINNED); } +static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) +{ + skb->skb_mstamp = tp->tcp_mstamp; + list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -1003,10 +1009,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; oskb = skb; - if (unlikely(skb_cloned(skb))) - skb = pskb_copy(skb, gfp_mask); - else - skb = skb_clone(skb, gfp_mask); + + tcp_skb_tsorted_save(oskb) { + if (unlikely(skb_cloned(oskb))) + skb = pskb_copy(oskb, gfp_mask); + else + skb = skb_clone(oskb, gfp_mask); + } tcp_skb_tsorted_restore(oskb); + if (unlikely(!skb)) return -ENOBUFS; } @@ -1127,7 +1137,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, err = net_xmit_eval(err); } if (!err && oskb) { - oskb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, oskb); tcp_rate_skb_sent(sk, oskb); } return err; @@ -1328,6 +1338,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk); + list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } @@ -2260,7 +2271,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); goto repair; /* Skip network transmission */ } @@ -2838,11 +2849,14 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; - nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + tcp_skb_tsorted_save(skb) { + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; + } tcp_skb_tsorted_restore(skb); + if (!err) - skb->skb_mstamp = tp->tcp_mstamp; + tcp_update_skb_after_send(tp, skb); } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } @@ -3023,6 +3037,7 @@ void tcp_send_fin(struct sock *sk) goto coalesce; return; } + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ @@ -3078,9 +3093,14 @@ int tcp_send_synack(struct sock *sk) } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { - struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); + struct sk_buff *nskb; + + tcp_skb_tsorted_save(skb) { + nskb = skb_copy(skb, GFP_ATOMIC); + } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; + INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); tcp_unlink_write_queue(skb, sk); __skb_header_release(nskb); __tcp_add_write_queue_head(sk, nskb); -- GitLab From 043b87d7599ed8e86a33f4cbc3f062d57e263711 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 4 Oct 2017 12:59:59 -0700 Subject: [PATCH 1014/1507] tcp: more efficient RACK loss detection Use the new time-ordered list to speed up RACK. The detection logic is identical. But since the list is chronologically ordered by skb_mstamp and contains only skbs not yet acked or sacked, RACK can abort the loop upon hitting skbs that were sent more recently. On YouTube servers this patch reduces the iterations on write queue by 40x. The improvement is even bigger with large BDP networks. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_recovery.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 449cd914d58e1..8aa56caefde86 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -45,7 +45,7 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; + struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; @@ -58,17 +58,10 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U) reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd); - tcp_for_write_queue(skb, sk) { + list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, + tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - if (skb == tcp_send_head(sk)) - break; - - /* Skip ones already (s)acked */ - if (!after(scb->end_seq, tp->snd_una) || - scb->sacked & TCPCB_SACKED_ACKED) - continue; - if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, tp->rack.end_seq, scb->end_seq)) { /* Step 3 in draft-cheng-tcpm-rack-00.txt: @@ -81,6 +74,7 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) if (remaining < 0) { tcp_rack_mark_skb_lost(sk, skb); + list_del_init(&skb->tcp_tsorted_anchor); continue; } @@ -91,11 +85,7 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) /* Record maximum wait time (+1 to avoid 0) */ *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining); - - } else if (!(scb->sacked & TCPCB_RETRANS)) { - /* Original data are sent sequentially so stop early - * b/c the rest are all sent after rack_sent - */ + } else { break; } } -- GitLab From bef06223083b81d2064824afe2bc85be416ab73a Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 4 Oct 2017 13:00:00 -0700 Subject: [PATCH 1015/1507] tcp: a small refactor of RACK loss detection Refactor the RACK loop to improve readability and speed up the checks. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_recovery.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 8aa56caefde86..cda6074a429a2 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -61,32 +61,28 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + s32 remaining; - if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, - tp->rack.end_seq, scb->end_seq)) { - /* Step 3 in draft-cheng-tcpm-rack-00.txt: - * A packet is lost if its elapsed time is beyond - * the recent RTT plus the reordering window. - */ - u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, - skb->skb_mstamp); - s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; - - if (remaining < 0) { - tcp_rack_mark_skb_lost(sk, skb); - list_del_init(&skb->tcp_tsorted_anchor); - continue; - } - - /* Skip ones marked lost but not yet retransmitted */ - if ((scb->sacked & TCPCB_LOST) && - !(scb->sacked & TCPCB_SACKED_RETRANS)) - continue; + /* Skip ones marked lost but not yet retransmitted */ + if ((scb->sacked & TCPCB_LOST) && + !(scb->sacked & TCPCB_SACKED_RETRANS)) + continue; + if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, + tp->rack.end_seq, scb->end_seq)) + break; + + /* A packet is lost if it has not been s/acked beyond + * the recent RTT plus the reordering window. + */ + remaining = tp->rack.rtt_us + reo_wnd - + tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); + if (remaining < 0) { + tcp_rack_mark_skb_lost(sk, skb); + list_del_init(&skb->tcp_tsorted_anchor); + } else { /* Record maximum wait time (+1 to avoid 0) */ *reo_timeout = max_t(u32, *reo_timeout, 1 + remaining); - } else { - break; } } } -- GitLab From d009313c99ba575b65a944fe2c683c6346ea1721 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 5 Oct 2017 10:10:23 +0100 Subject: [PATCH 1016/1507] net: qcom/emac: make function emac_isr static The function emac_isr is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warnings: symbol 'emac_isr' was not declared. Should it be static? Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 759543512117c..f477ba29c569f 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -130,7 +130,7 @@ static int emac_start_xmit(struct sk_buff *skb, struct net_device *netdev) return emac_mac_tx_buf_send(adpt, &adpt->tx_q, skb); } -irqreturn_t emac_isr(int _irq, void *data) +static irqreturn_t emac_isr(int _irq, void *data) { struct emac_irq *irq = data; struct emac_adapter *adpt = -- GitLab From 1561b3266ebe029c487a95f92d1a58c03ded84a1 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 5 Oct 2017 15:53:47 +0300 Subject: [PATCH 1017/1507] selftests/net: rxtimestamp: Fix an off by one The > should be >= so that we don't write one element beyond the end of the array. Fixes: 16e781224198 ("selftests/net: Add a test to validate behavior of rx timestamps") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- tools/testing/selftests/networking/timestamping/rxtimestamp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c index 00f286661dcd2..dd4162fc0419b 100644 --- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -341,7 +341,7 @@ int main(int argc, char **argv) return 0; case 'n': t = atoi(optarg); - if (t > ARRAY_SIZE(test_cases)) + if (t >= ARRAY_SIZE(test_cases)) error(1, 0, "Invalid test case: %d", t); all_tests = false; test_cases[t].enabled = true; -- GitLab From b13c5c14dbfd5923d773de9661404ed9600c53ef Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Thu, 5 Oct 2017 10:41:57 -0400 Subject: [PATCH 1018/1507] libbpf: parse maps sections of varying size This library previously assumed a fixed-size map options structure. Any new options were ignored. In order to allow the options structure to grow and to support parsing older programs, this patch updates the maps section parsing to handle varying sizes. Object files with maps sections smaller than expected will have the new fields initialized to zero. Object files which have larger than expected maps sections will be rejected unless all of the unrecognized data is zero. This change still assumes that each map definition in the maps section is the same size. Signed-off-by: Craig Gallek Acked-by: Jesper Dangaard Brouer Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/lib/bpf/libbpf.c | 70 +++++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 29 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4f402dcdf3729..23152890ec606 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -579,31 +579,6 @@ bpf_object__init_kversion(struct bpf_object *obj, return 0; } -static int -bpf_object__validate_maps(struct bpf_object *obj) -{ - int i; - - /* - * If there's only 1 map, the only error case should have been - * catched in bpf_object__init_maps(). - */ - if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1)) - return 0; - - for (i = 1; i < obj->nr_maps; i++) { - const struct bpf_map *a = &obj->maps[i - 1]; - const struct bpf_map *b = &obj->maps[i]; - - if (b->offset - a->offset < sizeof(struct bpf_map_def)) { - pr_warning("corrupted map section in %s: map \"%s\" too small\n", - obj->path, a->name); - return -EINVAL; - } - } - return 0; -} - static int compare_bpf_map(const void *_a, const void *_b) { const struct bpf_map *a = _a; @@ -615,7 +590,7 @@ static int compare_bpf_map(const void *_a, const void *_b) static int bpf_object__init_maps(struct bpf_object *obj) { - int i, map_idx, nr_maps = 0; + int i, map_idx, map_def_sz, nr_maps = 0; Elf_Scn *scn; Elf_Data *data; Elf_Data *symbols = obj->efile.symbols; @@ -658,6 +633,15 @@ bpf_object__init_maps(struct bpf_object *obj) if (!nr_maps) return 0; + /* Assume equally sized map definitions */ + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } + obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); if (!obj->maps) { pr_warning("alloc maps for object failed\n"); @@ -690,7 +674,7 @@ bpf_object__init_maps(struct bpf_object *obj) obj->efile.strtabidx, sym.st_name); obj->maps[map_idx].offset = sym.st_value; - if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) { + if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; @@ -704,12 +688,40 @@ bpf_object__init_maps(struct bpf_object *obj) pr_debug("map %d is \"%s\"\n", map_idx, obj->maps[map_idx].name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); - obj->maps[map_idx].def = *def; + /* + * If the definition of the map in the object file fits in + * bpf_map_def, copy it. Any extra fields in our version + * of bpf_map_def will default to zero as a result of the + * calloc above. + */ + if (map_def_sz <= sizeof(struct bpf_map_def)) { + memcpy(&obj->maps[map_idx].def, def, map_def_sz); + } else { + /* + * Here the map structure being read is bigger than what + * we expect, truncate if the excess bits are all zero. + * If they are not zero, reject this map as + * incompatible. + */ + char *b; + for (b = ((char *)def) + sizeof(struct bpf_map_def); + b < ((char *)def) + map_def_sz; b++) { + if (*b != 0) { + pr_warning("maps section in %s: \"%s\" " + "has unrecognized, non-zero " + "options\n", + obj->path, map_name); + return -EINVAL; + } + } + memcpy(&obj->maps[map_idx].def, def, + sizeof(struct bpf_map_def)); + } map_idx++; } qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return bpf_object__validate_maps(obj); + return 0; } static int bpf_object__elf_collect(struct bpf_object *obj) -- GitLab From fe9b5f774b28143dcc2957eadffefdca6171a26a Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Thu, 5 Oct 2017 10:41:58 -0400 Subject: [PATCH 1019/1507] libbpf: use map_flags when creating maps This is required to use BPF_MAP_TYPE_LPM_TRIE or any other map type which requires flags. Signed-off-by: Craig Gallek Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/lib/bpf/libbpf.c | 2 +- tools/lib/bpf/libbpf.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 23152890ec606..5aa45f89da93a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -942,7 +942,7 @@ bpf_object__create_maps(struct bpf_object *obj) def->key_size, def->value_size, def->max_entries, - 0); + def->map_flags); if (*pfd < 0) { size_t j; int err = *pfd; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 7959086eb9c92..6e20003109e0f 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -207,6 +207,7 @@ struct bpf_map_def { unsigned int key_size; unsigned int value_size; unsigned int max_entries; + unsigned int map_flags; }; /* -- GitLab From 53ecde0b9126ff140abe3aefd7f0ec64d6fa36b0 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 7 Sep 2017 15:05:51 +1000 Subject: [PATCH 1020/1507] powerpc/powernv: Increase memory block size to 1GB on radix Memory hot unplug on PowerNV radix hosts is broken. Our memory block size is 256MB but since we map the linear region with very large pages, each pte we tear down maps 1GB. A hot unplug of one 256MB memory block results in 768MB of memory getting unintentionally unmapped. At this point we are likely to oops. Fix this by increasing our memory block size to 1GB on PowerNV radix hosts. Fixes: 4b5d62ca17a1 ("powerpc/mm: add radix__remove_section_mapping()") Cc: stable@vger.kernel.org # v4.11+ Signed-off-by: Anton Blanchard Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/setup.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 897aa1400eb83..bbb73aa0eb8f0 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -272,7 +272,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) { - return 256UL * 1024 * 1024; + /* + * We map the kernel linear region with 1GB large pages on radix. For + * memory hot unplug to work our memory block size must be at least + * this size. + */ + if (radix_enabled()) + return 1UL * 1024 * 1024 * 1024; + else + return 256UL * 1024 * 1024; } #endif -- GitLab From 380537b4f7f2e706e499695b38eabc90a5f72fa8 Mon Sep 17 00:00:00 2001 From: Lin Zhang Date: Fri, 6 Oct 2017 02:07:08 +0800 Subject: [PATCH 1021/1507] net: ipv6: remove unused code in ipv6_find_hdr() Storing the left length of skb into 'len' actually has no effect so we can remove it. Signed-off-by: Lin Zhang Signed-off-by: David S. Miller --- net/ipv6/exthdrs_core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 115d60919f72c..11025f8d124b8 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -187,7 +187,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, { unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; - unsigned int len; bool found; if (fragoff) @@ -204,7 +203,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, start = *offset + sizeof(struct ipv6hdr); nexthdr = ip6->nexthdr; } - len = skb->len - start; do { struct ipv6_opt_hdr _hdr, *hp; @@ -273,7 +271,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if (!found) { nexthdr = hp->nexthdr; - len -= hdrlen; start += hdrlen; } } while (!found); -- GitLab From cc71b7b071192ac1c288e272fdc3f3877eb96663 Mon Sep 17 00:00:00 2001 From: Tim Hansen Date: Thu, 5 Oct 2017 15:45:32 -0400 Subject: [PATCH 1022/1507] net/ipv6: remove unused err variable on icmpv6_push_pending_frames int err is unused by icmpv6_push_pending_frames(), this patch returns removes the variable and returns the function with 0. git bisect shows this variable has been around since linux has been in git in commit 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2. This was found by running make coccicheck M=net/ipv6/ on linus' tree on commit 77ede3a014a32746002f7889211f0cecf4803163 (current HEAD as of this patch). Signed-off-by: Tim Hansen Signed-off-by: David S. Miller --- net/ipv6/icmp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 5acb54405b10b..aeb49b4d8c7dd 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -255,7 +255,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, { struct sk_buff *skb; struct icmp6hdr *icmp6h; - int err = 0; skb = skb_peek(&sk->sk_write_queue); if (!skb) @@ -288,7 +287,7 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, } ip6_push_pending_frames(sk); out: - return err; + return 0; } struct icmpv6_msg { -- GitLab From 4c02d62fa37a05254a87575c7d430819f77bd6c9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 5 Oct 2017 10:39:10 -0700 Subject: [PATCH 1023/1507] net/mac80211/mesh_plink: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. This requires adding a pointer back to the sta_info since container_of() can't resolve the sta_info. Cc: Johannes Berg Cc: "David S. Miller" Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: Thomas Gleixner Signed-off-by: Kees Cook Signed-off-by: Johannes Berg --- net/mac80211/mesh.h | 1 + net/mac80211/mesh_plink.c | 10 ++++------ net/mac80211/sta_info.c | 4 +++- net/mac80211/sta_info.h | 2 ++ 4 files changed, 10 insertions(+), 7 deletions(-) diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 7e5f271e3c30d..465b7853edc0b 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -275,6 +275,7 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u32 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); +void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u32 mesh_plink_deactivate(struct sta_info *sta); u32 mesh_plink_open(struct sta_info *sta); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index dc8e10f872070..e2d00cce3c174 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -603,8 +603,9 @@ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, ieee80211_mbss_info_change_notify(sdata, changed); } -static void mesh_plink_timer(unsigned long data) +void mesh_plink_timer(struct timer_list *t) { + struct mesh_sta *mesh = from_timer(mesh, t, plink_timer); struct sta_info *sta; u16 reason = 0; struct ieee80211_sub_if_data *sdata; @@ -616,7 +617,7 @@ static void mesh_plink_timer(unsigned long data) * del_timer_sync() this timer after having made sure * it cannot be readded (by deleting the plink.) */ - sta = (struct sta_info *) data; + sta = mesh->plink_sta; if (sta->sdata->local->quiescing) return; @@ -696,11 +697,8 @@ static void mesh_plink_timer(unsigned long data) static inline void mesh_plink_timer_set(struct sta_info *sta, u32 timeout) { - sta->mesh->plink_timer.expires = jiffies + msecs_to_jiffies(timeout); - sta->mesh->plink_timer.data = (unsigned long) sta; - sta->mesh->plink_timer.function = mesh_plink_timer; sta->mesh->plink_timeout = timeout; - add_timer(&sta->mesh->plink_timer); + mod_timer(&sta->mesh->plink_timer, jiffies + msecs_to_jiffies(timeout)); } static bool llid_in_use(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index ffcd25c4908cc..9673e157bf8fd 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -329,10 +329,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->mesh = kzalloc(sizeof(*sta->mesh), gfp); if (!sta->mesh) goto free; + sta->mesh->plink_sta = sta; spin_lock_init(&sta->mesh->plink_lock); if (ieee80211_vif_is_mesh(&sdata->vif) && !sdata->u.mesh.user_mpm) - init_timer(&sta->mesh->plink_timer); + timer_setup(&sta->mesh->plink_timer, mesh_plink_timer, + 0); sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; } #endif diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index a35c964f6217a..5c54acd10562a 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -344,6 +344,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) * @plink_state: peer link state * @plink_timeout: timeout of peer link * @plink_timer: peer link watch timer + * @plink_sta: peer link watch timer's sta_info * @t_offset: timing offset relative to this host * @t_offset_setpoint: reference timing offset of this sta to be used when * calculating clockdrift @@ -356,6 +357,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) */ struct mesh_sta { struct timer_list plink_timer; + struct sta_info *plink_sta; s64 t_offset; s64 t_offset_setpoint; -- GitLab From 265e60a170d0a0ecfc2d20490134ed2c48dd45ab Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Thu, 17 Aug 2017 20:42:26 +1000 Subject: [PATCH 1024/1507] powerpc/64s: Use emergency stack for kernel TM Bad Thing program checks When using transactional memory (TM), the CPU can be in one of six states as far as TM is concerned, encoded in the Machine State Register (MSR). Certain state transitions are illegal and if attempted trigger a "TM Bad Thing" type program check exception. If we ever hit one of these exceptions it's treated as a bug, ie. we oops, and kill the process and/or panic, depending on configuration. One case where we can trigger a TM Bad Thing, is when returning to userspace after a system call or interrupt, using RFID. When this happens the CPU first restores the user register state, in particular r1 (the stack pointer) and then attempts to update the MSR. However the MSR update is not allowed and so we take the program check with the user register state, but the kernel MSR. This tricks the exception entry code into thinking we have a bad kernel stack pointer, because the MSR says we're coming from the kernel, but r1 is pointing to userspace. To avoid this we instead always switch to the emergency stack if we take a TM Bad Thing from the kernel. That way none of the user register values are used, other than for printing in the oops message. This is the fix for CVE-2017-1000255. Fixes: 5d176f751ee3 ("powerpc: tm: Enable transactional memory (TM) lazily for userspace") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Cyril Bur [mpe: Rewrite change log & comments, tweak asm slightly] Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/exceptions-64s.S | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 48da0f5d2f7fe..b82586c535604 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -734,7 +734,29 @@ EXC_REAL(program_check, 0x700, 0x100) EXC_VIRT(program_check, 0x4700, 0x100, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + /* + * It's possible to receive a TM Bad Thing type program check with + * userspace register values (in particular r1), but with SRR1 reporting + * that we came from the kernel. Normally that would confuse the bad + * stack logic, and we would report a bad kernel stack pointer. Instead + * we switch to the emergency stack if we're taking a TM Bad Thing from + * the kernel. + */ + li r10,MSR_PR /* Build a mask of MSR_PR .. */ + oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ + and r10,r10,r12 /* Mask SRR1 with that. */ + srdi r10,r10,8 /* Shift it so we can compare */ + cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ + bne 1f /* If != go to normal path. */ + + /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ + andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + /* 3 in EXCEPTION_PROLOG_COMMON */ + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + b 3f /* Jump into the macro !! */ +1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD -- GitLab From 044215d145a7a8a60ffa8fdc859d110a795fa6ea Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Tue, 22 Aug 2017 17:20:09 -0400 Subject: [PATCH 1025/1507] powerpc/tm: Fix illegal TM state in signal handler Currently it's possible that on returning from the signal handler through the restore_tm_sigcontexts() code path (e.g. from a signal caught due to a `trap` instruction executed in the middle of an HTM block, or a deliberately constructed sigframe) an illegal TM state (like TS=10 TM=0, i.e. "T0") is set in SRR1 and when `rfid` sets implicitly the MSR register from SRR1 register on return to userspace it causes a TM Bad Thing exception. That illegal state can be set (a) by a malicious user that disables the TM bit by tweaking the bits in uc_mcontext before returning from the signal handler or (b) by a sufficient number of context switches occurring such that the load_tm counter overflows and TM is disabled whilst in the signal handler. This commit fixes the illegal TM state by ensuring that TM bit is always enabled before we return from restore_tm_sigcontexts(). A small comment correction is made as well. Fixes: 5d176f751ee3 ("powerpc: tm: Enable transactional memory (TM) lazily for userspace") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Gustavo Romero Signed-off-by: Breno Leitao Signed-off-by: Cyril Bur Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/signal_64.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c83c115858c19..b2c002993d78d 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -452,9 +452,20 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TM from user context */ + /* pull in MSR TS bits from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + */ + regs->msr |= MSR_TM; + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); -- GitLab From 5f9bfe0ef622a7bb9707c22ceb4b6451e1e2cb7b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 4 Oct 2017 17:18:27 +0200 Subject: [PATCH 1026/1507] netfilter: nf_tables: do not dump chain counters if not enabled Chain counters are only enabled on demand since 9f08ea848117, skip them when dumping them via netlink. Fixes: 9f08ea848117 ("netfilter: nf_tables: keep chain counters away from hot path") Reported-by: Johny Mattsson Tested-by: Johny Mattsson Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 34adedcb239ea..64e1ee0912258 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1048,7 +1048,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_string(skb, NFTA_CHAIN_TYPE, basechain->type->name)) goto nla_put_failure; - if (nft_dump_stats(skb, nft_base_chain(chain)->stats)) + if (basechain->stats && nft_dump_stats(skb, basechain->stats)) goto nla_put_failure; } -- GitLab From e466af75c074e76107ae1cd5a2823e9c61894ffb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 02:50:07 -0700 Subject: [PATCH 1027/1507] netfilter: x_tables: avoid stack-out-of-bounds read in xt_copy_counters_from_user syzkaller reports an out of bound read in strlcpy(), triggered by xt_copy_counters_from_user() Fix this by using memcpy(), then forcing a zero byte at the last position of the destination, as Florian did for the non COMPAT code. Fixes: d7591f0c41ce ("netfilter: x_tables: introduce and use xt_copy_counters_from_user") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/x_tables.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c83a3b5e1c6c2..d8571f4142080 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -892,7 +892,7 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); - strlcpy(info->name, compat_tmp.name, sizeof(info->name)); + memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; user += sizeof(compat_tmp); } else @@ -905,9 +905,9 @@ void *xt_copy_counters_from_user(const void __user *user, unsigned int len, if (copy_from_user(info, user, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); - info->name[sizeof(info->name) - 1] = '\0'; user += sizeof(*info); } + info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; -- GitLab From ec2f25d203aaede93cef64198d93df698913101f Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Sat, 19 Aug 2017 00:20:31 +0300 Subject: [PATCH 1028/1507] i40e: fix a typo in i40e_pf documentation This patch fixes a typo in i40e_pf object documentation; num_req_vfs refers to the number of VFs requested for the PF. Signed-off-by: Rami Rosen Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 439c63cb2a0cf..2bc4dd0dbbf15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -350,7 +350,7 @@ struct i40e_pf { u16 num_vmdq_vsis; /* num vmdq vsis this PF has set up */ u16 num_vmdq_qps; /* num queue pairs per vmdq pool */ u16 num_vmdq_msix; /* num queue vectors per vmdq pool */ - u16 num_req_vfs; /* num VFs requested for this VF */ + u16 num_req_vfs; /* num VFs requested for this PF */ u16 num_vf_qps; /* num queue pairs per VF */ u16 num_lan_qps; /* num lan queues this PF has set up */ u16 num_lan_msix; /* num queue vectors for the base PF vsi */ -- GitLab From 64615b5418bac1d3b3a50a83fb2e42091fe299fe Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 29 Aug 2017 05:32:30 -0400 Subject: [PATCH 1029/1507] i40e: add private flag to control source pruning By default, our devices do source pruning, that is, they drop receive packets that have the source MAC matching one of the receive filters. Unfortunately, this breaks ARP monitoring in channel bonding, as the bonding driver expects devices to receive ARPs containing their own source address. Add an ethtool private flag to control this feature. Also, remove the netif_running() check when we process our private flags. It's OK to reset when the device is closed and in most cases we need the reset the apply these changes. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + .../net/ethernet/intel/i40e/i40e_ethtool.c | 7 ++++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 25 +++++++++++++++++++ 3 files changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2bc4dd0dbbf15..c78448daa7a17 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -452,6 +452,7 @@ struct i40e_pf { #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) #define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) #define I40E_FLAG_LEGACY_RX BIT_ULL(58) +#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(59) struct i40e_client_instance *cinst; bool stat_offsets_loaded; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 1136d02e2e956..6203d362438c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -227,6 +227,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_ENABLED, 0), I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), + I40E_PRIV_FLAG("disable-source-pruning", + I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -4189,8 +4191,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ - if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) || - ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev))) + if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | + I40E_FLAG_LEGACY_RX | + I40E_FLAG_SOURCE_PRUNING_DISABLED)) i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3f9e89b054ece..b539469f576fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9903,6 +9903,31 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) enabled_tc = i40e_pf_get_tc_map(pf); + /* Source pruning is enabled by default, so the flag is + * negative logic - if it's set, we need to fiddle with + * the VSI to disable source pruning. + */ + if (pf->flags & I40E_FLAG_SOURCE_PRUNING_DISABLED) { + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.seid = pf->main_vsi_seid; + ctxt.pf_num = pf->hw.pf_id; + ctxt.vf_num = 0; + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB); + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "update vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + ret = -ENOENT; + goto err; + } + } + /* MFP mode setup queue map and update VSI */ if ((pf->flags & I40E_FLAG_MFP_ENABLED) && !(pf->hw.func_caps.iscsi)) { /* NIC type PF */ -- GitLab From be664cbefc50977aaefc868ba6a1109ec9b7449d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 29 Aug 2017 05:32:31 -0400 Subject: [PATCH 1030/1507] i40e/i40evf: spread CPU affinity hints across online CPUs only Currently, when setting up the IRQ for a q_vector, we set an affinity hint based on the v_idx of that q_vector. Meaning a loop iterates on v_idx, which is an incremental value, and the cpumask is created based on this value. This is a problem in systems with multiple logical CPUs per core (like in simultaneous multithreading (SMT) scenarios). If we disable some logical CPUs, by turning SMT off for example, we will end up with a sparse cpu_online_mask, i.e., only the first CPU in a core is online, and incremental filling in q_vector cpumask might lead to multiple offline CPUs being assigned to q_vectors. Example: if we have a system with 8 cores each one containing 8 logical CPUs (SMT == 8 in this case), we have 64 CPUs in total. But if SMT is disabled, only the 1st CPU in each core remains online, so the cpu_online_mask in this case would have only 8 bits set, in a sparse way. In general case, when SMT is off the cpu_online_mask has only C bits set: 0, 1*N, 2*N, ..., C*(N-1) where C == # of cores; N == # of logical CPUs per core. In our example, only bits 0, 8, 16, 24, 32, 40, 48, 56 would be set. Instead, we should only assign hints for CPUs which are online. Even better, the kernel already provides a function, cpumask_local_spread() which takes an index and returns a CPU, spreading the interrupts across local NUMA nodes first, and then remote ones if necessary. Since we generally have a 1:1 mapping between vectors and CPUs, there is no real advantage to spreading vectors to local CPUs first. In order to avoid mismatch of the default XPS hints, we'll pass -1 so that it spreads across all CPUs without regard to the node locality. Note that we don't need to change the q_vector->affinity_mask as this is initialized to cpu_possible_mask, until an actual affinity is set and then notified back to us. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 16 +++++++++++----- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 9 ++++++--- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b539469f576fd..d2bb4f17c89e7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2885,14 +2885,15 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { struct i40e_vsi *vsi = ring->vsi; + int cpu; if (!ring->q_vector || !ring->netdev) return; if ((vsi->tc_config.numtc <= 1) && !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) { - netif_set_xps_queue(ring->netdev, - get_cpu_mask(ring->q_vector->v_idx), + cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); + netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), ring->queue_index); } @@ -3482,6 +3483,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) int tx_int_idx = 0; int vector, err; int irq_num; + int cpu; for (vector = 0; vector < q_vectors; vector++) { struct i40e_q_vector *q_vector = vsi->q_vectors[vector]; @@ -3517,10 +3519,14 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread affinity hints out across online CPUs. + * + * get_cpu_mask returns a static constant mask with + * a permanent lifetime so it's ok to pass to + * irq_set_affinity_hint without making a copy. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } vsi->irqs_ready = true; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f2f1e754c2ce3..bc76378a71e24 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -515,6 +515,7 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; + int cpu; i40evf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -553,10 +554,12 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) q_vector->affinity_notify.release = i40evf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* get_cpu_mask returns a static constant mask with - * a permanent lifetime so it's ok to use here. + /* Spread the IRQ affinity hints across online CPUs. Note that + * get_cpu_mask returns a mask with a permanent lifetime so + * it's safe to use as a hint for irq_set_affinity_hint. */ - irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); + cpu = cpumask_local_spread(q_vector->v_idx, -1); + irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } return 0; -- GitLab From c3d26b75c22b0487c452bd610338aa015eae517b Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 29 Aug 2017 05:32:32 -0400 Subject: [PATCH 1031/1507] i40e: re-enable PTP L4 capabilities for XL710 if FW >6.0 Starting with XL710 FW 5.3 PTP L4 was disabled for XL710 due to a bug. The bug has since been resolved in XL710 FW >6.0 and PTP L4 can now be re-enabled on those devices with updated firmware. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d2bb4f17c89e7..85132eee9f641 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9074,6 +9074,11 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.fw_maj_ver >= 5))) pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB; + /* Enable PTP L4 if FW > v6.0 */ + if (pf->hw.mac.type == I40E_MAC_XL710 && + pf->hw.aq.fw_maj_ver >= 6) + pf->hw_features |= I40E_HW_PTP_L4_CAPABLE; + if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; -- GitLab From 60518a048919a2781e3192981d2946149240b837 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 29 Aug 2017 05:32:33 -0400 Subject: [PATCH 1032/1507] i40e: redfine I40E_PHY_TYPE_MAX Since I40E_PHY_TYPE_MAX is used as an iterator, usually combined with some sort of bit-shifting, it should only include actual PHY types and not error cases. Move it up in the enum declaration so that loops only iterate across valid PHY types. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 2 +- drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 4c85ea9cd89ae..50c5a4c630b81 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1771,9 +1771,9 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_MAX, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index ed5602f4bbcd6..dc6fc8b1bc798 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1767,9 +1767,9 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_CR = 0x20, I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, + I40E_PHY_TYPE_MAX, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, - I40E_PHY_TYPE_MAX }; #define I40E_LINK_SPEED_100MB_SHIFT 0x1 -- GitLab From 0a0d9af5bc0b2130edaed9d9c57fc08bd338e3f5 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Tue, 29 Aug 2017 05:32:34 -0400 Subject: [PATCH 1033/1507] i40e: fix incorrect register definition This register was defined incorrectly. Fix the increment value to 8, and replace the iterator with _i to make the definition consistent with other statistics registers. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_register.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 86ca27f72f029..c234758dad156 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -2794,7 +2794,7 @@ #define I40E_GLV_RUPP_MAX_INDEX 383 #define I40E_GLV_RUPP_RUPP_SHIFT 0 #define I40E_GLV_RUPP_RUPP_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_RUPP_RUPP_SHIFT) -#define I40E_GLV_TEPC(_VSI) (0x00344000 + ((_VSI) * 4)) /* _i=0...383 */ /* Reset: CORER */ +#define I40E_GLV_TEPC(_i) (0x00344000 + ((_i) * 8)) /* _i=0...383 */ /* Reset: CORER */ #define I40E_GLV_TEPC_MAX_INDEX 383 #define I40E_GLV_TEPC_TEPC_SHIFT 0 #define I40E_GLV_TEPC_TEPC_MASK I40E_MASK(0xFFFFFFFF, I40E_GLV_TEPC_TEPC_SHIFT) -- GitLab From bd6cd4e6dd38a35215d3f28f12db51213c9aead6 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Tue, 29 Aug 2017 05:32:35 -0400 Subject: [PATCH 1034/1507] i40e/i40evf: use DECLARE_BITMAP for state When using set_bit and friends, we should be using actual bitmaps, and fix all the locations where we might access it. Signed-off-by: Jesse Brandeburg Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 8 ++++---- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 3 ++- drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 3 ++- 4 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8f326f87a815b..6f2725fc50a18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -278,8 +278,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->netdev, rx_ring->rx_bi); dev_info(&pf->pdev->dev, - " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, rx_ring->state, + " rx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *rx_ring->state, rx_ring->queue_index, rx_ring->reg_idx); dev_info(&pf->pdev->dev, @@ -334,8 +334,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) tx_ring->netdev, tx_ring->tx_bi); dev_info(&pf->pdev->dev, - " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n", - i, tx_ring->state, + " tx_rings[%i]: state = %lu, queue_index = %d, reg_idx = %d\n", + i, *tx_ring->state, tx_ring->queue_index, tx_ring->reg_idx); dev_info(&pf->pdev->dev, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 85132eee9f641..49401be7a2f4c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2891,7 +2891,7 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) return; if ((vsi->tc_config.numtc <= 1) && - !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) { + !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) { cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), ring->queue_index); @@ -3010,7 +3010,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hmc_obj_rxq rx_ctx; i40e_status err = 0; - ring->state = 0; + bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2f848bc5e3912..a4e3e665a1a14 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -342,6 +342,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -366,7 +367,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 0d9f98bc07bdd..d8ca802a71a92 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -325,6 +325,7 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, + __I40E_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -348,7 +349,7 @@ struct i40e_ring { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; }; - unsigned long state; + DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; -- GitLab From 7f6618226360b4aa0230a49525c81bf47d1d53c8 Mon Sep 17 00:00:00 2001 From: Alice Michael Date: Tue, 29 Aug 2017 05:32:36 -0400 Subject: [PATCH 1035/1507] i40e: fix merge error This patch removes some code that was accidentally added to the wrong function with a merge error. Fixes: c53934c6d1b1 ("i40e: fix: do not sleep in netdev_ops") Signed-off-by: Alice Michael Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 49401be7a2f4c..628101bb08d43 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1776,11 +1776,6 @@ static void i40e_set_rx_mode(struct net_device *netdev) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; vsi->back->flags |= I40E_FLAG_FILTER_SYNC; } - - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); } /** -- GitLab From 9a858178ef6dfee2b6e6ec65c42b65a129b4df02 Mon Sep 17 00:00:00 2001 From: Filip Sadowski Date: Tue, 29 Aug 2017 05:32:37 -0400 Subject: [PATCH 1036/1507] i40e: Display error message if module does not meet thermal requirements This patch causes error message to be displayed when NIC detects insertion of module that does not meet thermal requirements. Signed-off-by: Filip Sadowski Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + .../net/ethernet/intel/i40e/i40e_adminq_cmd.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 24 +++++++++++++++---- .../ethernet/intel/i40evf/i40e_adminq_cmd.h | 1 + 4 files changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index c78448daa7a17..4dc6d43f88120 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -451,6 +451,7 @@ struct i40e_pf { #define I40E_FLAG_CLIENT_RESET BIT_ULL(54) #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) #define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) +#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(57) #define I40E_FLAG_LEGACY_RX BIT_ULL(58) #define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(59) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 50c5a4c630b81..a8f65aed54217 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1772,6 +1772,7 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 628101bb08d43..3d6d6a2833276 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6558,12 +6558,26 @@ static void i40e_handle_link_event(struct i40e_pf *pf, */ i40e_link_event(pf); - /* check for unqualified module, if link is down */ - if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && - (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && - (!(status->link_info & I40E_AQ_LINK_UP))) + /* Check if module meets thermal requirements */ + if (status->phy_type == I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP) { dev_err(&pf->pdev->dev, - "The driver failed to link because an unqualified module was detected.\n"); + "Rx/Tx is disabled on this device because the module does not meet thermal requirements.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } else { + /* check for unqualified module, if link is down, suppress + * the message if link was forced to be down. + */ + if ((status->link_info & I40E_AQ_MEDIA_AVAILABLE) && + (!(status->an_info & I40E_AQ_QUALIFIED_MODULE)) && + (!(status->link_info & I40E_AQ_LINK_UP)) && + (!(pf->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED))) { + dev_err(&pf->pdev->dev, + "Rx/Tx is disabled on this device because an unsupported SFP module type was detected.\n"); + dev_err(&pf->pdev->dev, + "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + } + } } /** diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index dc6fc8b1bc798..60c892f559b91 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1768,6 +1768,7 @@ enum i40e_aq_phy_type { I40E_PHY_TYPE_25GBASE_SR = 0x21, I40E_PHY_TYPE_25GBASE_LR = 0x22, I40E_PHY_TYPE_MAX, + I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, I40E_PHY_TYPE_EMPTY = 0xFE, I40E_PHY_TYPE_DEFAULT = 0xFF, }; -- GitLab From 013df598d61161d356d5545f56422766ed3a3a38 Mon Sep 17 00:00:00 2001 From: Filip Sadowski Date: Tue, 29 Aug 2017 05:32:38 -0400 Subject: [PATCH 1037/1507] i40e: Properly maintain flow director filters list When there is no space for more flow director filters and user requested to add a new one it is rejected by firmware and automatically removed from the filter list maintained by driver. This behaviour is correct. Afterwards existing filter can be removed making free slot for the new one. This however causes the newly added filter to be accepted by firmware but removed from driver filter list resulting in not showing after issuing 'ethtool -n '. This happened due to not clearing the variable pf->fd_inv which stores filter number to be removed from the list when firmware refused to add the requested filter. It caused the filter with this specific ID to be constantly removed once it was added to the list although it has been accepted by firmware and effectively applied to the NIC. It was fixed by clearing pf->fd_inv variable after removal of the filter from the list when it was rejected by firmware. Signed-off-by: Filip Sadowski Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3d6d6a2833276..9704cfef2f059 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6232,6 +6232,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) hlist_del(&filter->fdir_node); kfree(filter); pf->fdir_pf_active_filters--; + pf->fd_inv = 0; } } } -- GitLab From 19b7960b2da1db56ec3f8b478c70bab244feb644 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Tue, 29 Aug 2017 05:32:39 -0400 Subject: [PATCH 1038/1507] i40e: implement split PCI error reset handler This patch implements the PCI error handler reset_prepare and reset_done. This allows us to handle function level reset. Without this patch we are unable to perform and recover from an FLR correctly and this will cause VFs to be unable to recover from an FLR on the PF. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 24 +++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9704cfef2f059..60b11fdeca2d5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12045,6 +12045,28 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) return result; } +/** + * i40e_pci_error_reset_prepare - prepare device driver for pci reset + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_prepare(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_prep_for_reset(pf, false); +} + +/** + * i40e_pci_error_reset_done - pci reset done, device driver reset can begin + * @pdev: PCI device information struct + */ +static void i40e_pci_error_reset_done(struct pci_dev *pdev) +{ + struct i40e_pf *pf = pci_get_drvdata(pdev); + + i40e_reset_and_rebuild(pf, false, false); +} + /** * i40e_pci_error_resume - restart operations after PCI error recovery * @pdev: PCI device information struct @@ -12235,6 +12257,8 @@ static int i40e_resume(struct device *dev) static const struct pci_error_handlers i40e_err_handler = { .error_detected = i40e_pci_error_detected, .slot_reset = i40e_pci_error_slot_reset, + .reset_prepare = i40e_pci_error_reset_prepare, + .reset_done = i40e_pci_error_reset_done, .resume = i40e_pci_error_resume, }; -- GitLab From 052b93d0c2ecf693f13561b4b100d541ced41af0 Mon Sep 17 00:00:00 2001 From: Mariusz Stachura Date: Tue, 29 Aug 2017 05:32:40 -0400 Subject: [PATCH 1039/1507] i40e: do not enter PHY debug mode while setting LEDs behaviour Previous implementation of LED set/get functions required to enter PHY debug mode, in order to prevent access to it from FW and SW at the same time. Reset of all ports was a unwanted side effect. Signed-off-by: Mariusz Stachura Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 6203d362438c4..de0dfe3404946 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2010,7 +2010,9 @@ static int i40e_set_phys_id(struct net_device *netdev, if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) { pf->led_status = i40e_led_get(hw); } else { - i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, + NULL); ret = i40e_led_get_phy(hw, &temp_status, &pf->phy_led_val); pf->led_status = temp_status; @@ -2035,7 +2037,8 @@ static int i40e_set_phys_id(struct net_device *netdev, ret = i40e_led_set_phy(hw, false, pf->led_status, (pf->phy_led_val | I40E_PHY_LED_MODE_ORIG)); - i40e_aq_set_phy_debug(hw, 0, NULL); + if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) + i40e_aq_set_phy_debug(hw, 0, NULL); } break; default: -- GitLab From 0a3b4f702fb1f76b03530d58af9efc5e10392185 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 29 Aug 2017 05:32:41 -0400 Subject: [PATCH 1040/1507] i40evf: enable support for VF VLAN tag stripping control A recent commit 809481484e5d ("i40e/i40evf: support for VF VLAN tag stripping control") added support for VFs to negotiate the control of VLAN tag stripping. This should have allowed VFs to disable the feature. Unfortunately, the flag was set only in netdev->feature flags and not in netdev->hw_features. This ultimately causes the stack to assume that it cannot change the flag, so it was unchangeable and marked as [fixed] in the ethtool -k output. Fix this by setting the feature in hw_features first, just as we do for the PF code. This enables ethtool -K to disable the feature correctly, and fully enables user control of the VLAN tag stripping feature. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/i40evf/i40evf_main.c | 22 ++++++++++++------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index bc76378a71e24..1d2fc898b6645 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -2423,10 +2423,6 @@ static netdev_features_t i40evf_features_check(struct sk_buff *skb, return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } -#define I40EVF_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_TX |\ - NETIF_F_HW_VLAN_CTAG_RX |\ - NETIF_F_HW_VLAN_CTAG_FILTER) - /** * i40evf_fix_features - fix up the netdev feature bits * @netdev: our net device @@ -2439,9 +2435,11 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, { struct i40evf_adapter *adapter = netdev_priv(netdev); - features &= ~I40EVF_VLAN_FEATURES; - if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) - features |= I40EVF_VLAN_FEATURES; + if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + features &= ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER); + return features; } @@ -2572,9 +2570,17 @@ int i40evf_process_config(struct i40evf_adapter *adapter) */ hw_features = hw_enc_features; + /* Enable VLAN features if supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + netdev->hw_features |= hw_features; - netdev->features |= hw_features | I40EVF_VLAN_FEATURES; + netdev->features |= hw_features; + + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; adapter->vsi.id = adapter->vsi_res->vsi_id; -- GitLab From a5340d933e3cd7829a24bacc156dd1e475a1ae2c Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Tue, 29 Aug 2017 05:32:42 -0400 Subject: [PATCH 1041/1507] i40e: ignore skb->xmit_more when deciding to set RS bit Since commit 6a7fded776a7 ("i40e: Fix RS bit update in Tx path and disable force WB workaround") we've tried to "optimize" setting the RS bit based around skb->xmit_more. This same logic was refactored in commit 1dc8b538795f ("i40e: Reorder logic for coalescing RS bits"), but ultimately was not functionally changed. Using skb->xmit_more in this way is incorrect, because in certain circumstances we may see a large number of skbs in sequence with xmit_more set. This leads to a performance loss as the hardware does not writeback anything for those packets, which delays the time it takes for us to respond to the stack transmit requests. This significantly impacts UDP performance, especially when layered with multiple devices, such as bonding, VLANs, and vnet setups. This was not noticed until now because it is difficult to create a setup which reproduces the issue. It was discovered in a UDP_STREAM test in a VM, connected using a vnet device to a bridge, which is connected to a bonded pair of X710 ports in active-backup mode with a VLAN. These layered devices seem to compound the number of skbs transmitted at once by the qdisc. Additionally, the problem can be masked by reducing the ITR value. Since the original commit does not provide strong justification for this RS bit "optimization", revert to the previous behavior of setting the RS bit every 4th packet. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 34 +++------------------ 1 file changed, 4 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d9fdf69bbc6e8..3bd176606c094 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3167,38 +3167,12 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* write last descriptor with EOP bit */ td_cmd |= I40E_TX_DESC_CMD_EOP; - /* We can OR these values together as they both are checked against - * 4 below and at this point desc_count will be used as a boolean value - * after this if/else block. + /* We OR these values together to check both against 4 (WB_STRIDE) + * below. This is safe since we don't re-use desc_count afterwards. */ desc_count |= ++tx_ring->packet_stride; - /* Algorithm to optimize tail and RS bit setting: - * if queue is stopped - * mark RS bit - * reset packet counter - * else if xmit_more is supported and is true - * advance packet counter to 4 - * reset desc_count to 0 - * - * if desc_count >= 4 - * mark RS bit - * reset packet counter - * if desc_count > 0 - * update tail - * - * Note: If there are less than 4 descriptors - * pending and interrupts were disabled the service task will - * trigger a force WB. - */ - if (netif_xmit_stopped(txring_txq(tx_ring))) { - goto do_rs; - } else if (skb->xmit_more) { - /* set stride to arm on next packet and reset desc_count */ - tx_ring->packet_stride = WB_STRIDE; - desc_count = 0; - } else if (desc_count >= WB_STRIDE) { -do_rs: + if (desc_count >= WB_STRIDE) { /* write last descriptor with RS bit set */ td_cmd |= I40E_TX_DESC_CMD_RS; tx_ring->packet_stride = 0; @@ -3219,7 +3193,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, first->next_to_watch = tx_desc; /* notify HW of packet */ - if (desc_count) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail -- GitLab From b74f571f59a8a3dae998e3b95e0f88fac39bfef3 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 1 Sep 2017 13:54:07 -0700 Subject: [PATCH 1042/1507] i40e/i40evf: organize and re-number feature flags Now that we've reduced the number of flags, organize similar flags together and re-number them accordingly. Since we don't yet have more than 32 flags, we'll use a u32 for both the hw_features and flag field. Should we gain more flags in the future, we may need to convert to a u64 or separate flags out into two fields. One alternative approach considered, but not implemented here, was to use an enumeration for the flag variables, and create a macro I40E_FLAG() which used string concatenation to generate BIT_ULL values. This has the advantage of making the actual bit values compile-time dynamic so that we do not need to worry about matching the order to the bit value. However, this does produce a high level of code churn, and makes it more difficult to read a dumped flags value when debugging. Change-ID: I8653fff69453cd547d6fe98d29dfa9d8710387d1 Signed-off-by: Jacob Keller Reviewed-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 98 +++++++++---------- .../net/ethernet/intel/i40e/i40e_ethtool.c | 6 +- drivers/net/ethernet/intel/i40evf/i40evf.h | 32 +++--- 3 files changed, 68 insertions(+), 68 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4dc6d43f88120..18c453a3e7286 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -403,57 +403,57 @@ struct i40e_pf { struct timer_list service_timer; struct work_struct service_task; - u64 hw_features; -#define I40E_HW_RSS_AQ_CAPABLE BIT_ULL(0) -#define I40E_HW_128_QP_RSS_CAPABLE BIT_ULL(1) -#define I40E_HW_ATR_EVICT_CAPABLE BIT_ULL(2) -#define I40E_HW_WB_ON_ITR_CAPABLE BIT_ULL(3) -#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(4) -#define I40E_HW_NO_PCI_LINK_CHECK BIT_ULL(5) -#define I40E_HW_100M_SGMII_CAPABLE BIT_ULL(6) -#define I40E_HW_NO_DCB_SUPPORT BIT_ULL(7) -#define I40E_HW_USE_SET_LLDP_MIB BIT_ULL(8) -#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT_ULL(9) -#define I40E_HW_PTP_L4_CAPABLE BIT_ULL(10) -#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(11) -#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT_ULL(12) -#define I40E_HW_HAVE_CRT_RETIMER BIT_ULL(13) -#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT_ULL(14) -#define I40E_HW_PHY_CONTROLS_LEDS BIT_ULL(15) -#define I40E_HW_STOP_FW_LLDP BIT_ULL(16) -#define I40E_HW_PORT_ID_VALID BIT_ULL(17) -#define I40E_HW_RESTART_AUTONEG BIT_ULL(18) + u32 hw_features; +#define I40E_HW_RSS_AQ_CAPABLE BIT(0) +#define I40E_HW_128_QP_RSS_CAPABLE BIT(1) +#define I40E_HW_ATR_EVICT_CAPABLE BIT(2) +#define I40E_HW_WB_ON_ITR_CAPABLE BIT(3) +#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT(4) +#define I40E_HW_NO_PCI_LINK_CHECK BIT(5) +#define I40E_HW_100M_SGMII_CAPABLE BIT(6) +#define I40E_HW_NO_DCB_SUPPORT BIT(7) +#define I40E_HW_USE_SET_LLDP_MIB BIT(8) +#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT(9) +#define I40E_HW_PTP_L4_CAPABLE BIT(10) +#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT(11) +#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT(12) +#define I40E_HW_HAVE_CRT_RETIMER BIT(13) +#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT(14) +#define I40E_HW_PHY_CONTROLS_LEDS BIT(15) +#define I40E_HW_STOP_FW_LLDP BIT(16) +#define I40E_HW_PORT_ID_VALID BIT(17) +#define I40E_HW_RESTART_AUTONEG BIT(18) u64 flags; -#define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1) -#define I40E_FLAG_MSI_ENABLED BIT_ULL(2) -#define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) -#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(4) -#define I40E_FLAG_RSS_ENABLED BIT_ULL(6) -#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) -#define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) -#define I40E_FLAG_FILTER_SYNC BIT_ULL(15) -#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16) -#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19) -#define I40E_FLAG_DCB_ENABLED BIT_ULL(20) -#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21) -#define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22) -#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(23) -#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(24) -#define I40E_FLAG_PTP BIT_ULL(25) -#define I40E_FLAG_MFP_ENABLED BIT_ULL(26) -#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) -#define I40E_FLAG_DCB_CAPABLE BIT_ULL(29) -#define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(37) -#define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) -#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) -#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) -#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) -#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) -#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) -#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(57) -#define I40E_FLAG_LEGACY_RX BIT_ULL(58) -#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(59) +#define I40E_FLAG_RX_CSUM_ENABLED BIT(0) +#define I40E_FLAG_MSI_ENABLED BIT(1) +#define I40E_FLAG_MSIX_ENABLED BIT(2) +#define I40E_FLAG_RSS_ENABLED BIT(3) +#define I40E_FLAG_VMDQ_ENABLED BIT(4) +#define I40E_FLAG_FILTER_SYNC BIT(5) +#define I40E_FLAG_SRIOV_ENABLED BIT(6) +#define I40E_FLAG_DCB_CAPABLE BIT(7) +#define I40E_FLAG_DCB_ENABLED BIT(8) +#define I40E_FLAG_FD_SB_ENABLED BIT(9) +#define I40E_FLAG_FD_ATR_ENABLED BIT(10) +#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT(11) +#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT(12) +#define I40E_FLAG_MFP_ENABLED BIT(13) +#define I40E_FLAG_UDP_FILTER_SYNC BIT(14) +#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT(15) +#define I40E_FLAG_VEB_MODE_ENABLED BIT(16) +#define I40E_FLAG_VEB_STATS_ENABLED BIT(17) +#define I40E_FLAG_LINK_POLLING_ENABLED BIT(18) +#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT(19) +#define I40E_FLAG_TEMP_LINK_POLLING BIT(20) +#define I40E_FLAG_LEGACY_RX BIT(21) +#define I40E_FLAG_PTP BIT(22) +#define I40E_FLAG_IWARP_ENABLED BIT(23) +#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT(24) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT(25) +#define I40E_FLAG_CLIENT_RESET BIT(26) +#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27) +#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28) struct i40e_client_instance *cinst; bool stat_offsets_loaded; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index de0dfe3404946..afd3ca8d98511 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4095,7 +4095,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u64 orig_flags, new_flags, changed_flags; + u32 orig_flags, new_flags, changed_flags; u32 i, j; orig_flags = READ_ONCE(pf->flags); @@ -4147,12 +4147,12 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) return -EOPNOTSUPP; /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg64 returns anything but the old value, this means that + * is if cmpxchg returns anything but the old value, this means that * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. */ - if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { + if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, "Unable to update pf->flags as it was modified by another thread...\n"); return -EAGAIN; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 5982362c56430..de0af521d602c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -222,22 +222,22 @@ struct i40evf_adapter { u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IMIR_ENABLED BIT(5) -#define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) -#define I40EVF_FLAG_RESET_PENDING BIT(9) -#define I40EVF_FLAG_RESET_NEEDED BIT(10) -#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(11) -#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) -#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) -#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) -#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) -#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) -#define I40EVF_FLAG_PROMISC_ON BIT(18) -#define I40EVF_FLAG_ALLMULTI_ON BIT(19) -#define I40EVF_FLAG_LEGACY_RX BIT(20) -#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(21) +#define I40EVF_FLAG_IMIR_ENABLED BIT(1) +#define I40EVF_FLAG_MQ_CAPABLE BIT(2) +#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) +#define I40EVF_FLAG_RESET_PENDING BIT(4) +#define I40EVF_FLAG_RESET_NEEDED BIT(5) +#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(7) +#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define I40EVF_FLAG_PROMISC_ON BIT(13) +#define I40EVF_FLAG_ALLMULTI_ON BIT(14) +#define I40EVF_FLAG_LEGACY_RX BIT(15) +#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED -- GitLab From c0d8832e78cbfd4a64b7112e34920af4b0b0e60e Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Fri, 6 Oct 2017 14:16:52 +0100 Subject: [PATCH 1043/1507] arm64: Ensure the instruction emulation is ready for userspace We trap and emulate some instructions (e.g, mrs, deprecated instructions) for the userspace. However the handlers for these are registered as late_initcalls and the userspace could be up and running from the initramfs by that time (with populate_rootfs, which is a rootfs_initcall()). This could cause problems for the early applications ending up in failure like : [ 11.152061] modprobe[93]: undefined instruction: pc=0000ffff8ca48ff4 This patch promotes the specific calls to core_initcalls, which are guaranteed to be completed before we hit userspace. Cc: stable@vger.kernel.org Cc: Dave Martin Cc: Matthias Brugger Cc: James Morse Reported-by: Matwey V. Kornilov Signed-off-by: Suzuki K Poulose Signed-off-by: Catalin Marinas --- arch/arm64/kernel/armv8_deprecated.c | 2 +- arch/arm64/kernel/cpufeature.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index f0e6d717885b1..d06fbe4cd38d7 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -649,4 +649,4 @@ static int __init armv8_deprecated_init(void) return 0; } -late_initcall(armv8_deprecated_init); +core_initcall(armv8_deprecated_init); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index cd52d365d1f01..21e2c95d24e72 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1307,4 +1307,4 @@ static int __init enable_mrs_emulation(void) return 0; } -late_initcall(enable_mrs_emulation); +core_initcall(enable_mrs_emulation); -- GitLab From ae2e972dae3cea795e9f8f94eb1601213c2d49f0 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Fri, 6 Oct 2017 14:16:53 +0100 Subject: [PATCH 1044/1507] arm64: Ensure fpsimd support is ready before userspace is active We register the pm/hotplug callbacks for FPSIMD as late_initcall, which happens after the userspace is active (from initramfs via populate_rootfs, a rootfs_initcall). Make sure we are ready even before the userspace could potentially use it, by promoting to a core_initcall. Cc: Will Deacon Cc: Mark Rutland Cc: Dave Martin Signed-off-by: Suzuki K Poulose Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f444f374bd7b3..5d547deb6996c 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -444,4 +444,4 @@ static int __init fpsimd_init(void) return 0; } -late_initcall(fpsimd_init); +core_initcall(fpsimd_init); -- GitLab From ab8eb7db1dcc03e7ae9eb379884fd701af6b1a38 Mon Sep 17 00:00:00 2001 From: Eugeniy Paltsev Date: Fri, 22 Sep 2017 19:49:11 +0300 Subject: [PATCH 1045/1507] ARC: [plat-hsdk]: Add reset controller node to manage ethernet reset DW ethernet controller on HSDK hangs sometimes after SW reset, so add reset node to make possible to reset DW ethernet controller HW. Signed-off-by: Eugeniy Paltsev Signed-off-by: Vineet Gupta --- arch/arc/boot/dts/hsdk.dts | 9 +++++++++ arch/arc/configs/hsdk_defconfig | 1 + 2 files changed, 10 insertions(+) diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index b922f3faf5549..8adde1b492f14 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -12,6 +12,7 @@ /dts-v1/; #include +#include / { model = "snps,hsdk"; @@ -102,6 +103,12 @@ soc { ranges = <0x00000000 0xf0000000 0x10000000>; + cgu_rst: reset-controller@8a0 { + compatible = "snps,hsdk-reset"; + #reset-cells = <1>; + reg = <0x8A0 0x4>, <0xFF0 0x4>; + }; + core_clk: core-clk@0 { compatible = "snps,hsdk-core-pll-clock"; reg = <0x00 0x10>, <0x14B8 0x4>; @@ -158,6 +165,8 @@ ethernet@8000 { clocks = <&gmacclk>; clock-names = "stmmaceth"; phy-handle = <&phy0>; + resets = <&cgu_rst HSDK_ETH_RESET>; + reset-names = "stmmaceth"; mdio { #address-cells = <1>; diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 7b8f8faf8a243..15f0f6b5fec1a 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -63,6 +63,7 @@ CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set +CONFIG_RESET_HSDK=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y -- GitLab From 4e64b1ed15e25b8dcc2819c6d43dab72eb0bea26 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 5 Oct 2017 23:46:14 -0700 Subject: [PATCH 1046/1507] net/ipv6: Convert icmpv6_push_pending_frames to void commit cc71b7b07119 ("net/ipv6: remove unused err variable on icmpv6_push_pending_frames") exposed icmpv6_push_pending_frames return value not being used. Remove now unnecessary int err declarations and uses. Miscellanea: o Remove unnecessary goto and out: labels o Realign arguments Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/net/ipv6.h | 4 ++-- net/ipv6/icmp.c | 43 ++++++++++++++++++------------------------- net/ipv6/ping.c | 5 ++--- 3 files changed, 22 insertions(+), 30 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 6eac5cf8f1e6e..3cda3b521c366 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -300,8 +300,8 @@ static inline void fl6_sock_release(struct ip6_flowlabel *fl) void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); -int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, - struct icmp6hdr *thdr, int len); +void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index aeb49b4d8c7dd..4e52d52a6752f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -250,15 +250,15 @@ static bool opt_unrec(struct sk_buff *skb, __u32 offset) return (*op & 0xC0) == 0x80; } -int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, - struct icmp6hdr *thdr, int len) +void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, + struct icmp6hdr *thdr, int len) { struct sk_buff *skb; struct icmp6hdr *icmp6h; skb = skb_peek(&sk->sk_write_queue); if (!skb) - goto out; + return; icmp6h = icmp6_hdr(skb); memcpy(icmp6h, thdr, sizeof(struct icmp6hdr)); @@ -286,8 +286,6 @@ int icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, tmp_csum); } ip6_push_pending_frames(sk); -out: - return 0; } struct icmpv6_msg { @@ -437,7 +435,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); if ((u8 *)hdr < skb->head || @@ -574,17 +571,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, rcu_read_lock(); idev = __in6_dev_get(skb->dev); - err = ip6_append_data(sk, icmpv6_getfrag, &msg, - len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - &ipc6, &fl6, (struct rt6_info *)dst, - MSG_DONTWAIT, &sockc_unused); - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), + &ipc6, &fl6, (struct rt6_info *)dst, + MSG_DONTWAIT, &sockc_unused)) { ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + len + sizeof(struct icmp6hdr)); } rcu_read_unlock(); out_dst_release: @@ -681,7 +677,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct icmpv6_msg msg; struct dst_entry *dst; struct ipcm6_cookie ipc6; - int err = 0; u32 mark = IP6_REPLY_MARK(net, skb->mark); struct sockcm_cookie sockc_unused = {0}; @@ -718,8 +713,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(net, sk, &dst, &fl6); - if (err) + if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) @@ -736,17 +730,16 @@ static void icmpv6_echo_reply(struct sk_buff *skb) ipc6.dontfrag = np->dontfrag; ipc6.opt = NULL; - err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), &ipc6, &fl6, - (struct rt6_info *)dst, MSG_DONTWAIT, - &sockc_unused); - - if (err) { + if (ip6_append_data(sk, icmpv6_getfrag, &msg, + skb->len + sizeof(struct icmp6hdr), + sizeof(struct icmp6hdr), &ipc6, &fl6, + (struct rt6_info *)dst, MSG_DONTWAIT, + &sockc_unused)) { __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, - skb->len + sizeof(struct icmp6hdr)); + icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, + skb->len + sizeof(struct icmp6hdr)); } dst_release(dst); out: diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ac826dd338ff0..d12c55dad7d14 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -154,9 +154,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { - err = icmpv6_push_pending_frames(sk, &fl6, - (struct icmp6hdr *) &pfh.icmph, - len); + icmpv6_push_pending_frames(sk, &fl6, + (struct icmp6hdr *)&pfh.icmph, len); } release_sock(sk); -- GitLab From bb055c198d9b2ba7baf292a440c2d24fe87db494 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:20 +0200 Subject: [PATCH 1047/1507] nfp: add mpls match offloading support Previously MPLS match offloading was not supported. This patch enables MPLS match offloading support for label, bos and tc fields. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/netronome/nfp/flower/cmsg.h | 5 +++++ .../net/ethernet/netronome/nfp/flower/match.c | 17 +++++++++++++++-- .../net/ethernet/netronome/nfp/flower/offload.c | 6 +----- 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 504ddaa21701a..fe4751607b2ba 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -57,6 +57,11 @@ #define NFP_FLOWER_MASK_VLAN_CFI BIT(12) #define NFP_FLOWER_MASK_VLAN_VID GENMASK(11, 0) +#define NFP_FLOWER_MASK_MPLS_LB GENMASK(31, 12) +#define NFP_FLOWER_MASK_MPLS_TC GENMASK(11, 9) +#define NFP_FLOWER_MASK_MPLS_BOS BIT(8) +#define NFP_FLOWER_MASK_MPLS_Q BIT(0) + #define NFP_FL_SC_ACT_DROP 0x80000000 #define NFP_FL_SC_ACT_USER 0x7D000000 #define NFP_FL_SC_ACT_POPV 0x6A000000 diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 865a815ab92ae..e35ade9cd3d55 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -111,8 +111,21 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, ether_addr_copy(frame->mac_src, &addr->src[0]); } - if (mask_version) - frame->mpls_lse = cpu_to_be32(~0); + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) { + struct flow_dissector_key_mpls *mpls; + u32 t_mpls; + + mpls = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_MPLS, + target); + + t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) | + NFP_FLOWER_MASK_MPLS_Q; + + frame->mpls_lse = cpu_to_be32(t_mpls); + } } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 3d9537ebdea40..a721a00a2bccf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -57,6 +57,7 @@ BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \ BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \ BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \ + BIT(FLOW_DISSECTOR_KEY_MPLS) | \ BIT(FLOW_DISSECTOR_KEY_IP)) #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR \ @@ -238,11 +239,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, case cpu_to_be16(ETH_P_ARP): return -EOPNOTSUPP; - /* Currently we do not offload MPLS. */ - case cpu_to_be16(ETH_P_MPLS_UC): - case cpu_to_be16(ETH_P_MPLS_MC): - return -EOPNOTSUPP; - /* Will be included in layer 2. */ case cpu_to_be16(ETH_P_8021Q): break; -- GitLab From a1e9203cc6e5247f6e7af897252ca92cdf5edb70 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:21 +0200 Subject: [PATCH 1048/1507] nfp: add IPv4 ttl and tos match offloading support Previously matching on IPv4 ttl and tos fields were not offloaded. This patch enables offloading IPv4 ttl and tos as match fields. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/flower/match.c | 11 ++++++++++- drivers/net/ethernet/netronome/nfp/flower/offload.c | 4 ---- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index e35ade9cd3d55..d6096b4f13918 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -156,7 +156,6 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, struct flow_dissector_key_ipv4_addrs *addr; struct flow_dissector_key_basic *basic; - /* Wildcard TOS/TTL for now. */ memset(frame, 0, sizeof(struct nfp_flower_ipv4)); if (dissector_uses_key(flow->dissector, @@ -174,6 +173,16 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, target); frame->proto = basic->ip_proto; } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) { + struct flow_dissector_key_ip *flow_ip; + + flow_ip = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_IP, + target); + frame->tos = flow_ip->tos; + frame->ttl = flow_ip->ttl; + } } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index a721a00a2bccf..3651db5dfb8b0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -216,10 +216,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, /* Ethernet type is present in the key. */ switch (key_basic->n_proto) { case cpu_to_be16(ETH_P_IP): - if (mask_ip && mask_ip->tos) - return -EOPNOTSUPP; - if (mask_ip && mask_ip->ttl) - return -EOPNOTSUPP; key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); break; -- GitLab From fc53b4a7014aab8c260c2b81ae6c24687dff3045 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:22 +0200 Subject: [PATCH 1049/1507] nfp: add IPv6 ttl and tos match offloading support Previously matching on IPv6 ttl and tos fields were not offloaded. This patch enables offloading IPv6 ttl and tos as match fields. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/flower/match.c | 11 ++++++++++- drivers/net/ethernet/netronome/nfp/flower/offload.c | 10 ---------- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index d6096b4f13918..60614d4f0e225 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -194,7 +194,6 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, struct flow_dissector_key_ipv6_addrs *addr; struct flow_dissector_key_basic *basic; - /* Wildcard LABEL/TOS/TTL for now. */ memset(frame, 0, sizeof(struct nfp_flower_ipv6)); if (dissector_uses_key(flow->dissector, @@ -212,6 +211,16 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, target); frame->proto = basic->ip_proto; } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) { + struct flow_dissector_key_ip *flow_ip; + + flow_ip = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_IP, + target); + frame->tos = flow_ip->tos; + frame->ttl = flow_ip->ttl; + } } static void diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 3651db5dfb8b0..6f239c27964e1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -135,7 +135,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, { struct flow_dissector_key_basic *mask_basic = NULL; struct flow_dissector_key_basic *key_basic = NULL; - struct flow_dissector_key_ip *mask_ip = NULL; u32 key_layer_two; u8 key_layer; int key_size; @@ -207,11 +206,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, flow->key); } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) - mask_ip = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IP, - flow->mask); - if (mask_basic && mask_basic->n_proto) { /* Ethernet type is present in the key. */ switch (key_basic->n_proto) { @@ -221,10 +215,6 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, break; case cpu_to_be16(ETH_P_IPV6): - if (mask_ip && mask_ip->tos) - return -EOPNOTSUPP; - if (mask_ip && mask_ip->ttl) - return -EOPNOTSUPP; key_layer |= NFP_FLOWER_LAYER_IPV6; key_size += sizeof(struct nfp_flower_ipv6); break; -- GitLab From da83d8fe5889822691384d2b3edf1716fb6debdb Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:23 +0200 Subject: [PATCH 1050/1507] nfp: add set ethernet header action flower offload Previously we did not have offloading support for set ethernet actions. This patch enables TC flower offload of set ethernet actions. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/flower/action.c | 85 +++++++++++++++++++ .../net/ethernet/netronome/nfp/flower/cmsg.h | 8 ++ 2 files changed, 93 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 38f3835ae1767..631ea4b7d08e5 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -223,6 +224,87 @@ nfp_fl_set_vxlan(struct nfp_fl_set_vxlan *set_vxlan, return 0; } +static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask) +{ + u32 oldvalue = get_unaligned((u32 *)p_exact); + u32 oldmask = get_unaligned((u32 *)p_mask); + + value &= mask; + value |= oldvalue & ~mask; + + put_unaligned(oldmask | mask, (u32 *)p_mask); + put_unaligned(value, (u32 *)p_exact); +} + +static int +nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off, + struct nfp_fl_set_eth *set_eth) +{ + u16 tmp_set_eth_op; + u32 exact, mask; + + if (off + 4 > ETH_ALEN * 2) + return -EOPNOTSUPP; + + mask = ~tcf_pedit_mask(action, idx); + exact = tcf_pedit_val(action, idx); + + if (exact & ~mask) + return -EOPNOTSUPP; + + nfp_fl_set_helper32(exact, mask, &set_eth->eth_addr_val[off], + &set_eth->eth_addr_mask[off]); + + set_eth->reserved = cpu_to_be16(0); + tmp_set_eth_op = FIELD_PREP(NFP_FL_ACT_LEN_LW, + sizeof(*set_eth) >> NFP_FL_LW_SIZ) | + FIELD_PREP(NFP_FL_ACT_JMP_ID, + NFP_FL_ACTION_OPCODE_SET_ETHERNET); + set_eth->a_op = cpu_to_be16(tmp_set_eth_op); + + return 0; +} + +static int +nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) +{ + struct nfp_fl_set_eth set_eth; + enum pedit_header_type htype; + int idx, nkeys, err; + size_t act_size; + u32 offset, cmd; + + memset(&set_eth, 0, sizeof(set_eth)); + nkeys = tcf_pedit_nkeys(action); + + for (idx = 0; idx < nkeys; idx++) { + cmd = tcf_pedit_cmd(action, idx); + htype = tcf_pedit_htype(action, idx); + offset = tcf_pedit_offset(action, idx); + + if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) + return -EOPNOTSUPP; + + switch (htype) { + case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + err = nfp_fl_set_eth(action, idx, offset, &set_eth); + break; + default: + return -EOPNOTSUPP; + } + if (err) + return err; + } + + if (set_eth.a_op) { + act_size = sizeof(set_eth); + memcpy(nfp_action, &set_eth, act_size); + *a_len += act_size; + } + + return 0; +} + static int nfp_flower_loop_action(const struct tc_action *a, struct nfp_fl_payload *nfp_fl, int *a_len, @@ -301,6 +383,9 @@ nfp_flower_loop_action(const struct tc_action *a, } else if (is_tcf_tunnel_release(a)) { /* Tunnel decap is handled by default so accept action. */ return 0; + } else if (is_tcf_pedit(a)) { + if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len)) + return -EOPNOTSUPP; } else { /* Currently we do not handle any other actions. */ return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index fe4751607b2ba..ffeaf85aa4207 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -77,6 +77,7 @@ #define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1 #define NFP_FL_ACTION_OPCODE_POP_VLAN 2 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 +#define NFP_FL_ACTION_OPCODE_SET_ETHERNET 7 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17 #define NFP_FL_ACTION_OPCODE_NUM 32 @@ -107,6 +108,13 @@ enum nfp_flower_tun_type { NFP_FL_TUNNEL_VXLAN = 2, }; +struct nfp_fl_set_eth { + __be16 a_op; + __be16 reserved; + u8 eth_addr_mask[ETH_ALEN * 2]; + u8 eth_addr_val[ETH_ALEN * 2]; +}; + struct nfp_fl_output { __be16 a_op; __be16 flags; -- GitLab From c0b1bd9a8b8ac81e4e0985aad4a8de869ab6a668 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:24 +0200 Subject: [PATCH 1051/1507] nfp: add set ipv4 header action flower offload Previously we did not have offloading support for set IPv4 actions. This patch enables TC flower offload of set IPv4 src and dst address actions. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/flower/action.c | 46 +++++++++++++++++++ .../net/ethernet/netronome/nfp/flower/cmsg.h | 10 ++++ 2 files changed, 56 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 631ea4b7d08e5..2f886a529ee49 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -265,15 +265,54 @@ nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off, return 0; } +static int +nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off, + struct nfp_fl_set_ip4_addrs *set_ip_addr) +{ + u16 tmp_set_ipv4_op; + __be32 exact, mask; + + /* We are expecting tcf_pedit to return a big endian value */ + mask = (__force __be32)~tcf_pedit_mask(action, idx); + exact = (__force __be32)tcf_pedit_val(action, idx); + + if (exact & ~mask) + return -EOPNOTSUPP; + + switch (off) { + case offsetof(struct iphdr, daddr): + set_ip_addr->ipv4_dst_mask = mask; + set_ip_addr->ipv4_dst = exact; + break; + case offsetof(struct iphdr, saddr): + set_ip_addr->ipv4_src_mask = mask; + set_ip_addr->ipv4_src = exact; + break; + default: + return -EOPNOTSUPP; + } + + set_ip_addr->reserved = cpu_to_be16(0); + tmp_set_ipv4_op = FIELD_PREP(NFP_FL_ACT_LEN_LW, + sizeof(*set_ip_addr) >> NFP_FL_LW_SIZ) | + FIELD_PREP(NFP_FL_ACT_JMP_ID, + NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS); + set_ip_addr->a_op = cpu_to_be16(tmp_set_ipv4_op); + + return 0; +} + static int nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) { + struct nfp_fl_set_ip4_addrs set_ip_addr; struct nfp_fl_set_eth set_eth; enum pedit_header_type htype; int idx, nkeys, err; size_t act_size; u32 offset, cmd; + memset(&set_ip_addr, 0, sizeof(set_ip_addr)); memset(&set_eth, 0, sizeof(set_eth)); nkeys = tcf_pedit_nkeys(action); @@ -289,6 +328,9 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: err = nfp_fl_set_eth(action, idx, offset, &set_eth); break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr); + break; default: return -EOPNOTSUPP; } @@ -300,6 +342,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) act_size = sizeof(set_eth); memcpy(nfp_action, &set_eth, act_size); *a_len += act_size; + } else if (set_ip_addr.a_op) { + act_size = sizeof(set_ip_addr); + memcpy(nfp_action, &set_ip_addr, act_size); + *a_len += act_size; } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index ffeaf85aa4207..7ace557fdf841 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -78,6 +78,7 @@ #define NFP_FL_ACTION_OPCODE_POP_VLAN 2 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET 7 +#define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS 9 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17 #define NFP_FL_ACTION_OPCODE_NUM 32 @@ -115,6 +116,15 @@ struct nfp_fl_set_eth { u8 eth_addr_val[ETH_ALEN * 2]; }; +struct nfp_fl_set_ip4_addrs { + __be16 a_op; + __be16 reserved; + __be32 ipv4_src_mask; + __be32 ipv4_src; + __be32 ipv4_dst_mask; + __be32 ipv4_dst; +}; + struct nfp_fl_output { __be16 a_op; __be16 flags; -- GitLab From 354b82bb320e04547e4755d2cc2ebab87a6d8abe Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:25 +0200 Subject: [PATCH 1052/1507] nfp: add set ipv6 source and destination address Previously we did not have offloading support for set IPv6 actions. This patch enables TC flower offload of set IPv6 src and dst address actions. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/flower/action.c | 72 +++++++++++++++++++ .../net/ethernet/netronome/nfp/flower/cmsg.h | 11 +++ 2 files changed, 83 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 2f886a529ee49..4394e4f15fdb2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -302,9 +302,55 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off, return 0; } +static void +nfp_fl_set_ip6_helper(int opcode_tag, int idx, __be32 exact, __be32 mask, + struct nfp_fl_set_ipv6_addr *ip6) +{ + u16 tmp_set_op; + + ip6->ipv6[idx % 4].mask = mask; + ip6->ipv6[idx % 4].exact = exact; + + ip6->reserved = cpu_to_be16(0); + tmp_set_op = FIELD_PREP(NFP_FL_ACT_LEN_LW, sizeof(*ip6) >> + NFP_FL_LW_SIZ) | + FIELD_PREP(NFP_FL_ACT_JMP_ID, opcode_tag); + ip6->a_op = cpu_to_be16(tmp_set_op); +} + +static int +nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off, + struct nfp_fl_set_ipv6_addr *ip_dst, + struct nfp_fl_set_ipv6_addr *ip_src) +{ + __be32 exact, mask; + + /* We are expecting tcf_pedit to return a big endian value */ + mask = (__force __be32)~tcf_pedit_mask(action, idx); + exact = (__force __be32)tcf_pedit_val(action, idx); + + if (exact & ~mask) + return -EOPNOTSUPP; + + if (off < offsetof(struct ipv6hdr, saddr)) + return -EOPNOTSUPP; + else if (off < offsetof(struct ipv6hdr, daddr)) + nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_SRC, idx, + exact, mask, ip_src); + else if (off < offsetof(struct ipv6hdr, daddr) + + sizeof(struct in6_addr)) + nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_DST, idx, + exact, mask, ip_dst); + else + return -EOPNOTSUPP; + + return 0; +} + static int nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) { + struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src; struct nfp_fl_set_ip4_addrs set_ip_addr; struct nfp_fl_set_eth set_eth; enum pedit_header_type htype; @@ -312,6 +358,8 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) size_t act_size; u32 offset, cmd; + memset(&set_ip6_dst, 0, sizeof(set_ip6_dst)); + memset(&set_ip6_src, 0, sizeof(set_ip6_src)); memset(&set_ip_addr, 0, sizeof(set_ip_addr)); memset(&set_eth, 0, sizeof(set_eth)); nkeys = tcf_pedit_nkeys(action); @@ -331,6 +379,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr); break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst, + &set_ip6_src); + break; default: return -EOPNOTSUPP; } @@ -346,6 +398,26 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) act_size = sizeof(set_ip_addr); memcpy(nfp_action, &set_ip_addr, act_size); *a_len += act_size; + } else if (set_ip6_dst.a_op && set_ip6_src.a_op) { + /* TC compiles set src and dst IPv6 address as a single action, + * the hardware requires this to be 2 separate actions. + */ + act_size = sizeof(set_ip6_src); + memcpy(nfp_action, &set_ip6_src, act_size); + *a_len += act_size; + + act_size = sizeof(set_ip6_dst); + memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst, + act_size); + *a_len += act_size; + } else if (set_ip6_dst.a_op) { + act_size = sizeof(set_ip6_dst); + memcpy(nfp_action, &set_ip6_dst, act_size); + *a_len += act_size; + } else if (set_ip6_src.a_op) { + act_size = sizeof(set_ip6_src); + memcpy(nfp_action, &set_ip6_src, act_size); + *a_len += act_size; } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 7ace557fdf841..527914e294d7b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -79,6 +79,8 @@ #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET 7 #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS 9 +#define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC 11 +#define NFP_FL_ACTION_OPCODE_SET_IPV6_DST 12 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17 #define NFP_FL_ACTION_OPCODE_NUM 32 @@ -125,6 +127,15 @@ struct nfp_fl_set_ip4_addrs { __be32 ipv4_dst; }; +struct nfp_fl_set_ipv6_addr { + __be16 a_op; + __be16 reserved; + struct { + __be32 mask; + __be32 exact; + } ipv6[4]; +}; + struct nfp_fl_output { __be16 a_op; __be16 flags; -- GitLab From f8b7b0a6b113eea5b528e51a2086e6f93f4e4933 Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Fri, 6 Oct 2017 10:21:26 +0200 Subject: [PATCH 1053/1507] nfp: add set tcp and udp header action flower offload Previously we did not have offloading support for set TCP/UDP actions. This patch enables TC flower offload of set TCP/UDP sport and dport actions. Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/netronome/nfp/flower/action.c | 42 +++++++++++++++++++ .../net/ethernet/netronome/nfp/flower/cmsg.h | 9 ++++ 2 files changed, 51 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 4394e4f15fdb2..1194c47ef8275 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -347,11 +347,40 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off, return 0; } +static int +nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off, + struct nfp_fl_set_tport *set_tport, int opcode) +{ + u32 exact, mask; + u16 tmp_set_op; + + if (off) + return -EOPNOTSUPP; + + mask = ~tcf_pedit_mask(action, idx); + exact = tcf_pedit_val(action, idx); + + if (exact & ~mask) + return -EOPNOTSUPP; + + nfp_fl_set_helper32(exact, mask, set_tport->tp_port_val, + set_tport->tp_port_mask); + + set_tport->reserved = cpu_to_be16(0); + tmp_set_op = FIELD_PREP(NFP_FL_ACT_LEN_LW, + sizeof(*set_tport) >> NFP_FL_LW_SIZ); + tmp_set_op |= FIELD_PREP(NFP_FL_ACT_JMP_ID, opcode); + set_tport->a_op = cpu_to_be16(tmp_set_op); + + return 0; +} + static int nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) { struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src; struct nfp_fl_set_ip4_addrs set_ip_addr; + struct nfp_fl_set_tport set_tport; struct nfp_fl_set_eth set_eth; enum pedit_header_type htype; int idx, nkeys, err; @@ -361,6 +390,7 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) memset(&set_ip6_dst, 0, sizeof(set_ip6_dst)); memset(&set_ip6_src, 0, sizeof(set_ip6_src)); memset(&set_ip_addr, 0, sizeof(set_ip_addr)); + memset(&set_tport, 0, sizeof(set_tport)); memset(&set_eth, 0, sizeof(set_eth)); nkeys = tcf_pedit_nkeys(action); @@ -383,6 +413,14 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst, &set_ip6_src); break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + err = nfp_fl_set_tport(action, idx, offset, &set_tport, + NFP_FL_ACTION_OPCODE_SET_TCP); + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + err = nfp_fl_set_tport(action, idx, offset, &set_tport, + NFP_FL_ACTION_OPCODE_SET_UDP); + break; default: return -EOPNOTSUPP; } @@ -418,6 +456,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len) act_size = sizeof(set_ip6_src); memcpy(nfp_action, &set_ip6_src, act_size); *a_len += act_size; + } else if (set_tport.a_op) { + act_size = sizeof(set_tport); + memcpy(nfp_action, &set_tport, act_size); + *a_len += act_size; } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 527914e294d7b..f7b7242a22bcb 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -81,6 +81,8 @@ #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS 9 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC 11 #define NFP_FL_ACTION_OPCODE_SET_IPV6_DST 12 +#define NFP_FL_ACTION_OPCODE_SET_UDP 14 +#define NFP_FL_ACTION_OPCODE_SET_TCP 15 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL 17 #define NFP_FL_ACTION_OPCODE_NUM 32 @@ -136,6 +138,13 @@ struct nfp_fl_set_ipv6_addr { } ipv6[4]; }; +struct nfp_fl_set_tport { + __be16 a_op; + __be16 reserved; + u8 tp_port_mask[4]; + u8 tp_port_val[4]; +}; + struct nfp_fl_output { __be16 a_op; __be16 flags; -- GitLab From f4ce0a0116bc90803adac10865f14429313cb2b6 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 6 Oct 2017 10:41:41 +0200 Subject: [PATCH 1054/1507] samples/bpf: xdp_monitor first 8 bytes are not accessible by bpf The first 8 bytes of the tracepoint context struct are not accessible by the bpf code. This is a choice that dates back to the original inclusion of this code. See explaination in: commit 98b5c2c65c29 ("perf, bpf: allow bpf programs attach to tracepoints") Signed-off-by: Jesper Dangaard Brouer Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- samples/bpf/xdp_monitor_kern.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c index 74f3fd8ed7295..cc7e19d2ad760 100644 --- a/samples/bpf/xdp_monitor_kern.c +++ b/samples/bpf/xdp_monitor_kern.c @@ -17,19 +17,15 @@ struct bpf_map_def SEC("maps") redirect_err_cnt = { * Code in: kernel/include/trace/events/xdp.h */ struct xdp_redirect_ctx { - unsigned short common_type; // offset:0; size:2; signed:0; - unsigned char common_flags; // offset:2; size:1; signed:0; - unsigned char common_preempt_count;// offset:3; size:1; signed:0; - int common_pid; // offset:4; size:4; signed:1; - - int prog_id; // offset:8; size:4; signed:1; - u32 act; // offset:12 size:4; signed:0; - int ifindex; // offset:16 size:4; signed:1; - int err; // offset:20 size:4; signed:1; - int to_ifindex; // offset:24 size:4; signed:1; - u32 map_id; // offset:28 size:4; signed:0; - int map_index; // offset:32 size:4; signed:1; -}; // offset:36 + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12 size:4; signed:0; + int ifindex; // offset:16 size:4; signed:1; + int err; // offset:20 size:4; signed:1; + int to_ifindex; // offset:24 size:4; signed:1; + u32 map_id; // offset:28 size:4; signed:0; + int map_index; // offset:32 size:4; signed:1; +}; // offset:36 enum { XDP_REDIRECT_SUCCESS = 0, -- GitLab From 280b058d4801cb431477dc101a776e4b24995f2f Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 6 Oct 2017 10:41:46 +0200 Subject: [PATCH 1055/1507] samples/bpf: xdp_monitor also record xdp_exception tracepoint Also monitor the tracepoint xdp_exception. This tracepoint is usually invoked by the drivers. Programs themselves can activate this by returning XDP_ABORTED, which will drop the packet but also trigger the tracepoint. This is useful for distinguishing intentional (XDP_DROP) vs. ebpf-program error cases that cased a drop (XDP_ABORTED). Drivers also use this tracepoint for reporting on XDP actions that are unknown to the specific driver. This can help the user to detect if a driver e.g. doesn't implement XDP_REDIRECT yet. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- samples/bpf/xdp_monitor_kern.c | 38 +++++++++++- samples/bpf/xdp_monitor_user.c | 108 +++++++++++++++++++++++++-------- 2 files changed, 121 insertions(+), 25 deletions(-) diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c index cc7e19d2ad760..2fe2f761a0d05 100644 --- a/samples/bpf/xdp_monitor_kern.c +++ b/samples/bpf/xdp_monitor_kern.c @@ -13,6 +13,14 @@ struct bpf_map_def SEC("maps") redirect_err_cnt = { /* TODO: have entries for all possible errno's */ }; +#define XDP_UNKNOWN XDP_REDIRECT + 1 +struct bpf_map_def SEC("maps") exception_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u64), + .max_entries = XDP_UNKNOWN + 1, +}; + /* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format * Code in: kernel/include/trace/events/xdp.h */ @@ -44,7 +52,7 @@ int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) cnt = bpf_map_lookup_elem(&redirect_err_cnt, &key); if (!cnt) - return 0; + return 1; *cnt += 1; return 0; /* Indicate event was filtered (no further processing)*/ @@ -82,3 +90,31 @@ int trace_xdp_redirect_map(struct xdp_redirect_ctx *ctx) { return xdp_redirect_collect_stat(ctx); } + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_exception_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int ifindex; // offset:16; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_exception") +int trace_xdp_exception(struct xdp_exception_ctx *ctx) +{ + u64 *cnt;; + u32 key; + + key = ctx->act; + if (key > XDP_REDIRECT) + key = XDP_UNKNOWN; + + cnt = bpf_map_lookup_elem(&exception_cnt, &key); + if (!cnt) + return 1; + *cnt += 1; + + return 0; +} diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index c5ab8b776973a..97c3456c11b2b 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -89,6 +89,23 @@ static const char *err2str(int err) return redir_names[err]; return NULL; } +/* enum xdp_action */ +#define XDP_UNKNOWN XDP_REDIRECT + 1 +#define XDP_ACTION_MAX (XDP_UNKNOWN + 1) +static const char *xdp_action_names[XDP_ACTION_MAX] = { + [XDP_ABORTED] = "XDP_ABORTED", + [XDP_DROP] = "XDP_DROP", + [XDP_PASS] = "XDP_PASS", + [XDP_TX] = "XDP_TX", + [XDP_REDIRECT] = "XDP_REDIRECT", + [XDP_UNKNOWN] = "XDP_UNKNOWN", +}; +static const char *action2str(int action) +{ + if (action < XDP_ACTION_MAX) + return xdp_action_names[action]; + return NULL; +} struct record { __u64 counter; @@ -97,6 +114,7 @@ struct record { struct stats_record { struct record xdp_redir[REDIR_RES_MAX]; + struct record xdp_exception[XDP_ACTION_MAX]; }; static void stats_print_headers(bool err_only) @@ -104,39 +122,72 @@ static void stats_print_headers(bool err_only) if (err_only) printf("\n%s\n", __doc_err_only__); - printf("%-14s %-10s %-18s %-9s\n", - "XDP_REDIRECT", "pps ", "pps-human-readable", "measure-period"); + printf("%-14s %-11s %-10s %-18s %-9s\n", + "ACTION", "result", "pps ", "pps-human-readable", "measure-period"); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static double calc_pps(struct record *r, struct record *p, double period) +{ + __u64 packets = 0; + double pps = 0; + + if (period > 0) { + packets = r->counter - p->counter; + pps = packets / period; + } + return pps; } static void stats_print(struct stats_record *rec, struct stats_record *prev, bool err_only) { + double period = 0, pps = 0; + struct record *r, *p; int i = 0; + char *fmt = "%-14s %-11s %-10.0f %'-18.0f %f\n"; + + /* tracepoint: xdp:xdp_redirect_* */ if (err_only) i = REDIR_ERROR; for (; i < REDIR_RES_MAX; i++) { - struct record *r = &rec->xdp_redir[i]; - struct record *p = &prev->xdp_redir[i]; - __u64 period = 0; - __u64 packets = 0; - double pps = 0; - double period_ = 0; + r = &rec->xdp_redir[i]; + p = &prev->xdp_redir[i]; if (p->timestamp) { - packets = r->counter - p->counter; - period = r->timestamp - p->timestamp; - if (period > 0) { - period_ = ((double) period / NANOSEC_PER_SEC); - pps = packets / period_; - } + period = calc_period(r, p); + pps = calc_pps(r, p, period); } + printf(fmt, "XDP_REDIRECT", err2str(i), pps, pps, period); + } - printf("%-14s %-10.0f %'-18.0f %f\n", - err2str(i), pps, pps, period_); + /* tracepoint: xdp:xdp_exception */ + for (i = 0; i < XDP_ACTION_MAX; i++) { + r = &rec->xdp_exception[i]; + p = &prev->xdp_exception[i]; + if (p->timestamp) { + period = calc_period(r, p); + pps = calc_pps(r, p, period); + } + if (pps > 0) + printf(fmt, action2str(i), "Exception", + pps, pps, period); } + printf("\n"); } static __u64 get_key32_value64_percpu(int fd, __u32 key) @@ -160,25 +211,33 @@ static __u64 get_key32_value64_percpu(int fd, __u32 key) return sum; } -static bool stats_collect(int fd, struct stats_record *rec) +static bool stats_collect(struct stats_record *rec) { + int fd; int i; /* TODO: Detect if someone unloaded the perf event_fd's, as * this can happen by someone running perf-record -e */ + fd = map_data[0].fd; /* map0: redirect_err_cnt */ for (i = 0; i < REDIR_RES_MAX; i++) { rec->xdp_redir[i].timestamp = gettime(); rec->xdp_redir[i].counter = get_key32_value64_percpu(fd, i); } + + fd = map_data[1].fd; /* map1: exception_cnt */ + for (i = 0; i < XDP_ACTION_MAX; i++) { + rec->xdp_exception[i].timestamp = gettime(); + rec->xdp_exception[i].counter = get_key32_value64_percpu(fd, i); + } + return true; } static void stats_poll(int interval, bool err_only) { struct stats_record rec, prev; - int map_fd; memset(&rec, 0, sizeof(rec)); @@ -190,16 +249,17 @@ static void stats_poll(int interval, bool err_only) printf("\n%s", __doc__); /* TODO Need more advanced stats on error types */ - if (verbose) - printf(" - Stats map: %s\n", map_data[0].name); - map_fd = map_data[0].fd; - - stats_print_headers(err_only); + if (verbose) { + printf(" - Stats map0: %s\n", map_data[0].name); + printf(" - Stats map1: %s\n", map_data[1].name); + printf("\n"); + } fflush(stdout); while (1) { memcpy(&prev, &rec, sizeof(rec)); - stats_collect(map_fd, &rec); + stats_collect(&rec); + stats_print_headers(err_only); stats_print(&rec, &prev, err_only); fflush(stdout); sleep(interval); -- GitLab From c4eb7f4643ce3741e63b7d3f9b70bb7a637e738a Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 6 Oct 2017 10:41:51 +0200 Subject: [PATCH 1056/1507] samples/bpf: xdp_monitor increase memory rlimit Other concurrent running programs, like perf or the XDP program what needed to be monitored, might take up part of the max locked memory limit. Thus, the xdp_monitor tool have to set the RLIMIT_MEMLOCK to RLIM_INFINITY, as it cannot determine a more sane limit. Using the man exit(3) specified EXIT_FAILURE return exit code, and correct other users too. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- samples/bpf/xdp_monitor_user.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index 97c3456c11b2b..eaba165b35492 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -20,6 +20,7 @@ static const char *__doc_err_only__= #include #include +#include #include #include #include @@ -295,6 +296,7 @@ static void print_bpf_prog_info(void) int main(int argc, char **argv) { + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int longindex = 0, opt; int ret = EXIT_SUCCESS; char bpf_obj_file[256]; @@ -325,13 +327,18 @@ int main(int argc, char **argv) } } + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return EXIT_FAILURE; + } + if (load_bpf_file(bpf_obj_file)) { printf("ERROR - bpf_log_buf: %s", bpf_log_buf); - return 1; + return EXIT_FAILURE; } if (!prog_fd[0]) { printf("ERROR - load_bpf_file: %s\n", strerror(errno)); - return 1; + return EXIT_FAILURE; } if (debug) { -- GitLab From d2746fe5380e9af79807994756672baaf42cb130 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 6 Oct 2017 06:00:30 -0500 Subject: [PATCH 1057/1507] bnx2x: Use pci_ari_enabled() instead of local copy Use pci_ari_enabled() from the PCI core instead of the identical local copy bnx2x_ari_enabled(). No functional change intended. Signed-off-by: Bjorn Helgaas Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9ca994d0bab66..3591077a5f6b1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1074,11 +1074,6 @@ static void bnx2x_vf_set_bars(struct bnx2x *bp, struct bnx2x_virtf *vf) } } -static int bnx2x_ari_enabled(struct pci_dev *dev) -{ - return dev->bus->self && dev->bus->self->ari_enabled; -} - static int bnx2x_get_vf_igu_cam_info(struct bnx2x *bp) { @@ -1212,7 +1207,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, err = -EIO; /* verify ari is enabled */ - if (!bnx2x_ari_enabled(bp->pdev)) { + if (!pci_ari_enabled(bp->pdev->bus)) { BNX2X_ERR("ARI not supported (check pci bridge ARI forwarding), SRIOV can not be enabled\n"); return 0; } -- GitLab From 6151b8b37b119e8e3a8401b080d532520c95faf4 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Oct 2017 17:05:49 +0200 Subject: [PATCH 1058/1507] ppp: fix race in ppp device destruction ppp_release() tries to ensure that netdevices are unregistered before decrementing the unit refcount and running ppp_destroy_interface(). This is all fine as long as the the device is unregistered by ppp_release(): the unregister_netdevice() call, followed by rtnl_unlock(), guarantee that the unregistration process completes before rtnl_unlock() returns. However, the device may be unregistered by other means (like ppp_nl_dellink()). If this happens right before ppp_release() calling rtnl_lock(), then ppp_release() has to wait for the concurrent unregistration code to release the lock. But rtnl_unlock() releases the lock before completing the device unregistration process. This allows ppp_release() to proceed and eventually call ppp_destroy_interface() before the unregistration process completes. Calling free_netdev() on this partially unregistered device will BUG(): ------------[ cut here ]------------ kernel BUG at net/core/dev.c:8141! invalid opcode: 0000 [#1] SMP CPU: 1 PID: 1557 Comm: pppd Not tainted 4.14.0-rc2+ #4 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1.fc26 04/01/2014 Call Trace: ppp_destroy_interface+0xd8/0xe0 [ppp_generic] ppp_disconnect_channel+0xda/0x110 [ppp_generic] ppp_unregister_channel+0x5e/0x110 [ppp_generic] pppox_unbind_sock+0x23/0x30 [pppox] pppoe_connect+0x130/0x440 [pppoe] SYSC_connect+0x98/0x110 ? do_fcntl+0x2c0/0x5d0 SyS_connect+0xe/0x10 entry_SYSCALL_64_fastpath+0x1a/0xa5 RIP: free_netdev+0x107/0x110 RSP: ffffc28a40573d88 ---[ end trace ed294ff0cc40eeff ]--- We could set the ->needs_free_netdev flag on PPP devices and move the ppp_destroy_interface() logic in the ->priv_destructor() callback. But that'd be quite intrusive as we'd first need to unlink from the other channels and units that depend on the device (the ones that used the PPPIOCCONNECT and PPPIOCATTACH ioctls). Instead, we can just let the netdevice hold a reference on its ppp_file. This reference is dropped in ->priv_destructor(), at the very end of the unregistration process, so that neither ppp_release() nor ppp_disconnect_channel() can call ppp_destroy_interface() in the interim. Reported-by: Beniamino Galvani Fixes: 8cb775bc0a34 ("ppp: fix device unregistration upon netns deletion") Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index c3f77e3b7819c..e365866600ba0 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1339,7 +1339,17 @@ ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) static int ppp_dev_init(struct net_device *dev) { + struct ppp *ppp; + netdev_lockdep_set_classes(dev); + + ppp = netdev_priv(dev); + /* Let the netdevice take a reference on the ppp file. This ensures + * that ppp_destroy_interface() won't run before the device gets + * unregistered. + */ + atomic_inc(&ppp->file.refcnt); + return 0; } @@ -1362,6 +1372,15 @@ static void ppp_dev_uninit(struct net_device *dev) wake_up_interruptible(&ppp->file.rwait); } +static void ppp_dev_priv_destructor(struct net_device *dev) +{ + struct ppp *ppp; + + ppp = netdev_priv(dev); + if (atomic_dec_and_test(&ppp->file.refcnt)) + ppp_destroy_interface(ppp); +} + static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, @@ -1387,6 +1406,7 @@ static void ppp_setup(struct net_device *dev) dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } -- GitLab From 18a4c0eab2623cc95be98a1e6af1ad18e7695977 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:21 -0700 Subject: [PATCH 1059/1507] net: add rb_to_skb() and other rb tree helpers Geeralize private netem_rb_to_skb() TCP rtx queue will soon be converted to rb-tree, so we will need skb_rbtree_walk() helpers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 ++++++++++++++++++ net/ipv4/tcp_fastopen.c | 8 +++----- net/ipv4/tcp_input.c | 33 ++++++++++++--------------------- net/sched/sch_netem.c | 14 ++++---------- 4 files changed, 37 insertions(+), 36 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 01a9859378679..03634ec2f9181 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3158,6 +3158,12 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) return __skb_grow(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) +#define skb_rb_first(root) rb_to_skb(rb_first(root)) +#define skb_rb_last(root) rb_to_skb(rb_last(root)) +#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) +#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -3172,6 +3178,18 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) +#define skb_rbtree_walk(skb, root) \ + for (skb = skb_rb_first(root); skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from(skb) \ + for (; skb != NULL; \ + skb = skb_rb_next(skb)) + +#define skb_rbtree_walk_from_safe(skb, tmp) \ + for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ + skb = tmp) + #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 29fff14d5a53d..7ee4aadcdd711 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -465,17 +465,15 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node *p; - struct sk_buff *skb; struct dst_entry *dst; + struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { - p = rb_first(&tp->out_of_order_queue); - if (p && !rb_next(p)) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); + if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fb0d7ed84b941..90afe41435966 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4335,7 +4335,7 @@ static void tcp_ofo_queue(struct sock *sk) p = rb_first(&tp->out_of_order_queue); while (p) { - skb = rb_entry(p, struct sk_buff, rbnode); + skb = rb_to_skb(p); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4399,7 +4399,7 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct rb_node **p, *q, *parent; + struct rb_node **p, *parent; struct sk_buff *skb1; u32 seq, end_seq; bool fragstolen; @@ -4458,7 +4458,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) parent = NULL; while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(seq, TCP_SKB_CB(skb1)->seq)) { p = &parent->rb_left; continue; @@ -4503,9 +4503,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) merge_right: /* Remove other segments covered by skb. */ - while ((q = rb_next(&skb->rbnode)) != NULL) { - skb1 = rb_entry(q, struct sk_buff, rbnode); - + while ((skb1 = skb_rb_next(skb)) != NULL) { if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { @@ -4520,7 +4518,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tcp_drop(sk, skb1); } /* If there is no skb after us, we are the last_skb ! */ - if (!q) + if (!skb1) tp->ooo_last_skb = skb; add_sack: @@ -4706,7 +4704,7 @@ static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *li if (list) return !skb_queue_is_last(list, skb) ? skb->next : NULL; - return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); + return skb_rb_next(skb); } static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, @@ -4735,7 +4733,7 @@ static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) while (*p) { parent = *p; - skb1 = rb_entry(parent, struct sk_buff, rbnode); + skb1 = rb_to_skb(parent); if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) p = &parent->rb_left; else @@ -4854,26 +4852,19 @@ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *head; - struct rb_node *p; u32 start, end; - p = rb_first(&tp->out_of_order_queue); - skb = rb_entry_safe(p, struct sk_buff, rbnode); + skb = skb_rb_first(&tp->out_of_order_queue); new_range: if (!skb) { - p = rb_last(&tp->out_of_order_queue); - /* Note: This is possible p is NULL here. We do not - * use rb_entry_safe(), as ooo_last_skb is valid only - * if rbtree is not empty. - */ - tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); + tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue); return; } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; for (head = skb;;) { - skb = tcp_skb_next(skb, NULL); + skb = skb_rb_next(skb); /* Range is terminated when we see a gap or when * we are at the queue end. @@ -4916,14 +4907,14 @@ static bool tcp_prune_ofo_queue(struct sock *sk) do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode)); + tcp_drop(sk, rb_to_skb(node)); sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; node = prev; } while (node); - tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); + tp->ooo_last_skb = rb_to_skb(prev); /* Reset SACK state. A conforming SACK implementation will * do the same at a timeout based retransmit. When a connection diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 5a4f100802906..db0228a65e8c5 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -148,12 +148,6 @@ struct netem_skb_cb { psched_time_t time_to_send; }; - -static struct sk_buff *netem_rb_to_skb(struct rb_node *rb) -{ - return rb_entry(rb, struct sk_buff, rbnode); -} - static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ @@ -364,7 +358,7 @@ static void tfifo_reset(struct Qdisc *sch) struct rb_node *p = rb_first(&q->t_root); while (p) { - struct sk_buff *skb = netem_rb_to_skb(p); + struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &q->t_root); @@ -382,7 +376,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) struct sk_buff *skb; parent = *p; - skb = netem_rb_to_skb(parent); + skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else @@ -538,7 +532,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *t_skb; struct netem_skb_cb *t_last; - t_skb = netem_rb_to_skb(rb_last(&q->t_root)); + t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) { @@ -617,7 +611,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (p) { psched_time_t time_to_send; - skb = netem_rb_to_skb(p); + skb = rb_to_skb(p); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; -- GitLab From ac3f09ba3e496bd7cc780ead05b1d1bb5f33aedb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:22 -0700 Subject: [PATCH 1060/1507] tcp: uninline tcp_write_queue_purge() Since the upcoming rtx rbtree will add some extra code, it is time to not inline this fat function anymore. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 15 +-------------- net/ipv4/tcp.c | 14 ++++++++++++++ 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 3b16f353b539a..744559b727847 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1606,20 +1606,7 @@ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) skb->_skb_refdst = _save; \ } -/* write queue abstraction */ -static inline void tcp_write_queue_purge(struct sock *sk) -{ - struct sk_buff *skb; - - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { - tcp_skb_tsorted_anchor_cleanup(skb); - sk_wmem_free_skb(sk, skb); - } - INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); - sk_mem_reclaim(sk); - tcp_clear_all_retrans_hints(tcp_sk(sk)); -} +void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8cf742fd4f99d..f8ebae62f834c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2318,6 +2318,20 @@ static inline bool tcp_need_reset(int state) TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } +void tcp_write_queue_purge(struct sock *sk) +{ + struct sk_buff *skb; + + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { + tcp_skb_tsorted_anchor_cleanup(skb); + sk_wmem_free_skb(sk, skb); + } + INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); + sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); +} + int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); -- GitLab From 4e8cc22803080853a33bafc6748e133448fb8182 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:23 -0700 Subject: [PATCH 1061/1507] tcp: tcp_tx_timestamp() cleanup tcp_write_queue_tail() call can be factorized. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f8ebae62f834c..b8d379c809366 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -469,8 +469,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op) tcp_init_buffer_space(sk); } -static void tcp_tx_timestamp(struct sock *sk, u16 tsflags, struct sk_buff *skb) +static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) { + struct sk_buff *skb = tcp_write_queue_tail(sk); + if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -1041,7 +1043,7 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, out: if (copied) { - tcp_tx_timestamp(sk, sk->sk_tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sk->sk_tsflags); if (!(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } @@ -1418,7 +1420,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) out: if (copied) { - tcp_tx_timestamp(sk, sockc.tsflags, tcp_write_queue_tail(sk)); + tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: -- GitLab From 5e76ee4b8e90384936a214cde5b7816424f70232 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:24 -0700 Subject: [PATCH 1062/1507] tcp: tcp_mark_head_lost() optimization It will be a bit more expensive to get the head of rtx queue once rtx queue is converted to an rb-tree. We can avoid this extra cost in case tp->lost_skb_hint is set. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 90afe41435966..abc3b1db81f85 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2207,12 +2207,12 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; WARN_ON(packets > tp->packets_out); - if (tp->lost_skb_hint) { - skb = tp->lost_skb_hint; - cnt = tp->lost_cnt_hint; + skb = tp->lost_skb_hint; + if (skb) { /* Head already handled? */ - if (mark_head && skb != tcp_write_queue_head(sk)) + if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una)) return; + cnt = tp->lost_cnt_hint; } else { skb = tcp_write_queue_head(sk); cnt = 0; -- GitLab From 8ba6ddaaf86c4c6814774e4e4ef158b732bd9f9f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:25 -0700 Subject: [PATCH 1063/1507] tcp: reduce tcp_fastretrans_alert() verbosity With upcoming rb-tree implementation, the checks will trigger more often, and this is expected. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index abc3b1db81f85..be7644204cd44 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2804,9 +2804,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - if (WARN_ON(!tp->packets_out && tp->sacked_out)) + if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; - if (WARN_ON(!tp->sacked_out && tp->fackets_out)) + if (!tp->sacked_out && tp->fackets_out) tp->fackets_out = 0; /* Now state machine starts. -- GitLab From f33198163a0fbb03766444253edf6ea50685d725 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:26 -0700 Subject: [PATCH 1064/1507] tcp: pass previous skb to tcp_shifted_skb() No need to recompute previous skb, as it will be a bit more expensive when rtx queue is converted to RB tree. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index be7644204cd44..72c4732ae2da1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1288,13 +1288,13 @@ static u8 tcp_sacktag_one(struct sock *sk, /* Shift newly-SACKed bytes from this skb to the immediately previous * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. */ -static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, +static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, + struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, bool dup_sack) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *prev = tcp_write_queue_prev(sk, skb); u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ @@ -1495,7 +1495,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!skb_shift(prev, skb, len)) goto fallback; - if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) + if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack)) goto out; /* Hole filled allows collapsing with the next as well, this is very @@ -1514,7 +1514,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, len = skb->len; if (skb_shift(prev, skb, len)) { pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); + tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb), + len, mss, 0); } out: -- GitLab From 75c119afe14f74b4dd967d75ed9f57ab6c0ef045 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Oct 2017 22:21:27 -0700 Subject: [PATCH 1065/1507] tcp: implement rb-tree based retransmit queue Using a linear list to store all skbs in write queue has been okay for quite a while : O(N) is not too bad when N < 500. Things get messy when N is the order of 100,000 : Modern TCP stacks want 10Gbit+ of throughput even with 200 ms RTT flows. 40 ns per cache line miss means a full scan can use 4 ms, blowing away CPU caches. SACK processing often can use various hints to avoid parsing whole retransmit queue. But with high packet losses and/or high reordering, hints no longer work. Sender has to process thousands of unfriendly SACK, accumulating a huge socket backlog, burning a cpu and massively dropping packets. Using an rb-tree for retransmit queue has been avoided for years because it added complexity and overhead, but now is the time to be more resistant and say no to quadratic behavior. 1) RTX queue is no longer part of the write queue : already sent skbs are stored in one rb-tree. 2) Since reaching the head of write queue no longer needs sk->sk_send_head, we added an union of sk_send_head and tcp_rtx_queue Tested: On receiver : netem on ingress : delay 150ms 200us loss 1 GRO disabled to force stress and SACK storms. for f in `seq 1 10` do ./netperf -H lpaa6 -l30 -- -K bbr -o THROUGHPUT|tail -1 done | awk '{print $0} {sum += $0} END {printf "%7u\n",sum}' Before patch : 323.87 351.48 339.59 338.62 306.72 204.07 304.93 291.88 202.47 176.88 2840 After patch: 1700.83 2207.98 2070.17 1544.26 2114.76 2124.89 1693.14 1080.91 2216.82 1299.94 18053 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 7 ++- include/net/tcp.h | 89 ++++++++++++++------------- net/ipv4/tcp.c | 41 ++++++++++--- net/ipv4/tcp_input.c | 133 +++++++++++++++++++++------------------- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_output.c | 137 +++++++++++++++++++++++------------------- net/ipv4/tcp_timer.c | 24 +++++--- 7 files changed, 245 insertions(+), 188 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index a6b9a8d1a6df3..4827094f1db44 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -60,7 +60,7 @@ #include #include #include - +#include #include #include #include @@ -397,7 +397,10 @@ struct sock { int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; - struct sk_buff *sk_send_head; + union { + struct sk_buff *sk_send_head; + struct rb_root tcp_rtx_queue; + }; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; diff --git a/include/net/tcp.h b/include/net/tcp.h index 744559b727847..5a95e5886b55e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -551,7 +551,13 @@ void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); -int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t); +enum tcp_queue { + TCP_FRAG_IN_WRITE_QUEUE, + TCP_FRAG_IN_RTX_QUEUE, +}; +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, + unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); @@ -1608,6 +1614,11 @@ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) void tcp_write_queue_purge(struct sock *sk); +static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) +{ + return skb_rb_first(&sk->tcp_rtx_queue); +} + static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); @@ -1630,18 +1641,12 @@ static inline struct sk_buff *tcp_write_queue_prev(const struct sock *sk, return skb_queue_prev(&sk->sk_write_queue, skb); } -#define tcp_for_write_queue(skb, sk) \ - skb_queue_walk(&(sk)->sk_write_queue, skb) - -#define tcp_for_write_queue_from(skb, sk) \ - skb_queue_walk_from(&(sk)->sk_write_queue, skb) - #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { - return sk->sk_send_head; + return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, @@ -1650,29 +1655,30 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } -static inline void tcp_advance_send_head(struct sock *sk, const struct sk_buff *skb) +static inline bool tcp_write_queue_empty(const struct sock *sk) { - if (tcp_skb_is_last(sk, skb)) - sk->sk_send_head = NULL; - else - sk->sk_send_head = tcp_write_queue_next(sk, skb); + return skb_queue_empty(&sk->sk_write_queue); +} + +static inline bool tcp_rtx_queue_empty(const struct sock *sk) +{ + return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); +} + +static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) +{ + return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked) { - if (sk->sk_send_head == skb_unlinked) { - sk->sk_send_head = NULL; + if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - } + if (tcp_sk(sk)->highest_sack == skb_unlinked) tcp_sk(sk)->highest_sack = NULL; } -static inline void tcp_init_send_head(struct sock *sk) -{ - sk->sk_send_head = NULL; -} - static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); @@ -1683,8 +1689,7 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb __tcp_add_write_queue_tail(sk, skb); /* Queue it, remembering where we must start sending. */ - if (sk->sk_send_head == NULL) { - sk->sk_send_head = skb; + if (sk->sk_write_queue.next == skb) { tcp_chrono_start(sk, TCP_CHRONO_BUSY); if (tcp_sk(sk)->highest_sack == NULL) @@ -1697,35 +1702,32 @@ static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *s __skb_queue_head(&sk->sk_write_queue, skb); } -/* Insert buff after skb on the write queue of sk. */ -static inline void tcp_insert_write_queue_after(struct sk_buff *skb, - struct sk_buff *buff, - struct sock *sk) -{ - __skb_queue_after(&sk->sk_write_queue, skb, buff); -} - /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); - - if (sk->sk_send_head == skb) - sk->sk_send_head = new; } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { - list_del(&skb->tcp_tsorted_anchor); - tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } -static inline bool tcp_write_queue_empty(struct sock *sk) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); + +static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + tcp_skb_tsorted_anchor_cleanup(skb); + rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); +} + +static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) +{ + list_del(&skb->tcp_tsorted_anchor); + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) @@ -1754,8 +1756,9 @@ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { - tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL : - tcp_write_queue_next(sk, skb); + struct sk_buff *next = skb_rb_next(skb); + + tcp_sk(sk)->highest_sack = next ?: tcp_send_head(sk); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) @@ -1765,7 +1768,9 @@ static inline struct sk_buff *tcp_highest_sack(struct sock *sk) static inline void tcp_highest_sack_reset(struct sock *sk) { - tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk); + struct sk_buff *skb = tcp_rtx_queue_head(sk); + + tcp_sk(sk)->highest_sack = skb ?: tcp_send_head(sk); } /* Called when old skb is about to be deleted (to be combined with new skb) */ @@ -1935,7 +1940,7 @@ extern void tcp_rack_reo_timeout(struct sock *sk); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { - const struct sk_buff *skb = tcp_write_queue_head(sk); + const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; u64 rto_time_stamp_us = skb->skb_mstamp + jiffies_to_usecs(rto); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8d379c809366..3b34850d361fd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -413,6 +413,7 @@ void tcp_init_sock(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; + sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); @@ -701,10 +702,9 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - if (!tcp_send_head(sk)) - return; - skb = tcp_write_queue_tail(sk); + if (!skb) + return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); @@ -964,14 +964,14 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, int copy, i; bool can_coalesce; - if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0 || + if (!skb || (copy = size_goal - skb->len) <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, - skb_queue_empty(&sk->sk_write_queue)); + tcp_rtx_and_write_queues_empty(sk)); if (!skb) goto wait_for_memory; @@ -1199,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - skb = tcp_send_head(sk) ? tcp_write_queue_tail(sk) : NULL; + skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; @@ -1275,7 +1275,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int max = size_goal; skb = tcp_write_queue_tail(sk); - if (tcp_send_head(sk)) { + if (skb) { if (skb->ip_summed == CHECKSUM_NONE) max = mss_now; copy = max - skb->len; @@ -1295,7 +1295,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) process_backlog = false; goto restart; } - first_skb = skb_queue_empty(&sk->sk_write_queue); + first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, select_size(sk, sg, first_skb), sk->sk_allocation, @@ -1521,6 +1521,13 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) /* XXX -- need to support SO_PEEK_OFF */ + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { + err = skb_copy_datagram_msg(skb, 0, msg, skb->len); + if (err) + return err; + copied += skb->len; + } + skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -2320,6 +2327,22 @@ static inline bool tcp_need_reset(int state) TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } +static void tcp_rtx_queue_purge(struct sock *sk) +{ + struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + + while (p) { + struct sk_buff *skb = rb_to_skb(p); + + p = rb_next(p); + /* Since we are deleting whole queue, no need to + * list_del(&skb->tcp_tsorted_anchor) + */ + tcp_rtx_queue_unlink(skb, sk); + sk_wmem_free_skb(sk, skb); + } +} + void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; @@ -2329,6 +2352,7 @@ void tcp_write_queue_purge(struct sock *sk) tcp_skb_tsorted_anchor_cleanup(skb); sk_wmem_free_skb(sk, skb); } + tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); @@ -2392,7 +2416,6 @@ int tcp_disconnect(struct sock *sk, int flags) * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; - tcp_init_send_head(sk); memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(sk->sk_rx_dst); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 72c4732ae2da1..d0682ce2a5d67 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1142,6 +1142,7 @@ struct tcp_sacktag_state { u64 last_sackt; struct rate_sample *rate; int flag; + unsigned int mss_now; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1191,7 +1192,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, if (pkt_len >= skb->len && !in_sack) return 0; - err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC); + err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + pkt_len, mss, GFP_ATOMIC); if (err < 0) return err; } @@ -1363,8 +1365,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + tcp_rtx_queue_unlink_and_free(skb, sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED); @@ -1414,9 +1415,9 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, goto fallback; /* Can only happen with delayed DSACK + discard craziness */ - if (unlikely(skb == tcp_write_queue_head(sk))) + prev = skb_rb_prev(skb); + if (!prev) goto fallback; - prev = tcp_write_queue_prev(sk, skb); if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; @@ -1501,12 +1502,11 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, /* Hole filled allows collapsing with the next as well, this is very * useful when hole on every nth skb pattern happens */ - if (prev == tcp_write_queue_tail(sk)) + skb = skb_rb_next(prev); + if (!skb) goto out; - skb = tcp_write_queue_next(sk, prev); if (!skb_can_shift(skb) || - (skb == tcp_send_head(sk)) || ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || (mss != tcp_skb_seglen(skb))) goto out; @@ -1539,13 +1539,10 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *tmp; - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { int in_sack = 0; bool dup_sack = dup_sack_in; - if (skb == tcp_send_head(sk)) - break; - /* queue is in-order => we can short-circuit the walk early */ if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; @@ -1607,23 +1604,44 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, return skb; } -/* Avoid all extra work that is being done by sacktag while walking in - * a normal way - */ +static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk, + struct tcp_sacktag_state *state, + u32 seq) +{ + struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node; + struct sk_buff *skb; + int unack_bytes; + + while (*p) { + parent = *p; + skb = rb_to_skb(parent); + if (before(seq, TCP_SKB_CB(skb)->seq)) { + p = &parent->rb_left; + continue; + } + if (!before(seq, TCP_SKB_CB(skb)->end_seq)) { + p = &parent->rb_right; + continue; + } + + state->fack_count = 0; + unack_bytes = TCP_SKB_CB(skb)->seq - tcp_sk(sk)->snd_una; + if (state->mss_now && unack_bytes > 0) + state->fack_count = unack_bytes / state->mss_now; + + return skb; + } + return NULL; +} + static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, struct tcp_sacktag_state *state, u32 skip_to_seq) { - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) - break; + if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq)) + return skb; - state->fack_count += tcp_skb_pcount(skb); - } - return skb; + return tcp_sacktag_bsearch(sk, state, skip_to_seq); } static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, @@ -1745,8 +1763,9 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } } - skb = tcp_write_queue_head(sk); + state->mss_now = tcp_current_mss(sk); state->fack_count = 0; + skb = NULL; i = 0; if (!tp->sacked_out) { @@ -1970,7 +1989,7 @@ void tcp_enter_loss(struct sock *sk) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); if (is_reneg) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); @@ -1979,10 +1998,7 @@ void tcp_enter_loss(struct sock *sk) } tcp_clear_all_retrans_hints(tp); - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - + skb_rbtree_walk_from(skb) { mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || is_reneg); if (mark_lost) @@ -2215,13 +2231,11 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) return; cnt = tp->lost_cnt_hint; } else { - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); cnt = 0; } - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk_from(skb) { /* TODO: do this better */ /* this is not the most efficient way to do this... */ tp->lost_skb_hint = skb; @@ -2245,7 +2259,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) /* If needed, chop off the prefix to mark as lost. */ lost = (packets - oldcnt) * mss; if (lost < skb->len && - tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) + tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2329,7 +2344,7 @@ static bool tcp_any_retrans_done(const struct sock *sk) if (tp->retrans_out) return true; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS)) return true; @@ -2370,9 +2385,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) if (unmark_loss) { struct sk_buff *skb; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; } tp->lost_out = 0; @@ -2617,9 +2630,7 @@ void tcp_simple_retransmit(struct sock *sk) unsigned int mss = tcp_current_mss(sk); u32 prior_lost = tp->lost_out; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; + skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { if (tcp_skb_seglen(skb) > mss && !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { @@ -2713,7 +2724,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, * is updated in tcp_ack()). Otherwise fall back to * the conventional recovery. */ - if (tcp_send_head(sk) && + if (!tcp_write_queue_empty(sk) && after(tcp_wnd_end(tp), tp->snd_nxt)) { *rexmit = REXMIT_NEW; return; @@ -3077,11 +3088,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sock *tp = tcp_sk(sk); u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; + struct sk_buff *skb, *next; bool fully_acked = true; long sack_rtt_us = -1L; long seq_rtt_us = -1L; long ca_rtt_us = -1L; - struct sk_buff *skb; u32 pkts_acked = 0; u32 last_in_flight = 0; bool rtt_update; @@ -3089,7 +3100,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, first_ackt = 0; - while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { + for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u8 sacked = scb->sacked; u32 acked_pcount; @@ -3107,8 +3118,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, break; fully_acked = false; } else { - /* Speedup tcp_unlink_write_queue() and next loop */ - prefetchw(skb->next); acked_pcount = tcp_skb_pcount(skb); } @@ -3160,12 +3169,12 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (!fully_acked) break; - tcp_unlink_write_queue(skb, sk); - sk_wmem_free_skb(sk, skb); + next = skb_rb_next(skb); if (unlikely(skb == tp->retransmit_skb_hint)) tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_rtx_queue_unlink_and_free(skb, sk); } if (!skb) @@ -3257,12 +3266,14 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, static void tcp_ack_probe(struct sock *sk) { - const struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *head = tcp_send_head(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Was it a usable window open? */ - - if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) { + if (!head) + return; + if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). @@ -3382,7 +3393,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); - if (tcp_send_head(sk)) + if (!tcp_write_queue_empty(sk)) tcp_slow_start_after_idle_check(sk); if (nwin > tp->max_window) { @@ -3567,8 +3578,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) sack_state.first_sackt = 0; sack_state.rate = &rs; - /* We very likely will need to access write queue head. */ - prefetchw(sk->sk_write_queue.next); + /* We very likely will need to access rtx queue. */ + prefetch(sk->tcp_rtx_queue.rb_node); /* If the ack is older than previous acks * then we can probably ignore it. @@ -3682,8 +3693,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. */ - if (tcp_send_head(sk)) - tcp_ack_probe(sk); + tcp_ack_probe(sk); if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -4726,7 +4736,7 @@ static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, } /* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ -static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -5530,7 +5540,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, struct tcp_fastopen_cookie *cookie) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; + struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL; u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; bool syn_drop = false; @@ -5565,9 +5575,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ - tcp_for_write_queue_from(data, sk) { - if (data == tcp_send_head(sk) || - __tcp_retransmit_skb(sk, data, 1)) + skb_rbtree_walk_from(data) { + if (__tcp_retransmit_skb(sk, data, 1)) break; } tcp_rearm_rto(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c7460fd90884c..5418ecf03b787 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -480,7 +480,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); BUG_ON(!skb); tcp_mstamp_refresh(tp); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8162e28801784..696b0a168f160 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -66,15 +66,17 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ -static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) +static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + __skb_unlink(skb, &sk->sk_write_queue); + tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -1249,12 +1251,25 @@ static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) TCP_SKB_CB(skb)->eor = 0; } +/* Insert buff after skb on the write or rtx queue of sk. */ +static void tcp_insert_write_queue_after(struct sk_buff *skb, + struct sk_buff *buff, + struct sock *sk, + enum tcp_queue tcp_queue) +{ + if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) + __skb_queue_after(&sk->sk_write_queue, skb, buff); + else + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); +} + /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ -int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, +int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); @@ -1337,7 +1352,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; @@ -1625,10 +1640,10 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) - * 3) no more data to send (null tcp_send_head ) + * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ - if (!tcp_send_head(sk) && sk->sk_socket && + if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); @@ -1824,7 +1839,8 @@ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ -static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, +static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, + struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; @@ -1833,7 +1849,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) - return tcp_fragment(sk, skb, len, mss_now, gfp); + return tcp_fragment(sk, tcp_queue, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) @@ -1869,7 +1885,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, /* Link BUFF into the send queue. */ __skb_header_release(buff); - tcp_insert_write_queue_after(skb, buff, sk); + tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); return 0; } @@ -1939,8 +1955,10 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, goto send_now; } - head = tcp_write_queue_head(sk); - + /* TODO : use tsorted_sent_queue ? */ + head = tcp_rtx_queue_head(sk); + if (!head) + goto send_now; age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) @@ -2158,13 +2176,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send the 1st or 2nd skb in write queue. + /* Always send skb if rtx queue is empty. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (skb == sk->sk_write_queue.next || - skb->prev == sk->sk_write_queue.next) + if (tcp_rtx_queue_empty(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2215,7 +2232,7 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ - if (tcp_write_queue_empty(sk)) + if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); @@ -2310,7 +2327,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, nonagle); if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) + unlikely(tso_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, limit, mss_now, gfp))) break; if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) @@ -2350,7 +2368,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return !tp->packets_out && tcp_send_head(sk); + return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2374,7 +2392,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) return false; if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && - tcp_send_head(sk)) + !tcp_write_queue_empty(sk)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account @@ -2427,18 +2445,14 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); skb = tcp_send_head(sk); - if (skb) { - if (tcp_snd_wnd_test(tp, skb, mss)) { - pcount = tp->packets_out; - tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - if (tp->packets_out > pcount) - goto probe_sent; - goto rearm_timer; - } - skb = tcp_write_queue_prev(sk, skb); - } else { - skb = tcp_write_queue_tail(sk); + if (skb && tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; } + skb = skb_rb_last(&sk->tcp_rtx_queue); /* At most one outstanding TLP retransmission. */ if (tp->tlp_high_seq) @@ -2456,10 +2470,11 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { - if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, + if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_next(sk, skb); + skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) @@ -2659,7 +2674,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb, static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); + struct sk_buff *next_skb = skb_rb_next(skb); int skb_size, next_skb_size; skb_size = skb->len; @@ -2676,8 +2691,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_combine(sk, next_skb, skb); - tcp_unlink_write_queue(next_skb, sk); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; @@ -2705,7 +2718,7 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) tcp_skb_collapse_tstamp(skb, next_skb); - sk_wmem_free_skb(sk, next_skb); + tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } @@ -2716,8 +2729,6 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; - if (skb == tcp_send_head(sk)) - return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -2740,7 +2751,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; - tcp_for_write_queue_from_safe(skb, tmp, sk) { + skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; @@ -2815,7 +2826,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) len = cur_mss * segs; if (skb->len > len) { - if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, + cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) @@ -2906,29 +2918,24 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb, *rtx_head = NULL, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - struct sk_buff *hole = NULL; u32 max_segs; int mib_idx; if (!tp->packets_out) return; - if (tp->retransmit_skb_hint) { - skb = tp->retransmit_skb_hint; - } else { - skb = tcp_write_queue_head(sk); + skb = tp->retransmit_skb_hint; + if (!skb) { + rtx_head = tcp_rtx_queue_head(sk); + skb = rtx_head; } - max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); - tcp_for_write_queue_from(skb, sk) { + skb_rbtree_walk_from(skb) { __u8 sacked; int segs; - if (skb == tcp_send_head(sk)) - break; - if (tcp_pacing_check(sk)) break; @@ -2973,7 +2980,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); - if (skb == tcp_write_queue_head(sk) && + if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, @@ -3015,12 +3022,15 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ - if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { + if (!tskb && tcp_under_memory_pressure(sk)) + tskb = skb_rb_last(&sk->tcp_rtx_queue); + + if (tskb) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (!tcp_send_head(sk)) { + if (tcp_write_queue_empty(sk)) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have @@ -3086,9 +3096,9 @@ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; - skb = tcp_write_queue_head(sk); + skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { - pr_debug("%s: wrong queue state\n", __func__); + pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { @@ -3101,10 +3111,9 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); - tcp_unlink_write_queue(skb, sk); + tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); - __tcp_add_write_queue_head(sk, nskb); - sk_wmem_free_skb(sk, skb); + tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; @@ -3327,7 +3336,6 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - __tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); tp->write_seq = tcb->end_seq; @@ -3405,12 +3413,13 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); + tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } - /* data was not sent, this is our new send_head */ - sk->sk_send_head = syn_data; + /* data was not sent, put it in write_queue */ + __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: @@ -3453,6 +3462,7 @@ int tcp_connect(struct sock *sk) tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); + tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : @@ -3647,7 +3657,8 @@ int tcp_write_wakeup(struct sock *sk, int mib) skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; - if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) + if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, + skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); @@ -3677,7 +3688,7 @@ void tcp_send_probe0(struct sock *sk) err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 655dd8d7f064f..7014cc00c74c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -156,8 +156,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (unlikely(!start_ts)) - start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); + if (unlikely(!start_ts)) { + struct sk_buff *head = tcp_rtx_queue_head(sk); + + if (!head) + return false; + start_ts = tcp_skb_timestamp(head); + } if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); @@ -304,11 +309,12 @@ static void tcp_delack_timer(unsigned long data) static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; u32 start_ts; - if (tp->packets_out || !tcp_send_head(sk)) { + if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; return; } @@ -321,9 +327,9 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + start_ts = tcp_skb_timestamp(skb); if (!start_ts) - tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > jiffies_to_msecs(icsk->icsk_user_timeout)) @@ -408,7 +414,7 @@ void tcp_retransmit_timer(struct sock *sk) if (!tp->packets_out) goto out; - WARN_ON(tcp_write_queue_empty(sk)); + WARN_ON(tcp_rtx_queue_empty(sk)); tp->tlp_high_seq = 0; @@ -441,7 +447,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1); + tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); __sk_dst_reset(sk); goto out_reset_timer; } @@ -473,7 +479,7 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); - if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) { + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * do not backoff. */ @@ -647,7 +653,7 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ - if (tp->packets_out || tcp_send_head(sk)) + if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); -- GitLab From 0d7b70e83642f01c451a52faa3908e7b054ff7c6 Mon Sep 17 00:00:00 2001 From: Jonathan Toppins Date: Fri, 6 Oct 2017 15:48:30 -0400 Subject: [PATCH 1066/1507] bnxt_en: don't consider building bnxt_tc.o if option not enabled Instead of zeroing out bnxt_tc.c with a #ifdef foo, instead don't compile the file when the option is not enabled. Now make and the preprocessor do not have to waste time compiling a no-op. Signed-off-by: Jonathan Toppins Acked-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/Makefile | 3 ++- drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 5 ----- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index 4f0cb8e1ffc07..457201f409a71 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_BNXT) += bnxt_en.o -bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o +bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o +bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 7dd3d131043a7..4730c048ed9bd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -23,8 +23,6 @@ #include "bnxt_tc.h" #include "bnxt_vfr.h" -#ifdef CONFIG_BNXT_FLOWER_OFFLOAD - #define BNXT_FID_INVALID 0xffff #define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT)) @@ -833,6 +831,3 @@ void bnxt_shutdown_tc(struct bnxt *bp) rhashtable_destroy(&tc_info->flow_table); rhashtable_destroy(&tc_info->l2_table); } - -#else -#endif -- GitLab From 180ca444b985c42948fa26abd278e616b5ce7eb2 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:05:56 -0700 Subject: [PATCH 1067/1507] ipv6: introduce a new function fib6_update_sernum() This function takes a route as input and tries to update the sernum in the fib6_node this route is associated with. It will be used in later commit when adding a cached route into the exception table under that route. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 ++ net/ipv6/ip6_fib.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index d060d711a6245..152b7b14a5a53 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -358,6 +358,8 @@ void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb); +void fib6_update_sernum(struct rt6_info *rt); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); void fib6_rules_cleanup(void); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e5308d7cbd75c..0ba4fbb2f8555 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -110,6 +110,20 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; +void fib6_update_sernum(struct rt6_info *rt) +{ + struct fib6_table *table = rt->rt6i_table; + struct net *net = dev_net(rt->dst.dev); + struct fib6_node *fn; + + write_lock_bh(&table->tb6_lock); + fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&table->tb6_lock)); + if (fn) + fn->fn_sernum = fib6_new_sernum(net); + write_unlock_bh(&table->tb6_lock); +} + /* * Auxiliary address test functions for the radix tree. * -- GitLab From 35732d01fe311ec13c4e42936878b782b8e7ea85 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:05:57 -0700 Subject: [PATCH 1068/1507] ipv6: introduce a hash table to store dst cache Add a hash table into struct rt6_info in order to store dst caches created by pmtu discovery and ip redirect in ipv6 routing code. APIs to add dst cache, delete dst cache, find dst cache and update dst cache in the hash table are implemented and will be used in later commits. This is a preparation work to move all cache routes into the exception table instead of getting inserted into the fib6 tree. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 19 +++ include/net/ip6_route.h | 3 + net/ipv6/route.c | 341 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 363 insertions(+) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 152b7b14a5a53..c4864c1e8f136 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -98,6 +98,22 @@ struct rt6key { struct fib6_table; +struct rt6_exception_bucket { + struct hlist_head chain; + int depth; +}; + +struct rt6_exception { + struct hlist_node hlist; + struct rt6_info *rt6i; + unsigned long stamp; + struct rcu_head rcu; +}; + +#define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 +#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) +#define FIB6_MAX_DEPTH 5 + struct rt6_info { struct dst_entry dst; @@ -134,12 +150,15 @@ struct rt6_info { struct inet6_dev *rt6i_idev; struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; u32 rt6i_metric; u32 rt6i_pmtu; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; u8 rt6i_protocol; + u8 exception_bucket_flushed:1, + unused:7; }; static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index ee96f402cb75a..3315605f34c97 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -95,6 +95,9 @@ int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); +void rt6_flush_exceptions(struct rt6_info *rt); +int rt6_remove_exception_rt(struct rt6_info *rt); + static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, const struct in6_addr *daddr, unsigned int prefs, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 26cc9f483b6d2..dc5e709759664 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include @@ -104,6 +105,9 @@ static int rt6_fill_node(struct net *net, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -392,6 +396,7 @@ EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; + struct rt6_exception_bucket *bucket; struct dst_entry *from = dst->from; struct inet6_dev *idev; @@ -404,6 +409,11 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); + if (bucket) { + rt->rt6i_exception_bucket = NULL; + kfree(bucket); + } dst->from = NULL; dst_release(from); @@ -1091,6 +1101,337 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) return pcpu_rt; } +/* exception hash table implementation + */ +static DEFINE_SPINLOCK(rt6_exception_lock); + +/* Remove rt6_ex from hash table and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_remove_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex) +{ + if (!bucket || !rt6_ex) + return; + rt6_ex->rt6i->rt6i_node = NULL; + hlist_del_rcu(&rt6_ex->hlist); + rt6_release(rt6_ex->rt6i); + kfree_rcu(rt6_ex, rcu); + WARN_ON_ONCE(!bucket->depth); + bucket->depth--; +} + +/* Remove oldest rt6_ex in bucket and free the memory + * Caller must hold rt6_exception_lock + */ +static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) +{ + struct rt6_exception *rt6_ex, *oldest = NULL; + + if (!bucket) + return; + + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) + oldest = rt6_ex; + } + rt6_remove_exception(bucket, oldest); +} + +static u32 rt6_exception_hash(const struct in6_addr *dst, + const struct in6_addr *src) +{ + static u32 seed __read_mostly; + u32 val; + + net_get_random_once(&seed, sizeof(seed)); + val = jhash(dst, sizeof(*dst), seed); + +#ifdef CONFIG_IPV6_SUBTREES + if (src) + val = jhash(src, sizeof(*src), val); +#endif + return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rt6_exception_lock + */ +static struct rt6_exception * +__rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +/* Helper function to find the cached rt in the hash table + * and update bucket pointer to point to the bucket for this + * (daddr, saddr) pair + * Caller must hold rcu_read_lock() + */ +static struct rt6_exception * +__rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, + const struct in6_addr *daddr, + const struct in6_addr *saddr) +{ + struct rt6_exception *rt6_ex; + u32 hval; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!(*bucket) || !daddr) + return NULL; + + hval = rt6_exception_hash(daddr, saddr); + *bucket += hval; + + hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { + struct rt6_info *rt6 = rt6_ex->rt6i; + bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); + +#ifdef CONFIG_IPV6_SUBTREES + if (matched && saddr) + matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); +#endif + if (matched) + return rt6_ex; + } + return NULL; +} + +static int rt6_insert_exception(struct rt6_info *nrt, + struct rt6_info *ort) +{ + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err = 0; + + /* ort can't be a cache or pcpu route */ + if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) + ort = (struct rt6_info *)ort->dst.from; + WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); + + spin_lock_bh(&rt6_exception_lock); + + if (ort->exception_bucket_flushed) { + err = -EINVAL; + goto out; + } + + bucket = rcu_dereference_protected(ort->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) { + bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), + GFP_ATOMIC); + if (!bucket) { + err = -ENOMEM; + goto out; + } + rcu_assign_pointer(ort->rt6i_exception_bucket, bucket); + } + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates ort is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (ort->rt6i_src.plen) + src_key = &nrt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_remove_exception(bucket, rt6_ex); + + rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); + if (!rt6_ex) { + err = -ENOMEM; + goto out; + } + rt6_ex->rt6i = nrt; + rt6_ex->stamp = jiffies; + atomic_inc(&nrt->rt6i_ref); + nrt->rt6i_node = ort->rt6i_node; + hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); + bucket->depth++; + + if (bucket->depth > FIB6_MAX_DEPTH) + rt6_exception_remove_oldest(bucket); + +out: + spin_unlock_bh(&rt6_exception_lock); + + /* Update fn->fn_sernum to invalidate all cached dst */ + if (!err) + fib6_update_sernum(ort); + + return err; +} + +void rt6_flush_exceptions(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + spin_lock_bh(&rt6_exception_lock); + /* Prevent rt6_insert_exception() to recreate the bucket list */ + rt->exception_bucket_flushed = 1; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + if (!bucket) + goto out; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) + rt6_remove_exception(bucket, rt6_ex); + WARN_ON_ONCE(bucket->depth); + bucket++; + } + +out: + spin_unlock_bh(&rt6_exception_lock); +} + +/* Find cached rt in the hash table inside passed in rt + * Caller has to hold rcu_read_lock() + */ +static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, + struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + struct rt6_info *res = NULL; + + bucket = rcu_dereference(rt->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates rt is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (rt->rt6i_src.plen) + src_key = saddr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); + + if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) + res = rt6_ex->rt6i; + + return res; +} + +/* Remove the passed in cached rt from the hash table that contains it */ +int rt6_remove_exception_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + int err; + + if (!from || + !(rt->rt6i_flags | RTF_CACHE)) + return -EINVAL; + + if (!rcu_access_pointer(from->rt6i_exception_bucket)) + return -ENOENT; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(from->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_spinlock(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) { + rt6_remove_exception(bucket, rt6_ex); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&rt6_exception_lock); + return err; +} + +/* Find rt6_ex which contains the passed in rt cache and + * refresh its stamp + */ +static void rt6_update_exception_stamp_rt(struct rt6_info *rt) +{ + struct rt6_info *from = (struct rt6_info *)rt->dst.from; + struct rt6_exception_bucket *bucket; + struct in6_addr *src_key = NULL; + struct rt6_exception *rt6_ex; + + if (!from || + !(rt->rt6i_flags | RTF_CACHE)) + return; + + rcu_read_lock(); + bucket = rcu_dereference(from->rt6i_exception_bucket); + +#ifdef CONFIG_IPV6_SUBTREES + /* rt6i_src.plen != 0 indicates 'from' is in subtree + * and exception table is indexed by a hash of + * both rt6i_dst and rt6i_src. + * Otherwise, the exception table is indexed by + * a hash of only rt6i_dst. + */ + if (from->rt6i_src.plen) + src_key = &rt->rt6i_src.addr; +#endif + rt6_ex = __rt6_find_exception_rcu(&bucket, + &rt->rt6i_dst.addr, + src_key); + if (rt6_ex) + rt6_ex->stamp = jiffies; + + rcu_read_unlock(); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { -- GitLab From 60006a4825f9e71adf770745e17790c6e6c97a89 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:05:58 -0700 Subject: [PATCH 1069/1507] ipv6: prepare fib6_remove_prefsrc() for exception table After we move cached dst entries into the exception table under its parent route, current fib6_remove_prefsrc() no longer can access them. This commit makes fib6_remove_prefsrc() also go through all routes in the exception table to remove the pref src. This is a preparation patch in order to move all cached dst into the exception table. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/route.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dc5e709759664..f52ac57dcc991 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1264,6 +1264,12 @@ static int rt6_insert_exception(struct rt6_info *nrt, if (ort->rt6i_src.plen) src_key = &nrt->rt6i_src.addr; #endif + + /* Update rt6i_prefsrc as it could be changed + * in rt6_remove_prefsrc() + */ + nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) @@ -1432,6 +1438,25 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } +static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + rt6_ex->rt6i->rt6i_prefsrc.plen = 0; + } + bucket++; + } + } +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { @@ -3159,8 +3184,12 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) if (((void *)rt->dst.dev == dev || !dev) && rt != net->ipv6.ip6_null_entry && ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->rt6i_prefsrc.plen = 0; + /* need to update cache as well */ + rt6_exceptions_remove_prefsrc(rt); + spin_unlock_bh(&rt6_exception_lock); } return 0; } -- GitLab From f5bbe7ee79c2842ca69f25afd0b6b65a9011b735 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:05:59 -0700 Subject: [PATCH 1070/1507] ipv6: prepare rt6_mtu_change() for exception table If we move all cached dst into the exception table under the main route, current rt6_mtu_change() will no longer be able to access them. This commit makes rt6_mtu_change_route() function to also go through all cached routes in the exception table under the main route and do proper updates on the mtu. This is a preparation in order to move all cached routes into the exception table. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/route.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f52ac57dcc991..d9805a857809c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1269,6 +1269,14 @@ static int rt6_insert_exception(struct rt6_info *nrt, * in rt6_remove_prefsrc() */ nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + /* rt6_mtu_change() might lower mtu on ort. + * Only insert this exception route if its mtu + * is less than ort's mtu value. + */ + if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + err = -EINVAL; + goto out; + } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); @@ -1457,6 +1465,32 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } +static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + int i; + + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) + entry->rt6i_pmtu = mtu; + } + bucket++; + } + } +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { @@ -3296,6 +3330,10 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) if (rt->dst.dev == arg->dev && dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { + spin_lock_bh(&rt6_exception_lock); + /* This case will be removed once the exception table + * is hooked up. + */ if (rt->rt6i_flags & RTF_CACHE) { /* For RTF_CACHE with rt6i_pmtu == 0 * (i.e. a redirected route), @@ -3309,6 +3347,8 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) dst_mtu(&rt->dst) == idev->cnf.mtu6)) { dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } + rt6_exceptions_update_pmtu(rt, arg->mtu); + spin_unlock_bh(&rt6_exception_lock); } return 0; } -- GitLab From b16cb459d77800dcb886b5e73e1beafd3d596897 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:00 -0700 Subject: [PATCH 1071/1507] ipv6: prepare rt6_clean_tohost() for exception table If we move all cached dst into the exception table under the main route, current rt6_clean_tohost() will no longer be able to access them. This commit makes fib6_clean_tohost() to also go through all cached routes in exception table and removes cached gateway routes to the passed in gateway. This is a preparation in order to move all cached routes into the exception table. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/route.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d9805a857809c..e8e9015895649 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1491,6 +1491,43 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) } } +#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) + +static void rt6_exceptions_clean_tohost(struct rt6_info *rt, + struct in6_addr *gateway) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == + RTF_CACHE_GATEWAY && + ipv6_addr_equal(gateway, + &entry->rt6i_gateway)) { + rt6_remove_exception(bucket, rt6_ex); + } + } + bucket++; + } + } + + spin_unlock_bh(&rt6_exception_lock); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { @@ -3240,18 +3277,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) -#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; + /* RTF_CACHE_GATEWAY case will be removed once the exception + * table is hooked up to store all cached routes. + */ if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } + + /* Further clean up cached routes in exception table. + * This is needed because cached route may have a different + * gateway than its 'parent' in the case of an ip redirect. + */ + rt6_exceptions_clean_tohost(rt, gateway); + return 0; } -- GitLab From c757faa8bfa26a0dd24b41ff783e0da042156887 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:01 -0700 Subject: [PATCH 1072/1507] ipv6: prepare fib6_age() for exception table If all dst cache entries are stored in the exception table under the main route, we have to go through them during fib6_age() when doing garbage collecting. Introduce a new function rt6_age_exception() which goes through all dst entries in the exception table and remove those entries that are expired. This function is called in fib6_age() so that all dst caches are also garbage collected. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 13 +++++++++ include/net/ip6_route.h | 2 ++ net/ipv6/ip6_fib.c | 26 +++++++----------- net/ipv6/route.c | 60 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 84 insertions(+), 17 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c4864c1e8f136..11a79ef87a283 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -29,6 +29,14 @@ #define FIB6_TABLE_HASHSZ 1 #endif +#define RT6_DEBUG 2 + +#if RT6_DEBUG >= 3 +#define RT6_TRACE(x...) pr_debug(x) +#else +#define RT6_TRACE(x...) do { ; } while (0) +#endif + struct rt6_info; struct fib6_config { @@ -75,6 +83,11 @@ struct fib6_node { struct rcu_head rcu; }; +struct fib6_gc_args { + int timeout; + int more; +}; + #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL #else diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 3315605f34c97..a0087fb9864bc 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -97,6 +97,8 @@ int ip6_del_rt(struct rt6_info *); void rt6_flush_exceptions(struct rt6_info *rt); int rt6_remove_exception_rt(struct rt6_info *rt); +void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args, + unsigned long now); static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, const struct in6_addr *daddr, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0ba4fbb2f8555..3afbe50f27797 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -38,14 +38,6 @@ #include #include -#define RT6_DEBUG 2 - -#if RT6_DEBUG >= 3 -#define RT6_TRACE(x...) pr_debug(x) -#else -#define RT6_TRACE(x...) do { ; } while (0) -#endif - static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { @@ -1890,12 +1882,6 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -struct fib6_gc_args -{ - int timeout; - int more; -}; - static int fib6_age(struct rt6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; @@ -1904,9 +1890,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) /* * check addrconf expiration here. * Routes are expired even if they are in use. - * - * Also age clones. Note, that clones are aged out - * only if they are not in use now. */ if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { @@ -1915,6 +1898,9 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } gc_args->more++; + /* The following part will soon be removed when the exception + * table is hooked up to store all cached routes. + */ } else if (rt->rt6i_flags & RTF_CACHE) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1940,6 +1926,12 @@ static int fib6_age(struct rt6_info *rt, void *arg) gc_args->more++; } + /* Also age clones in the exception table. + * Note, that clones are aged out + * only if they are not in use now. + */ + rt6_age_exceptions(rt, gc_args, now); + return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e8e9015895649..d2dd55f58b5d1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1528,6 +1528,66 @@ static void rt6_exceptions_clean_tohost(struct rt6_info *rt, spin_unlock_bh(&rt6_exception_lock); } +static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, + struct rt6_exception *rt6_ex, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_info *rt = rt6_ex->rt6i; + + if (atomic_read(&rt->dst.__refcnt) == 1 && + time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + RT6_TRACE("aging clone %p\n", rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (!(neigh_flags & NTF_ROUTER)) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + rt6_remove_exception(bucket, rt6_ex); + return; + } + } + gc_args->more++; +} + +void rt6_age_exceptions(struct rt6_info *rt, + struct fib6_gc_args *gc_args, + unsigned long now) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct hlist_node *tmp; + int i; + + if (!rcu_access_pointer(rt->rt6i_exception_bucket)) + return; + + spin_lock_bh(&rt6_exception_lock); + bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, + lockdep_is_held(&rt6_exception_lock)); + + if (bucket) { + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry_safe(rt6_ex, tmp, + &bucket->chain, hlist) { + rt6_age_examine_exception(bucket, rt6_ex, + gc_args, now); + } + bucket++; + } + } + spin_unlock_bh(&rt6_exception_lock); +} + struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { -- GitLab From 38fbeeeeccdb38d0635398e8e344d245f6d8dc52 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:02 -0700 Subject: [PATCH 1073/1507] ipv6: prepare fib6_locate() for exception table fib6_locate() is used to find the fib6_node according to the passed in prefix address key. It currently tries to find the fib6_node with the exact match of the passed in key. However, when we move cached routes into the exception table, fib6_locate() will fail to find the fib6_node for it as the cached routes will be stored in the exception table under the fib6_node with the longest prefix match of the cache's dst addr key. This commit adds a new parameter to let the caller specify if it needs exact match or longest prefix match. Right now, all callers still does exact match when calling fib6_locate(). It will be changed in later commit where exception table is hooked up to store cached routes. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- net/ipv6/addrconf.c | 2 +- net/ipv6/ip6_fib.c | 30 +++++++++++++++++++++++------- net/ipv6/route.c | 5 +++-- 4 files changed, 29 insertions(+), 11 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 11a79ef87a283..4497a1eb4d415 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -357,7 +357,8 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len); + const struct in6_addr *saddr, int src_len, + bool exact_match); void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), void *arg); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 837418ff2d4bf..3ccaf52824c96 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2322,7 +2322,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, return NULL; read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); + fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 3afbe50f27797..b3e4cf0962f81 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1343,14 +1343,21 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) + * exact_match == true means we try to find fn with exact match of + * the passed in prefix addr + * exact_match == false means we try to find fn with longest prefix + * match of the passed in prefix addr. This is useful for finding fn + * for cached route as it will be stored in the exception table under + * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, - int plen, int offset) + int plen, int offset, + bool exact_match) { - struct fib6_node *fn; + struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset); @@ -1360,11 +1367,13 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) - return NULL; + goto out; if (plen == fn->fn_bit) return fn; + prev = fn; + /* * We have more bits to go */ @@ -1373,24 +1382,31 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, else fn = fn->left; } - return NULL; +out: + if (exact_match) + return NULL; + else + return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) + const struct in6_addr *saddr, int src_len, + bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst)); + offsetof(struct rt6_info, rt6i_dst), + exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn && fn->subtree) fn = fib6_locate_1(fn->subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src)); + offsetof(struct rt6_info, rt6i_src), + exact_match); } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d2dd55f58b5d1..855b4ceec3497 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2800,7 +2800,8 @@ static int ip6_route_del(struct fib6_config *cfg, fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, - &cfg->fc_src, cfg->fc_src_len); + &cfg->fc_src, cfg->fc_src_len, + true); if (fn) { for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { @@ -3009,7 +3010,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, return NULL; read_lock_bh(&table->tb6_lock); - fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0); + fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; -- GitLab From 2b760fcf5cfb34e8610df56d83745b2b74ae1379 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:03 -0700 Subject: [PATCH 1074/1507] ipv6: hook up exception table to store dst cache This commit makes use of the exception hash table implementation to store dst caches created by pmtu discovery and ip redirect into the hash table under the rt_info and no longer inserts these routes into fib6 tree. This makes the fib6 tree only contain static configured routes and could now be protected by rcu instead of a rw lock. With this change, in the route lookup related functions, after finding the rt6_info with the longest prefix, we also need to search for the exception table before doing backtracking. In the route delete function, if the route being deleted is not a dst cache, deletion of this route also need to flush the whole hash table under it. If it is a dst cache, then only delete the cached dst in the hash table. Note: for fib6_walk_continue() function, w->root now is always pointing to a root node considering that fib6_prune_clones() is removed from the code. So we add a WARN_ON() msg to make sure w->root always points to a root node and also removed the update of w->root in fib6_repair_tree(). This is a prerequisite for later patch because we don't need to make w->root as rcu protected when replacing rwlock with RCU. Also, we remove all prune related variables as it is no longer used. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 - net/ipv6/addrconf.c | 1 - net/ipv6/ip6_fib.c | 95 +++++++------------------------------ net/ipv6/route.c | 108 +++++++++++++++++++++--------------------- 4 files changed, 72 insertions(+), 133 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4497a1eb4d415..d0b7283073e3c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -280,7 +280,6 @@ struct fib6_walker { struct fib6_node *root, *node; struct rt6_info *leaf; enum fib6_walk_state state; - bool prune; unsigned int skip; unsigned int count; int (*func)(struct fib6_walker *); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3ccaf52824c96..873afafddfc4c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2326,7 +2326,6 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (!fn) goto out; - noflags |= RTF_CACHE; for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (rt->dst.dev->ifindex != dev->ifindex) continue; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b3e4cf0962f81..9c8e704e6af7d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -54,7 +54,6 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn); static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); @@ -1101,6 +1100,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; + if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) + return -EINVAL; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1192,11 +1193,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, #endif err = fib6_add_rt2node(fn, rt, info, mxc); - if (!err) { + if (!err) fib6_start_gc(info->nl_net, rt); - if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn); - } out: if (err) { @@ -1511,19 +1509,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { - if (w->root == fn) { - w->root = w->node = NULL; - RT6_TRACE("W %p adjusted by delroot 1\n", w); - } else if (w->node == fn) { + if (w->node == fn) { RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { - if (w->root == fn) { - w->root = child; - RT6_TRACE("W %p adjusted by delroot 2\n", w); - } if (w->node == fn) { w->node = child; if (children&2) { @@ -1557,12 +1548,17 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, RT6_TRACE("fib6_del_route\n"); + WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); + /* Unlink it */ *rtp = rt->dst.rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; + /* Flush all cached dst in exception table */ + rt6_flush_exceptions(rt); + /* Reset round-robin state, if necessary */ if (fn->rr_ptr == rt) fn->rr_ptr = NULL; @@ -1625,18 +1621,9 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - if (!(rt->rt6i_flags & RTF_CACHE)) { - struct fib6_node *pn = fn; -#ifdef CONFIG_IPV6_SUBTREES - /* clones of this route might be in another subtree */ - if (rt->rt6i_src.plen) { - while (!(pn->fn_flags & RTN_ROOT)) - pn = pn->parent; - pn = pn->parent; - } -#endif - fib6_prune_clones(info->nl_net, pn); - } + /* remove cached dst from exception table */ + if (rt->rt6i_flags & RTF_CACHE) + return rt6_remove_exception_rt(rt); /* * Walk the leaf entries looking for ourself @@ -1679,16 +1666,14 @@ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn; + /* w->root should always be table->tb6_root */ + WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); + for (;;) { fn = w->node; if (!fn) return 0; - if (w->prune && fn != w->root && - fn->fn_flags & RTN_RTINFO && w->state < FWS_C) { - w->state = FWS_C; - w->leaf = fn->leaf; - } switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: @@ -1820,20 +1805,16 @@ static int fib6_clean_node(struct fib6_walker *w) * func is called on each route. * It may return -1 -> delete this route. * 0 -> continue walking - * - * prune==1 -> only immediate children of node (certainly, - * ignoring pure split nodes) will be scanned. */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct rt6_info *, void *arg), - bool prune, int sernum, void *arg) + int sernum, void *arg) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; - c.w.prune = prune; c.w.count = 0; c.w.skip = 0; c.func = func; @@ -1858,7 +1839,7 @@ static void __fib6_clean_all(struct net *net, hlist_for_each_entry_rcu(table, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, false, sernum, arg); + func, sernum, arg); write_unlock_bh(&table->tb6_lock); } } @@ -1871,22 +1852,6 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); } -static int fib6_prune_clone(struct rt6_info *rt, void *arg) -{ - if (rt->rt6i_flags & RTF_CACHE) { - RT6_TRACE("pruning clone %p\n", rt); - return -1; - } - - return 0; -} - -static void fib6_prune_clones(struct net *net, struct fib6_node *fn) -{ - fib6_clean_tree(net, fn, fib6_prune_clone, true, - FIB6_NO_SERNUM_CHANGE, NULL); -} - static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); @@ -1914,32 +1879,6 @@ static int fib6_age(struct rt6_info *rt, void *arg) return -1; } gc_args->more++; - /* The following part will soon be removed when the exception - * table is hooked up to store all cached routes. - */ - } else if (rt->rt6i_flags & RTF_CACHE) { - if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) - rt->dst.obsolete = DST_OBSOLETE_KILL; - if (atomic_read(&rt->dst.__refcnt) == 1 && - rt->dst.obsolete == DST_OBSOLETE_KILL) { - RT6_TRACE("aging clone %p\n", rt); - return -1; - } else if (rt->rt6i_flags & RTF_GATEWAY) { - struct neighbour *neigh; - __u8 neigh_flags = 0; - - neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); - if (neigh) { - neigh_flags = neigh->flags; - neigh_release(neigh); - } - if (!(neigh_flags & NTF_ROUTER)) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; - } - } - gc_args->more++; } /* Also age clones in the exception table. diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 855b4ceec3497..65130dde276a9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -878,8 +878,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, int flags) { + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; - struct rt6_info *rt; read_lock_bh(&table->tb6_lock); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); @@ -893,6 +893,11 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, if (fn) goto restart; } + /* Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; + dst_use(&rt->dst, jiffies); read_unlock_bh(&table->tb6_lock); @@ -1592,7 +1597,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -1624,6 +1629,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, } } + /*Search through exception table */ + rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); + if (rt_cache) + rt = rt_cache; if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { dst_use(&rt->dst, jiffies); @@ -1988,23 +1997,17 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); + /* update rt6_ex->stamp for cache */ + if (rt6->rt6i_flags & RTF_CACHE) + rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct rt6_info *nrt6; nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - - /* ip6_ins_rt(nrt6) will bump the - * rt6->rt6i_node->fn_sernum - * which will fail the next rt6_check() and - * invalidate the sk->sk_dst_cache. - */ - ip6_ins_rt(nrt6); - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt6->dst); + if (rt6_insert_exception(nrt6, rt6)) + dst_release_immediate(&nrt6->dst); } } } @@ -2068,7 +2071,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt; + struct rt6_info *rt, *rt_cache; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -2093,8 +2096,23 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, continue; if (fl6->flowi6_oif != rt->dst.dev->ifindex) continue; - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) + /* rt_cache's gateway might be different from its 'parent' + * in the case of an ip redirect. + * So we keep searching in the exception table if the gateway + * is different. + */ + if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + rt_cache = rt6_find_cached_rt(rt, + &fl6->daddr, + &fl6->saddr); + if (rt_cache && + ipv6_addr_equal(&rdfl->gateway, + &rt_cache->rt6i_gateway)) { + rt = rt_cache; + break; + } continue; + } break; } @@ -2785,9 +2803,9 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { + struct rt6_info *rt, *rt_cache; struct fib6_table *table; struct fib6_node *fn; - struct rt6_info *rt; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); @@ -2801,13 +2819,17 @@ static int ip6_route_del(struct fib6_config *cfg, fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, - true); + !(cfg->fc_flags & RTF_CACHE)); if (fn) { for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if ((rt->rt6i_flags & RTF_CACHE) && - !(cfg->fc_flags & RTF_CACHE)) - continue; + if (cfg->fc_flags & RTF_CACHE) { + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, + &cfg->fc_src); + if (!rt_cache) + continue; + rt = rt_cache; + } if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -2933,8 +2955,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - if (ip6_ins_rt(nrt)) - goto out_release; + /* No need to remove rt from the exception table if rt is + * a cached route because rt6_insert_exception() will + * takes care of it + */ + if (rt6_insert_exception(nrt, rt)) { + dst_release_immediate(&nrt->dst); + goto out; + } netevent.old = &rt->dst; netevent.new = &nrt->dst; @@ -2942,17 +2970,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); - if (rt->rt6i_flags & RTF_CACHE) { - rt = (struct rt6_info *) dst_clone(&rt->dst); - ip6_del_rt(rt); - } - -out_release: - /* Release the reference taken in - * ip6_rt_cache_alloc() - */ - dst_release(&nrt->dst); - out: neigh_release(neigh); } @@ -3344,12 +3361,8 @@ static int fib6_clean_tohost(struct rt6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - /* RTF_CACHE_GATEWAY case will be removed once the exception - * table is hooked up to store all cached routes. - */ - if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) || - ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { return -1; } @@ -3438,20 +3451,9 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - /* This case will be removed once the exception table - * is hooked up. - */ - if (rt->rt6i_flags & RTF_CACHE) { - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) - rt->rt6i_pmtu = arg->mtu; - } else if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); } rt6_exceptions_update_pmtu(rt, arg->mtu); -- GitLab From a94b9367e044ba672c9f4105eb1516ff6ff4948a Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:04 -0700 Subject: [PATCH 1075/1507] ipv6: grab rt->rt6i_ref before allocating pcpu rt After rwlock is replaced with rcu and spinlock, ip6_pol_route() will be called with only rcu held. That means rt6 route deletion could happen simultaneously with rt6_make_pcpu_rt(). This could potentially cause memory leak if rt6_release() is called right before rt6_make_pcpu_rt() on the same route. This patch grabs rt->rt6i_ref safely before calling rt6_make_pcpu_rt() to make sure rt6_release() will not get triggered while rt6_make_pcpu_rt() is in progress. And rt6_release() is called after rt6_make_pcpu_rt() is finished. Note: As we are incrementing rt->rt6i_ref in ip6_pol_route(), there is a very slim chance that fib6_purge_rt() will be triggered unnecessarily when deleting a route if ip6_pol_route() running on another thread picks this route as well and tries to make pcpu cache for it. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/route.c | 58 ++++++++++++++++++++++++------------------------ 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 65130dde276a9..941c062389d2b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1070,7 +1070,6 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) { - struct fib6_table *table = rt->rt6i_table; struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); @@ -1081,28 +1080,20 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) return net->ipv6.ip6_null_entry; } - read_lock_bh(&table->tb6_lock); - if (rt->rt6i_pcpu) { - p = this_cpu_ptr(rt->rt6i_pcpu); - prev = cmpxchg(p, NULL, pcpu_rt); - if (prev) { - /* If someone did it before us, return prev instead */ - dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = prev; - } - } else { - /* rt has been removed from the fib6 tree - * before we have a chance to acquire the read_lock. - * In this case, don't brother to create a pcpu rt - * since rt is going away anyway. The next - * dst_check() will trigger a re-lookup. - */ + dst_hold(&pcpu_rt->dst); + p = this_cpu_ptr(rt->rt6i_pcpu); + prev = cmpxchg(p, NULL, pcpu_rt); + if (prev) { + /* If someone did it before us, return prev instead */ + /* release refcnt taken by ip6_rt_pcpu_alloc() */ + dst_release_immediate(&pcpu_rt->dst); + /* release refcnt taken by above dst_hold() */ dst_release_immediate(&pcpu_rt->dst); - pcpu_rt = rt; + dst_hold(&prev->dst); + pcpu_rt = prev; } - dst_hold(&pcpu_rt->dst); + rt6_dst_from_metrics_check(pcpu_rt); - read_unlock_bh(&table->tb6_lock); return pcpu_rt; } @@ -1683,19 +1674,28 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (pcpu_rt) { read_unlock_bh(&table->tb6_lock); } else { - /* We have to do the read_unlock first - * because rt6_make_pcpu_route() may trigger - * ip6_dst_gc() which will take the write_lock. - */ - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - pcpu_rt = rt6_make_pcpu_route(rt); - dst_release(&rt->dst); + /* atomic_inc_not_zero() is needed when using rcu */ + if (atomic_inc_not_zero(&rt->rt6i_ref)) { + /* We have to do the read_unlock first + * because rt6_make_pcpu_route() may trigger + * ip6_dst_gc() which will take the write_lock. + * + * No dst_hold() on rt is needed because grabbing + * rt->rt6i_ref makes sure rt can't be released. + */ + read_unlock_bh(&table->tb6_lock); + pcpu_rt = rt6_make_pcpu_route(rt); + rt6_release(rt); + } else { + /* rt is already removed from tree */ + read_unlock_bh(&table->tb6_lock); + pcpu_rt = net->ipv6.ip6_null_entry; + dst_hold(&pcpu_rt->dst); + } } trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); return pcpu_rt; - } } EXPORT_SYMBOL_GPL(ip6_pol_route); -- GitLab From 51e398e86d61b69b9a4be49ff7f6afeb87530df1 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:05 -0700 Subject: [PATCH 1076/1507] ipv6: don't release rt->rt6i_pcpu memory during rt6_release() After rwlock is replaced with rcu and spinlock, route lookup can happen simultanously with route deletion. This patch removes the call to free_percpu(rt->rt6i_pcpu) from rt6_release() to avoid the race condition between rt6_release() and rt6_get_pcpu_route(). And as free_percpu(rt->rt6i_pcpu) is already called in ip6_dst_destroy() after the rcu grace period, it is safe to do this change. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 9c8e704e6af7d..eee392f7b1f60 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -190,9 +190,6 @@ void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) *ppcpu_rt = NULL; } } - - free_percpu(non_pcpu_rt->rt6i_pcpu); - non_pcpu_rt->rt6i_pcpu = NULL; } EXPORT_SYMBOL_GPL(rt6_free_pcpu); -- GitLab From d3843fe5fd45be0e04a251a2cc68893c859a31bd Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:06 -0700 Subject: [PATCH 1077/1507] ipv6: replace dst_hold() with dst_hold_safe() in routing code With rwlock, it is safe to call dst_hold() in the read thread because read thread is guaranteed to be separated from write thread. However, after we replace rwlock with rcu, it is no longer safe to use dst_hold(). A dst might already have been deleted but is waiting for the rcu grace period to pass before freeing the memory when a read thread is trying to do dst_hold(). This could potentially cause double free issue. So this commit replaces all dst_hold() with dst_hold_safe() in all read thread to avoid this double free issue. And in order to make the code more compact, a new function ip6_hold_safe() is introduced. It calls dst_hold_safe() first, and if that fails, it will either fall back to hold and return net->ipv6.ip6_null_entry or set rt to NULL according to the caller's need. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 3 +- net/ipv6/route.c | 71 +++++++++++++++++++++++++++++++++------------ 2 files changed, 54 insertions(+), 20 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 873afafddfc4c..f86e931d555ef 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2333,7 +2333,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->rt6i_flags & noflags) != 0) continue; - dst_hold(&rt->dst); + if (!dst_hold_safe(&rt->dst)) + rt = NULL; break; } out: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 941c062389d2b..aeb349aea429a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -874,6 +874,23 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn, } } +static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, + bool null_fallback) +{ + struct rt6_info *rt = *prt; + + if (dst_hold_safe(&rt->dst)) + return true; + if (null_fallback) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = NULL; + } + *prt = rt; + return false; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, int flags) @@ -898,7 +915,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, if (rt_cache) rt = rt_cache; - dst_use(&rt->dst, jiffies); + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + read_unlock_bh(&table->tb6_lock); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); @@ -1061,10 +1080,9 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt) { - dst_hold(&pcpu_rt->dst); + if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) rt6_dst_from_metrics_check(pcpu_rt); - } + return pcpu_rt; } @@ -1625,12 +1643,17 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (rt_cache) rt = rt_cache; - if (rt == net->ipv6.ip6_null_entry || (rt->rt6i_flags & RTF_CACHE)) { - dst_use(&rt->dst, jiffies); + if (rt == net->ipv6.ip6_null_entry) { + read_unlock_bh(&table->tb6_lock); + dst_hold(&rt->dst); + trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + return rt; + } else if (rt->rt6i_flags & RTF_CACHE) { + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + rt6_dst_from_metrics_check(rt); + } read_unlock_bh(&table->tb6_lock); - - rt6_dst_from_metrics_check(rt); - trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && @@ -1643,7 +1666,13 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, struct rt6_info *uncached_rt; - dst_use(&rt->dst, jiffies); + if (ip6_hold_safe(net, &rt, true)) { + dst_use_noref(&rt->dst, jiffies); + } else { + read_unlock_bh(&table->tb6_lock); + uncached_rt = rt; + goto uncached_rt_out; + } read_unlock_bh(&table->tb6_lock); uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); @@ -1659,6 +1688,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, dst_hold(&uncached_rt->dst); } +uncached_rt_out: trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); return uncached_rt; @@ -1667,8 +1697,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, struct rt6_info *pcpu_rt; - rt->dst.lastuse = jiffies; - rt->dst.__use++; + dst_use_noref(&rt->dst, jiffies); pcpu_rt = rt6_get_pcpu_route(rt); if (pcpu_rt) { @@ -2130,7 +2159,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, } out: - dst_hold(&rt->dst); + ip6_hold_safe(net, &rt, true); read_unlock_bh(&table->tb6_lock); @@ -2841,7 +2870,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) continue; - dst_hold(&rt->dst); + if (!dst_hold_safe(&rt->dst)) + break; read_unlock_bh(&table->tb6_lock); /* if gateway was specified only delete the one hop */ @@ -3038,7 +3068,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) continue; - dst_hold(&rt->dst); + ip6_hold_safe(NULL, &rt, false); break; } out: @@ -3096,7 +3126,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev break; } if (rt) - dst_hold(&rt->dst); + ip6_hold_safe(NULL, &rt, false); read_unlock_bh(&table->tb6_lock); return rt; } @@ -3139,9 +3169,12 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table) for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt); + if (dst_hold_safe(&rt->dst)) { + read_unlock_bh(&table->tb6_lock); + ip6_del_rt(rt); + } else { + read_unlock_bh(&table->tb6_lock); + } goto restart; } } -- GitLab From bbd63f06d114a52be33f6982fc89ca2768cdeb62 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:07 -0700 Subject: [PATCH 1078/1507] ipv6: update fn_sernum after route is inserted to tree fib6_add() logic currently calls fib6_add_1() to figure out what node should be used for the newly added route and then call fib6_add_rt2node() to insert the route to the node. And during the call of fib6_add_1(), fn_sernum is updated for all nodes that share the same prefix as the new route. This does not have issue in the current code because reader thread will not be able to access the tree while writer thread is inserting new route to it. However, it is not the case once we transition to use RCU. Reader thread could potentially see the new fn_sernum before the new route is inserted. As a result, reader thread's route lookup will return a stale route with the new fn_sernum. In order to solve this issue, we remove all the update of fn_sernum in fib6_add_1(), and instead, introduce a new function that updates fn_sernum for all related nodes and call this functions once the route is successfully inserted to the tree. Also, smp_wmb() is used after a route is successfully inserted into the fib tree and right before the updated of fn->sernum. And smp_rmb() is used right after fn->sernum is accessed in rt6_get_cookie_safe(). This is to guarantee that when the reader thread sees the new fn->sernum, the new route is already inserted in the tree in memory. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 ++ net/ipv6/ip6_fib.c | 39 +++++++++++++++++++++------------------ 2 files changed, 23 insertions(+), 18 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index d0b7283073e3c..6bf929b509515 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -220,6 +220,8 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, if (fn) { *cookie = fn->fn_sernum; + /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */ + smp_rmb(); status = true; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index eee392f7b1f60..f604b311cc3e3 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -585,7 +585,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) static struct fib6_node *fib6_add_1(struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required, int sernum, + int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; @@ -631,8 +631,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn->leaf = NULL; } - fn->fn_sernum = sernum; - return fn; } @@ -641,7 +639,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, */ /* Try to walk down on tree. */ - fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? fn->right : fn->left; @@ -677,7 +674,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, ln->fn_bit = plen; ln->parent = pn; - ln->fn_sernum = sernum; if (dir) pn->right = ln; @@ -737,8 +733,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, in->leaf = fn->leaf; atomic_inc(&in->leaf->rt6i_ref); - in->fn_sernum = sernum; - /* update parent pointer */ if (dir) pn->right = in; @@ -750,8 +744,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, ln->parent = in; fn->parent = in; - ln->fn_sernum = sernum; - if (addr_bit_set(addr, bit)) { in->right = ln; in->left = fn; @@ -776,8 +768,6 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, ln->parent = pn; - ln->fn_sernum = sernum; - if (dir) pn->right = ln; else @@ -1079,6 +1069,20 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } +static void fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) +{ + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); + + /* paired with smp_rmb() in rt6_get_cookie_safe() */ + smp_wmb(); + while (fn) { + fn->fn_sernum = sernum; + fn = fn->parent; + } +} + /* * Add routing information to the routing tree. * / @@ -1111,7 +1115,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum, extack); + replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1145,15 +1149,13 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); sfn->fn_flags = RTN_ROOT; - sfn->fn_sernum = sernum; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -1172,8 +1174,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum, - extack); + allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -1190,8 +1191,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, #endif err = fib6_add_rt2node(fn, rt, info, mxc); - if (!err) + if (!err) { + fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); + } out: if (err) { -- GitLab From 8d1040e808bb2a5aeb4f0791b32bc7356a01ab11 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:08 -0700 Subject: [PATCH 1079/1507] ipv6: check fn->leaf before it is used If rwlock is replaced with rcu and spinlock, it is possible that the reader thread will see fn->leaf as NULL in the following scenarios: 1. fib6_add() is in progress and we have already inserted a new node but not yet inserted the route. 2. fib6_del_route() is in progress and we have already set fn->leaf to NULL but not yet freed the node because of rcu grace period. This patch makes sure all the reader threads check fn->leaf first before using it. And together with later patch to grab rcu_read_lock() and rcu_dereference() fn->leaf, it makes sure reader threads are safe when accessing fn->leaf. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 23 ++++++++++++++++++----- net/ipv6/route.c | 20 ++++++++++++-------- 2 files changed, 30 insertions(+), 13 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index f604b311cc3e3..cf6137e81408b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1279,10 +1279,13 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, while (fn) { if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { + struct rt6_info *leaf = fn->leaf; struct rt6key *key; - key = (struct rt6key *) ((u8 *) fn->leaf + - args->offset); + if (!leaf) + goto backtrack; + + key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES @@ -1299,9 +1302,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, return fn; } } -#ifdef CONFIG_IPV6_SUBTREES backtrack: -#endif if (fn->fn_flags & RTN_ROOT) break; @@ -1358,7 +1359,18 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6key *key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = fn->leaf; + struct rt6key *key; + + /* This node is being deleted */ + if (!leaf) { + if (plen <= fn->fn_bit) + goto out; + else + goto next; + } + + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match @@ -1372,6 +1384,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, prev = fn; +next: /* * We have more bits to go */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aeb349aea429a..05dc450af4416 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -712,6 +712,7 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, } static struct rt6_info *find_rr_leaf(struct fib6_node *fn, + struct rt6_info *leaf, struct rt6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) @@ -730,7 +731,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = find_match(rt, oif, strict, &mpri, match, do_rr); } - for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + for (rt = leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -748,17 +749,21 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, return match; } -static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) +static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, + int oif, int strict) { + struct rt6_info *leaf = fn->leaf; struct rt6_info *match, *rt0; - struct net *net; bool do_rr = false; + if (!leaf) + return net->ipv6.ip6_null_entry; + rt0 = fn->rr_ptr; if (!rt0) - fn->rr_ptr = rt0 = fn->leaf; + fn->rr_ptr = rt0 = leaf; - match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict, + match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, &do_rr); if (do_rr) { @@ -766,13 +771,12 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict) /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) - next = fn->leaf; + next = leaf; if (next != rt0) fn->rr_ptr = next; } - net = dev_net(rt0->dst.dev); return match ? match : net->ipv6.ip6_null_entry; } @@ -1623,7 +1627,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, oif = 0; redo_rt6_select: - rt = rt6_select(fn, oif, strict); + rt = rt6_select(net, fn, oif, strict); if (rt->rt6i_nsiblings) rt = rt6_multipath_select(rt, fl6, oif, strict); if (rt == net->ipv6.ip6_null_entry) { -- GitLab From 17ecf590b3cba19d9ecb410e340aa78128382abb Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:09 -0700 Subject: [PATCH 1080/1507] ipv6: add key length check into rt6_select() After rwlock is replaced with rcu and spinlock, fib6_lookup() could potentially return an intermediate node if other thread is doing fib6_del() on a route which is the only route on the node so that fib6_repair_tree() will be called on this node and potentially assigns fn->leaf to the its child's fn->leaf. In order to detect this situation in rt6_select(), we have to check if fn->fn_bit is consistent with the key length stored in the route. And depending on if the fn is in the subtree or not, the key is either rt->rt6i_dst or rt->rt6i_src. If any inconsistency is found, that means the node no longer holds valid routes in it. So net->ipv6.ip6_null_entry is returned. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/route.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 05dc450af4416..24b80f43bbfbb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -755,6 +755,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, struct rt6_info *leaf = fn->leaf; struct rt6_info *match, *rt0; bool do_rr = false; + int key_plen; if (!leaf) return net->ipv6.ip6_null_entry; @@ -763,6 +764,19 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, if (!rt0) fn->rr_ptr = rt0 = leaf; + /* Double check to make sure fn is not an intermediate node + * and fn->leaf does not points to its child's leaf + * (This might happen if all routes under fn are deleted from + * the tree and fib6_repair_tree() is called on the node.) + */ + key_plen = rt0->rt6i_dst.plen; +#ifdef CONFIG_IPV6_SUBTREES + if (rt0->rt6i_src.plen) + key_plen = rt0->rt6i_src.plen; +#endif + if (fn->fn_bit != key_plen) + return net->ipv6.ip6_null_entry; + match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, &do_rr); -- GitLab From 66f5d6ce53e665477d2a33e8f539d4fa4ca81c83 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:10 -0700 Subject: [PATCH 1081/1507] ipv6: replace rwlock with rcu and spinlock in fib6_table With all the preparation work before, we are now ready to replace rwlock with rcu and spinlock in fib6_table. That means now all fib6_node in fib6_table are protected by rcu. And when freeing fib6_node, call_rcu() is used to wait for the rcu grace period before releasing the memory. When accessing fib6_node, corresponding rcu APIs need to be used. And all previous sessions protected by the write lock will now be protected by the spin lock per table. All previous sessions protected by read lock will now be protected by rcu_read_lock(). A couple of things to note here: 1. As part of the work of replacing rwlock with rcu, the linked list of fn->leaf now has to be rcu protected as well. So both fn->leaf and rt->dst.rt6_next are now __rcu tagged and corresponding rcu APIs are used when manipulating them. 2. For fn->rr_ptr, first of all, it also needs to be rcu protected now and is tagged with __rcu and rcu APIs are used in corresponding places. Secondly, fn->rr_ptr is changed in rt6_select() which is a reader thread. This makes the issue a bit complicated. We think a valid solution for it is to let rt6_select() grab the tb6_lock if it decides to change it. As it is not in the normal operation and only happens when there is no valid neighbor cache for the route, we think the performance impact should be low. 3. fib6_walk_continue() has to be called with tb6_lock held even in the route dumping related functions, e.g. inet6_dump_fib(), fib6_tables_dump() and ipv6_route_seq_ops. It is because fib6_walk_continue() makes modifications to the walker structure, and so are fib6_repair_tree() and fib6_del_route(). In order to do proper syncing between them, we need to let fib6_walk_continue() hold the lock. We may be able to do further improvement on the way we do the tree walk to get rid of the need for holding the spin lock. But not for now. 4. When fib6_del_route() removes a route from the tree, we no longer mark rt->dst.rt6_next to NULL to make simultaneous reader be able to further traverse the list with rcu. However, rt->dst.rt6_next is only valid within this same rcu period. No one should access it later. 5. All the operation of atomic_inc(rt->rt6i_ref) is changed to be performed before we publish this route (either by linking it to fn->leaf or insert it in the list pointed by fn->leaf) just to be safe because as soon as we publish the route, some read thread will be able to access it. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- include/net/ip6_fib.h | 24 ++- net/ipv6/addrconf.c | 11 +- net/ipv6/ip6_fib.c | 405 +++++++++++++++++++++++++----------------- net/ipv6/route.c | 121 +++++++------ 5 files changed, 333 insertions(+), 230 deletions(-) diff --git a/include/net/dst.h b/include/net/dst.h index 06a6765da0744..204c19e254568 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -101,7 +101,7 @@ struct dst_entry { union { struct dst_entry *next; struct rtable __rcu *rt_next; - struct rt6_info *rt6_next; + struct rt6_info __rcu *rt6_next; struct dn_route __rcu *dn_next; }; }; diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6bf929b509515..0b438b9bcb107 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -68,18 +68,18 @@ struct fib6_config { }; struct fib6_node { - struct fib6_node *parent; - struct fib6_node *left; - struct fib6_node *right; + struct fib6_node __rcu *parent; + struct fib6_node __rcu *left; + struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES - struct fib6_node *subtree; + struct fib6_node __rcu *subtree; #endif - struct rt6_info *leaf; + struct rt6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; - struct rt6_info *rr_ptr; + struct rt6_info __rcu *rr_ptr; struct rcu_head rcu; }; @@ -91,7 +91,7 @@ struct fib6_gc_args { #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL #else -#define FIB6_SUBTREE(fn) ((fn)->subtree) +#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif struct mx6_config { @@ -174,6 +174,14 @@ struct rt6_info { unused:7; }; +#define for_each_fib6_node_rt_rcu(fn) \ + for (rt = rcu_dereference((fn)->leaf); rt; \ + rt = rcu_dereference(rt->dst.rt6_next)) + +#define for_each_fib6_walker_rt(w) \ + for (rt = (w)->leaf; rt; \ + rt = rcu_dereference_protected(rt->dst.rt6_next, 1)) + static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; @@ -310,7 +318,7 @@ struct rt6_statistics { struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; - rwlock_t tb6_lock; + spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f86e931d555ef..9854d93e45bb5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2321,12 +2321,12 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != dev->ifindex) continue; if ((rt->rt6i_flags & flags) != flags) @@ -2338,7 +2338,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -5898,10 +5898,9 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) spin_lock(&ifa->lock); if (ifa->rt) { struct rt6_info *rt = ifa->rt; - struct fib6_table *table = rt->rt6i_table; int cpu; - read_lock(&table->tb6_lock); + rcu_read_lock(); addrconf_set_nopolicy(ifa->rt, val); if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { @@ -5911,7 +5910,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) addrconf_set_nopolicy(*rtp, val); } } - read_unlock(&table->tb6_lock); + rcu_read_unlock(); } spin_unlock(&ifa->lock); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index cf6137e81408b..3f95908b39c3d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -54,8 +54,12 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); -static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); +static struct fib6_node *fib6_repair_tree(struct net *net, + struct fib6_table *table, + struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); @@ -107,12 +111,12 @@ void fib6_update_sernum(struct rt6_info *rt) struct net *net = dev_net(rt->dst.dev); struct fib6_node *fn; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&table->tb6_lock)); if (fn) fn->fn_sernum = fib6_new_sernum(net); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); } /* @@ -207,8 +211,7 @@ static void fib6_link_table(struct net *net, struct fib6_table *tb) * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ - rwlock_init(&tb->tb6_lock); - + spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* @@ -227,7 +230,8 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; - table->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(table->tb6_root.leaf, + net->ipv6.ip6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -324,11 +328,8 @@ unsigned int fib6_tables_seq_read(struct net *net) struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; - hlist_for_each_entry_rcu(tb, head, tb6_hlist) { - read_lock_bh(&tb->tb6_lock); + hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += tb->fib_seq; - read_unlock_bh(&tb->tb6_lock); - } } rcu_read_unlock(); @@ -374,7 +375,7 @@ static int fib6_node_dump(struct fib6_walker *w) { struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) + for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); w->leaf = NULL; return 0; @@ -384,9 +385,9 @@ static void fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { w->root = &tb->tb6_root; - read_lock_bh(&tb->tb6_lock); + spin_lock_bh(&tb->tb6_lock); fib6_walk(net, w); - read_unlock_bh(&tb->tb6_lock); + spin_unlock_bh(&tb->tb6_lock); } /* Called with rcu_read_lock() */ @@ -423,7 +424,7 @@ static int fib6_dump_node(struct fib6_walker *w) int res; struct rt6_info *rt; - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); if (res < 0) { /* Frame is full, suspend walking */ @@ -482,9 +483,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, w->count = 0; w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = w->root->fn_sernum; @@ -499,9 +500,9 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, } else w->skip = 0; - read_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); - read_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; @@ -582,11 +583,12 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) * node. */ -static struct fib6_node *fib6_add_1(struct fib6_node *root, - struct in6_addr *addr, int plen, - int offset, int allow_create, - int replace_required, - struct netlink_ext_ack *extack) +static struct fib6_node *fib6_add_1(struct fib6_table *table, + struct fib6_node *root, + struct in6_addr *addr, int plen, + int offset, int allow_create, + int replace_required, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -601,7 +603,9 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn = root; do { - key = (struct rt6key *)((u8 *)fn->leaf + offset); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match @@ -627,8 +631,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { - rt6_release(fn->leaf); - fn->leaf = NULL; + RCU_INIT_POINTER(fn->leaf, NULL); + rt6_release(leaf); } return fn; @@ -641,7 +645,11 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right : fn->left; + fn = dir ? + rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)) : + rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { @@ -672,13 +680,12 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; - - ln->parent = pn; + RCU_INIT_POINTER(ln->parent, pn); if (dir) - pn->right = ln; + rcu_assign_pointer(pn->right, ln); else - pn->left = ln; + rcu_assign_pointer(pn->left, ln); return ln; @@ -692,7 +699,8 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, * and the current */ - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. @@ -729,27 +737,28 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, in->fn_bit = bit; - in->parent = pn; + RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; - atomic_inc(&in->leaf->rt6i_ref); + atomic_inc(&rcu_dereference_protected(in->leaf, + lockdep_is_held(&table->tb6_lock))->rt6i_ref); /* update parent pointer */ if (dir) - pn->right = in; + rcu_assign_pointer(pn->right, in); else - pn->left = in; + rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; - ln->parent = in; - fn->parent = in; + RCU_INIT_POINTER(ln->parent, in); + rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { - in->right = ln; - in->left = fn; + rcu_assign_pointer(in->right, ln); + rcu_assign_pointer(in->left, fn); } else { - in->left = ln; - in->right = fn; + rcu_assign_pointer(in->left, ln); + rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ @@ -766,19 +775,19 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, ln->fn_bit = plen; - ln->parent = pn; - - if (dir) - pn->right = ln; - else - pn->left = ln; + RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) - ln->right = fn; + RCU_INIT_POINTER(ln->right, fn); else - ln->left = fn; + RCU_INIT_POINTER(ln->left, fn); + + rcu_assign_pointer(fn->parent, ln); - fn->parent = ln; + if (dir) + rcu_assign_pointer(pn->right, ln); + else + rcu_assign_pointer(pn->left, ln); } return ln; } @@ -824,6 +833,8 @@ static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, struct net *net) { + struct fib6_table *table = rt->rt6i_table; + if (atomic_read(&rt->rt6i_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, @@ -832,12 +843,17 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) { - fn->leaf = fib6_find_prefix(net, fn); - atomic_inc(&fn->leaf->rt6i_ref); + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_leaf; + if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { + new_leaf = fib6_find_prefix(net, table, fn); + atomic_inc(&new_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_leaf); rt6_release(rt); } - fn = fn->parent; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); } } } @@ -849,9 +865,11 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc) { + struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct rt6_info *iter = NULL; - struct rt6_info **ins; - struct rt6_info **fallback_ins = NULL; + struct rt6_info __rcu **ins; + struct rt6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -866,7 +884,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; - for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) { + for (iter = leaf; iter; + iter = rcu_dereference_protected(iter->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock))) { /* * Search for duplicates */ @@ -928,7 +948,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (fallback_ins && !found) { /* No ECMP-able route found, replace first non-ECMP one */ ins = fallback_ins; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); found++; } @@ -942,7 +963,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, struct rt6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ - sibling = fn->leaf; + sibling = leaf; while (sibling) { if (sibling->rt6i_metric == rt->rt6i_metric && rt6_qualify_for_ecmp(sibling)) { @@ -950,7 +971,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, &sibling->rt6i_siblings); break; } - sibling = sibling->dst.rt6_next; + sibling = rcu_dereference_protected(sibling->dst.rt6_next, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings @@ -979,10 +1001,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (err) return err; - rt->dst.rt6_next = iter; - *ins = rt; - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->dst.rt6_next, iter); atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, rt); if (!info->skip_notify) @@ -1008,10 +1030,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (err) return err; - *ins = rt; + atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; - atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt); if (!info->skip_notify) @@ -1023,14 +1045,15 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, nsiblings = iter->rt6i_nsiblings; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->dst.rt6_next; - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); while (iter) { if (iter->rt6i_metric > rt->rt6i_metric) break; @@ -1038,14 +1061,15 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, *ins = iter->dst.rt6_next; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); - if (fn->rr_ptr == iter) + if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; } else { ins = &iter->dst.rt6_next; } - iter = *ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } WARN_ON(nsiblings != 0); } @@ -1079,7 +1103,8 @@ static void fib6_update_sernum_upto_root(struct rt6_info *rt, smp_wmb(); while (fn) { fn->fn_sernum = sernum; - fn = fn->parent; + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); } } @@ -1087,12 +1112,14 @@ static void fib6_update_sernum_upto_root(struct rt6_info *rt, * Add routing information to the routing tree. * / * with source addr info in sub-trees + * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc, struct netlink_ext_ack *extack) { + struct fib6_table *table = rt->rt6i_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; @@ -1113,7 +1140,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + fn = fib6_add_1(table, root, + &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { @@ -1128,7 +1156,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (rt->rt6i_src.plen) { struct fib6_node *sn; - if (!fn->subtree) { + if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* @@ -1146,13 +1174,14 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!sfn) goto failure; - sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + rcu_assign_pointer(sfn->leaf, + info->nl_net->ipv6.ip6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ - sn = fib6_add_1(sfn, &rt->rt6i_src.addr, + sn = fib6_add_1(table, sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required, extack); @@ -1168,10 +1197,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } /* Now link new subtree to main tree */ - sfn->parent = fn; - fn->subtree = sfn; + rcu_assign_pointer(sfn->parent, fn); + rcu_assign_pointer(fn->subtree, sfn); } else { - sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, + sn = fib6_add_1(table, FIB6_SUBTREE(fn), &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required, extack); @@ -1182,9 +1211,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } } - if (!fn->leaf) { - fn->leaf = rt; + if (!rcu_access_pointer(fn->leaf)) { atomic_inc(&rt->rt6i_ref); + rcu_assign_pointer(fn->leaf, rt); } fn = sn; } @@ -1203,19 +1232,23 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ - if (pn != fn && pn->leaf == rt) { - pn->leaf = NULL; + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (pn != fn && pn_leaf == rt) { + pn_leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); atomic_dec(&rt->rt6i_ref); } - if (pn != fn && !pn->leaf && !(pn->fn_flags & RTN_RTINFO)) { - pn->leaf = fib6_find_prefix(info->nl_net, pn); + if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn_leaf = fib6_find_prefix(info->nl_net, table, pn); #if RT6_DEBUG >= 2 - if (!pn->leaf) { - WARN_ON(pn->leaf == NULL); - pn->leaf = info->nl_net->ipv6.ip6_null_entry; + if (!pn_leaf) { + WARN_ON(!pn_leaf); + pn_leaf = info->nl_net->ipv6.ip6_null_entry; } #endif - atomic_inc(&pn->leaf->rt6i_ref); + atomic_inc(&pn_leaf->rt6i_ref); + rcu_assign_pointer(pn->leaf, pn_leaf); } #endif goto failure; @@ -1230,7 +1263,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, * fn->leaf. */ if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) - fib6_repair_tree(info->nl_net, fn); + fib6_repair_tree(info->nl_net, table, fn); /* Always release dst as dst->__refcnt is guaranteed * to be taken before entering this function */ @@ -1268,7 +1301,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, dir = addr_bit_set(args->addr, fn->fn_bit); - next = dir ? fn->right : fn->left; + next = dir ? rcu_dereference(fn->right) : + rcu_dereference(fn->left); if (next) { fn = next; @@ -1278,8 +1312,10 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, } while (fn) { - if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) { - struct rt6_info *leaf = fn->leaf; + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree || fn->fn_flags & RTN_RTINFO) { + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) @@ -1289,10 +1325,9 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES - if (fn->subtree) { + if (subtree) { struct fib6_node *sfn; - sfn = fib6_lookup_1(fn->subtree, - args + 1); + sfn = fib6_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; @@ -1306,12 +1341,14 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, if (fn->fn_flags & RTN_ROOT) break; - fn = fn->parent; + fn = rcu_dereference(fn->parent); } return NULL; } +/* called with rcu_read_lock() held + */ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1359,7 +1396,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6_info *leaf = fn->leaf; + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ @@ -1389,9 +1426,9 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) - fn = fn->right; + fn = rcu_dereference(fn->right); else - fn = fn->left; + fn = rcu_dereference(fn->left); } out: if (exact_match) @@ -1413,9 +1450,11 @@ struct fib6_node *fib6_locate(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (src_len) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + WARN_ON(saddr == NULL); - if (fn && fn->subtree) - fn = fib6_locate_1(fn->subtree, saddr, src_len, + if (fn && subtree) + fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct rt6_info, rt6i_src), exact_match); } @@ -1433,16 +1472,26 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) +static struct rt6_info *fib6_find_prefix(struct net *net, + struct fib6_table *table, + struct fib6_node *fn) { + struct fib6_node *child_left, *child_right; + if (fn->fn_flags & RTN_ROOT) return net->ipv6.ip6_null_entry; while (fn) { - if (fn->left) - return fn->left->leaf; - if (fn->right) - return fn->right->leaf; + child_left = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + child_right = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + if (child_left) + return rcu_dereference_protected(child_left->leaf, + lockdep_is_held(&table->tb6_lock)); + if (child_right) + return rcu_dereference_protected(child_right->leaf, + lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } @@ -1452,31 +1501,49 @@ static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn) /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. + * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, - struct fib6_node *fn) + struct fib6_table *table, + struct fib6_node *fn) { int children; int nstate; - struct fib6_node *child, *pn; + struct fib6_node *child; struct fib6_walker *w; int iter = 0; for (;;) { + struct fib6_node *fn_r = rcu_dereference_protected(fn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *fn_l = rcu_dereference_protected(fn->left, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_r = rcu_dereference_protected(pn->right, + lockdep_is_held(&table->tb6_lock)); + struct fib6_node *pn_l = rcu_dereference_protected(pn->left, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + struct rt6_info *new_fn_leaf; + RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf); + WARN_ON(fn_leaf); children = 0; child = NULL; - if (fn->right) - child = fn->right, children |= 1; - if (fn->left) - child = fn->left, children |= 2; + if (fn_r) + child = fn_r, children |= 1; + if (fn_l) + child = fn_l, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1484,36 +1551,36 @@ static struct fib6_node *fib6_repair_tree(struct net *net, || (children && fn->fn_flags & RTN_ROOT) #endif ) { - fn->leaf = fib6_find_prefix(net, fn); + new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 - if (!fn->leaf) { - WARN_ON(!fn->leaf); - fn->leaf = net->ipv6.ip6_null_entry; + if (!new_fn_leaf) { + WARN_ON(!new_fn_leaf); + new_fn_leaf = net->ipv6.ip6_null_entry; } #endif - atomic_inc(&fn->leaf->rt6i_ref); - return fn->parent; + atomic_inc(&new_fn_leaf->rt6i_ref); + rcu_assign_pointer(fn->leaf, new_fn_leaf); + return pn; } - pn = fn->parent; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); - FIB6_SUBTREE(pn) = NULL; + RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) - pn->right = child; - else if (pn->left == fn) - pn->left = child; + if (pn_r == fn) + rcu_assign_pointer(pn->right, child); + else if (pn_l == fn) + rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) - child->parent = pn; + rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } @@ -1546,17 +1613,18 @@ static struct fib6_node *fib6_repair_tree(struct net *net, if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; - rt6_release(pn->leaf); - pn->leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); + rt6_release(pn_leaf); fn = pn; } } -static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nl_info *info) +static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, + struct rt6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = *rtp; + struct rt6_info *rt = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); @@ -1573,7 +1641,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, rt6_flush_exceptions(rt); /* Reset round-robin state, if necessary */ - if (fn->rr_ptr == rt) + if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ @@ -1592,20 +1660,19 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rt->dst.rt6_next; + w->leaf = rcu_dereference_protected(rt->dst.rt6_next, + lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); - rt->dst.rt6_next = NULL; - /* If it was last route, expunge its radix tree node */ - if (!fn->leaf) { + if (!rcu_access_pointer(fn->leaf)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; - fn = fib6_repair_tree(net, fn); + fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); @@ -1616,12 +1683,15 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, rt6_release(rt); } +/* Need to own table->tb6_lock */ int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_table *table = rt->rt6i_table; struct net *net = info->nl_net; - struct rt6_info **rtp; + struct rt6_info __rcu **rtp; + struct rt6_info __rcu **rtp_next; #if RT6_DEBUG >= 2 if (rt->dst.obsolete > 0) { @@ -1642,11 +1712,14 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * Walk the leaf entries looking for ourself */ - for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->dst.rt6_next) { - if (*rtp == rt) { - fib6_del_route(fn, rtp, info); + for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { + struct rt6_info *cur = rcu_dereference_protected(*rtp, + lockdep_is_held(&table->tb6_lock)); + if (rt == cur) { + fib6_del_route(table, fn, rtp, info); return 0; } + rtp_next = &cur->dst.rt6_next; } return -ENOENT; } @@ -1673,11 +1746,13 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. + * + * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { - struct fib6_node *fn, *pn; + struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); @@ -1697,20 +1772,22 @@ static int fib6_walk_continue(struct fib6_walker *w) w->state = FWS_L; #endif case FWS_L: - if (fn->left) { - w->node = fn->left; + left = rcu_dereference_protected(fn->left, 1); + if (left) { + w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; case FWS_R: - if (fn->right) { - w->node = fn->right; + right = rcu_dereference_protected(fn->right, 1); + if (right) { + w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; - w->leaf = fn->leaf; + w->leaf = rcu_dereference_protected(fn->leaf, 1); case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -1732,7 +1809,9 @@ static int fib6_walk_continue(struct fib6_walker *w) case FWS_U: if (fn == w->root) return 0; - pn = fn->parent; + pn = rcu_dereference_protected(fn->parent, 1); + left = rcu_dereference_protected(pn->left, 1); + right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { @@ -1741,13 +1820,13 @@ static int fib6_walk_continue(struct fib6_walker *w) continue; } #endif - if (pn->left == fn) { + if (left == fn) { w->state = FWS_R; continue; } - if (pn->right == fn) { + if (right == fn) { w->state = FWS_C; - w->leaf = w->node->leaf; + w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 @@ -1790,7 +1869,7 @@ static int fib6_clean_node(struct fib6_walker *w) return 0; } - for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; @@ -1850,10 +1929,10 @@ static void __fib6_clean_all(struct net *net, for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); @@ -1967,7 +2046,8 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; - net->ipv6.fib6_main_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -1978,7 +2058,8 @@ static int __net_init fib6_net_init(struct net *net) if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; - net->ipv6.fib6_local_tbl->tb6_root.leaf = net->ipv6.ip6_null_entry; + rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, + net->ipv6.ip6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2108,7 +2189,9 @@ static int ipv6_route_yield(struct fib6_walker *w) return 1; do { - iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->w.leaf = rcu_dereference_protected( + iter->w.leaf->dst.rt6_next, + lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; @@ -2173,7 +2256,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = ((struct rt6_info *)v)->dst.rt6_next; + n = rcu_dereference(((struct rt6_info *)v)->dst.rt6_next); if (n) { ++*pos; return n; @@ -2181,9 +2264,9 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) iter_table: ipv6_route_check_sernum(iter); - read_lock(&iter->tbl->tb6_lock); + spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); - read_unlock(&iter->tbl->tb6_lock); + spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { if (v) ++*pos; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 24b80f43bbfbb..cf44d0994b1e8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -488,7 +488,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match, } /* - * Route lookup. Any table->tb6_lock is implied. + * Route lookup. rcu_read_lock() should be held. */ static inline struct rt6_info *rt6_device_match(struct net *net, @@ -503,7 +503,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (!oif && ipv6_addr_any(saddr)) goto out; - for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) { + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->dst.rt6_next)) { struct net_device *dev = sprt->dst.dev; if (oif) { @@ -722,7 +722,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -731,7 +731,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, match = find_match(rt, oif, strict, &mpri, match, do_rr); } - for (rt = leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + for (rt = leaf; rt && rt != rr_head; + rt = rcu_dereference(rt->dst.rt6_next)) { if (rt->rt6i_metric != metric) { cont = rt; break; @@ -743,7 +744,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rt->dst.rt6_next) + for (rt = cont; rt; rt = rcu_dereference(rt->dst.rt6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; @@ -752,7 +753,7 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, int oif, int strict) { - struct rt6_info *leaf = fn->leaf; + struct rt6_info *leaf = rcu_dereference(fn->leaf); struct rt6_info *match, *rt0; bool do_rr = false; int key_plen; @@ -760,9 +761,9 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, if (!leaf) return net->ipv6.ip6_null_entry; - rt0 = fn->rr_ptr; + rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) - fn->rr_ptr = rt0 = leaf; + rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf @@ -781,14 +782,19 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, &do_rr); if (do_rr) { - struct rt6_info *next = rt0->dst.rt6_next; + struct rt6_info *next = rcu_dereference(rt0->dst.rt6_next); /* no entries matched; do round-robin */ if (!next || next->rt6i_metric != rt0->rt6i_metric) next = leaf; - if (next != rt0) - fn->rr_ptr = next; + if (next != rt0) { + spin_lock_bh(&leaf->rt6i_table->tb6_lock); + /* make sure next is not being deleted from the tree */ + if (next->rt6i_node) + rcu_assign_pointer(fn->rr_ptr, next); + spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + } } return match ? match : net->ipv6.ip6_null_entry; @@ -878,13 +884,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { - struct fib6_node *pn; + struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; - pn = fn->parent; - if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) - fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); + pn = rcu_dereference(fn->parent); + sn = FIB6_SUBTREE(pn); + if (sn && sn != fn) + fn = fib6_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) @@ -916,13 +923,19 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct rt6_info *rt, *rt_cache; struct fib6_node *fn; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = fn->leaf; - rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags); + rt = rcu_dereference(fn->leaf); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + } else { + rt = rt6_device_match(net, rt, &fl6->saddr, + fl6->flowi6_oif, flags); + if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) + rt = rt6_multipath_select(rt, fl6, + fl6->flowi6_oif, flags); + } if (rt == net->ipv6.ip6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) @@ -936,7 +949,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, if (ip6_hold_safe(net, &rt, true)) dst_use_noref(&rt->dst, jiffies); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); @@ -990,9 +1003,9 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, struct fib6_table *table; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, mxc, extack); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); return err; } @@ -1090,7 +1103,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) return pcpu_rt; } -/* It should be called with read_lock_bh(&tb6_lock) acquired */ +/* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) { struct rt6_info *pcpu_rt, **p; @@ -1632,7 +1645,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (net->ipv6.devconf_all->forwarding == 0) strict |= RT6_LOOKUP_F_REACHABLE; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; @@ -1662,7 +1675,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, rt = rt_cache; if (rt == net->ipv6.ip6_null_entry) { - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); dst_hold(&rt->dst); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; @@ -1671,7 +1684,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, dst_use_noref(&rt->dst, jiffies); rt6_dst_from_metrics_check(rt); } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && @@ -1687,11 +1700,11 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, if (ip6_hold_safe(net, &rt, true)) { dst_use_noref(&rt->dst, jiffies); } else { - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); uncached_rt = rt; goto uncached_rt_out; } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); dst_release(&rt->dst); @@ -1719,7 +1732,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, pcpu_rt = rt6_get_pcpu_route(rt); if (pcpu_rt) { - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); } else { /* atomic_inc_not_zero() is needed when using rcu */ if (atomic_inc_not_zero(&rt->rt6i_ref)) { @@ -1730,12 +1743,12 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, * No dst_hold() on rt is needed because grabbing * rt->rt6i_ref makes sure rt can't be released. */ - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); pcpu_rt = rt6_make_pcpu_route(rt); rt6_release(rt); } else { /* rt is already removed from tree */ - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); pcpu_rt = net->ipv6.ip6_null_entry; dst_hold(&pcpu_rt->dst); } @@ -2131,10 +2144,10 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, * routes. */ - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt6_check_expired(rt)) continue; if (rt->dst.error) @@ -2179,7 +2192,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, out: ip6_hold_safe(net, &rt, true); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; @@ -2778,9 +2791,9 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) } table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out: ip6_rt_put(rt); @@ -2806,7 +2819,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) if (rt == net->ipv6.ip6_null_entry) goto out_put; table = rt->rt6i_table; - write_lock_bh(&table->tb6_lock); + spin_lock_bh(&table->tb6_lock); if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { struct rt6_info *sibling, *next_sibling; @@ -2836,7 +2849,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) err = fib6_del(rt, info); out_unlock: - write_unlock_bh(&table->tb6_lock); + spin_unlock_bh(&table->tb6_lock); out_put: ip6_rt_put(rt); @@ -2861,7 +2874,7 @@ static int ip6_route_del(struct fib6_config *cfg, return err; } - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, @@ -2869,7 +2882,7 @@ static int ip6_route_del(struct fib6_config *cfg, !(cfg->fc_flags & RTF_CACHE)); if (fn) { - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (cfg->fc_flags & RTF_CACHE) { rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, &cfg->fc_src); @@ -2890,7 +2903,7 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (!dst_hold_safe(&rt->dst)) break; - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) @@ -2899,7 +2912,7 @@ static int ip6_route_del(struct fib6_config *cfg, return __ip6_del_rt_siblings(rt, cfg); } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return err; } @@ -3074,12 +3087,12 @@ static struct rt6_info *rt6_get_route_info(struct net *net, if (!table) return NULL; - read_lock_bh(&table->tb6_lock); + rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; - for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + for_each_fib6_node_rt_rcu(fn) { if (rt->dst.dev->ifindex != ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) @@ -3090,7 +3103,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, break; } out: - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -3136,8 +3149,8 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev if (!table) return NULL; - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (dev == rt->dst.dev && ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&rt->rt6i_gateway, addr)) @@ -3145,7 +3158,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev } if (rt) ip6_hold_safe(NULL, &rt, false); - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); return rt; } @@ -3183,20 +3196,20 @@ static void __rt6_purge_dflt_routers(struct fib6_table *table) struct rt6_info *rt; restart: - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { + rcu_read_lock(); + for_each_fib6_node_rt_rcu(&table->tb6_root) { if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { if (dst_hold_safe(&rt->dst)) { - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); ip6_del_rt(rt); } else { - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); } goto restart; } } - read_unlock_bh(&table->tb6_lock); + rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } -- GitLab From 81eb8447daae3b62247aa66bb17b82f8fef68249 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 6 Oct 2017 12:06:11 -0700 Subject: [PATCH 1082/1507] ipv6: take care of rt6_stats Currently, most of the rt6_stats are not hooked up correctly. As the last part of this patch series, hook up all existing rt6_stats and add one new stat fib_rt_uncache to indicate the number of routes in the uncached list. For details of the stats, please refer to the comments added in include/net/ip6_fib.h. Note: fib_rt_alloc and fib_rt_uncache are not guaranteed to be modified under a lock. So atomic_t is used for them. Signed-off-by: Wei Wang Signed-off-by: Martin KaFai Lau Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 15 +++++++++------ net/ipv6/ip6_fib.c | 42 ++++++++++++++++++++++++------------------ net/ipv6/route.c | 16 ++++++++++++++-- 3 files changed, 47 insertions(+), 26 deletions(-) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 0b438b9bcb107..10c9138160329 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -297,12 +297,15 @@ struct fib6_walker { }; struct rt6_statistics { - __u32 fib_nodes; - __u32 fib_route_nodes; - __u32 fib_rt_alloc; /* permanent routes */ - __u32 fib_rt_entries; /* rt entries in table */ - __u32 fib_rt_cache; /* cache routes */ - __u32 fib_discarded_routes; + __u32 fib_nodes; /* all fib6 nodes */ + __u32 fib_route_nodes; /* intermediate nodes */ + __u32 fib_rt_entries; /* rt entries in fib table */ + __u32 fib_rt_cache; /* cached rt entries in exception table */ + __u32 fib_discarded_routes; /* total number of routes delete */ + + /* The following stats are not protected by any lock */ + atomic_t fib_rt_alloc; /* total number of routes alloced */ + atomic_t fib_rt_uncache; /* rt entries in uncached list */ }; #define RTN_TL_ROOT 0x0001 diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 3f95908b39c3d..52a29ba329285 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -149,18 +149,21 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static struct fib6_node *node_alloc(void) +static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); + if (fn) + net->ipv6.rt6_stats->fib_nodes++; return fn; } -static void node_free_immediate(struct fib6_node *fn) +static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); + net->ipv6.rt6_stats->fib_nodes--; } static void node_free_rcu(struct rcu_head *head) @@ -170,9 +173,10 @@ static void node_free_rcu(struct rcu_head *head) kmem_cache_free(fib6_node_kmem, fn); } -static void node_free(struct fib6_node *fn) +static void node_free(struct net *net, struct fib6_node *fn) { call_rcu(&fn->rcu, node_free_rcu); + net->ipv6.rt6_stats->fib_nodes--; } void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) @@ -583,7 +587,8 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) * node. */ -static struct fib6_node *fib6_add_1(struct fib6_table *table, +static struct fib6_node *fib6_add_1(struct net *net, + struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, @@ -675,7 +680,7 @@ static struct fib6_node *fib6_add_1(struct fib6_table *table, * Create new leaf node without children. */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); @@ -716,14 +721,14 @@ static struct fib6_node *fib6_add_1(struct fib6_table *table, * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { - in = node_alloc(); - ln = node_alloc(); + in = node_alloc(net); + ln = node_alloc(net); if (!in || !ln) { if (in) - node_free_immediate(in); + node_free_immediate(net, in); if (ln) - node_free_immediate(ln); + node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } @@ -768,7 +773,7 @@ static struct fib6_node *fib6_add_1(struct fib6_table *table, * (old node)[fn] NULL */ - ln = node_alloc(); + ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); @@ -1065,6 +1070,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->dst.rt6_next; } @@ -1140,7 +1146,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(table, root, + fn = fib6_add_1(info->nl_net, table, root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, replace_required, extack); @@ -1170,7 +1176,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, */ /* Create subtree root node */ - sfn = node_alloc(); + sfn = node_alloc(info->nl_net); if (!sfn) goto failure; @@ -1181,8 +1187,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, /* Now add the first leaf node to new subtree */ - sn = fib6_add_1(table, sfn, &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, sfn, + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required, extack); @@ -1191,7 +1197,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, root, and then (in failure) stale node in main tree. */ - node_free_immediate(sfn); + node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } @@ -1200,8 +1206,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { - sn = fib6_add_1(table, FIB6_SUBTREE(fn), &rt->rt6i_src.addr, - rt->rt6i_src.plen, + sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), + &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required, extack); @@ -1609,7 +1615,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } read_unlock(&net->ipv6.fib6_walker_lock); - node_free(fn); + node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index cf44d0994b1e8..399d1bceec4a6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -143,9 +143,11 @@ static void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; + struct net *net = dev_net(rt->dst.dev); spin_lock_bh(&ul->lock); list_del(&rt->rt6i_uncached); + atomic_dec(&net->ipv6.rt6_stats->fib_rt_uncache); spin_unlock_bh(&ul->lock); } } @@ -359,8 +361,10 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) + if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); + } return rt; } @@ -1156,6 +1160,8 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct net *net = dev_net(rt6_ex->rt6i->dst.dev); + if (!bucket || !rt6_ex) return; rt6_ex->rt6i->rt6i_node = NULL; @@ -1164,6 +1170,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; + net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1270,6 +1277,7 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, static int rt6_insert_exception(struct rt6_info *nrt, struct rt6_info *ort) { + struct net *net = dev_net(ort->dst.dev); struct rt6_exception_bucket *bucket; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; @@ -1339,6 +1347,7 @@ static int rt6_insert_exception(struct rt6_info *nrt, nrt->rt6i_node = ort->rt6i_node; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; + net->ipv6.rt6_stats->fib_rt_cache++; if (bucket->depth > FIB6_MAX_DEPTH) rt6_exception_remove_oldest(bucket); @@ -1714,6 +1723,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, * No need for another dst_hold() */ rt6_uncached_list_add(uncached_rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); } else { uncached_rt = net->ipv6.ip6_null_entry; dst_hold(&uncached_rt->dst); @@ -1894,6 +1904,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori DST_OBSOLETE_NONE, 0); if (rt) { rt6_info_init(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; @@ -2341,6 +2352,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, * do proper release of the net_device */ rt6_uncached_list_add(rt); + atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); @@ -4422,7 +4434,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, - net->ipv6.rt6_stats->fib_rt_alloc, + atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), -- GitLab From bdc476413dcdb5c38a7dec90fb2bca327021273a Mon Sep 17 00:00:00 2001 From: Amine Kherbouche Date: Wed, 4 Oct 2017 19:35:57 +0200 Subject: [PATCH 1083/1507] ip_tunnel: add mpls over gre support This commit introduces the MPLSoGRE support (RFC 4023), using ip tunnel API by simply adding ipgre_tunnel_encap_(add|del)_mpls_ops() and the new tunnel type TUNNEL_ENCAP_MPLS. Signed-off-by: Amine Kherbouche Signed-off-by: David S. Miller --- include/uapi/linux/if_tunnel.h | 1 + net/mpls/af_mpls.c | 36 ++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 2e520883c054c..a2f48c01365e0 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -84,6 +84,7 @@ enum tunnel_encap_types { TUNNEL_ENCAP_NONE, TUNNEL_ENCAP_FOU, TUNNEL_ENCAP_GUE, + TUNNEL_ENCAP_MPLS, }; #define TUNNEL_ENCAP_FLAG_CSUM (1<<0) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c5b9ce41d66fa..9745e8f698103 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #if IS_ENABLED(CONFIG_IPV6) #include @@ -39,6 +40,36 @@ static int one = 1; static int label_limit = (1 << 20) - 1; static int ttl_max = 255; +#if IS_ENABLED(CONFIG_NET_IP_TUNNEL) +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) +{ + return sizeof(struct mpls_shim_hdr); +} + +static const struct ip_tunnel_encap_ops mpls_iptun_ops = { + .encap_hlen = ipgre_mpls_encap_hlen, +}; + +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ + ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} +#else +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return 0; +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ +} +#endif + static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); @@ -2485,6 +2516,10 @@ static int __init mpls_init(void) 0); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, 0); + err = ipgre_tunnel_encap_add_mpls_ops(); + if (err) + pr_err("Can't add mpls over gre tunnel ops\n"); + err = 0; out: return err; @@ -2502,6 +2537,7 @@ static void __exit mpls_exit(void) dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); + ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); -- GitLab From 97562633bcbac4a07d605ae628d7655fa71caaf5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:19 -0700 Subject: [PATCH 1084/1507] bpf: perf event change needed for subsequent bpf helpers This patch does not impact existing functionalities. It contains the changes in perf event area needed for subsequent bpf_perf_event_read_value and bpf_perf_prog_read_value helpers. Signed-off-by: Yonghong Song Acked-by: Peter Zijlstra (Intel) Signed-off-by: David S. Miller --- include/linux/perf_event.h | 7 +++++-- kernel/bpf/arraymap.c | 2 +- kernel/events/core.c | 15 +++++++++++++-- kernel/trace/bpf_trace.c | 2 +- 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8e22f24ded6a3..79b18a20cf5d7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -806,6 +806,7 @@ struct perf_output_handle { struct bpf_perf_event_data_kern { struct pt_regs *regs; struct perf_sample_data *data; + struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF @@ -884,7 +885,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_event_read_local(struct perf_event *event, u64 *value); +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -1286,7 +1288,8 @@ static inline const struct perf_event_attr *perf_event_attrs(struct perf_event * { return ERR_PTR(-EINVAL); } -static inline int perf_event_read_local(struct perf_event *event, u64 *value) +static inline int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { return -EINVAL; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 98c0f00c3f5e0..68d866628be0d 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -492,7 +492,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - if (perf_event_read_local(event, &value) == -EOPNOTSUPP) + if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6bc21e202ae40..902149f053811 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3684,10 +3684,12 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -int perf_event_read_local(struct perf_event *event, u64 *value) +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { unsigned long flags; int ret = 0; + u64 now; /* * Disabling interrupts avoids all counter scheduling (context @@ -3718,13 +3720,21 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; } + now = event->shadow_ctx_time + perf_clock(); + if (enabled) + *enabled = now - event->tstamp_enabled; /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ - if (event->oncpu == smp_processor_id()) + if (event->oncpu == smp_processor_id()) { event->pmu->read(event); + if (running) + *running = now - event->tstamp_running; + } else if (running) { + *running = event->total_time_running; + } *value = local64_read(&event->count); out: @@ -8072,6 +8082,7 @@ static void bpf_overflow_handler(struct perf_event *event, struct bpf_perf_event_data_kern ctx = { .data = data, .regs = regs, + .event = event, }; int ret = 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index dc498b605d5dd..95888ae6c2634 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -275,7 +275,7 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value); + err = perf_event_read_local(ee->event, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi -- GitLab From 908432ca84fc229e906ba164219e9ad0fe56f755 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:20 -0700 Subject: [PATCH 1085/1507] bpf: add helper bpf_perf_event_read_value for perf event array map Hardware pmu counters are limited resources. When there are more pmu based perf events opened than available counters, kernel will multiplex these events so each event gets certain percentage (but not 100%) of the pmu time. In case that multiplexing happens, the number of samples or counter value will not reflect the case compared to no multiplexing. This makes comparison between different runs difficult. Typically, the number of samples or counter value should be normalized before comparing to other experiments. The typical normalization is done like: normalized_num_samples = num_samples * time_enabled / time_running normalized_counter_value = counter_value * time_enabled / time_running where time_enabled is the time enabled for event and time_running is the time running for event since last normalization. This patch adds helper bpf_perf_event_read_value for kprobed based perf event array map, to read perf counter and enabled/running time. The enabled/running time is accumulated since the perf event open. To achieve scaling factor between two bpf invocations, users can can use cpu_id as the key (which is typical for perf array usage model) to remember the previous value and do the calculation inside the bpf program. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 21 +++++++++++++++++-- kernel/bpf/verifier.c | 4 +++- kernel/trace/bpf_trace.c | 45 ++++++++++++++++++++++++++++++++++++---- 3 files changed, 63 insertions(+), 7 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6082faf5fd2a0..7b57a212c7d7d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -641,6 +641,14 @@ union bpf_attr { * @xdp_md: pointer to xdp_md * @delta: An positive/negative integer to be added to xdp_md.data_meta * Return: 0 on success or negative on error + * + * int bpf_perf_event_read_value(map, flags, buf, buf_size) + * read perf event counter value and perf event enabled/running time + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * @buf: buf to fill + * @buf_size: size of the buf + * Return: 0 on success or negative error code */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -697,7 +705,8 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ - FN(xdp_adjust_meta), + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -741,7 +750,9 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK /* BPF_FUNC_perf_event_output for sk_buff input context. */ @@ -934,4 +945,10 @@ enum { #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 52b022310f6ac..590125e29161c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1552,7 +1552,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && - func_id != BPF_FUNC_perf_event_output) + func_id != BPF_FUNC_perf_event_output && + func_id != BPF_FUNC_perf_event_read_value) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -1595,6 +1596,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: + case BPF_FUNC_perf_event_read_value: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 95888ae6c2634..0be86cc0130e7 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -255,14 +255,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +static __always_inline int +get_map_perf_counter(struct bpf_map *map, u64 flags, + u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - u64 value = 0; - int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -275,7 +275,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value, NULL, NULL); + return perf_event_read_local(ee->event, value, enabled, running); +} + +BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +{ + u64 value = 0; + int err; + + err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi @@ -293,6 +301,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_event_read_value_proto = { + .func = bpf_perf_event_read_value, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); static __always_inline u64 @@ -499,6 +534,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; default: return tracing_func_proto(func_id); } -- GitLab From 020a32d9581ac824d038b0b4e24e977e3cc8589f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:21 -0700 Subject: [PATCH 1086/1507] bpf: add a test case for helper bpf_perf_event_read_value The bpf sample program tracex6 is enhanced to use the new helper to read enabled/running time as well. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/tracex6_kern.c | 26 +++++++++++++++++++++++ samples/bpf/tracex6_user.c | 13 +++++++++++- tools/include/uapi/linux/bpf.h | 3 ++- tools/testing/selftests/bpf/bpf_helpers.h | 3 +++ 4 files changed, 43 insertions(+), 2 deletions(-) diff --git a/samples/bpf/tracex6_kern.c b/samples/bpf/tracex6_kern.c index e7d180305974e..46c557afac73a 100644 --- a/samples/bpf/tracex6_kern.c +++ b/samples/bpf/tracex6_kern.c @@ -15,6 +15,12 @@ struct bpf_map_def SEC("maps") values = { .value_size = sizeof(u64), .max_entries = 64, }; +struct bpf_map_def SEC("maps") values2 = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(struct bpf_perf_event_value), + .max_entries = 64, +}; SEC("kprobe/htab_map_get_next_key") int bpf_prog1(struct pt_regs *ctx) @@ -37,5 +43,25 @@ int bpf_prog1(struct pt_regs *ctx) return 0; } +SEC("kprobe/htab_map_lookup_elem") +int bpf_prog2(struct pt_regs *ctx) +{ + u32 key = bpf_get_smp_processor_id(); + struct bpf_perf_event_value *val, buf; + int error; + + error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf)); + if (error) + return 0; + + val = bpf_map_lookup_elem(&values2, &key); + if (val) + *val = buf; + else + bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST); + + return 0; +} + char _license[] SEC("license") = "GPL"; u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c index a05a99a0752f4..3341a96fc046c 100644 --- a/samples/bpf/tracex6_user.c +++ b/samples/bpf/tracex6_user.c @@ -22,6 +22,7 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr) { + struct bpf_perf_event_value value2; int pmu_fd, error = 0; cpu_set_t set; __u64 value; @@ -46,8 +47,18 @@ static void check_on_cpu(int cpu, struct perf_event_attr *attr) fprintf(stderr, "Value missing for CPU %d\n", cpu); error = 1; goto on_exit; + } else { + fprintf(stderr, "CPU %d: %llu\n", cpu, value); + } + /* The above bpf_map_lookup_elem should trigger the second kprobe */ + if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) { + fprintf(stderr, "Value2 missing for CPU %d\n", cpu); + error = 1; + goto on_exit; + } else { + fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu, + value2.counter, value2.enabled, value2.running); } - fprintf(stderr, "CPU %d: %llu\n", cpu, value); on_exit: assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cb2b9f95160aa..cdf6c4f50b0f1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -697,7 +697,8 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ - FN(xdp_adjust_meta), + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index a56053db26f54..c15ca83dbbd92 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -72,6 +72,9 @@ static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = static int (*bpf_sock_map_update)(void *map, void *key, void *value, unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; +static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, + void *buf, unsigned int buf_size) = + (void *) BPF_FUNC_perf_event_read_value; /* llvm builtin functions that eBPF C program may use to -- GitLab From 4bebdc7a85aa400c0222b5329861e4ad9252f1e5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:22 -0700 Subject: [PATCH 1087/1507] bpf: add helper bpf_perf_prog_read_value This patch adds helper bpf_perf_prog_read_cvalue for perf event based bpf programs, to read event counter and enabled/running time. The enabled/running time is accumulated since the perf event open. The typical use case for perf event based bpf program is to attach itself to a single event. In such cases, if it is desirable to get scaling factor between two bpf invocations, users can can save the time values in a map, and use the value from the map and the current value to calculate the scaling factor. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 10 +++++++++- kernel/trace/bpf_trace.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7b57a212c7d7d..5bbbec17aa5a6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -649,6 +649,13 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return: 0 on success or negative error code + * + * int bpf_perf_prog_read_value(ctx, buf, buf_size) + * read perf prog attached perf event counter and enabled/running time + * @ctx: pointer to ctx + * @buf: buf to fill + * @buf_size: size of the buf + * Return : 0 on success or negative error code */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -706,7 +713,8 @@ union bpf_attr { FN(sk_redirect_map), \ FN(sock_map_update), \ FN(xdp_adjust_meta), \ - FN(perf_event_read_value), + FN(perf_event_read_value), \ + FN(perf_prog_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0be86cc0130e7..04ea5314f2bc9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -613,6 +613,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { + .func = bpf_perf_prog_read_value_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -620,6 +646,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_perf_prog_read_value: + return &bpf_perf_prog_read_value_proto_tp; default: return tracing_func_proto(func_id); } -- GitLab From 81b9cf8028a17bdbdaa0da80b735b32150d4e89e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:23 -0700 Subject: [PATCH 1088/1507] bpf: add a test case for helper bpf_perf_prog_read_value The bpf sample program trace_event is enhanced to use the new helper to print out enabled/running time. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/trace_event_kern.c | 10 ++++++++++ samples/bpf/trace_event_user.c | 13 ++++++++----- tools/include/uapi/linux/bpf.h | 3 ++- tools/testing/selftests/bpf/bpf_helpers.h | 3 +++ 4 files changed, 23 insertions(+), 6 deletions(-) diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 41b6115a32eb1..a77a583d94d42 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -37,10 +37,14 @@ struct bpf_map_def SEC("maps") stackmap = { SEC("perf_event") int bpf_prog1(struct bpf_perf_event_data *ctx) { + char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu"; + char time_fmt2[] = "Get Time Failed, ErrCode: %d"; char fmt[] = "CPU-%d period %lld ip %llx"; u32 cpu = bpf_get_smp_processor_id(); + struct bpf_perf_event_value value_buf; struct key_t key; u64 *val, one = 1; + int ret; if (ctx->sample_period < 10000) /* ignore warmup */ @@ -54,6 +58,12 @@ int bpf_prog1(struct bpf_perf_event_data *ctx) return 0; } + ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value)); + if (!ret) + bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running); + else + bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret); + val = bpf_map_lookup_elem(&counts, &key); if (val) (*val)++; diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 7bd827b84a679..bf4f1b6d9a52e 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -127,6 +127,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr) int *pmu_fd = malloc(nr_cpus * sizeof(int)); int i, error = 0; + /* system wide perf event, no need to inherit */ + attr->inherit = 0; + /* open perf_event on all cpus */ for (i = 0; i < nr_cpus; i++) { pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0); @@ -154,6 +157,11 @@ static void test_perf_event_task(struct perf_event_attr *attr) { int pmu_fd; + /* per task perf event, enable inherit so the "dd ..." command can be traced properly. + * Enabling inherit will cause bpf_perf_prog_read_time helper failure. + */ + attr->inherit = 1; + /* open task bound event */ pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0); if (pmu_fd < 0) { @@ -175,14 +183,12 @@ static void test_bpf_perf_event(void) .freq = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, - .inherit = 1, }; struct perf_event_attr attr_type_sw = { .sample_freq = SAMPLE_FREQ, .freq = 1, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, - .inherit = 1, }; struct perf_event_attr attr_hw_cache_l1d = { .sample_freq = SAMPLE_FREQ, @@ -192,7 +198,6 @@ static void test_bpf_perf_event(void) PERF_COUNT_HW_CACHE_L1D | (PERF_COUNT_HW_CACHE_OP_READ << 8) | (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16), - .inherit = 1, }; struct perf_event_attr attr_hw_cache_branch_miss = { .sample_freq = SAMPLE_FREQ, @@ -202,7 +207,6 @@ static void test_bpf_perf_event(void) PERF_COUNT_HW_CACHE_BPU | (PERF_COUNT_HW_CACHE_OP_READ << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), - .inherit = 1, }; struct perf_event_attr attr_type_raw = { .sample_freq = SAMPLE_FREQ, @@ -210,7 +214,6 @@ static void test_bpf_perf_event(void) .type = PERF_TYPE_RAW, /* Intel Instruction Retired */ .config = 0xc0, - .inherit = 1, }; printf("Test HW_CPU_CYCLES\n"); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cdf6c4f50b0f1..0894fd20b12bd 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -698,7 +698,8 @@ union bpf_attr { FN(sk_redirect_map), \ FN(sock_map_update), \ FN(xdp_adjust_meta), \ - FN(perf_event_read_value), + FN(perf_event_read_value), \ + FN(perf_prog_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index c15ca83dbbd92..e25dbf6038cf6 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -75,6 +75,9 @@ static int (*bpf_sock_map_update)(void *map, void *key, void *value, static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, void *buf, unsigned int buf_size) = (void *) BPF_FUNC_perf_event_read_value; +static int (*bpf_perf_prog_read_value)(void *ctx, void *buf, + unsigned int buf_size) = + (void *) BPF_FUNC_perf_prog_read_value; /* llvm builtin functions that eBPF C program may use to -- GitLab From a2d3f3e33853ef52e5f66b41c3e8ee5710aa3305 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 5 Oct 2017 19:03:05 +0200 Subject: [PATCH 1089/1507] ipv6: fix net.ipv6.conf.all.accept_dad behaviour for real Commit 35e015e1f577 ("ipv6: fix net.ipv6.conf.all interface DAD handlers") was intended to affect accept_dad flag handling in such a way that DAD operation and mode on a given interface would be selected according to the maximum value of conf/{all,interface}/accept_dad. However, addrconf_dad_begin() checks for particular cases in which we need to skip DAD, and this check was modified in the wrong way. Namely, it was modified so that, if the accept_dad flag is 0 for the given interface *or* for all interfaces, DAD would be skipped. We have instead to skip DAD if accept_dad is 0 for the given interface *and* for all interfaces. Fixes: 35e015e1f577 ("ipv6: fix net.ipv6.conf.all interface DAD handlers") Acked-by: Stefano Brivio Signed-off-by: Matteo Croce Reported-by: Erik Kline Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 96861c702c069..4a96ebbf8eda5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3820,8 +3820,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) goto out; if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - dev_net(dev)->ipv6.devconf_all->accept_dad < 1 || - idev->cnf.accept_dad < 1 || + (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 && + idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bump_id = ifp->flags & IFA_F_TENTATIVE; -- GitLab From 64237470ddf97b63155fbd272c9e743e01d5f514 Mon Sep 17 00:00:00 2001 From: Lin Zhang Date: Fri, 6 Oct 2017 01:37:29 +0800 Subject: [PATCH 1090/1507] net: phonet: mark header_ops as const Signed-off-by: Lin Zhang Signed-off-by: David S. Miller --- include/linux/if_phonet.h | 2 +- net/phonet/af_phonet.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/if_phonet.h b/include/linux/if_phonet.h index bbcdb0a767d87..a118ee4a84281 100644 --- a/include/linux/if_phonet.h +++ b/include/linux/if_phonet.h @@ -10,5 +10,5 @@ #include -extern struct header_ops phonet_header_ops; +extern const struct header_ops phonet_header_ops; #endif diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index f925753668a7f..b12142e55d199 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -149,7 +149,7 @@ static int pn_header_parse(const struct sk_buff *skb, unsigned char *haddr) return 1; } -struct header_ops phonet_header_ops = { +const struct header_ops phonet_header_ops = { .create = pn_header_create, .parse = pn_header_parse, }; -- GitLab From 548ec114705bb8f0879a0da12abec17f17a7cc26 Mon Sep 17 00:00:00 2001 From: Lin Zhang Date: Fri, 6 Oct 2017 01:40:35 +0800 Subject: [PATCH 1091/1507] net: phonet: mark phonet_protocol as const The phonet_protocol structs don't need to be written by anyone and so can be marked as const. Signed-off-by: Lin Zhang Signed-off-by: David S. Miller --- include/net/phonet/phonet.h | 6 ++++-- net/phonet/af_phonet.c | 15 ++++++++------- net/phonet/datagram.c | 2 +- net/phonet/pep.c | 2 +- 4 files changed, 14 insertions(+), 11 deletions(-) diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 039cc29cb4a81..51e1a2a45d027 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -108,8 +108,10 @@ struct phonet_protocol { int sock_type; }; -int phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp); -void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp); +int phonet_proto_register(unsigned int protocol, + const struct phonet_protocol *pp); +void phonet_proto_unregister(unsigned int protocol, + const struct phonet_protocol *pp); int phonet_sysctl_init(void); void phonet_sysctl_exit(void); diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index b12142e55d199..3b0ef691f5b1b 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -35,11 +35,11 @@ #include /* Transport protocol registration */ -static struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; +static const struct phonet_protocol *proto_tab[PHONET_NPROTO] __read_mostly; -static struct phonet_protocol *phonet_proto_get(unsigned int protocol) +static const struct phonet_protocol *phonet_proto_get(unsigned int protocol) { - struct phonet_protocol *pp; + const struct phonet_protocol *pp; if (protocol >= PHONET_NPROTO) return NULL; @@ -53,7 +53,7 @@ static struct phonet_protocol *phonet_proto_get(unsigned int protocol) return pp; } -static inline void phonet_proto_put(struct phonet_protocol *pp) +static inline void phonet_proto_put(const struct phonet_protocol *pp) { module_put(pp->prot->owner); } @@ -65,7 +65,7 @@ static int pn_socket_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; struct pn_sock *pn; - struct phonet_protocol *pnp; + const struct phonet_protocol *pnp; int err; if (!capable(CAP_SYS_ADMIN)) @@ -470,7 +470,7 @@ static struct packet_type phonet_packet_type __read_mostly = { static DEFINE_MUTEX(proto_tab_lock); int __init_or_module phonet_proto_register(unsigned int protocol, - struct phonet_protocol *pp) + const struct phonet_protocol *pp) { int err = 0; @@ -492,7 +492,8 @@ int __init_or_module phonet_proto_register(unsigned int protocol, } EXPORT_SYMBOL(phonet_proto_register); -void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp) +void phonet_proto_unregister(unsigned int protocol, + const struct phonet_protocol *pp) { mutex_lock(&proto_tab_lock); BUG_ON(proto_tab[protocol] != pp); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 5e710435ffa96..b44fb9018fb83 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -195,7 +195,7 @@ static struct proto pn_proto = { .name = "PHONET", }; -static struct phonet_protocol pn_dgram_proto = { +static const struct phonet_protocol pn_dgram_proto = { .ops = &phonet_dgram_ops, .prot = &pn_proto, .sock_type = SOCK_DGRAM, diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e81537991ddf0..9fc76b19cd3c1 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -1351,7 +1351,7 @@ static struct proto pep_proto = { .name = "PNPIPE", }; -static struct phonet_protocol pep_pn_proto = { +static const struct phonet_protocol pep_pn_proto = { .ops = &phonet_stream_ops, .prot = &pep_proto, .sock_type = SOCK_SEQPACKET, -- GitLab From f192970de860d3ab90aa9e2a22853201a57bde78 Mon Sep 17 00:00:00 2001 From: William Tu Date: Thu, 5 Oct 2017 12:07:12 -0700 Subject: [PATCH 1092/1507] ip_gre: check packet length and mtu correctly in erspan tx Similarly to early patch for erspan_xmit(), the ARPHDR_ETHER device is the length of the whole ether packet. So skb->len should subtract the dev->hard_header_len. Fixes: 1a66a836da63 ("gre: add collect_md mode to ERSPAN tunnel") Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN") Signed-off-by: William Tu Cc: Xin Long Cc: David Laight Reviewed-by: Xin Long Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index dc23177764996..c105a315b1a3c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -579,8 +579,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, false)) goto err_free_rt; - if (skb->len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } @@ -731,8 +731,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; - if (skb->len - dev->hard_header_len > dev->mtu) { - pskb_trim(skb, dev->mtu); + if (skb->len > dev->mtu + dev->hard_header_len) { + pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } -- GitLab From 00a534e5ea5c21b95f58cbb2f7918cc9fa82dd47 Mon Sep 17 00:00:00 2001 From: Axel Beckert Date: Thu, 5 Oct 2017 22:00:33 +0200 Subject: [PATCH 1093/1507] doc: Fix typo "8023.ad" in bonding documentation Should be "802.3ad" like everywhere else in the document. Signed-off-by: Axel Beckert Signed-off-by: David S. Miller --- Documentation/networking/bonding.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 57f52cdce32e4..9ba04c0bab8db 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -2387,7 +2387,7 @@ broadcast: Like active-backup, there is not much advantage to this and packet type ID), so in a "gatewayed" configuration, all outgoing traffic will generally use the same device. Incoming traffic may also end up on a single device, but that is - dependent upon the balancing policy of the peer's 8023.ad + dependent upon the balancing policy of the peer's 802.3ad implementation. In a "local" configuration, traffic will be distributed across the devices in the bond. -- GitLab From 8fe2d6ccd52b086268f2f36e5e2fc0fe3aeffa80 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 5 Oct 2017 16:20:56 -0700 Subject: [PATCH 1094/1507] bpf: fix liveness marking while processing Rx = Ry instruction the verifier does regs[insn->dst_reg] = regs[insn->src_reg] which often clears write mark (when Ry doesn't have it) that was just set by check_reg_arg(Rx) prior to the assignment. That causes mark_reg_read() to keep marking Rx in this block as REG_LIVE_READ (since the logic incorrectly misses that it's screened by the write) and in many of its parents (until lucky write into the same Rx or beginning of the program). That causes is_state_visited() logic to miss many pruning opportunities. Furthermore mark_reg_read() logic propagates the read mark for BPF_REG_FP as well (though it's readonly) which causes harmless but unnecssary work during is_state_visited(). Note that do_propagate_liveness() skips FP correctly, so do the same in mark_reg_read() as well. It saves 0.2 seconds for the test below program before after bpf_lb-DLB_L3.o 2604 2304 bpf_lb-DLB_L4.o 11159 3723 bpf_lb-DUNKNOWN.o 1116 1110 bpf_lxc-DDROP_ALL.o 34566 28004 bpf_lxc-DUNKNOWN.o 53267 39026 bpf_netdev.o 17843 16943 bpf_overlay.o 8672 7929 time ~11 sec ~4 sec Fixes: dc503a8ad984 ("bpf/verifier: track liveness for pruning") Signed-off-by: Alexei Starovoitov Acked-by: Edward Cree Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e8..8b8d6ba39e238 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -653,6 +653,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; + if (regno == BPF_REG_FP) + /* We don't need to worry about FP liveness because it's read-only */ + return; + while (parent) { /* if read wasn't screened by an earlier write ... */ if (state->regs[regno].live & REG_LIVE_WRITTEN) @@ -2345,6 +2349,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * copy register state to dest reg */ regs[insn->dst_reg] = regs[insn->src_reg]; + regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { -- GitLab From 473d97343f94ff20f5196078314e4dd83156d3a2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 5 Oct 2017 21:52:11 -0700 Subject: [PATCH 1095/1507] bpf: Change bpf_obj_name_cpy() to better ensure map's name is init by 0 During get_info_by_fd, the prog/map name is memcpy-ed. It depends on the prog->aux->name and map->name to be zero initialized. bpf_prog_aux is easy to guarantee that aux->name is zero init. The name in bpf_map may be harder to be guaranteed in the future when new map type is added. Hence, this patch makes bpf_obj_name_cpy() to always zero init the prog/map name. Suggested-by: Daniel Borkmann Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0048cb24ba7b4..d124e702e040e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -322,6 +322,8 @@ static int bpf_obj_name_cpy(char *dst, const char *src) { const char *end = src + BPF_OBJ_NAME_LEN; + memset(dst, 0, BPF_OBJ_NAME_LEN); + /* Copy all isalnum() and '_' char */ while (src < end && *src) { if (!isalnum(*src) && *src != '_') @@ -333,9 +335,6 @@ static int bpf_obj_name_cpy(char *dst, const char *src) if (src == end) return -EINVAL; - /* '\0' terminates dst */ - *dst = 0; - return 0; } -- GitLab From 067cae47771c864604969fd902efe10916e0d79c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 5 Oct 2017 21:52:12 -0700 Subject: [PATCH 1096/1507] bpf: Use char in prog and map name Instead of u8, use char for prog and map name. It can avoid the userspace tool getting compiler's signess warning. The bpf_prog_aux, bpf_map, bpf_attr, bpf_prog_info and bpf_map_info are changed. Signed-off-by: Martin KaFai Lau Cc: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 ++-- include/uapi/linux/bpf.h | 8 ++++---- tools/include/uapi/linux/bpf.h | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a67daea731ab8..bc7da2ddfcaff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,7 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ @@ -189,7 +189,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5bbbec17aa5a6..6db9e1d679cd3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -230,7 +230,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,7 +253,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -888,7 +888,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -898,7 +898,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0894fd20b12bd..fb4fb81ce5b03 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -230,7 +230,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,7 +253,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -871,7 +871,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -881,7 +881,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops -- GitLab From 368211fb920a0b789c238942c6af0414539f79d6 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 5 Oct 2017 21:52:13 -0700 Subject: [PATCH 1097/1507] bpf: Append prog->aux->name in bpf_get_prog_name() This patch makes the bpf_prog's name available in kallsyms. The new format is bpf_prog_tag[_name]. Sample kallsyms from running selftests/bpf/test_progs: [root@arch-fb-vm1 ~]# egrep ' bpf_prog_[0-9a-fA-F]{16}' /proc/kallsyms ffffffffa0048000 t bpf_prog_dabf0207d1992486_test_obj_id ffffffffa0038000 t bpf_prog_a04f5eef06a7f555__123456789ABCDE ffffffffa0050000 t bpf_prog_a04f5eef06a7f555 Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/core.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c6be15ae83ee7..248961af2421d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -309,12 +309,25 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { + const char *end = sym + KSYM_NAME_LEN; + BUILD_BUG_ON(sizeof("bpf_prog_") + - sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN); + sizeof(prog->tag) * 2 + + /* name has been null terminated. + * We should need +1 for the '_' preceding + * the name. However, the null character + * is double counted between the name and the + * sizeof("bpf_prog_") above, so we omit + * the +1 here. + */ + sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); - *sym = 0; + if (prog->aux->name[0]) + snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); + else + *sym = 0; } static __always_inline unsigned long -- GitLab From a69518cf0b4cbf02c6bc1239cdeb8750a9eb8077 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 8 Oct 2017 11:53:26 +0200 Subject: [PATCH 1098/1507] mlxsw: spectrum_router: Avoid expensive lookup during route removal In commit fc922bb0dd94 ("mlxsw: spectrum_router: Use one LPM tree for all virtual routers") I increased the scale of supported VRFs by having all of them share the same LPM tree. In order to avoid look-ups for prefix lengths that don't exist, each route removal would trigger an aggregation across all the active virtual routers to see which prefix lengths are in use and which aren't and structure the tree accordingly. With the way the data structures are currently laid out, this is a very expensive operation. When preformed repeatedly - due to the invocation of the abort mechanism - and with enough VRFs, this can result in a hung task. For now, avoid this optimization until it can be properly re-added in net-next. Fixes: fc922bb0dd94 ("mlxsw: spectrum_router: Use one LPM tree for all virtual routers") Signed-off-by: Ido Schimmel Reported-by: David Ahern Tested-by: David Ahern Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 032089efc1a0f..c16718d296d38 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3505,20 +3505,6 @@ static int mlxsw_sp_fib_lpm_tree_link(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib) { - struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; - struct mlxsw_sp_lpm_tree *lpm_tree; - - /* Aggregate prefix lengths across all virtual routers to make - * sure we only have used prefix lengths in the LPM tree. - */ - mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - fib->proto); - if (IS_ERR(lpm_tree)) - goto err_tree_get; - mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); - -err_tree_get: if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) return; mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); -- GitLab From c1f2c6d025d365d961dcdf555ecf0f60066f38a3 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 8 Oct 2017 11:57:55 +0200 Subject: [PATCH 1099/1507] mlxsw: spectrum: Add extack for VLAN enslavements Similar to physical ports, enslavement of VLAN devices can also fail. Use extack to indicate why the enslavement failed. $ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10 $ ip link add name bond0 type bond mode 802.3ad $ ip link set dev enp1s0np1.10 master bond0 Error: spectrum: VLAN devices only support bridge and VRF uppers. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5cd4df08ce975..5ab4fd74a325f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -4389,18 +4390,25 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct netdev_notifier_changeupper_info *info = ptr; + struct netlink_ext_ack *extack; struct net_device *upper_dev; int err = 0; + extack = netdev_notifier_info_to_extack(&info->info); + switch (event) { case NETDEV_PRECHANGEUPPER: upper_dev = info->upper_dev; - if (!netif_is_bridge_master(upper_dev)) + if (!netif_is_bridge_master(upper_dev)) { + NL_SET_ERR_MSG(extack, "spectrum: VLAN devices only support bridge and VRF uppers"); return -EINVAL; + } if (!info->linking) break; - if (netdev_has_any_upper_dev(upper_dev)) + if (netdev_has_any_upper_dev(upper_dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; -- GitLab From 9b63ef88d3a16d67afbe7916625289650e9f30d9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 8 Oct 2017 11:57:56 +0200 Subject: [PATCH 1100/1507] mlxsw: spectrum: Propagate extack further for bridge enslavements The code that actually takes care of bridge offload introduces a few more non-trivial constraints with regards to bridge enslavements. Propagate extack there to indicate the reason. $ ip link add link enp1s0np1 name enp1s0np1.10 type vlan id 10 $ ip link add link enp1s0np1 name enp1s0np1.20 type vlan id 20 $ ip link add name br0 type bridge $ ip link set dev enp1s0np1.10 master br0 $ ip link set dev enp1s0np1.20 master br0 Error: spectrum: Can not bridge VLAN uppers of the same port. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 6 +++-- .../net/ethernet/mellanox/mlxsw/spectrum.h | 3 ++- .../mellanox/mlxsw/spectrum_switchdev.c | 25 +++++++++++++------ 3 files changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5ab4fd74a325f..321988ac57ccb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4299,7 +4299,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, if (info->linking) err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, lower_dev, - upper_dev); + upper_dev, + extack); else mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lower_dev, @@ -4416,7 +4417,8 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, if (info->linking) err = mlxsw_sp_port_bridge_join(mlxsw_sp_port, vlan_dev, - upper_dev); + upper_dev, + extack); else mlxsw_sp_port_bridge_leave(mlxsw_sp_port, vlan_dev, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ae67e6046098c..8e45183dc9bbb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -326,7 +326,8 @@ void mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, - struct net_device *br_dev); + struct net_device *br_dev, + struct netlink_ext_ack *extack); void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, struct net_device *br_dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0f9eac5f4ebfd..2cfdf22a145ff 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include "spectrum.h" @@ -107,7 +108,8 @@ struct mlxsw_sp_bridge_vlan { struct mlxsw_sp_bridge_ops { int (*port_join)(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port); + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack); void (*port_leave)(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, struct mlxsw_sp_port *mlxsw_sp_port); @@ -1735,12 +1737,15 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { static int mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port) + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - if (is_vlan_dev(bridge_port->dev)) + if (is_vlan_dev(bridge_port->dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Can not enslave a VLAN device to a VLAN-aware bridge"); return -EINVAL; + } mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1); if (WARN_ON(!mlxsw_sp_port_vlan)) @@ -1797,13 +1802,16 @@ mlxsw_sp_port_is_br_member(const struct mlxsw_sp_port *mlxsw_sp_port, static int mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_bridge_port *bridge_port, - struct mlxsw_sp_port *mlxsw_sp_port) + struct mlxsw_sp_port *mlxsw_sp_port, + struct netlink_ext_ack *extack) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; u16 vid; - if (!is_vlan_dev(bridge_port->dev)) + if (!is_vlan_dev(bridge_port->dev)) { + NL_SET_ERR_MSG(extack, "spectrum: Only VLAN devices can be enslaved to a VLAN-unaware bridge"); return -EINVAL; + } vid = vlan_dev_vlan_id(bridge_port->dev); mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); @@ -1811,7 +1819,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device, return -EINVAL; if (mlxsw_sp_port_is_br_member(mlxsw_sp_port, bridge_device->dev)) { - netdev_err(mlxsw_sp_port->dev, "Can't bridge VLAN uppers of the same port\n"); + NL_SET_ERR_MSG(extack, "spectrum: Can not bridge VLAN uppers of the same port"); return -EINVAL; } @@ -1854,7 +1862,8 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = { int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, - struct net_device *br_dev) + struct net_device *br_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_bridge_device *bridge_device; @@ -1867,7 +1876,7 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, bridge_device = bridge_port->bridge_device; err = bridge_device->ops->port_join(bridge_device, bridge_port, - mlxsw_sp_port); + mlxsw_sp_port, extack); if (err) goto err_port_join; -- GitLab From 486e3981057cacdafd62ba0618612193ff12d1dd Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 6 Oct 2017 08:33:57 -0700 Subject: [PATCH 1101/1507] hv_netvsc: Change the hash level variable to bit flags This simplifies the logic and make it easier to add more options. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 11 ++++- drivers/net/hyperv/netvsc_drv.c | 73 ++++++++++++++++++++++----------- 2 files changed, 59 insertions(+), 25 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 6f550e15a41cc..a81335e8ebe89 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -704,6 +704,14 @@ struct netvsc_reconfig { u32 event; }; +/* L4 hash bits for different protocols */ +#define HV_TCP4_L4HASH 1 +#define HV_TCP6_L4HASH 2 +#define HV_UDP4_L4HASH 4 +#define HV_UDP6_L4HASH 8 +#define HV_DEFAULT_L4HASH (HV_TCP4_L4HASH | HV_TCP6_L4HASH | HV_UDP4_L4HASH | \ + HV_UDP6_L4HASH) + /* The context of the netvsc device */ struct net_device_context { /* point back to our device context */ @@ -726,10 +734,9 @@ struct net_device_context { u32 tx_send_table[VRSS_SEND_TAB_SIZE]; /* Ethtool settings */ - bool udp4_l4_hash; - bool udp6_l4_hash; u8 duplex; u32 speed; + u32 l4_hash; /* L4 hash settings */ struct netvsc_ethtool_stats eth_stats; /* State to manage the associated VF interface. */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index dfb986421ec6f..9bc7dbab9506e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -203,7 +203,7 @@ static inline u32 netvsc_get_hash( const struct net_device_context *ndc) { struct flow_keys flow; - u32 hash; + u32 hash, pkt_proto = 0; static u32 hashrnd __read_mostly; net_get_random_once(&hashrnd, sizeof(hashrnd)); @@ -211,11 +211,25 @@ static inline u32 netvsc_get_hash( if (!skb_flow_dissect_flow_keys(skb, &flow, 0)) return 0; - if (flow.basic.ip_proto == IPPROTO_TCP || - (flow.basic.ip_proto == IPPROTO_UDP && - ((flow.basic.n_proto == htons(ETH_P_IP) && ndc->udp4_l4_hash) || - (flow.basic.n_proto == htons(ETH_P_IPV6) && - ndc->udp6_l4_hash)))) { + switch (flow.basic.ip_proto) { + case IPPROTO_TCP: + if (flow.basic.n_proto == htons(ETH_P_IP)) + pkt_proto = HV_TCP4_L4HASH; + else if (flow.basic.n_proto == htons(ETH_P_IPV6)) + pkt_proto = HV_TCP6_L4HASH; + + break; + + case IPPROTO_UDP: + if (flow.basic.n_proto == htons(ETH_P_IP)) + pkt_proto = HV_UDP4_L4HASH; + else if (flow.basic.n_proto == htons(ETH_P_IPV6)) + pkt_proto = HV_UDP6_L4HASH; + + break; + } + + if (pkt_proto & ndc->l4_hash) { return skb_get_hash(skb); } else { if (flow.basic.n_proto == htons(ETH_P_IP)) @@ -898,8 +912,7 @@ static void netvsc_init_settings(struct net_device *dev) { struct net_device_context *ndc = netdev_priv(dev); - ndc->udp4_l4_hash = true; - ndc->udp6_l4_hash = true; + ndc->l4_hash = HV_DEFAULT_L4HASH; ndc->speed = SPEED_UNKNOWN; ndc->duplex = DUPLEX_FULL; @@ -1245,23 +1258,25 @@ static int netvsc_get_rss_hash_opts(struct net_device_context *ndc, struct ethtool_rxnfc *info) { + const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data = RXH_IP_SRC | RXH_IP_DST; switch (info->flow_type) { case TCP_V4_FLOW: case TCP_V6_FLOW: - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data |= l4_flag; break; case UDP_V4_FLOW: - if (ndc->udp4_l4_hash) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + if (ndc->l4_hash & HV_UDP4_L4HASH) + info->data |= l4_flag; break; case UDP_V6_FLOW: - if (ndc->udp6_l4_hash) - info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + if (ndc->l4_hash & HV_UDP6_L4HASH) + info->data |= l4_flag; break; @@ -1302,23 +1317,35 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc, { if (info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) { - if (info->flow_type == UDP_V4_FLOW) - ndc->udp4_l4_hash = true; - else if (info->flow_type == UDP_V6_FLOW) - ndc->udp6_l4_hash = true; - else + switch (info->flow_type) { + case UDP_V4_FLOW: + ndc->l4_hash |= HV_UDP4_L4HASH; + break; + + case UDP_V6_FLOW: + ndc->l4_hash |= HV_UDP6_L4HASH; + break; + + default: return -EOPNOTSUPP; + } return 0; } if (info->data == (RXH_IP_SRC | RXH_IP_DST)) { - if (info->flow_type == UDP_V4_FLOW) - ndc->udp4_l4_hash = false; - else if (info->flow_type == UDP_V6_FLOW) - ndc->udp6_l4_hash = false; - else + switch (info->flow_type) { + case UDP_V4_FLOW: + ndc->l4_hash &= ~HV_UDP4_L4HASH; + break; + + case UDP_V6_FLOW: + ndc->l4_hash &= ~HV_UDP6_L4HASH; + break; + + default: return -EOPNOTSUPP; + } return 0; } -- GitLab From 0518ec4f9d8804a9b3ab4306b4b10828f35f715b Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 6 Oct 2017 08:33:58 -0700 Subject: [PATCH 1102/1507] hv_netvsc: Add ethtool handler to set and get TCP hash levels The patch supports the options to switch TCP hash level between L3 and L4 by ethtool command. TCP over IPv4 and v6 can be set differently. The default hash level is L4. We currently only allow switching TX hash level from within the guests. For example, for TCP over IPv4 on eth0: To include TCP port numbers in hashing: ethtool -N eth0 rx-flow-hash tcp4 sdfn To exclude TCP port numbers in hashing: ethtool -N eth0 rx-flow-hash tcp4 sd To show TCP hash level: ethtool -n eth0 rx-flow-hash tcp4 Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 9bc7dbab9506e..44746de3dd4ca 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1264,8 +1264,15 @@ netvsc_get_rss_hash_opts(struct net_device_context *ndc, switch (info->flow_type) { case TCP_V4_FLOW: + if (ndc->l4_hash & HV_TCP4_L4HASH) + info->data |= l4_flag; + + break; + case TCP_V6_FLOW: - info->data |= l4_flag; + if (ndc->l4_hash & HV_TCP6_L4HASH) + info->data |= l4_flag; + break; case UDP_V4_FLOW: @@ -1318,6 +1325,14 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc, if (info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) { switch (info->flow_type) { + case TCP_V4_FLOW: + ndc->l4_hash |= HV_TCP4_L4HASH; + break; + + case TCP_V6_FLOW: + ndc->l4_hash |= HV_TCP6_L4HASH; + break; + case UDP_V4_FLOW: ndc->l4_hash |= HV_UDP4_L4HASH; break; @@ -1335,6 +1350,14 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc, if (info->data == (RXH_IP_SRC | RXH_IP_DST)) { switch (info->flow_type) { + case TCP_V4_FLOW: + ndc->l4_hash &= ~HV_TCP4_L4HASH; + break; + + case TCP_V6_FLOW: + ndc->l4_hash &= ~HV_TCP6_L4HASH; + break; + case UDP_V4_FLOW: ndc->l4_hash &= ~HV_UDP4_L4HASH; break; -- GitLab From 78005d91c11ea45a93e68c7d59079784f4c46828 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 6 Oct 2017 08:33:59 -0700 Subject: [PATCH 1103/1507] hv_netvsc: Update netvsc Document for TCP hash level setting Update Documentation/networking/netvsc.txt for TCP hash level setting and related info. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- Documentation/networking/netvsc.txt | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt index 93560fb1170a6..92f5b31392fac 100644 --- a/Documentation/networking/netvsc.txt +++ b/Documentation/networking/netvsc.txt @@ -19,12 +19,12 @@ Features Receive Side Scaling -------------------- - Hyper-V supports receive side scaling. For TCP, packets are - distributed among available queues based on IP address and port + Hyper-V supports receive side scaling. For TCP & UDP, packets can + be distributed among available queues based on IP address and port number. - For UDP, we can switch UDP hash level between L3 and L4 by ethtool - command. UDP over IPv4 and v6 can be set differently. The default + For TCP & UDP, we can switch hash level between L3 and L4 by ethtool + command. TCP/UDP over IPv4 and v6 can be set differently. The default hash level is L4. We currently only allow switching TX hash level from within the guests. -- GitLab From 3d0241d57c7b25bb75ac9d7a62753642264fdbce Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Fri, 6 Oct 2017 19:02:35 +0300 Subject: [PATCH 1104/1507] gso: fix payload length when gso_size is zero When gso_size reset to zero for the tail segment in skb_segment(), later in ipv6_gso_segment(), __skb_udp_tunnel_segment() and gre_gso_segment() we will get incorrect results (payload length, pcsum) for that segment. inet_gso_segment() already has a check for gso_size before calculating payload. The issue was found with LTP vxlan & gre tests over ixgbe NIC. Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer") Signed-off-by: Alexey Kodanev Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/gre_offload.c | 2 +- net/ipv4/udp_offload.c | 2 +- net/ipv6/ip6_offload.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 416bb304a281a..1859c473b21a8 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -86,7 +86,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 97658bfc1b58a..e360d55be5554 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -120,7 +120,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ - if (gso_partial) { + if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cdb3728faca77..4a87f9428ca51 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); - if (gso_partial) + if (gso_partial && skb_is_gso(skb)) payload_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)(ipv6h + 1); -- GitLab From 8a5776a5f49812d29fe4b2d0a2d71675c3facf3f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 Oct 2017 20:53:29 -0700 Subject: [PATCH 1105/1507] Linux 4.14-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index cf007a31d575d..2835863bdd5a4 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Fearless Coyote # *DOCUMENTATION* -- GitLab From 951f788a80ff8b6339c5c1ab888b0d4b4352efd8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Oct 2017 21:07:18 -0700 Subject: [PATCH 1106/1507] ipv6: fix a BUG in rt6_get_pcpu_route() Ido reported following splat and provided a patch. [ 122.221814] BUG: using smp_processor_id() in preemptible [00000000] code: sshd/2672 [ 122.221845] caller is debug_smp_processor_id+0x17/0x20 [ 122.221866] CPU: 0 PID: 2672 Comm: sshd Not tainted 4.14.0-rc3-idosch-next-custom #639 [ 122.221880] Hardware name: Mellanox Technologies Ltd. MSN2100-CB2FO/SA001017, BIOS 5.6.5 06/07/2016 [ 122.221893] Call Trace: [ 122.221919] dump_stack+0xb1/0x10c [ 122.221946] ? _atomic_dec_and_lock+0x124/0x124 [ 122.221974] ? ___ratelimit+0xfe/0x240 [ 122.222020] check_preemption_disabled+0x173/0x1b0 [ 122.222060] debug_smp_processor_id+0x17/0x20 [ 122.222083] ip6_pol_route+0x1482/0x24a0 ... I believe we can simplify this code path a bit, since we no longer hold a read_lock and need to release it to avoid a dead lock. By disabling BH, we make sure we'll prevent code re-entry and rt6_get_pcpu_route()/rt6_make_pcpu_route() run on the same cpu. Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Ido Schimmel Signed-off-by: Eric Dumazet Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- net/ipv6/route.c | 26 ++++++-------------------- 1 file changed, 6 insertions(+), 20 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 399d1bceec4a6..606e80325b21c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1136,15 +1136,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) dst_hold(&pcpu_rt->dst); p = this_cpu_ptr(rt->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); - if (prev) { - /* If someone did it before us, return prev instead */ - /* release refcnt taken by ip6_rt_pcpu_alloc() */ - dst_release_immediate(&pcpu_rt->dst); - /* release refcnt taken by above dst_hold() */ - dst_release_immediate(&pcpu_rt->dst); - dst_hold(&prev->dst); - pcpu_rt = prev; - } + BUG_ON(prev); rt6_dst_from_metrics_check(pcpu_rt); return pcpu_rt; @@ -1739,31 +1731,25 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, struct rt6_info *pcpu_rt; dst_use_noref(&rt->dst, jiffies); + local_bh_disable(); pcpu_rt = rt6_get_pcpu_route(rt); - if (pcpu_rt) { - rcu_read_unlock(); - } else { + if (!pcpu_rt) { /* atomic_inc_not_zero() is needed when using rcu */ if (atomic_inc_not_zero(&rt->rt6i_ref)) { - /* We have to do the read_unlock first - * because rt6_make_pcpu_route() may trigger - * ip6_dst_gc() which will take the write_lock. - * - * No dst_hold() on rt is needed because grabbing + /* No dst_hold() on rt is needed because grabbing * rt->rt6i_ref makes sure rt can't be released. */ - rcu_read_unlock(); pcpu_rt = rt6_make_pcpu_route(rt); rt6_release(rt); } else { /* rt is already removed from tree */ - rcu_read_unlock(); pcpu_rt = net->ipv6.ip6_null_entry; dst_hold(&pcpu_rt->dst); } } - + local_bh_enable(); + rcu_read_unlock(); trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); return pcpu_rt; } -- GitLab From 821f1b21cabb46827ce39ddf82e2789680b5042a Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 6 Oct 2017 22:12:37 -0700 Subject: [PATCH 1107/1507] bridge: add new BR_NEIGH_SUPPRESS port flag to suppress arp and nd flood This patch adds a new bridge port flag BR_NEIGH_SUPPRESS to suppress arp and nd flood on bridge ports. It implements rfc7432, section 10. https://tools.ietf.org/html/rfc7432#section-10 for ethernet VPN deployments. It is similar to the existing BR_PROXYARP* flags but has a few semantic differences to conform to EVPN standard. Unlike the existing flags, this new flag suppresses flood of all neigh discovery packets (arp and nd) to tunnel ports. Supports both vlan filtering and non-vlan filtering bridges. In case of EVPN, it is mainly used to avoid flooding of arp and nd packets to tunnel ports like vxlan. This patch adds netlink and sysfs support to set this bridge port flag. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + net/bridge/Makefile | 2 +- net/bridge/br_arp_nd_proxy.c | 32 ++++++++++++++++++++++++++++++++ net/bridge/br_forward.c | 2 +- net/bridge/br_if.c | 5 +++++ net/bridge/br_netlink.c | 10 +++++++++- net/bridge/br_private.h | 2 ++ net/bridge/br_sysfs_if.c | 2 ++ 9 files changed, 54 insertions(+), 3 deletions(-) create mode 100644 net/bridge/br_arp_nd_proxy.c diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3cd18ac0697f8..316ee113a2201 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) +#define BR_NEIGH_SUPPRESS BIT(15) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cd580fc0e58ff..b037e0ab19751 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -327,6 +327,7 @@ enum { IFLA_BRPORT_VLAN_TUNNEL, IFLA_BRPORT_BCAST_FLOOD, IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 40b1ede527cae..4aee55fdcc92f 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o \ - br_netlink_tunnel.o + br_netlink_tunnel.o br_arp_nd_proxy.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c new file mode 100644 index 0000000000000..f889ad5f0048b --- /dev/null +++ b/net/bridge/br_arp_nd_proxy.c @@ -0,0 +1,32 @@ +/* + * Handle bridge arp/nd proxy/suppress + * + * Copyright (C) 2017 Cumulus Networks + * Copyright (c) 2017 Roopa Prabhu + * + * Authors: + * Roopa Prabhu + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include "br_private.h" + +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool neigh_suppress = false; + + list_for_each_entry(p, &br->port_list, list) { + if (p->flags & BR_NEIGH_SUPPRESS) { + neigh_suppress = true; + break; + } + } + + br->neigh_suppress_enabled = neigh_suppress; +} diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48fb17417fac3..b4eed113d2ec8 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; - if ((p->flags & BR_PROXYARP_WIFI) && + if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) && BR_INPUT_SKB_CB(skb)->proxyarp_replied) continue; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 59a74a414e204..ae38547bbf914 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_recalculate_neigh_suppress_enabled(br); + br_fdb_delete_by_port(br, NULL, 0, 1); cancel_delayed_work_sync(&br->gc_work); @@ -660,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) if (mask & BR_AUTO_MASK) nbp_update_port_count(br); + + if (mask & BR_NEIGH_SUPPRESS) + br_recalculate_neigh_suppress_enabled(br); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index dea88a255d263..f0e82682e0716 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -210,7 +211,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || - nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask)) + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || + nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, + !!(p->flags & BR_NEIGH_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -785,6 +788,11 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) p->group_fwd_mask = fwd_mask; } + err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, + BR_NEIGH_SUPPRESS); + if (err) + return err; + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ab4df24f7bba5..00fa371b1fb2d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -404,6 +404,7 @@ struct net_bridge { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + bool neigh_suppress_enabled; }; struct br_input_skb_cb { @@ -1139,4 +1140,5 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) } #endif /* CONFIG_NET_SWITCHDEV */ +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); #endif diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 9110d5e56085c..0a1fa9ccd8b78 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -191,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD); +BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -241,6 +242,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_flood, &brport_attr_broadcast_flood, &brport_attr_group_fwd_mask, + &brport_attr_neigh_suppress, NULL }; -- GitLab From 057658cb33fbf4d4309f01fe8845903b1cd07fad Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 6 Oct 2017 22:12:38 -0700 Subject: [PATCH 1108/1507] bridge: suppress arp pkts on BR_NEIGH_SUPPRESS ports This patch avoids flooding and proxies arp packets for BR_NEIGH_SUPPRESS ports. Moves existing br_do_proxy_arp to br_do_proxy_suppress_arp to support both proxy arp and neigh suppress. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/bridge/br_arp_nd_proxy.c | 188 +++++++++++++++++++++++++++++++++++ net/bridge/br_device.c | 9 ++ net/bridge/br_input.c | 63 +----------- net/bridge/br_private.h | 3 + 4 files changed, 205 insertions(+), 58 deletions(-) diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index f889ad5f0048b..a79c1824e1636 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -14,6 +14,14 @@ */ #include +#include +#include +#include +#include +#include +#include +#include + #include "br_private.h" void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) @@ -30,3 +38,183 @@ void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) br->neigh_suppress_enabled = neigh_suppress; } + +#if IS_ENABLED(CONFIG_INET) +static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, + struct net_device *dev, __be32 dest_ip, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, + __be16 vlan_proto, u16 vlan_tci) +{ + struct net_bridge_vlan_group *vg; + struct sk_buff *skb; + u16 pvid; + + netdev_dbg(dev, "arp send dev %s dst %pI4 dst_hw %pM src %pI4 src_hw %pM\n", + dev->name, &dest_ip, dest_hw, &src_ip, src_hw); + + if (!vlan_tci) { + arp_send(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + return; + } + + skb = arp_create(ARPOP_REPLY, ETH_P_ARP, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); + + if (p) { + arp_xmit(skb); + } else { + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->pkt_type = PACKET_HOST; + + netif_rx_ni(skb); + } +} + +static int br_chk_addr_ip(struct net_device *dev, void *data) +{ + __be32 ip = *(__be32 *)data; + struct in_device *in_dev; + __be32 addr = 0; + + in_dev = __in_dev_get_rcu(dev); + if (in_dev) + addr = inet_confirm_addr(dev_net(dev), in_dev, 0, ip, + RT_SCOPE_HOST); + + if (addr == ip) + return 1; + + return 0; +} + +static bool br_is_local_ip(struct net_device *dev, __be32 ip) +{ + if (br_chk_addr_ip(dev, &ip)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip)) + return true; + + return false; +} + +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = dev; + struct neighbour *n; + struct arphdr *parp; + u8 *arpptr, *sha; + __be32 sip, tip; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if ((dev->flags & IFF_NOARP) || + !pskb_may_pull(skb, arp_hdr_len(dev))) + return; + + parp = arp_hdr(skb); + + if (parp->ar_pro != htons(ETH_P_IP) || + parp->ar_hln != dev->addr_len || + parp->ar_pln != 4) + return; + + arpptr = (u8 *)parp + sizeof(struct arphdr); + sha = arpptr; + arpptr += dev->addr_len; /* sha */ + memcpy(&sip, arpptr, sizeof(sip)); + arpptr += sizeof(sip); + arpptr += dev->addr_len; /* tha */ + memcpy(&tip, arpptr, sizeof(tip)); + + if (ipv4_is_loopback(tip) || + ipv4_is_multicast(tip)) + return; + + if (br->neigh_suppress_enabled) { + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + if (ipv4_is_zeronet(sip) || sip == tip) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + } + + if (parp->ar_op != htons(ARPOP_REQUEST)) + return; + + if (vid != 0) { + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } + + if (br->neigh_suppress_enabled && br_is_local_ip(vlandev, tip)) { + /* its our local ip, so don't proxy reply + * and don't forward to neigh suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(&arp_tbl, &tip, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if ((p && (p->flags & BR_PROXYARP)) || + (f->dst && (f->dst->flags & (BR_PROXYARP_WIFI | + BR_NEIGH_SUPPRESS)))) { + if (!vid) + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, 0, 0); + else + br_arp_send(br, p, skb->dev, sip, tip, + sha, n->ha, sha, + skb->vlan_proto, + skb_vlan_tag_get(skb)); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to arp replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + + neigh_release(n); + } +} +#endif diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 7acb77c9bd65c..eb30c6a274c37 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; const unsigned char *dest; + struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -57,11 +58,19 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); + eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; + if (IS_ENABLED(CONFIG_INET) && + (eth->h_proto == htons(ETH_P_ARP) || + eth->h_proto == htons(ETH_P_RARP)) && + br->neigh_suppress_enabled) { + br_do_proxy_suppress_arp(skb, br, vid, NULL); + } + dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7cb613776b318..4b8d2ec2fa23c 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -71,62 +71,6 @@ static int br_pass_frame_up(struct sk_buff *skb) br_netif_receive_skb); } -static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, - u16 vid, struct net_bridge_port *p) -{ - struct net_device *dev = br->dev; - struct neighbour *n; - struct arphdr *parp; - u8 *arpptr, *sha; - __be32 sip, tip; - - BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; - - if ((dev->flags & IFF_NOARP) || - !pskb_may_pull(skb, arp_hdr_len(dev))) - return; - - parp = arp_hdr(skb); - - if (parp->ar_pro != htons(ETH_P_IP) || - parp->ar_op != htons(ARPOP_REQUEST) || - parp->ar_hln != dev->addr_len || - parp->ar_pln != 4) - return; - - arpptr = (u8 *)parp + sizeof(struct arphdr); - sha = arpptr; - arpptr += dev->addr_len; /* sha */ - memcpy(&sip, arpptr, sizeof(sip)); - arpptr += sizeof(sip); - arpptr += dev->addr_len; /* tha */ - memcpy(&tip, arpptr, sizeof(tip)); - - if (ipv4_is_loopback(tip) || - ipv4_is_multicast(tip)) - return; - - n = neigh_lookup(&arp_tbl, &tip, dev); - if (n) { - struct net_bridge_fdb_entry *f; - - if (!(n->nud_state & NUD_VALID)) { - neigh_release(n); - return; - } - - f = br_fdb_find_rcu(br, n->ha, vid); - if (f && ((p->flags & BR_PROXYARP) || - (f->dst && (f->dst->flags & BR_PROXYARP_WIFI)))) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, skb->dev, tip, - sha, n->ha, sha); - BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; - } - - neigh_release(n); - } -} - /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -171,8 +115,11 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb BR_INPUT_SKB_CB(skb)->brdev = br->dev; - if (IS_ENABLED(CONFIG_INET) && skb->protocol == htons(ETH_P_ARP)) - br_do_proxy_arp(skb, br, vid, p); + if (IS_ENABLED(CONFIG_INET) && + (skb->protocol == htons(ETH_P_ARP) || + skb->protocol == htons(ETH_P_RARP))) { + br_do_proxy_suppress_arp(skb, br, vid, p); + } switch (pkt_type) { case BR_PKT_MULTICAST: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 00fa371b1fb2d..4e6b25be14d03 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1140,5 +1140,8 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) } #endif /* CONFIG_NET_SWITCHDEV */ +/* br_arp_nd_proxy.c */ void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); +void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p); #endif -- GitLab From ed842faeb2bd49256f00485402f3113205f91d30 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 6 Oct 2017 22:12:39 -0700 Subject: [PATCH 1109/1507] bridge: suppress nd pkts on BR_NEIGH_SUPPRESS ports This patch avoids flooding and proxies ndisc packets for BR_NEIGH_SUPPRESS ports. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- net/bridge/br_arp_nd_proxy.c | 249 +++++++++++++++++++++++++++++++++++ net/bridge/br_device.c | 11 ++ net/bridge/br_input.c | 11 ++ net/bridge/br_private.h | 3 + 4 files changed, 274 insertions(+) diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index a79c1824e1636..2cf7716254be6 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -21,6 +21,9 @@ #include #include #include +#if IS_ENABLED(CONFIG_IPV6) +#include +#endif #include "br_private.h" @@ -218,3 +221,249 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, } } #endif + +#if IS_ENABLED(CONFIG_IPV6) +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *msg) +{ + struct nd_msg *m; + + m = skb_header_pointer(skb, skb_network_offset(skb) + + sizeof(struct ipv6hdr), sizeof(*msg), msg); + if (!m) + return NULL; + + if (m->icmph.icmp6_code != 0 || + (m->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + m->icmph.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) + return NULL; + + return m; +} + +static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, + struct sk_buff *request, struct neighbour *n, + __be16 vlan_proto, u16 vlan_tci, struct nd_msg *ns) +{ + struct net_device *dev = request->dev; + struct net_bridge_vlan_group *vg; + struct sk_buff *reply; + struct nd_msg *na; + struct ipv6hdr *pip6; + int na_olen = 8; /* opt hdr + ETH_ALEN for target */ + int ns_olen; + int i, len; + u8 *daddr; + u16 pvid; + + if (!dev) + return; + + len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + + sizeof(*na) + na_olen + dev->needed_tailroom; + + reply = alloc_skb(len, GFP_ATOMIC); + if (!reply) + return; + + reply->protocol = htons(ETH_P_IPV6); + reply->dev = dev; + skb_reserve(reply, LL_RESERVED_SPACE(dev)); + skb_push(reply, sizeof(struct ethhdr)); + skb_set_mac_header(reply, 0); + + daddr = eth_hdr(request)->h_source; + + /* Do we need option processing ? */ + ns_olen = request->len - (skb_network_offset(request) + + sizeof(struct ipv6hdr)) - sizeof(*ns); + for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { + if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { + daddr = ns->opt + i + sizeof(struct nd_opt_hdr); + break; + } + } + + /* Ethernet header */ + ether_addr_copy(eth_hdr(reply)->h_dest, daddr); + ether_addr_copy(eth_hdr(reply)->h_source, n->ha); + eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); + reply->protocol = htons(ETH_P_IPV6); + + skb_pull(reply, sizeof(struct ethhdr)); + skb_set_network_header(reply, 0); + skb_put(reply, sizeof(struct ipv6hdr)); + + /* IPv6 header */ + pip6 = ipv6_hdr(reply); + memset(pip6, 0, sizeof(struct ipv6hdr)); + pip6->version = 6; + pip6->priority = ipv6_hdr(request)->priority; + pip6->nexthdr = IPPROTO_ICMPV6; + pip6->hop_limit = 255; + pip6->daddr = ipv6_hdr(request)->saddr; + pip6->saddr = *(struct in6_addr *)n->primary_key; + + skb_pull(reply, sizeof(struct ipv6hdr)); + skb_set_transport_header(reply, 0); + + na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen); + + /* Neighbor Advertisement */ + memset(na, 0, sizeof(*na) + na_olen); + na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + na->icmph.icmp6_router = 0; /* XXX: should be 1 ? */ + na->icmph.icmp6_override = 1; + na->icmph.icmp6_solicited = 1; + na->target = ns->target; + ether_addr_copy(&na->opt[2], n->ha); + na->opt[0] = ND_OPT_TARGET_LL_ADDR; + na->opt[1] = na_olen >> 3; + + na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, + &pip6->daddr, + sizeof(*na) + na_olen, + IPPROTO_ICMPV6, + csum_partial(na, sizeof(*na) + na_olen, 0)); + + pip6->payload_len = htons(sizeof(*na) + na_olen); + + skb_push(reply, sizeof(struct ipv6hdr)); + skb_push(reply, sizeof(struct ethhdr)); + + reply->ip_summed = CHECKSUM_UNNECESSARY; + + if (p) + vg = nbp_vlan_group_rcu(p); + else + vg = br_vlan_group_rcu(br); + pvid = br_get_pvid(vg); + if (pvid == (vlan_tci & VLAN_VID_MASK)) + vlan_tci = 0; + + if (vlan_tci) + __vlan_hwaccel_put_tag(reply, vlan_proto, vlan_tci); + + netdev_dbg(dev, "nd send dev %s dst %pI6 dst_hw %pM src %pI6 src_hw %pM\n", + dev->name, &pip6->daddr, daddr, &pip6->saddr, n->ha); + + if (p) { + dev_queue_xmit(reply); + } else { + skb_reset_mac_header(reply); + __skb_pull(reply, skb_network_offset(reply)); + reply->ip_summed = CHECKSUM_UNNECESSARY; + reply->pkt_type = PACKET_HOST; + + netif_rx_ni(reply); + } +} + +static int br_chk_addr_ip6(struct net_device *dev, void *data) +{ + struct in6_addr *addr = (struct in6_addr *)data; + + if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) + return 1; + + return 0; +} + +static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) + +{ + if (br_chk_addr_ip6(dev, addr)) + return true; + + /* check if ip is configured on upper dev */ + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr)) + return true; + + return false; +} + +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg) +{ + struct net_device *dev = br->dev; + struct net_device *vlandev = NULL; + struct in6_addr *saddr, *daddr; + struct ipv6hdr *iphdr; + struct neighbour *n; + + BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; + + if (p && (p->flags & BR_NEIGH_SUPPRESS)) + return; + + if (msg->icmph.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT && + !msg->icmph.icmp6_solicited) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + iphdr = ipv6_hdr(skb); + saddr = &iphdr->saddr; + daddr = &iphdr->daddr; + + if (ipv6_addr_any(saddr) || !ipv6_addr_cmp(saddr, daddr)) { + /* prevent flooding to neigh suppress ports */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + if (vid != 0) { + /* build neigh table lookup on the vlan device */ + vlandev = __vlan_find_dev_deep_rcu(br->dev, skb->vlan_proto, + vid); + if (!vlandev) + return; + } else { + vlandev = dev; + } + + if (br_is_local_ip6(vlandev, &msg->target)) { + /* its our own ip, so don't proxy reply + * and don't forward to arp suppress ports + */ + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + return; + } + + n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, vlandev); + if (n) { + struct net_bridge_fdb_entry *f; + + if (!(n->nud_state & NUD_VALID)) { + neigh_release(n); + return; + } + + f = br_fdb_find_rcu(br, n->ha, vid); + if (f) { + bool replied = false; + + if (f->dst && (f->dst->flags & BR_NEIGH_SUPPRESS)) { + if (vid != 0) + br_nd_send(br, p, skb, n, + skb->vlan_proto, + skb_vlan_tag_get(skb), msg); + else + br_nd_send(br, p, skb, n, 0, 0, msg); + replied = true; + } + + /* If we have replied or as long as we know the + * mac, indicate to NEIGH_SUPPRESS ports that we + * have replied + */ + if (replied || br->neigh_suppress_enabled) + BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; + } + neigh_release(n); + } +} +#endif diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index eb30c6a274c37..28bb22186fa01 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -69,6 +69,17 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth->h_proto == htons(ETH_P_RARP)) && br->neigh_suppress_enabled) { br_do_proxy_suppress_arp(skb, br, vid, NULL); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, NULL, msg); } dest = eth_hdr(skb)->h_dest; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 4b8d2ec2fa23c..a096d3e189daf 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -119,6 +119,17 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6) && + br->neigh_suppress_enabled && + pskb_may_pull(skb, sizeof(struct ipv6hdr) + + sizeof(struct nd_msg)) && + ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { + struct nd_msg *msg, _msg; + + msg = br_is_nd_neigh_msg(skb, &_msg); + if (msg) + br_do_suppress_nd(skb, br, vid, p, msg); } switch (pkt_type) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 4e6b25be14d03..fa0039f448184 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1144,4 +1144,7 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p); +void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, + u16 vid, struct net_bridge_port *p, struct nd_msg *msg); +struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m); #endif -- GitLab From 3382605fd8db1ed1fb03f3f1529490133fe3ab08 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Sat, 7 Oct 2017 14:32:49 +0200 Subject: [PATCH 1110/1507] tipc: correct initialization of skb list We change the initialization of the skb transmit buffer queues in the functions tipc_bcast_xmit() and tipc_rcast_xmit() to also initialize their spinlocks. This is needed because we may, during error conditions, need to call skb_queue_purge() on those queues further down the stack. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bcast.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 7d99029df342f..a140dd4a84afc 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -233,7 +233,7 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, struct sk_buff_head xmitq; int rc = 0; - __skb_queue_head_init(&xmitq); + skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); @@ -263,7 +263,7 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, u32 dst, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); - __skb_queue_head_init(&_pkts); + skb_queue_head_init(&_pkts); list_for_each_entry_safe(n, tmp, &dests->list, list) { dst = n->value; -- GitLab From a9e2971b8cd3ef469de0112ba15778b5b98ad72e Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Sat, 7 Oct 2017 15:07:20 +0200 Subject: [PATCH 1111/1507] tipc: Unclone message at secondary destination lookup When a bundling message is received, the function tipc_link_input() calls function tipc_msg_extract() to unbundle all inner messages of the bundling message before adding them to input queue. The function tipc_msg_extract() just clones all inner skb for all inner messagges from the bundling skb. This means that the skb headroom of an inner message overlaps with the data part of the preceding message in the bundle. If the message in question is a name addressed message, it may be subject to a secondary destination lookup, and eventually be sent out on one of the interfaces again. But, since what is perceived as headroom by the device driver in reality is the last bytes of the preceding message in the bundle, the latter will be overwritten by the MAC addresses of the L2 header. If the preceding message has not yet been consumed by the user, it will evenually be delivered with corrupted contents. This commit fixes this by uncloning all messages passing through the function tipc_msg_lookup_dest(), hence ensuring that the headroom is always valid when the message is passed on. Signed-off-by: Tung Nguyen Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/msg.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 121e59a1d0e72..17146c16ee2df 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -568,6 +568,14 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; + + if (!skb_cloned(skb)) + return true; + + /* Unclone buffer in case it was bundled */ + if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) + return false; + return true; } -- GitLab From 8ef802aa8ec87a0fec20d28f8f51cad964265902 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:23 -0700 Subject: [PATCH 1112/1507] ipv6: prepare RCU lookups for idev->addr_list inet6_ifa_finish_destroy() already uses kfree_rcu() to free inet6_ifaddr structs. We need to use proper list additions/deletions in order to allow readers to use RCU instead of idev->lock rwlock. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9854d93e45bb5..d1ff0955b709e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -945,7 +945,7 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) break; } - list_add_tail(&ifp->if_list, p); + list_add_tail_rcu(&ifp->if_list, p); } static u32 inet6_addr_hash(const struct in6_addr *addr) @@ -1204,7 +1204,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); - list_del_init(&ifp->if_list); + list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); @@ -3562,7 +3562,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; int _keep_addr; bool keep_addr; int state, i; @@ -3654,7 +3653,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) */ keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct rt6_info *rt = NULL; bool keep; @@ -3663,8 +3661,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); - if (!keep) - list_move(&ifa->if_list, &del_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -3698,19 +3694,14 @@ static int addrconf_ifdown(struct net_device *dev, int how) } write_lock_bh(&idev->lock); + if (!keep) { + list_del_rcu(&ifa->if_list); + in6_ifa_put(ifa); + } } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); -- GitLab From d9bf82c2f61be534873a37a0631b58761b6d6506 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:24 -0700 Subject: [PATCH 1113/1507] ipv6: ipv6_count_addresses() rcu conversion Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d1ff0955b709e..2e029c8be1f2e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -152,7 +152,7 @@ static void ipv6_regen_rndid(struct inet6_dev *idev); static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpaddr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); -static int ipv6_count_addresses(struct inet6_dev *idev); +static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); @@ -1785,15 +1785,15 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, return err; } -static int ipv6_count_addresses(struct inet6_dev *idev) +static int ipv6_count_addresses(const struct inet6_dev *idev) { + const struct inet6_ifaddr *ifp; int cnt = 0; - struct inet6_ifaddr *ifp; - read_lock_bh(&idev->lock); - list_for_each_entry(ifp, &idev->addr_list, if_list) + rcu_read_lock(); + list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; - read_unlock_bh(&idev->lock); + rcu_read_unlock(); return cnt; } -- GitLab From 47e26941f78d6ec03c5dd547425409f1f7852ff5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:25 -0700 Subject: [PATCH 1114/1507] ipv6: ipv6_chk_custom_prefix() rcu conversion Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2e029c8be1f2e..33ee84c2512b5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1859,20 +1859,18 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); -- GitLab From 24ba333b2c1a609fc17214ceb215e19bd9d54951 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:26 -0700 Subject: [PATCH 1115/1507] ipv6: ipv6_chk_prefix() rcu conversion Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 33ee84c2512b5..ea63442209bf2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1880,22 +1880,20 @@ EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; + const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - list_for_each_entry(ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } - read_unlock_bh(&idev->lock); } rcu_read_unlock(); return onlink; -- GitLab From f59c031e9134bb16c38980196a73d7ba40979baa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:27 -0700 Subject: [PATCH 1116/1507] ipv6: __ipv6_dev_get_saddr() rcu conversion Callers hold rcu_read_lock(), so we do not need the rcu_read_lock()/rcu_read_unlock() pair. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ea63442209bf2..20c3ca777529f 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1558,8 +1558,7 @@ static int __ipv6_dev_get_saddr(struct net *net, { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1625,7 +1624,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } } out: - read_unlock_bh(&idev->lock); return hiscore_idx; } -- GitLab From cc429c8f6fa7cc1c9109bb4a1ad63a6d1f232f0e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Oct 2017 19:30:28 -0700 Subject: [PATCH 1117/1507] ipv6: avoid cache line dirtying in ipv6_dev_get_saddr() By extending the rcu section a bit, we can avoid these very expensive in6_ifa_put()/in6_ifa_hold() calls done in __ipv6_dev_get_saddr() and ipv6_dev_get_saddr() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 20c3ca777529f..cab3faad2bf13 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1608,11 +1608,6 @@ static int __ipv6_dev_get_saddr(struct net *net, } break; } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; @@ -1660,6 +1655,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; + int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1735,15 +1731,14 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, } out: - rcu_read_unlock(); - hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) - return -EADDRNOTAVAIL; + ret = -EADDRNOTAVAIL; + else + *saddr = hiscore->ifa->addr; - *saddr = hiscore->ifa->addr; - in6_ifa_put(hiscore->ifa); - return 0; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); -- GitLab From c778c32118167adcfe6b40063c49bfeac6bc1cf1 Mon Sep 17 00:00:00 2001 From: Christos Gkekas Date: Sun, 8 Oct 2017 20:13:49 +0100 Subject: [PATCH 1118/1507] net: ethernet: stmmac: Clean up dead code Many macros in dwmac-ipq806x are unused and should be removed. Moreover gmac->id is an unsigned variable and therefore checking whether it is less than zero is redundant. Signed-off-by: Christos Gkekas Signed-off-by: David S. Miller --- .../net/ethernet/stmicro/stmmac/dwmac-ipq806x.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 866444b6c82fa..2c6d7c69c8f74 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -51,15 +51,11 @@ #define NSS_COMMON_CLK_SRC_CTRL_RGMII(x) 1 #define NSS_COMMON_CLK_SRC_CTRL_SGMII(x) ((x >= 2) ? 1 : 0) -#define NSS_COMMON_MACSEC_CTL 0x28 -#define NSS_COMMON_MACSEC_CTL_EXT_BYPASS_EN(x) (1 << x) - #define NSS_COMMON_GMAC_CTL(x) (0x30 + (x * 4)) #define NSS_COMMON_GMAC_CTL_CSYS_REQ BIT(19) #define NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL BIT(16) #define NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET 8 #define NSS_COMMON_GMAC_CTL_IFG_OFFSET 0 -#define NSS_COMMON_GMAC_CTL_IFG_MASK 0x3f #define NSS_COMMON_CLK_DIV_RGMII_1000 1 #define NSS_COMMON_CLK_DIV_RGMII_100 9 @@ -68,9 +64,6 @@ #define NSS_COMMON_CLK_DIV_SGMII_100 4 #define NSS_COMMON_CLK_DIV_SGMII_10 49 -#define QSGMII_PCS_MODE_CTL 0x68 -#define QSGMII_PCS_MODE_CTL_AUTONEG_EN(x) BIT((x * 8) + 7) - #define QSGMII_PCS_CAL_LCKDT_CTL 0x120 #define QSGMII_PCS_CAL_LCKDT_CTL_RST BIT(19) @@ -83,15 +76,10 @@ #define QSGMII_PHY_TX_DRIVER_EN BIT(3) #define QSGMII_PHY_QSGMII_EN BIT(7) #define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET 12 -#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK 0x7 #define QSGMII_PHY_RX_DC_BIAS_OFFSET 18 -#define QSGMII_PHY_RX_DC_BIAS_MASK 0x3 #define QSGMII_PHY_RX_INPUT_EQU_OFFSET 20 -#define QSGMII_PHY_RX_INPUT_EQU_MASK 0x3 #define QSGMII_PHY_CDR_PI_SLEW_OFFSET 22 -#define QSGMII_PHY_CDR_PI_SLEW_MASK 0x3 #define QSGMII_PHY_TX_DRV_AMP_OFFSET 28 -#define QSGMII_PHY_TX_DRV_AMP_MASK 0xf struct ipq806x_gmac { struct platform_device *pdev; @@ -217,7 +205,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) * code and keep it consistent with the Linux convention, we'll number * them from 0 to 3 here. */ - if (gmac->id < 0 || gmac->id > 3) { + if (gmac->id > 3) { dev_err(dev, "invalid gmac id\n"); return -EINVAL; } -- GitLab From c49c777f9c87749b73bc888f097f8a4178382449 Mon Sep 17 00:00:00 2001 From: Christos Gkekas Date: Sun, 8 Oct 2017 23:46:47 +0100 Subject: [PATCH 1119/1507] qed: Delete redundant check on dcb_app priority dcb_app priority is unsigned thus checking whether it is less than zero is redundant. Signed-off-by: Christos Gkekas Acked-By: Tomer Tayar Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 8f6ccc0c39e5e..6e15d3c10ebf7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -2308,7 +2308,7 @@ static int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app) DP_VERBOSE(hwfn, QED_MSG_DCB, "selector = %d protocol = %d pri = %d\n", app->selector, app->protocol, app->priority); - if (app->priority < 0 || app->priority >= QED_MAX_PFC_PRIORITIES) { + if (app->priority >= QED_MAX_PFC_PRIORITIES) { DP_INFO(hwfn, "Invalid priority %d\n", app->priority); return -EINVAL; } -- GitLab From 49f817d793d1bcc11d721881aac037b996feef5c Mon Sep 17 00:00:00 2001 From: Lin Zhang Date: Fri, 6 Oct 2017 00:44:03 +0800 Subject: [PATCH 1120/1507] netfilter: SYNPROXY: skip non-tcp packet in {ipv4, ipv6}_synproxy_hook In function {ipv4,ipv6}_synproxy_hook we expect a normal tcp packet, but the real server maybe reply an icmp error packet related to the exist tcp conntrack, so we will access wrong tcp data. Fix it by checking for the protocol field and only process tcp traffic. Signed-off-by: Lin Zhang Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/ipt_SYNPROXY.c | 3 ++- net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 811689e523c31..f75fc6b531152 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (synproxy == NULL) return NF_ACCEPT; - if (nf_is_loopback_packet(skb)) + if (nf_is_loopback_packet(skb) || + ip_hdr(skb)->protocol != IPPROTO_TCP) return NF_ACCEPT; thoff = ip_hdrlen(skb); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index a5cd43d75393d..437af8c95277f 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -353,7 +353,7 @@ static unsigned int ipv6_synproxy_hook(void *priv, nexthdr = ipv6_hdr(skb)->nexthdr; thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); - if (thoff < 0) + if (thoff < 0 || nexthdr != IPPROTO_TCP) return NF_ACCEPT; th = skb_header_pointer(skb, thoff, sizeof(_th), &_th); -- GitLab From 98589a0998b8b13c4a8fa1ccb0e62751a019faa5 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 9 Oct 2017 15:27:15 +0300 Subject: [PATCH 1121/1507] netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder Signed-off-by: Shmulik Ladkani Acked-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/bpf.h | 5 +++++ include/uapi/linux/netfilter/xt_bpf.h | 1 + kernel/bpf/inode.c | 1 + net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e70..f1af7d63d6786 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0e..da161b56c79e4 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed9143583..be1dde967208e 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ int bpf_obj_get_user(const char __user *pathname) putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216cd..29123934887bb 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } -- GitLab From e0f06bba9629987fb3ec1d6928bf17ef689702e8 Mon Sep 17 00:00:00 2001 From: Mark D Rustad Date: Wed, 31 Aug 2016 10:34:28 -0700 Subject: [PATCH 1122/1507] ixgbe: Return error when getting PHY address if PHY access is not supported In cases where PHY register access is not supported, don't mislead a caller into thinking that it is supported by returning a PHY address. Instead, return -EOPNOTSUPP when PHY access is not supported. Signed-off-by: Mark Rustad Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368d08d0f..822cdb4f2c258 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8529,6 +8529,10 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) return ixgbe_ptp_set_ts_config(adapter, req); case SIOCGHWTSTAMP: return ixgbe_ptp_get_ts_config(adapter, req); + case SIOCGMIIPHY: + if (!adapter->hw.phy.ops.read_reg) + return -EOPNOTSUPP; + /* fall through */ default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } -- GitLab From a39221ce969b316d3c3dcf7fcff8c0d8cf223007 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Mon, 3 Jul 2017 13:02:55 +0200 Subject: [PATCH 1123/1507] ixgbe: fix masking of bits read from IXGBE_VXLANCTRL register In ixgbe_clear_udp_tunnel_port(), we read the IXGBE_VXLANCTRL register and then try to mask some bits out of the value, using the logical instead of bitwise and operator. Fixes: a21d0822ff69 ("ixgbe: add support for geneve Rx offload") Signed-off-by: Sabrina Dubroca Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 822cdb4f2c258..4d76afd138685 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4881,7 +4881,7 @@ static void ixgbe_clear_udp_tunnel_port(struct ixgbe_adapter *adapter, u32 mask) IXGBE_FLAG_GENEVE_OFFLOAD_CAPABLE))) return; - vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) && ~mask; + vxlanctrl = IXGBE_READ_REG(hw, IXGBE_VXLANCTRL) & ~mask; IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, vxlanctrl); if (mask & IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK) -- GitLab From f4986d250ada29ae0c65c209a9d8f97968ea7eae Mon Sep 17 00:00:00 2001 From: Ding Tianhong Date: Fri, 18 Aug 2017 14:21:04 +0800 Subject: [PATCH 1124/1507] Revert commit 1a8b6d76dc5b ("net:add one common config...") The new flag PCI_DEV_FLAGS_NO_RELAXED_ORDERING has been added to indicate that Relaxed Ordering Attributes (RO) should not be used for Transaction Layer Packets (TLP) targeted toward these affected Root Port, it will clear the bit4 in the PCIe Device Control register, so the PCIe device drivers could query PCIe configuration space to determine if it can send TLPs to Root Port with the Relaxed Ordering Attributes set. With this new flag we don't need the config ARCH_WANT_RELAX_ORDER to control the Relaxed Ordering Attributes for the ixgbe drivers just like the commit 1a8b6d76dc5b ("net:add one common config...") did, so revert this commit. Signed-off-by: Ding Tianhong Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- arch/Kconfig | 3 --- arch/sparc/Kconfig | 1 - drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 2 +- 3 files changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/Kconfig b/arch/Kconfig index 1aafb4efbb51d..d789a89cb32c4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -937,9 +937,6 @@ config STRICT_MODULE_RWX and non-text memory will be made non-executable. This provides protection against certain security exploits (e.g. writing to text) -config ARCH_WANT_RELAX_ORDER - bool - config ARCH_HAS_REFCOUNT bool help diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 0be3828752e5b..4e83f950713e9 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -44,7 +44,6 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select LOCKDEP_SMALL if LOCKDEP - select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 2c19070d2a0b0..e8c1788aed1f8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -366,7 +366,7 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_ARCH_WANT_RELAX_ORDER +#ifndef CONFIG_SPARC /* Disable relaxed ordering */ for (i = 0; i < hw->mac.max_tx_queues; i++) { u32 regval; -- GitLab From 5e0fac63a694918870af9d6eaf716af19e7f5652 Mon Sep 17 00:00:00 2001 From: Ding Tianhong Date: Fri, 18 Aug 2017 14:21:05 +0800 Subject: [PATCH 1125/1507] net: ixgbe: Use new PCI_DEV_FLAGS_NO_RELAXED_ORDERING flag The ixgbe driver use the compile check to determine if it can send TLPs to Root Port with the Relaxed Ordering Attribute set, this is too inconvenient, now the new flag PCI_DEV_FLAGS_NO_RELAXED_ORDERING has been added to the kernel and we could check the bit4 in the PCIe Device Control register to determine whether we should use the Relaxed Ordering Attributes or not, so use this new way in the ixgbe driver. Signed-off-by: Ding Tianhong Acked-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ixgbe/ixgbe_82598.c | 22 ------------------- .../net/ethernet/intel/ixgbe/ixgbe_common.c | 19 ---------------- 2 files changed, 41 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 523f9d05a810f..8a32eb7d47b9b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -175,31 +175,9 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) **/ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) { -#ifndef CONFIG_SPARC - u32 regval; - u32 i; -#endif s32 ret_val; ret_val = ixgbe_start_hw_generic(hw); - -#ifndef CONFIG_SPARC - /* Disable relaxed ordering */ - for (i = 0; ((i < hw->mac.max_tx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval); - } - - for (i = 0; ((i < hw->mac.max_rx_queues) && - (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif if (ret_val) return ret_val; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index e8c1788aed1f8..6e6ab6f6875eb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -366,25 +366,6 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) } IXGBE_WRITE_FLUSH(hw); -#ifndef CONFIG_SPARC - /* Disable relaxed ordering */ - for (i = 0; i < hw->mac.max_tx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i)); - regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_EN; - IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval); - } - - for (i = 0; i < hw->mac.max_rx_queues; i++) { - u32 regval; - - regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); - regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | - IXGBE_DCA_RXCTRL_HEAD_WRO_EN); - IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); - } -#endif return 0; } -- GitLab From 8e679021c5b9465ac5b0d7efd26baab9b10a2dbd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 7 Sep 2017 10:32:48 -0700 Subject: [PATCH 1126/1507] ixgbe: incorrect XDP ring accounting in ethtool tx_frame param Changing the TX ring parameters with an XDP program attached may cause the XDP queues to be cleared and the TX rings to be incorrectly configured. Fix by doing correct ring accounting in setup call. Fixes: 33fdc82f0883 ("ixgbe: add support for XDP_TX action") Signed-off-by: John Fastabend Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 72c565712a5f8..c3e7a8191128d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1048,7 +1048,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *temp_ring; - int i, err = 0; + int i, j, err = 0; u32 new_rx_count, new_tx_count; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1085,8 +1085,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } /* allocate temporary buffer to store rings in */ - i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); - i = max_t(int, i, adapter->num_xdp_queues); + i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues, + adapter->num_rx_queues); temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); if (!temp_ring) { @@ -1118,8 +1118,8 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } } - for (i = 0; i < adapter->num_xdp_queues; i++) { - memcpy(&temp_ring[i], adapter->xdp_ring[i], + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[j], sizeof(struct ixgbe_ring)); temp_ring[i].count = new_tx_count; @@ -1139,10 +1139,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev, memcpy(adapter->tx_ring[i], &temp_ring[i], sizeof(struct ixgbe_ring)); } - for (i = 0; i < adapter->num_xdp_queues; i++) { - ixgbe_free_tx_resources(adapter->xdp_ring[i]); + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[j]); - memcpy(adapter->xdp_ring[i], &temp_ring[i], + memcpy(adapter->xdp_ring[j], &temp_ring[i], sizeof(struct ixgbe_ring)); } -- GitLab From 2e22a75c55c1e70f36e21d4fa4e165af7f356aa9 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Wed, 5 Jul 2017 15:57:30 -0700 Subject: [PATCH 1127/1507] ixgbe: Clear SWFW_SYNC register during init Added clearing of SW resource bits in the SW/FW synchronization register to ixgbe_init_swfw_sync_X540(). Updated ixgbe_acquire_swfw_sync_X540 SW Manageability host interface resource bit error case to match the error handling of the other SW resource bits. Which is to release the SW resource bits if SW times out while attempting to acquire the resource. This allows the driver to load in cases where the semaphore bits could be stuck after a reset or a crash. Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 6ea0d6a5fb90c..b8c5fd2a2115c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -619,12 +619,6 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) usleep_range(5000, 10000); } - /* Failed to get SW only semaphore */ - if (swmask == IXGBE_GSSR_SW_MNG_SM) { - hw_dbg(hw, "Failed to get SW only semaphore\n"); - return IXGBE_ERR_SWFW_SYNC; - } - /* If the resource is not released by the FW/HW the SW can assume that * the FW/HW malfunctions. In that case the SW should set the SW bit(s) * of the requested resource(s) while ignoring the corresponding FW/HW @@ -647,7 +641,8 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) */ if (swfw_sync & swmask) { u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | - IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM; + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM; if (swi2c_mask) rmask |= IXGBE_GSSR_I2C_MASK; @@ -763,6 +758,8 @@ static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw) **/ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) { + u32 rmask; + /* First try to grab the semaphore but we don't need to bother * looking to see whether we got the lock or not since we do * the same thing regardless of whether we got the lock or not. @@ -771,6 +768,14 @@ void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) */ ixgbe_get_swfw_sync_semaphore(hw); ixgbe_release_swfw_sync_semaphore(hw); + + /* Acquire and release all software resources. */ + rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_I2C_MASK; + + ixgbe_acquire_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_X540(hw, rmask); } /** -- GitLab From 2e033eace7557a4b67ba1cb2746bd87d6ca2620b Mon Sep 17 00:00:00 2001 From: Bhumika Goyal Date: Mon, 17 Jul 2017 20:31:18 +0530 Subject: [PATCH 1128/1507] ixgbe: declare ixgbe_mac_operations structures as const Declare ixgbe_mac_operations structures as const as they are only stored in the mac_ops field of ixgbe_info structure. This field is of type const and therefore ixgbe_mac_operations structure can be made const too. Signed-off-by: Bhumika Goyal Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 19fbb2f28ea45..933c5070f1b62 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3884,7 +3884,7 @@ static const struct ixgbe_mac_operations mac_ops_X550EM_x_fw = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, }; -static struct ixgbe_mac_operations mac_ops_x550em_a = { +static const struct ixgbe_mac_operations mac_ops_x550em_a = { X550_COMMON_MAC .led_on = ixgbe_led_on_t_x550em, .led_off = ixgbe_led_off_t_x550em, @@ -3905,7 +3905,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, }; -static struct ixgbe_mac_operations mac_ops_x550em_a_fw = { +static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = { X550_COMMON_MAC .led_on = ixgbe_led_on_generic, .led_off = ixgbe_led_off_generic, -- GitLab From f5a71caa1763cc8fd1b108234689d6a7e4fe9d2f Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 15 Aug 2017 08:59:54 -0700 Subject: [PATCH 1129/1507] ixgbe: restore normal RSS after last macvlan offload is removed Just like when the last VF is removed, we need to restore normal operations after the last macvlan offload is removed, else we get stuck in single queue operations. To test: ethtool -l eth1 # note the number of queues in use, ~= cpus ethtool -K eth1 l2-fwd-offload on ip link add mv1 link eth1 type macvlan mode bridge ip link set dev mv1 up ip link del mv1 ethtool -l eth1 # are we back to the same # of queues, or stuck on 1? Signed-off-by: Shannon Nelson Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3942c6208745c..d83cc9d34de33 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -9758,6 +9758,17 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) limit = find_last_bit(&adapter->fwd_bitmask, 32); adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter); + + /* go back to full RSS if we're done with our VMQs */ + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + adapter->ring_feature[RING_F_RSS].limit = rss; + } + ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", fwd_adapter->pool, adapter->num_rx_pools, -- GitLab From c69be946d687a99dbc891ebc66539c1c2f082c1d Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Fri, 18 Aug 2017 15:48:02 -0700 Subject: [PATCH 1130/1507] ixgbe: add error checks when initializing the PHY Ignoring errors when attempting to identify the PHY can lead to a crash. Specifically in the case of FW controlled PHYs where the PHY read/write operations are set to NULL. Removed redundant comment. Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 933c5070f1b62..8cea53b62e1b7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3192,6 +3192,9 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); + if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || + ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + return ret_val; /* Setup function pointers based on detected hardware */ ixgbe_init_mac_link_ops_X550em(hw); @@ -3394,9 +3397,10 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) ixgbe_clear_tx_pending(hw); /* PHY ops must be identified and initialized prior to reset */ - - /* Identify PHY and related function pointers */ status = hw->phy.ops.init(hw); + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || + status == IXGBE_ERR_PHY_ADDR_INVALID) + return status; /* start the external PHY */ if (hw->phy.type == ixgbe_phy_x550em_ext_t) { -- GitLab From 62cf27e52b8c9a39066172ca6b6134cb5eaa9450 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 9 Oct 2017 08:39:43 +0200 Subject: [PATCH 1131/1507] ipv6: Fix traffic triggered IPsec connections. A recent patch removed the dst_free() on the allocated dst_entry in ipv6_blackhole_route(). The dst_free() marked the dst_entry as dead and added it to the gc list. I.e. it was setup for a one time usage. As a result we may now have a blackhole route cached at a socket on some IPsec scenarios. This makes the connection unusable. Fix this by marking the dst_entry directly at allocation time as 'dead', so it is used only once. Fixes: 587fea741134 ("ipv6: mark DST_NOGC and remove the operation of dst_free()") Reported-by: Tobias Brunner Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 26cc9f483b6d2..a96d5b385d8fa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1325,7 +1325,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, - DST_OBSOLETE_NONE, 0); + DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); -- GitLab From 6c0e7284d89995877740d8a26c3e99a937312a3c Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 9 Oct 2017 08:43:55 +0200 Subject: [PATCH 1132/1507] ipv4: Fix traffic triggered IPsec connections. A recent patch removed the dst_free() on the allocated dst_entry in ipv4_blackhole_route(). The dst_free() marked the dst_entry as dead and added it to the gc list. I.e. it was setup for a one time usage. As a result we may now have a blackhole route cached at a socket on some IPsec scenarios. This makes the connection unusable. Fix this by marking the dst_entry directly at allocation time as 'dead', so it is used only once. Fixes: b838d5e1c5b6 ("ipv4: mark DST_NOGC and remove the operation of dst_free()") Reported-by: Tobias Brunner Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ac6fde5d45f14..3d9f1c2f81c58 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2513,7 +2513,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; -- GitLab From 761c2a48c70d871b0622dccaa20ccad024101a51 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Tue, 29 Aug 2017 12:21:48 -0700 Subject: [PATCH 1133/1507] ixgbe: split Tx/Rx ring clearing for ethtool loopback test Commit: fed21bcee7a5 ("ixgbe: Don't bother clearing buffer memory for descriptor rings) exposed some issues with the logic in the current implementation of ixgbe_clean_test_rings() that are being addressed in this patch: - Split the clearing of the Tx and Rx rings in separate loops. Previously both Tx and Rx rings were cleared in a rx_desc->wb.upper.length based loop which could lead to issues if for w/e reason packets were received outside of the frames transmitted for the loopback test. - Add check for IXGBE_TXD_STAT_DD to avoid clearing the rings if the transmits have not comlpeted by the time we enter ixgbe_clean_test_rings() - Exit early on ixgbe_check_lbtest_frame() failure. This change fixes a crash during ethtool diagnostic (ethtool -t). Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 53 ++++++++++++------- 1 file changed, 34 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 72c565712a5f8..6d89f28cae062 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1916,8 +1916,6 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, unsigned int size) { union ixgbe_adv_rx_desc *rx_desc; - struct ixgbe_rx_buffer *rx_buffer; - struct ixgbe_tx_buffer *tx_buffer; u16 rx_ntc, tx_ntc, count = 0; /* initialize next to clean and descriptor values */ @@ -1925,7 +1923,38 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); + while (tx_ntc != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_buffer; + + tx_desc = IXGBE_TX_DESC(tx_ring, tx_ntc); + + /* if DD is not set transmit has not completed */ + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + return count; + + /* unmap buffer on Tx side */ + tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + /* increment Tx next to clean counter */ + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + } + while (rx_desc->wb.upper.length) { + struct ixgbe_rx_buffer *rx_buffer; + /* check Rx buffer */ rx_buffer = &rx_ring->rx_buffer_info[rx_ntc]; @@ -1938,6 +1967,8 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, /* verify contents of skb */ if (ixgbe_check_lbtest_frame(rx_buffer, size)) count++; + else + break; /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, @@ -1945,26 +1976,10 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, ixgbe_rx_bufsz(rx_ring), DMA_FROM_DEVICE); - /* unmap buffer on Tx side */ - tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; - - /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - - /* increment Rx/Tx next to clean counters */ + /* increment Rx next to clean counter */ rx_ntc++; if (rx_ntc == rx_ring->count) rx_ntc = 0; - tx_ntc++; - if (tx_ntc == tx_ring->count) - tx_ntc = 0; /* fetch next descriptor */ rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); -- GitLab From 5bca3b94dfbf9259d972a5be91333dda6eb9f350 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:43:55 +0800 Subject: [PATCH 1134/1507] net: hns3: Cleanup for shifting true in hns3 driver This patch fixes a shifting true in hclge_main module. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 1a13614af3dec..5c1bf12beade6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1687,7 +1687,7 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev, req->buf_num[i] = cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S); req->buf_num[i] |= - cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B); + cpu_to_le16(1 << HCLGE_TC0_PRI_BUF_EN_B); } req->shared_buf = -- GitLab From 9780cb97afd868fb11500f38826b7f30d554535c Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:43:56 +0800 Subject: [PATCH 1135/1507] net: hns3: Add hns3_get_handle macro in hns3 driver There are many places that will need to get the handle of netdev, so add a macro to get the handle of netdev. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hns3_dcbnl.c | 18 +++------ .../hisilicon/hns3/hns3pf/hns3_enet.c | 39 +++++++------------ .../hisilicon/hns3/hns3pf/hns3_enet.h | 3 ++ .../hisilicon/hns3/hns3pf/hns3_ethtool.c | 38 +++++++----------- 4 files changed, 35 insertions(+), 63 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c index 9832172bfb08e..925619a7c50ab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_dcbnl.c @@ -13,8 +13,7 @@ static int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_getets) return h->kinfo.dcb_ops->ieee_getets(h, ets); @@ -25,8 +24,7 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets) static int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_setets) return h->kinfo.dcb_ops->ieee_setets(h, ets); @@ -37,8 +35,7 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets) static int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_getpfc) return h->kinfo.dcb_ops->ieee_getpfc(h, pfc); @@ -49,8 +46,7 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc) static int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->ieee_setpfc) return h->kinfo.dcb_ops->ieee_setpfc(h, pfc); @@ -61,8 +57,7 @@ int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc) /* DCBX configuration */ static u8 hns3_dcbnl_getdcbx(struct net_device *ndev) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->getdcbx) return h->kinfo.dcb_ops->getdcbx(h); @@ -73,8 +68,7 @@ static u8 hns3_dcbnl_getdcbx(struct net_device *ndev) /* return 0 if successful, otherwise fail */ static u8 hns3_dcbnl_setdcbx(struct net_device *ndev, u8 mode) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(ndev); if (h->kinfo.dcb_ops->setdcbx) return h->kinfo.dcb_ops->setdcbx(h, mode); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index c31506514e5da..c2a0537c649f8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -198,8 +198,7 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector) static int hns3_nic_set_real_num_queue(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct hnae3_knic_private_info *kinfo = &h->kinfo; unsigned int queue_size = kinfo->rss_size * kinfo->num_tc; int ret; @@ -307,8 +306,7 @@ static int hns3_nic_net_stop(struct net_device *netdev) void hns3_set_multicast_list(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct netdev_hw_addr *ha = NULL; if (h->ae_algo->ops->set_mc_addr) { @@ -321,8 +319,7 @@ void hns3_set_multicast_list(struct net_device *netdev) static int hns3_nic_uc_sync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->add_uc_addr) return h->ae_algo->ops->add_uc_addr(h, addr); @@ -333,8 +330,7 @@ static int hns3_nic_uc_sync(struct net_device *netdev, static int hns3_nic_uc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->rm_uc_addr) return h->ae_algo->ops->rm_uc_addr(h, addr); @@ -345,8 +341,7 @@ static int hns3_nic_uc_unsync(struct net_device *netdev, static int hns3_nic_mc_sync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->add_mc_addr) return h->ae_algo->ops->add_mc_addr(h, addr); @@ -357,8 +352,7 @@ static int hns3_nic_mc_sync(struct net_device *netdev, static int hns3_nic_mc_unsync(struct net_device *netdev, const unsigned char *addr) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->rm_mc_addr) return h->ae_algo->ops->rm_mc_addr(h, addr); @@ -368,8 +362,7 @@ static int hns3_nic_mc_unsync(struct net_device *netdev, void hns3_nic_set_rx_mode(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo->ops->set_promisc_mode) { if (netdev->flags & IFF_PROMISC) @@ -1025,8 +1018,7 @@ static netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct sockaddr *mac_addr = p; int ret; @@ -1208,8 +1200,7 @@ static void hns3_nic_udp_tunnel_del(struct net_device *netdev, static int hns3_setup_tc(struct net_device *netdev, u8 tc) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); struct hnae3_knic_private_info *kinfo = &h->kinfo; unsigned int i; int ret; @@ -1259,8 +1250,7 @@ static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type, static int hns3_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vlan_filter) @@ -1272,8 +1262,7 @@ static int hns3_vlan_rx_add_vid(struct net_device *netdev, static int hns3_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vlan_filter) @@ -1285,8 +1274,7 @@ static int hns3_vlan_rx_kill_vid(struct net_device *netdev, static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; if (h->ae_algo->ops->set_vf_vlan_filter) @@ -1298,8 +1286,7 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); bool if_running = netif_running(netdev); int ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h index 481eada73e2d8..dd8d40ca1dcce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -587,6 +587,9 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) #define hns3_for_each_ring(pos, head) \ for (pos = (head).ring; pos; pos = pos->next) +#define hns3_get_handle(ndev) \ + (((struct hns3_nic_priv *)netdev_priv(ndev))->ae_handle) + void hns3_ethtool_set_ops(struct net_device *netdev); int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index d636399232fb1..a892a157f3462 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -102,8 +102,7 @@ static void hns3_driv_to_eth_caps(u32 caps, struct ethtool_link_ksettings *cmd, static int hns3_get_sset_count(struct net_device *netdev, int stringset) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; if (!ops->get_sset_count) @@ -164,8 +163,7 @@ static u8 *hns3_get_strings_tqps(struct hnae3_handle *handle, u8 *data) static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; char *buff = (char *)data; @@ -220,8 +218,7 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data) void hns3_get_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); u64 *p = data; if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) { @@ -262,10 +259,7 @@ static void hns3_get_drvinfo(struct net_device *netdev, static u32 hns3_get_link(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h; - - h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_status) return h->ae_algo->ops->get_status(h); @@ -277,7 +271,8 @@ static void hns3_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *param) { struct hns3_nic_priv *priv = netdev_priv(netdev); - int queue_num = priv->ae_handle->kinfo.num_tqps; + struct hnae3_handle *h = priv->ae_handle; + int queue_num = h->kinfo.num_tqps; param->tx_max_pending = HNS3_RING_MAX_PENDING; param->rx_max_pending = HNS3_RING_MAX_PENDING; @@ -289,8 +284,7 @@ static void hns3_get_ringparam(struct net_device *netdev, static void hns3_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *param) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_pauseparam) h->ae_algo->ops->get_pauseparam(h, ¶m->autoneg, @@ -300,8 +294,7 @@ static void hns3_get_pauseparam(struct net_device *netdev, static int hns3_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); u32 supported_caps; u32 advertised_caps; u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN; @@ -392,8 +385,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev, static u32 hns3_get_rss_key_size(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_key_size) @@ -404,8 +396,7 @@ static u32 hns3_get_rss_key_size(struct net_device *netdev) static u32 hns3_get_rss_indir_size(struct net_device *netdev) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss_indir_size) @@ -417,8 +408,7 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev) static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss) return -EOPNOTSUPP; @@ -429,8 +419,7 @@ static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key, static int hns3_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key, const u8 hfunc) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss) return -EOPNOTSUPP; @@ -454,8 +443,7 @@ static int hns3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; + struct hnae3_handle *h = hns3_get_handle(netdev); if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_tc_size) return -EOPNOTSUPP; -- GitLab From 56cf68c73019ec3f04b1ae69f76f524918fb22cb Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:43:57 +0800 Subject: [PATCH 1136/1507] net: hns3: Cleanup indentation for Kconfig in the the hisilicon folder This patch fixes a few indentation for Kconfig file in the hisilicon folder. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 9d7cb0387bf70..30000b6aa7b8f 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -78,7 +78,7 @@ config HNS_ENET config HNS3 tristate "Hisilicon Network Subsystem Support HNS3 (Framework)" - depends on PCI + depends on PCI ---help--- This selects the framework support for Hisilicon Network Subsystem 3. This layer facilitates clients like ENET, RoCE and user-space ethernet @@ -87,7 +87,7 @@ config HNS3 config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" - depends on PCI_MSI + depends on PCI_MSI depends on HNS3 ---help--- This selects the HNS3_HCLGE network acceleration engine & its hardware @@ -96,7 +96,7 @@ config HNS3_HCLGE config HNS3_ENET tristate "Hisilicon HNS3 Ethernet Device Support" - depends on 64BIT && PCI + depends on 64BIT && PCI depends on HNS3 && HNS3_HCLGE ---help--- This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08 -- GitLab From 5392902d332b85a93e3be2755f7f6df183e5cafc Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:43:58 +0800 Subject: [PATCH 1137/1507] net: hns3: Consistently using GENMASK in hns3 driver This patch uses GENMASK to generate bit mask whenever possible in hns3 driver. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.h | 48 +++++++++---------- .../hisilicon/hns3/hns3pf/hclge_main.h | 4 +- 2 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 6b6d28eff664a..9cff7dbca5dd0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -250,11 +250,11 @@ struct hclge_ctrl_vector_chain { u8 int_vector_id; u8 int_cause_num; #define HCLGE_INT_TYPE_S 0 -#define HCLGE_INT_TYPE_M 0x3 +#define HCLGE_INT_TYPE_M GENMASK(1, 0) #define HCLGE_TQP_ID_S 2 -#define HCLGE_TQP_ID_M (0x7ff << HCLGE_TQP_ID_S) +#define HCLGE_TQP_ID_M GENMASK(12, 2) #define HCLGE_INT_GL_IDX_S 13 -#define HCLGE_INT_GL_IDX_M (0x3 << HCLGE_INT_GL_IDX_S) +#define HCLGE_INT_GL_IDX_M GENMASK(14, 13) __le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD]; u8 vfid; u8 rsv; @@ -372,28 +372,28 @@ struct hclge_pf_res { }; #define HCLGE_CFG_OFFSET_S 0 -#define HCLGE_CFG_OFFSET_M 0xfffff /* Byte (8-10.3) */ +#define HCLGE_CFG_OFFSET_M GENMASK(19, 0) #define HCLGE_CFG_RD_LEN_S 24 -#define HCLGE_CFG_RD_LEN_M (0xf << HCLGE_CFG_RD_LEN_S) +#define HCLGE_CFG_RD_LEN_M GENMASK(27, 24) #define HCLGE_CFG_RD_LEN_BYTES 16 #define HCLGE_CFG_RD_LEN_UNIT 4 #define HCLGE_CFG_VMDQ_S 0 -#define HCLGE_CFG_VMDQ_M (0xff << HCLGE_CFG_VMDQ_S) +#define HCLGE_CFG_VMDQ_M GENMASK(7, 0) #define HCLGE_CFG_TC_NUM_S 8 -#define HCLGE_CFG_TC_NUM_M (0xff << HCLGE_CFG_TC_NUM_S) +#define HCLGE_CFG_TC_NUM_M GENMASK(15, 8) #define HCLGE_CFG_TQP_DESC_N_S 16 -#define HCLGE_CFG_TQP_DESC_N_M (0xffff << HCLGE_CFG_TQP_DESC_N_S) +#define HCLGE_CFG_TQP_DESC_N_M GENMASK(31, 16) #define HCLGE_CFG_PHY_ADDR_S 0 -#define HCLGE_CFG_PHY_ADDR_M (0x1f << HCLGE_CFG_PHY_ADDR_S) +#define HCLGE_CFG_PHY_ADDR_M GENMASK(4, 0) #define HCLGE_CFG_MEDIA_TP_S 8 -#define HCLGE_CFG_MEDIA_TP_M (0xff << HCLGE_CFG_MEDIA_TP_S) +#define HCLGE_CFG_MEDIA_TP_M GENMASK(15, 8) #define HCLGE_CFG_RX_BUF_LEN_S 16 -#define HCLGE_CFG_RX_BUF_LEN_M (0xffff << HCLGE_CFG_RX_BUF_LEN_S) +#define HCLGE_CFG_RX_BUF_LEN_M GENMASK(31, 16) #define HCLGE_CFG_MAC_ADDR_H_S 0 -#define HCLGE_CFG_MAC_ADDR_H_M (0xffff << HCLGE_CFG_MAC_ADDR_H_S) +#define HCLGE_CFG_MAC_ADDR_H_M GENMASK(15, 0) #define HCLGE_CFG_DEFAULT_SPEED_S 16 -#define HCLGE_CFG_DEFAULT_SPEED_M (0xff << HCLGE_CFG_DEFAULT_SPEED_S) +#define HCLGE_CFG_DEFAULT_SPEED_M GENMASK(23, 16) struct hclge_cfg_param { __le32 offset; @@ -441,9 +441,9 @@ struct hclge_rss_indirection_table { }; #define HCLGE_RSS_TC_OFFSET_S 0 -#define HCLGE_RSS_TC_OFFSET_M (0x3ff << HCLGE_RSS_TC_OFFSET_S) +#define HCLGE_RSS_TC_OFFSET_M GENMASK(9, 0) #define HCLGE_RSS_TC_SIZE_S 12 -#define HCLGE_RSS_TC_SIZE_M (0x7 << HCLGE_RSS_TC_SIZE_S) +#define HCLGE_RSS_TC_SIZE_M GENMASK(14, 12) #define HCLGE_RSS_TC_VALID_B 15 struct hclge_rss_tc_mode { u16 rss_tc_mode[HCLGE_MAX_TC_NUM]; @@ -501,7 +501,7 @@ struct hclge_config_mac_mode { }; #define HCLGE_CFG_SPEED_S 0 -#define HCLGE_CFG_SPEED_M (0x3f << HCLGE_CFG_SPEED_S) +#define HCLGE_CFG_SPEED_M GENMASK(5, 0) #define HCLGE_CFG_DUPLEX_B 7 #define HCLGE_CFG_DUPLEX_M BIT(HCLGE_CFG_DUPLEX_B) @@ -518,7 +518,7 @@ struct hclge_config_mac_speed_dup { #define HCLGE_QUERY_AN_B 0 #define HCLGE_QUERY_DUPLEX_B 2 -#define HCLGE_QUERY_SPEED_M (0x1f << HCLGE_QUERY_SPEED_S) +#define HCLGE_QUERY_SPEED_M GENMASK(4, 0) #define HCLGE_QUERY_AN_M BIT(HCLGE_QUERY_AN_B) #define HCLGE_QUERY_DUPLEX_M BIT(HCLGE_QUERY_DUPLEX_B) @@ -528,7 +528,7 @@ struct hclge_query_an_speed_dup { u8 rsv[23]; }; -#define HCLGE_RING_ID_MASK 0x3ff +#define HCLGE_RING_ID_MASK GENMASK(9, 0) #define HCLGE_TQP_ENABLE_B 0 #define HCLGE_MAC_CFG_AN_EN_B 0 @@ -565,9 +565,9 @@ enum hclge_mac_vlan_tbl_opcode { #define HCLGE_MAC_EPORT_SW_EN_B 0xc #define HCLGE_MAC_EPORT_TYPE_B 0xb #define HCLGE_MAC_EPORT_VFID_S 0x3 -#define HCLGE_MAC_EPORT_VFID_M (0xff << HCLGE_MAC_EPORT_VFID_S) +#define HCLGE_MAC_EPORT_VFID_M GENMASK(10, 3) #define HCLGE_MAC_EPORT_PFID_S 0x0 -#define HCLGE_MAC_EPORT_PFID_M (0x7 << HCLGE_MAC_EPORT_PFID_S) +#define HCLGE_MAC_EPORT_PFID_M GENMASK(2, 0) struct hclge_mac_vlan_tbl_entry { u8 flags; u8 resp_code; @@ -583,7 +583,7 @@ struct hclge_mac_vlan_tbl_entry { }; #define HCLGE_CFG_MTA_MAC_SEL_S 0x0 -#define HCLGE_CFG_MTA_MAC_SEL_M (0x3 << HCLGE_CFG_MTA_MAC_SEL_S) +#define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) #define HCLGE_CFG_MTA_MAC_EN_B 0x7 struct hclge_mta_filter_mode { u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ @@ -599,7 +599,7 @@ struct hclge_cfg_func_mta_filter { #define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0x0 #define HCLGE_CFG_MTA_ITEM_IDX_S 0x0 -#define HCLGE_CFG_MTA_ITEM_IDX_M (0xfff << HCLGE_CFG_MTA_ITEM_IDX_S) +#define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) struct hclge_cfg_func_mta_item { u16 item_idx; /* Only used lowest 12 bit */ u8 accept; /* Only used lowest 1 bit */ @@ -670,10 +670,10 @@ struct hclge_cfg_tx_queue_pointer { }; #define HCLGE_TSO_MSS_MIN_S 0 -#define HCLGE_TSO_MSS_MIN_M (0x3FFF << HCLGE_TSO_MSS_MIN_S) +#define HCLGE_TSO_MSS_MIN_M GENMASK(13, 0) #define HCLGE_TSO_MSS_MAX_S 16 -#define HCLGE_TSO_MSS_MAX_M (0x3FFF << HCLGE_TSO_MSS_MAX_S) +#define HCLGE_TSO_MSS_MAX_M GENMASK(29, 16) struct hclge_cfg_tso_status { __le16 tso_mss_min; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 7c66c00e8a3ef..79c1a06cb941b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -32,7 +32,7 @@ #define HCLGE_VECTOR_VF_OFFSET 0x100000 #define HCLGE_RSS_IND_TBL_SIZE 512 -#define HCLGE_RSS_SET_BITMAP_MSK 0xffff +#define HCLGE_RSS_SET_BITMAP_MSK GENMASK(15, 0) #define HCLGE_RSS_KEY_SIZE 40 #define HCLGE_RSS_HASH_ALGO_TOEPLITZ 0 #define HCLGE_RSS_HASH_ALGO_SIMPLE 1 @@ -65,7 +65,7 @@ #define HCLGE_PHY_CSS_REG 17 #define HCLGE_PHY_MDIX_CTRL_S (5) -#define HCLGE_PHY_MDIX_CTRL_M (3 << HCLGE_PHY_MDIX_CTRL_S) +#define HCLGE_PHY_MDIX_CTRL_M GENMASK(6, 5) #define HCLGE_PHY_MDIX_STATUS_B (6) #define HCLGE_PHY_SPEED_DUP_RESOLVE_B (11) -- GitLab From d44f9b631fbc137b1b16a22318ceb136f934db48 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:43:59 +0800 Subject: [PATCH 1138/1507] net: hns3: Cleanup for struct that used to send cmd to firmware The hclge_tm module has already added _cmd to the end of struct that used to send cmd to firmware. This will help us finding the endian issues. This patch adds the _cmd to the end of struct that used to send cmd to firmware in hclge_main module. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.c | 4 +- .../hisilicon/hns3/hns3pf/hclge_cmd.h | 72 ++++---- .../hisilicon/hns3/hns3pf/hclge_main.c | 163 +++++++++--------- 3 files changed, 120 insertions(+), 119 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 8b511e6e0ce9d..648b64bc363a1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -279,12 +279,12 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw, u32 *version) { - struct hclge_query_version *resp; + struct hclge_query_version_cmd *resp; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FW_VER, 1); - resp = (struct hclge_query_version *)desc.data; + resp = (struct hclge_query_version_cmd *)desc.data; ret = hclge_cmd_send(hw, &desc, 1); if (!ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 9cff7dbca5dd0..d2ff0e37f9f57 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -221,12 +221,12 @@ enum hclge_opcode_type { #define HCLGE_RCB_INIT_QUERY_TIMEOUT 10 #define HCLGE_RCB_INIT_FLAG_EN_B 0 #define HCLGE_RCB_INIT_FLAG_FINI_B 8 -struct hclge_config_rcb_init { +struct hclge_config_rcb_init_cmd { __le16 rcb_init_flag; u8 rsv[22]; }; -struct hclge_tqp_map { +struct hclge_tqp_map_cmd { __le16 tqp_id; /* Absolute tqp id for in this pf */ u8 tqp_vf; /* VF id */ #define HCLGE_TQP_MAP_TYPE_PF 0 @@ -246,7 +246,7 @@ enum hclge_int_type { HCLGE_INT_EVENT, }; -struct hclge_ctrl_vector_chain { +struct hclge_ctrl_vector_chain_cmd { u8 int_vector_id; u8 int_cause_num; #define HCLGE_INT_TYPE_S 0 @@ -263,18 +263,18 @@ struct hclge_ctrl_vector_chain { #define HCLGE_TC_NUM 8 #define HCLGE_TC0_PRI_BUF_EN_B 15 /* Bit 15 indicate enable or not */ #define HCLGE_BUF_UNIT_S 7 /* Buf size is united by 128 bytes */ -struct hclge_tx_buff_alloc { +struct hclge_tx_buff_alloc_cmd { __le16 tx_pkt_buff[HCLGE_TC_NUM]; u8 tx_buff_rsv[8]; }; -struct hclge_rx_priv_buff { +struct hclge_rx_priv_buff_cmd { __le16 buf_num[HCLGE_TC_NUM]; __le16 shared_buf; u8 rsv[6]; }; -struct hclge_query_version { +struct hclge_query_version_cmd { __le32 firmware; __le32 firmware_rsv[5]; }; @@ -328,14 +328,14 @@ struct hclge_pkt_buf_alloc { }; #define HCLGE_RX_COM_WL_EN_B 15 -struct hclge_rx_com_wl_buf { +struct hclge_rx_com_wl_buf_cmd { __le16 high_wl; __le16 low_wl; u8 rsv[20]; }; #define HCLGE_RX_PKT_EN_B 15 -struct hclge_rx_pkt_buf { +struct hclge_rx_pkt_buf_cmd { __le16 high_pkt; __le16 low_pkt; u8 rsv[20]; @@ -348,7 +348,7 @@ struct hclge_rx_pkt_buf { #define HCLGE_PF_MAC_NUM_MASK 0x3 #define HCLGE_PF_STATE_MAIN BIT(HCLGE_PF_STATE_MAIN_B) #define HCLGE_PF_STATE_DONE BIT(HCLGE_PF_STATE_DONE_B) -struct hclge_func_status { +struct hclge_func_status_cmd { __le32 vf_rst_state[4]; u8 pf_state; u8 mac_id; @@ -359,7 +359,7 @@ struct hclge_func_status { u8 rsv[2]; }; -struct hclge_pf_res { +struct hclge_pf_res_cmd { __le16 tqp_num; __le16 buf_size; __le16 msixcap_localid_ba_nic; @@ -395,7 +395,7 @@ struct hclge_pf_res { #define HCLGE_CFG_DEFAULT_SPEED_S 16 #define HCLGE_CFG_DEFAULT_SPEED_M GENMASK(23, 16) -struct hclge_cfg_param { +struct hclge_cfg_param_cmd { __le32 offset; __le32 rsv; __le32 param[4]; @@ -405,7 +405,7 @@ struct hclge_cfg_param { #define HCLGE_DESC_NUM 0x40 #define HCLGE_ALLOC_VALID_B 0 -struct hclge_vf_num { +struct hclge_vf_num_cmd { u8 alloc_valid; u8 rsv[23]; }; @@ -413,13 +413,13 @@ struct hclge_vf_num { #define HCLGE_RSS_DEFAULT_OUTPORT_B 4 #define HCLGE_RSS_HASH_KEY_OFFSET_B 4 #define HCLGE_RSS_HASH_KEY_NUM 16 -struct hclge_rss_config { +struct hclge_rss_config_cmd { u8 hash_config; u8 rsv[7]; u8 hash_key[HCLGE_RSS_HASH_KEY_NUM]; }; -struct hclge_rss_input_tuple { +struct hclge_rss_input_tuple_cmd { u8 ipv4_tcp_en; u8 ipv4_udp_en; u8 ipv4_sctp_en; @@ -433,7 +433,7 @@ struct hclge_rss_input_tuple { #define HCLGE_RSS_CFG_TBL_SIZE 16 -struct hclge_rss_indirection_table { +struct hclge_rss_indirection_table_cmd { u16 start_table_index; u16 rss_set_bitmap; u8 rsv[4]; @@ -445,14 +445,14 @@ struct hclge_rss_indirection_table { #define HCLGE_RSS_TC_SIZE_S 12 #define HCLGE_RSS_TC_SIZE_M GENMASK(14, 12) #define HCLGE_RSS_TC_VALID_B 15 -struct hclge_rss_tc_mode { +struct hclge_rss_tc_mode_cmd { u16 rss_tc_mode[HCLGE_MAX_TC_NUM]; u8 rsv[8]; }; #define HCLGE_LINK_STS_B 0 #define HCLGE_LINK_STATUS BIT(HCLGE_LINK_STS_B) -struct hclge_link_status { +struct hclge_link_status_cmd { u8 status; u8 rsv[23]; }; @@ -467,7 +467,7 @@ struct hclge_promisc_param { #define HCLGE_PROMISC_EN_UC 0x1 #define HCLGE_PROMISC_EN_MC 0x2 #define HCLGE_PROMISC_EN_BC 0x4 -struct hclge_promisc_cfg { +struct hclge_promisc_cfg_cmd { u8 flag; u8 vf_id; __le16 rsv0; @@ -495,7 +495,7 @@ enum hclge_promisc_type { #define HCLGE_MAC_TX_UNDER_MIN_ERR_B 21 #define HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B 22 -struct hclge_config_mac_mode { +struct hclge_config_mac_mode_cmd { __le32 txrx_pad_fcs_loop_en; u8 rsv[20]; }; @@ -506,7 +506,7 @@ struct hclge_config_mac_mode { #define HCLGE_CFG_DUPLEX_B 7 #define HCLGE_CFG_DUPLEX_M BIT(HCLGE_CFG_DUPLEX_B) -struct hclge_config_mac_speed_dup { +struct hclge_config_mac_speed_dup_cmd { u8 speed_dup; #define HCLGE_CFG_MAC_SPEED_CHANGE_EN_B 0 @@ -522,7 +522,7 @@ struct hclge_config_mac_speed_dup { #define HCLGE_QUERY_AN_M BIT(HCLGE_QUERY_AN_B) #define HCLGE_QUERY_DUPLEX_M BIT(HCLGE_QUERY_DUPLEX_B) -struct hclge_query_an_speed_dup { +struct hclge_query_an_speed_dup_cmd { u8 an_syn_dup_speed; u8 pause; u8 rsv[23]; @@ -539,7 +539,7 @@ struct hclge_query_an_speed_dup { #define HCLGE_MAC_CFG_AN_EN BIT(HCLGE_MAC_CFG_AN_EN_B) -struct hclge_config_auto_neg { +struct hclge_config_auto_neg_cmd { __le32 cfg_an_cmd_flag; u8 rsv[20]; }; @@ -548,7 +548,7 @@ struct hclge_config_auto_neg { #define HCLGE_MAC_MAX_MTU 9728 #define HCLGE_MAC_UPLINK_PORT 0x100 -struct hclge_config_max_frm_size { +struct hclge_config_max_frm_size_cmd { __le16 max_frm_size; u8 rsv[22]; }; @@ -568,7 +568,7 @@ enum hclge_mac_vlan_tbl_opcode { #define HCLGE_MAC_EPORT_VFID_M GENMASK(10, 3) #define HCLGE_MAC_EPORT_PFID_S 0x0 #define HCLGE_MAC_EPORT_PFID_M GENMASK(2, 0) -struct hclge_mac_vlan_tbl_entry { +struct hclge_mac_vlan_tbl_entry_cmd { u8 flags; u8 resp_code; __le16 vlan_tag; @@ -585,13 +585,13 @@ struct hclge_mac_vlan_tbl_entry { #define HCLGE_CFG_MTA_MAC_SEL_S 0x0 #define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) #define HCLGE_CFG_MTA_MAC_EN_B 0x7 -struct hclge_mta_filter_mode { +struct hclge_mta_filter_mode_cmd { u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ u8 rsv[23]; }; #define HCLGE_CFG_FUNC_MTA_ACCEPT_B 0x0 -struct hclge_cfg_func_mta_filter { +struct hclge_cfg_func_mta_filter_cmd { u8 accept; /* Only used lowest 1 bit */ u8 function_id; u8 rsv[22]; @@ -600,13 +600,13 @@ struct hclge_cfg_func_mta_filter { #define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0x0 #define HCLGE_CFG_MTA_ITEM_IDX_S 0x0 #define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) -struct hclge_cfg_func_mta_item { +struct hclge_cfg_func_mta_item_cmd { u16 item_idx; /* Only used lowest 12 bit */ u8 accept; /* Only used lowest 1 bit */ u8 rsv[21]; }; -struct hclge_mac_vlan_add { +struct hclge_mac_vlan_add_cmd { __le16 flags; __le16 mac_addr_hi16; __le32 mac_addr_lo32; @@ -619,7 +619,7 @@ struct hclge_mac_vlan_add { }; #define HNS3_MAC_VLAN_CFG_FLAG_BIT 0 -struct hclge_mac_vlan_remove { +struct hclge_mac_vlan_remove_cmd { __le16 flags; __le16 mac_addr_hi16; __le32 mac_addr_lo32; @@ -631,20 +631,20 @@ struct hclge_mac_vlan_remove { u8 rsv[4]; }; -struct hclge_vlan_filter_ctrl { +struct hclge_vlan_filter_ctrl_cmd { u8 vlan_type; u8 vlan_fe; u8 rsv[22]; }; -struct hclge_vlan_filter_pf_cfg { +struct hclge_vlan_filter_pf_cfg_cmd { u8 vlan_offset; u8 vlan_cfg; u8 rsv[2]; u8 vlan_offset_bitmap[20]; }; -struct hclge_vlan_filter_vf_cfg { +struct hclge_vlan_filter_vf_cfg_cmd { u16 vlan_id; u8 resp_code; u8 rsv; @@ -653,14 +653,14 @@ struct hclge_vlan_filter_vf_cfg { u8 vf_bitmap[16]; }; -struct hclge_cfg_com_tqp_queue { +struct hclge_cfg_com_tqp_queue_cmd { __le16 tqp_id; __le16 stream_id; u8 enable; u8 rsv[19]; }; -struct hclge_cfg_tx_queue_pointer { +struct hclge_cfg_tx_queue_pointer_cmd { __le16 tqp_id; __le16 tx_tail; __le16 tx_head; @@ -675,7 +675,7 @@ struct hclge_cfg_tx_queue_pointer { #define HCLGE_TSO_MSS_MAX_S 16 #define HCLGE_TSO_MSS_MAX_M GENMASK(29, 16) -struct hclge_cfg_tso_status { +struct hclge_cfg_tso_status_cmd { __le16 tso_mss_min; __le16 tso_mss_max; u8 rsv[20]; @@ -685,7 +685,7 @@ struct hclge_cfg_tso_status { #define HCLGE_TSO_MSS_MAX 9668 #define HCLGE_TQP_RESET_B 0 -struct hclge_reset_tqp_queue { +struct hclge_reset_tqp_queue_cmd { __le16 tqp_id; u8 reset_req; u8 ready_to_reset; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5c1bf12beade6..5103f234d1c32 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -820,7 +820,7 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) } static int hclge_parse_func_status(struct hclge_dev *hdev, - struct hclge_func_status *status) + struct hclge_func_status_cmd *status) { if (!(status->pf_state & HCLGE_PF_STATE_DONE)) return -EINVAL; @@ -837,13 +837,13 @@ static int hclge_parse_func_status(struct hclge_dev *hdev, static int hclge_query_function_status(struct hclge_dev *hdev) { - struct hclge_func_status *req; + struct hclge_func_status_cmd *req; struct hclge_desc desc; int timeout = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FUNC_STATUS, true); - req = (struct hclge_func_status *)desc.data; + req = (struct hclge_func_status_cmd *)desc.data; do { ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -868,7 +868,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev) static int hclge_query_pf_resource(struct hclge_dev *hdev) { - struct hclge_pf_res *req; + struct hclge_pf_res_cmd *req; struct hclge_desc desc; int ret; @@ -880,7 +880,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev) return ret; } - req = (struct hclge_pf_res *)desc.data; + req = (struct hclge_pf_res_cmd *)desc.data; hdev->num_tqps = __le16_to_cpu(req->tqp_num); hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S; @@ -938,12 +938,12 @@ static int hclge_parse_speed(int speed_cmd, int *speed) static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { - struct hclge_cfg_param *req; + struct hclge_cfg_param_cmd *req; u64 mac_addr_tmp_high; u64 mac_addr_tmp; int i; - req = (struct hclge_cfg_param *)desc[0].data; + req = (struct hclge_cfg_param_cmd *)desc[0].data; /* get the configuration */ cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]), @@ -978,7 +978,7 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) for (i = 0; i < ETH_ALEN; i++) cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff; - req = (struct hclge_cfg_param *)desc[1].data; + req = (struct hclge_cfg_param_cmd *)desc[1].data; cfg->numa_node_map = __le32_to_cpu(req->param[0]); } @@ -989,11 +989,11 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg) { struct hclge_desc desc[HCLGE_PF_CFG_DESC_NUM]; - struct hclge_cfg_param *req; + struct hclge_cfg_param_cmd *req; int i, ret; for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) { - req = (struct hclge_cfg_param *)desc[i].data; + req = (struct hclge_cfg_param_cmd *)desc[i].data; hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM, true); hnae_set_field(req->offset, HCLGE_CFG_OFFSET_M, @@ -1099,12 +1099,12 @@ static int hclge_configure(struct hclge_dev *hdev) static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min, int tso_mss_max) { - struct hclge_cfg_tso_status *req; + struct hclge_cfg_tso_status_cmd *req; struct hclge_desc desc; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false); - req = (struct hclge_cfg_tso_status *)desc.data; + req = (struct hclge_cfg_tso_status_cmd *)desc.data; hnae_set_field(req->tso_mss_min, HCLGE_TSO_MSS_MIN_M, HCLGE_TSO_MSS_MIN_S, tso_mss_min); hnae_set_field(req->tso_mss_max, HCLGE_TSO_MSS_MIN_M, @@ -1144,13 +1144,13 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev) static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id, u16 tqp_pid, u16 tqp_vid, bool is_pf) { - struct hclge_tqp_map *req; + struct hclge_tqp_map_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SET_TQP_MAP, false); - req = (struct hclge_tqp_map *)desc.data; + req = (struct hclge_tqp_map_cmd *)desc.data; req->tqp_id = cpu_to_le16(tqp_pid); req->tqp_vf = cpu_to_le16(func_id); req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B | @@ -1340,12 +1340,12 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, /* TX buffer size is unit by 128 byte */ #define HCLGE_BUF_SIZE_UNIT_SHIFT 7 #define HCLGE_BUF_SIZE_UPDATE_EN_MSK BIT(15) - struct hclge_tx_buff_alloc *req; + struct hclge_tx_buff_alloc_cmd *req; struct hclge_desc desc; int ret; u8 i; - req = (struct hclge_tx_buff_alloc *)desc.data; + req = (struct hclge_tx_buff_alloc_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); for (i = 0; i < HCLGE_TC_NUM; i++) { @@ -1672,13 +1672,13 @@ int hclge_rx_buffer_calc(struct hclge_dev *hdev, static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev, struct hclge_pkt_buf_alloc *buf_alloc) { - struct hclge_rx_priv_buff *req; + struct hclge_rx_priv_buff_cmd *req; struct hclge_desc desc; int ret; int i; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, false); - req = (struct hclge_rx_priv_buff *)desc.data; + req = (struct hclge_rx_priv_buff_cmd *)desc.data; /* Alloc private buffer TCs */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { @@ -2000,11 +2000,11 @@ static void hclge_check_speed_dup(struct hclge_dev *hdev, int duplex, int speed) int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) { - struct hclge_config_mac_speed_dup *req; + struct hclge_config_mac_speed_dup_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_config_mac_speed_dup *)desc.data; + req = (struct hclge_config_mac_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false); @@ -2075,12 +2075,12 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, u8 *duplex) { - struct hclge_query_an_speed_dup *req; + struct hclge_query_an_speed_dup_cmd *req; struct hclge_desc desc; int speed_tmp; int ret; - req = (struct hclge_query_an_speed_dup *)desc.data; + req = (struct hclge_query_an_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2108,11 +2108,11 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, static int hclge_query_autoneg_result(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; - struct hclge_query_an_speed_dup *req; + struct hclge_query_an_speed_dup_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_query_an_speed_dup *)desc.data; + req = (struct hclge_query_an_speed_dup_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2129,13 +2129,13 @@ static int hclge_query_autoneg_result(struct hclge_dev *hdev) static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) { - struct hclge_config_auto_neg *req; + struct hclge_config_auto_neg_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false); - req = (struct hclge_config_auto_neg *)desc.data; + req = (struct hclge_config_auto_neg_cmd *)desc.data; hnae_set_bit(req->cfg_an_cmd_flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2214,7 +2214,7 @@ static void hclge_task_schedule(struct hclge_dev *hdev) static int hclge_get_mac_link_status(struct hclge_dev *hdev) { - struct hclge_link_status *req; + struct hclge_link_status_cmd *req; struct hclge_desc desc; int link_status; int ret; @@ -2227,7 +2227,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev) return ret; } - req = (struct hclge_link_status *)desc.data; + req = (struct hclge_link_status_cmd *)desc.data; link_status = req->status & HCLGE_LINK_STATUS; return !!link_status; @@ -2451,7 +2451,7 @@ static u32 hclge_get_rss_indir_size(struct hnae3_handle *handle) static int hclge_get_rss_algo(struct hclge_dev *hdev) { - struct hclge_rss_config *req; + struct hclge_rss_config_cmd *req; struct hclge_desc desc; int rss_hash_algo; int ret; @@ -2465,7 +2465,7 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev) return ret; } - req = (struct hclge_rss_config *)desc.data; + req = (struct hclge_rss_config_cmd *)desc.data; rss_hash_algo = (req->hash_config & HCLGE_RSS_HASH_ALGO_MASK); if (rss_hash_algo == HCLGE_RSS_HASH_ALGO_TOEPLITZ) @@ -2477,13 +2477,13 @@ static int hclge_get_rss_algo(struct hclge_dev *hdev) static int hclge_set_rss_algo_key(struct hclge_dev *hdev, const u8 hfunc, const u8 *key) { - struct hclge_rss_config *req; + struct hclge_rss_config_cmd *req; struct hclge_desc desc; int key_offset; int key_size; int ret; - req = (struct hclge_rss_config *)desc.data; + req = (struct hclge_rss_config_cmd *)desc.data; for (key_offset = 0; key_offset < 3; key_offset++) { hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG, @@ -2514,12 +2514,12 @@ static int hclge_set_rss_algo_key(struct hclge_dev *hdev, static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) { - struct hclge_rss_indirection_table *req; + struct hclge_rss_indirection_table_cmd *req; struct hclge_desc desc; int i, j; int ret; - req = (struct hclge_rss_indirection_table *)desc.data; + req = (struct hclge_rss_indirection_table_cmd *)desc.data; for (i = 0; i < HCLGE_RSS_CFG_TBL_NUM; i++) { hclge_cmd_setup_basic_desc @@ -2546,13 +2546,13 @@ static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, u16 *tc_size, u16 *tc_offset) { - struct hclge_rss_tc_mode *req; + struct hclge_rss_tc_mode_cmd *req; struct hclge_desc desc; int ret; int i; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_TC_MODE, false); - req = (struct hclge_rss_tc_mode *)desc.data; + req = (struct hclge_rss_tc_mode_cmd *)desc.data; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { hnae_set_bit(req->rss_tc_mode[i], HCLGE_RSS_TC_VALID_B, @@ -2577,13 +2577,13 @@ static int hclge_set_rss_input_tuple(struct hclge_dev *hdev) { #define HCLGE_RSS_INPUT_TUPLE_OTHER 0xf #define HCLGE_RSS_INPUT_TUPLE_SCTP 0x1f - struct hclge_rss_input_tuple *req; + struct hclge_rss_input_tuple_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, false); - req = (struct hclge_rss_input_tuple *)desc.data; + req = (struct hclge_rss_input_tuple_cmd *)desc.data; req->ipv4_tcp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; req->ipv4_udp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; req->ipv4_sctp_en = HCLGE_RSS_INPUT_TUPLE_SCTP; @@ -2750,7 +2750,7 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, struct hnae3_ring_chain_node *ring_chain) { struct hclge_dev *hdev = vport->back; - struct hclge_ctrl_vector_chain *req; + struct hclge_ctrl_vector_chain_cmd *req; struct hnae3_ring_chain_node *node; struct hclge_desc desc; int ret; @@ -2758,7 +2758,7 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ADD_RING_TO_VECTOR, false); - req = (struct hclge_ctrl_vector_chain *)desc.data; + req = (struct hclge_ctrl_vector_chain_cmd *)desc.data; req->int_vector_id = vector_id; i = 0; @@ -2831,7 +2831,7 @@ static int hclge_unmap_ring_from_vector( { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - struct hclge_ctrl_vector_chain *req; + struct hclge_ctrl_vector_chain_cmd *req; struct hnae3_ring_chain_node *node; struct hclge_desc desc; int i, vector_id; @@ -2846,7 +2846,7 @@ static int hclge_unmap_ring_from_vector( hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_DEL_RING_TO_VECTOR, false); - req = (struct hclge_ctrl_vector_chain *)desc.data; + req = (struct hclge_ctrl_vector_chain_cmd *)desc.data; req->int_vector_id = vector_id; i = 0; @@ -2898,13 +2898,13 @@ static int hclge_unmap_ring_from_vector( int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, struct hclge_promisc_param *param) { - struct hclge_promisc_cfg *req; + struct hclge_promisc_cfg_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PROMISC_MODE, false); - req = (struct hclge_promisc_cfg *)desc.data; + req = (struct hclge_promisc_cfg_cmd *)desc.data; req->vf_id = param->vf_id; req->flag = (param->enable << HCLGE_PROMISC_EN_B); @@ -2946,8 +2946,8 @@ static void hclge_set_promisc_mode(struct hnae3_handle *handle, u32 en) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { struct hclge_desc desc; - struct hclge_config_mac_mode *req = - (struct hclge_config_mac_mode *)desc.data; + struct hclge_config_mac_mode_cmd *req = + (struct hclge_config_mac_mode_cmd *)desc.data; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false); @@ -2980,8 +2980,8 @@ static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id, int stream_id, bool enable) { struct hclge_desc desc; - struct hclge_cfg_com_tqp_queue *req = - (struct hclge_cfg_com_tqp_queue *)desc.data; + struct hclge_cfg_com_tqp_queue_cmd *req = + (struct hclge_cfg_com_tqp_queue_cmd *)desc.data; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false); @@ -3174,7 +3174,7 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc) return true; } -static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req, +static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, const u8 *addr) { const unsigned char *mac_addr = addr; @@ -3201,11 +3201,11 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, enum hclge_mta_dmac_sel_type mta_mac_sel, bool enable) { - struct hclge_mta_filter_mode *req; + struct hclge_mta_filter_mode_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_mta_filter_mode *)desc.data; + req = (struct hclge_mta_filter_mode_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, @@ -3228,11 +3228,11 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, u8 func_id, bool enable) { - struct hclge_cfg_func_mta_filter *req; + struct hclge_cfg_func_mta_filter_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_cfg_func_mta_filter *)desc.data; + req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, @@ -3255,11 +3255,11 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, bool enable) { struct hclge_dev *hdev = vport->back; - struct hclge_cfg_func_mta_item *req; + struct hclge_cfg_func_mta_item_cmd *req; struct hclge_desc desc; int ret; - req = (struct hclge_cfg_func_mta_item *)desc.data; + req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); @@ -3279,7 +3279,7 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, } static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req) + struct hclge_mac_vlan_tbl_entry_cmd *req) { struct hclge_dev *hdev = vport->back; struct hclge_desc desc; @@ -3288,7 +3288,7 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_REMOVE, false); - memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -3304,7 +3304,7 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, } static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req, + struct hclge_mac_vlan_tbl_entry_cmd *req, struct hclge_desc *desc, bool is_mc) { @@ -3317,7 +3317,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); memcpy(desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_MAC_VLAN_ADD, true); @@ -3329,7 +3329,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, } else { memcpy(desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, desc, 1); } if (ret) { @@ -3345,7 +3345,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, } static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, - struct hclge_mac_vlan_tbl_entry *req, + struct hclge_mac_vlan_tbl_entry_cmd *req, struct hclge_desc *mc_desc) { struct hclge_dev *hdev = vport->back; @@ -3359,7 +3359,8 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ADD, false); - memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + memcpy(desc.data, req, + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); resp_code = (desc.data[0] >> 8) & 0xff; cfg_status = hclge_get_mac_vlan_cmd_status(vport, desc.retval, @@ -3373,7 +3374,7 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_NEXT); memcpy(mc_desc[0].data, req, - sizeof(struct hclge_mac_vlan_tbl_entry)); + sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, mc_desc, 3); resp_code = (mc_desc[0].data[0] >> 8) & 0xff; cfg_status = hclge_get_mac_vlan_cmd_status(vport, @@ -3404,7 +3405,7 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; /* mac addr check */ @@ -3454,7 +3455,7 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; /* mac addr check */ @@ -3488,7 +3489,7 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; struct hclge_desc desc[3]; u16 tbl_idx; int status; @@ -3539,7 +3540,7 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, const unsigned char *addr) { struct hclge_dev *hdev = vport->back; - struct hclge_mac_vlan_tbl_entry req; + struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; struct hclge_desc desc[3]; u16 tbl_idx; @@ -3622,13 +3623,13 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p) static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, bool filter_en) { - struct hclge_vlan_filter_ctrl *req; + struct hclge_vlan_filter_ctrl_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false); - req = (struct hclge_vlan_filter_ctrl *)desc.data; + req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; req->vlan_type = vlan_type; req->vlan_fe = filter_en; @@ -3646,8 +3647,8 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, bool is_kill, u16 vlan, u8 qos, __be16 proto) { #define HCLGE_MAX_VF_BYTES 16 - struct hclge_vlan_filter_vf_cfg *req0; - struct hclge_vlan_filter_vf_cfg *req1; + struct hclge_vlan_filter_vf_cfg_cmd *req0; + struct hclge_vlan_filter_vf_cfg_cmd *req1; struct hclge_desc desc[2]; u8 vf_byte_val; u8 vf_byte_off; @@ -3663,8 +3664,8 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, vf_byte_off = vfid / 8; vf_byte_val = 1 << (vfid % 8); - req0 = (struct hclge_vlan_filter_vf_cfg *)desc[0].data; - req1 = (struct hclge_vlan_filter_vf_cfg *)desc[1].data; + req0 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[0].data; + req1 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[1].data; req0->vlan_id = vlan; req0->vlan_cfg = is_kill; @@ -3707,7 +3708,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - struct hclge_vlan_filter_pf_cfg *req; + struct hclge_vlan_filter_pf_cfg_cmd *req; struct hclge_desc desc; u8 vlan_offset_byte_val; u8 vlan_offset_byte; @@ -3720,7 +3721,7 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, vlan_offset_byte = (vlan_id % 160) / 8; vlan_offset_byte_val = 1 << (vlan_id % 8); - req = (struct hclge_vlan_filter_pf_cfg *)desc.data; + req = (struct hclge_vlan_filter_pf_cfg_cmd *)desc.data; req->vlan_offset = vlan_offset_160; req->vlan_cfg = is_kill; req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val; @@ -3782,7 +3783,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_config_max_frm_size *req; + struct hclge_config_max_frm_size_cmd *req; struct hclge_dev *hdev = vport->back; struct hclge_desc desc; int ret; @@ -3793,7 +3794,7 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) hdev->mps = new_mtu; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false); - req = (struct hclge_config_max_frm_size *)desc.data; + req = (struct hclge_config_max_frm_size_cmd *)desc.data; req->max_frm_size = cpu_to_le16(new_mtu); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -3808,13 +3809,13 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, bool enable) { - struct hclge_reset_tqp_queue *req; + struct hclge_reset_tqp_queue_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, false); - req = (struct hclge_reset_tqp_queue *)desc.data; + req = (struct hclge_reset_tqp_queue_cmd *)desc.data; req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable); @@ -3830,13 +3831,13 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) { - struct hclge_reset_tqp_queue *req; + struct hclge_reset_tqp_queue_cmd *req; struct hclge_desc desc; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, true); - req = (struct hclge_reset_tqp_queue *)desc.data; + req = (struct hclge_reset_tqp_queue_cmd *)desc.data; req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); ret = hclge_cmd_send(&hdev->hw, &desc, 1); -- GitLab From a90bb9a5ea1db7f10096e7573b7d45295ad4eada Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:44:00 +0800 Subject: [PATCH 1139/1507] net: hns3: Cleanup for endian issue in hns3 driver This patch fixes a lot of endian issues detected by sparse. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.c | 8 +- .../hisilicon/hns3/hns3pf/hclge_cmd.h | 10 +- .../hisilicon/hns3/hns3pf/hclge_main.c | 206 ++++++++++-------- .../ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 26 ++- .../hisilicon/hns3/hns3pf/hns3_enet.c | 4 +- 5 files changed, 145 insertions(+), 109 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 648b64bc363a1..05985d81dda05 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -208,7 +208,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) * which will be use for hardware to write back */ ntc = hw->cmq.csq.next_to_use; - opcode = desc[0].opcode; + opcode = le16_to_cpu(desc[0].opcode); while (handle < num) { desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use]; *desc_to_use = desc[handle]; @@ -225,7 +225,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) * If the command is sync, wait for the firmware to write back, * if multi descriptors to be sent, use the first one to check */ - if (HCLGE_SEND_SYNC(desc->flag)) { + if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) { do { if (hclge_cmd_csq_done(hw)) break; @@ -244,9 +244,9 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) pr_debug("Get cmd desc:\n"); if (likely(!hclge_is_special_opcode(opcode))) - desc_ret = desc[handle].retval; + desc_ret = le16_to_cpu(desc[handle].retval); else - desc_ret = desc[0].retval; + desc_ret = le16_to_cpu(desc[0].retval); if ((enum hclge_cmd_return_status)desc_ret == HCLGE_CMD_EXEC_SUCCESS) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index d2ff0e37f9f57..8f3ba02aea3ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -434,8 +434,8 @@ struct hclge_rss_input_tuple_cmd { #define HCLGE_RSS_CFG_TBL_SIZE 16 struct hclge_rss_indirection_table_cmd { - u16 start_table_index; - u16 rss_set_bitmap; + __le16 start_table_index; + __le16 rss_set_bitmap; u8 rsv[4]; u8 rss_result[HCLGE_RSS_CFG_TBL_SIZE]; }; @@ -446,7 +446,7 @@ struct hclge_rss_indirection_table_cmd { #define HCLGE_RSS_TC_SIZE_M GENMASK(14, 12) #define HCLGE_RSS_TC_VALID_B 15 struct hclge_rss_tc_mode_cmd { - u16 rss_tc_mode[HCLGE_MAX_TC_NUM]; + __le16 rss_tc_mode[HCLGE_MAX_TC_NUM]; u8 rsv[8]; }; @@ -601,7 +601,7 @@ struct hclge_cfg_func_mta_filter_cmd { #define HCLGE_CFG_MTA_ITEM_IDX_S 0x0 #define HCLGE_CFG_MTA_ITEM_IDX_M GENMASK(11, 0) struct hclge_cfg_func_mta_item_cmd { - u16 item_idx; /* Only used lowest 12 bit */ + __le16 item_idx; /* Only used lowest 12 bit */ u8 accept; /* Only used lowest 1 bit */ u8 rsv[21]; }; @@ -645,7 +645,7 @@ struct hclge_vlan_filter_pf_cfg_cmd { }; struct hclge_vlan_filter_vf_cfg_cmd { - u16 vlan_id; + __le16 vlan_id; u8 resp_code; u8 rsv; u8 vlan_cfg; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5103f234d1c32..6115c2f730ce4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -362,7 +362,7 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev) #define HCLGE_64_BIT_RTN_DATANUM 4 u64 *data = (u64 *)(&hdev->hw_stats.all_64_bit_stats); struct hclge_desc desc[HCLGE_64_BIT_CMD_NUM]; - u64 *desc_data; + __le64 *desc_data; int i, k, n; int ret; @@ -376,14 +376,14 @@ static int hclge_64_bit_update_stats(struct hclge_dev *hdev) for (i = 0; i < HCLGE_64_BIT_CMD_NUM; i++) { if (unlikely(i == 0)) { - desc_data = (u64 *)(&desc[i].data[0]); + desc_data = (__le64 *)(&desc[i].data[0]); n = HCLGE_64_BIT_RTN_DATANUM - 1; } else { - desc_data = (u64 *)(&desc[i]); + desc_data = (__le64 *)(&desc[i]); n = HCLGE_64_BIT_RTN_DATANUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le64(*desc_data); + *data++ += le64_to_cpu(*desc_data); desc_data++; } } @@ -411,7 +411,7 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev) struct hclge_desc desc[HCLGE_32_BIT_CMD_NUM]; struct hclge_32_bit_stats *all_32_bit_stats; - u32 *desc_data; + __le32 *desc_data; int i, k, n; u64 *data; int ret; @@ -431,21 +431,27 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev) hclge_reset_partial_32bit_counter(all_32_bit_stats); for (i = 0; i < HCLGE_32_BIT_CMD_NUM; i++) { if (unlikely(i == 0)) { + __le16 *desc_data_16bit; + all_32_bit_stats->igu_rx_err_pkt += - cpu_to_le32(desc[i].data[0]); + le32_to_cpu(desc[i].data[0]); + + desc_data_16bit = (__le16 *)&desc[i].data[1]; all_32_bit_stats->igu_rx_no_eof_pkt += - cpu_to_le32(desc[i].data[1] & 0xffff); + le16_to_cpu(*desc_data_16bit); + + desc_data_16bit++; all_32_bit_stats->igu_rx_no_sof_pkt += - cpu_to_le32((desc[i].data[1] >> 16) & 0xffff); + le16_to_cpu(*desc_data_16bit); - desc_data = (u32 *)(&desc[i].data[2]); + desc_data = &desc[i].data[2]; n = HCLGE_32_BIT_RTN_DATANUM - 4; } else { - desc_data = (u32 *)(&desc[i]); + desc_data = (__le32 *)&desc[i]; n = HCLGE_32_BIT_RTN_DATANUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le32(*desc_data); + *data++ += le32_to_cpu(*desc_data); desc_data++; } } @@ -460,7 +466,7 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev) u64 *data = (u64 *)(&hdev->hw_stats.mac_stats); struct hclge_desc desc[HCLGE_MAC_CMD_NUM]; - u64 *desc_data; + __le64 *desc_data; int i, k, n; int ret; @@ -475,14 +481,14 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev) for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) { if (unlikely(i == 0)) { - desc_data = (u64 *)(&desc[i].data[0]); + desc_data = (__le64 *)(&desc[i].data[0]); n = HCLGE_RTN_DATA_NUM - 2; } else { - desc_data = (u64 *)(&desc[i]); + desc_data = (__le64 *)(&desc[i]); n = HCLGE_RTN_DATA_NUM; } for (k = 0; k < n; k++) { - *data++ += cpu_to_le64(*desc_data); + *data++ += le64_to_cpu(*desc_data); desc_data++; } } @@ -508,7 +514,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) HCLGE_OPC_QUERY_RX_STATUS, true); - desc[0].data[0] = (tqp->index & 0x1ff); + desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff)); ret = hclge_cmd_send(&hdev->hw, desc, 1); if (ret) { dev_err(&hdev->pdev->dev, @@ -517,7 +523,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) return ret; } tqp->tqp_stats.rcb_rx_ring_pktnum_rcd += - cpu_to_le32(desc[0].data[4]); + le32_to_cpu(desc[0].data[4]); } for (i = 0; i < kinfo->num_tqps; i++) { @@ -528,7 +534,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) HCLGE_OPC_QUERY_TX_STATUS, true); - desc[0].data[0] = (tqp->index & 0x1ff); + desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff)); ret = hclge_cmd_send(&hdev->hw, desc, 1); if (ret) { dev_err(&hdev->pdev->dev, @@ -537,7 +543,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle) return ret; } tqp->tqp_stats.rcb_tx_ring_pktnum_rcd += - cpu_to_le32(desc[0].data[4]); + le32_to_cpu(desc[0].data[4]); } return 0; @@ -552,12 +558,12 @@ static u64 *hclge_tqps_get_stats(struct hnae3_handle *handle, u64 *data) for (i = 0; i < kinfo->num_tqps; i++) { tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); - *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_tx_ring_pktnum_rcd); + *buff++ = tqp->tqp_stats.rcb_tx_ring_pktnum_rcd; } for (i = 0; i < kinfo->num_tqps; i++) { tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); - *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_rx_ring_pktnum_rcd); + *buff++ = tqp->tqp_stats.rcb_rx_ring_pktnum_rcd; } return buff; @@ -993,16 +999,17 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg) int i, ret; for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) { + u32 offset = 0; + req = (struct hclge_cfg_param_cmd *)desc[i].data; hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM, true); - hnae_set_field(req->offset, HCLGE_CFG_OFFSET_M, + hnae_set_field(offset, HCLGE_CFG_OFFSET_M, HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES); /* Len should be united by 4 bytes when send to hardware */ - hnae_set_field(req->offset, HCLGE_CFG_RD_LEN_M, - HCLGE_CFG_RD_LEN_S, + hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S, HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT); - req->offset = cpu_to_le32(req->offset); + req->offset = cpu_to_le32(offset); } ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM); @@ -1101,14 +1108,21 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min, { struct hclge_cfg_tso_status_cmd *req; struct hclge_desc desc; + u16 tso_mss; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false); req = (struct hclge_cfg_tso_status_cmd *)desc.data; - hnae_set_field(req->tso_mss_min, HCLGE_TSO_MSS_MIN_M, + + tso_mss = 0; + hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, HCLGE_TSO_MSS_MIN_S, tso_mss_min); - hnae_set_field(req->tso_mss_max, HCLGE_TSO_MSS_MIN_M, + req->tso_mss_min = cpu_to_le16(tso_mss); + + tso_mss = 0; + hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M, HCLGE_TSO_MSS_MIN_S, tso_mss_max); + req->tso_mss_max = cpu_to_le16(tso_mss); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -1152,7 +1166,7 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id, req = (struct hclge_tqp_map_cmd *)desc.data; req->tqp_id = cpu_to_le16(tqp_pid); - req->tqp_vf = cpu_to_le16(func_id); + req->tqp_vf = func_id; req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B | 1 << HCLGE_TQP_MAP_EN_B; req->tqp_vid = cpu_to_le16(tqp_vid); @@ -2131,12 +2145,14 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) { struct hclge_config_auto_neg_cmd *req; struct hclge_desc desc; + u32 flag = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false); req = (struct hclge_config_auto_neg_cmd *)desc.data; - hnae_set_bit(req->cfg_an_cmd_flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + req->cfg_an_cmd_flag = cpu_to_le32(flag); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -2525,8 +2541,9 @@ static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) hclge_cmd_setup_basic_desc (&desc, HCLGE_OPC_RSS_INDIR_TABLE, false); - req->start_table_index = i * HCLGE_RSS_CFG_TBL_SIZE; - req->rss_set_bitmap = HCLGE_RSS_SET_BITMAP_MSK; + req->start_table_index = + cpu_to_le16(i * HCLGE_RSS_CFG_TBL_SIZE); + req->rss_set_bitmap = cpu_to_le16(HCLGE_RSS_SET_BITMAP_MSK); for (j = 0; j < HCLGE_RSS_CFG_TBL_SIZE; j++) req->rss_result[j] = @@ -2555,12 +2572,15 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, req = (struct hclge_rss_tc_mode_cmd *)desc.data; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - hnae_set_bit(req->rss_tc_mode[i], HCLGE_RSS_TC_VALID_B, - (tc_valid[i] & 0x1)); - hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_SIZE_M, + u16 mode = 0; + + hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1)); + hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M, HCLGE_RSS_TC_SIZE_S, tc_size[i]); - hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_OFFSET_M, + hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M, HCLGE_RSS_TC_OFFSET_S, tc_offset[i]); + + req->rss_tc_mode[i] = cpu_to_le16(mode); } ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -2763,15 +2783,16 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, i = 0; for (node = ring_chain; node; node = node->next) { - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, - HCLGE_INT_TYPE_S, + u16 type_and_id = 0; + + hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, - HCLGE_TQP_ID_S, node->tqp_index); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, + node->tqp_index); + hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M, HCLGE_INT_GL_IDX_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->tqp_type_and_id[i] = cpu_to_le16(type_and_id); req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { @@ -2851,16 +2872,17 @@ static int hclge_unmap_ring_from_vector( i = 0; for (node = ring_chain; node; node = node->next) { - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, - HCLGE_INT_TYPE_S, + u16 type_and_id = 0; + + hnae_set_field(type_and_id, HCLGE_INT_TYPE_M, HCLGE_INT_TYPE_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, - HCLGE_TQP_ID_S, node->tqp_index); - hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M, + hnae_set_field(type_and_id, HCLGE_TQP_ID_M, HCLGE_TQP_ID_S, + node->tqp_index); + hnae_set_field(type_and_id, HCLGE_INT_GL_IDX_M, HCLGE_INT_GL_IDX_S, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); - req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + req->tqp_type_and_id[i] = cpu_to_le16(type_and_id); req->vfid = vport->vport_id; if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { @@ -2948,27 +2970,25 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; + u32 loop_en = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_TX_EN_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_EN_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_TX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_RX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_TX_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_RX_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_APP_LP_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_LINE_LP_B, 0); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_FCS_TX_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_FCS_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_RX_FCS_STRIP_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); - hnae_set_bit(req->txrx_pad_fcs_loop_en, - HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0); + hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) @@ -3145,16 +3165,16 @@ static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr) word_num = vfid / 32; bit_num = vfid % 32; if (clr) - desc[1].data[word_num] &= ~(1 << bit_num); + desc[1].data[word_num] &= cpu_to_le32(~(1 << bit_num)); else - desc[1].data[word_num] |= (1 << bit_num); + desc[1].data[word_num] |= cpu_to_le32(1 << bit_num); } else { word_num = (vfid - 192) / 32; bit_num = vfid % 32; if (clr) - desc[2].data[word_num] &= ~(1 << bit_num); + desc[2].data[word_num] &= cpu_to_le32(~(1 << bit_num)); else - desc[2].data[word_num] |= (1 << bit_num); + desc[2].data[word_num] |= cpu_to_le32(1 << bit_num); } return 0; @@ -3257,15 +3277,16 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_cfg_func_mta_item_cmd *req; struct hclge_desc desc; + u16 item_idx = 0; int ret; req = (struct hclge_cfg_func_mta_item_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); - hnae_set_field(req->item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, + hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, HCLGE_CFG_MTA_ITEM_IDX_S, idx); - req->item_idx = cpu_to_le16(req->item_idx); + req->item_idx = cpu_to_le16(item_idx); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { @@ -3284,6 +3305,7 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_desc desc; u8 resp_code; + u16 retval; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_REMOVE, false); @@ -3297,9 +3319,10 @@ static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, ret); return ret; } - resp_code = (desc.data[0] >> 8) & 0xff; + resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc.retval); - return hclge_get_mac_vlan_cmd_status(vport, desc.retval, resp_code, + return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_REMOVE); } @@ -3310,6 +3333,7 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, { struct hclge_dev *hdev = vport->back; u8 resp_code; + u16 retval; int ret; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_MAC_VLAN_ADD, true); @@ -3338,9 +3362,10 @@ static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, ret); return ret; } - resp_code = (desc[0].data[0] >> 8) & 0xff; + resp_code = (le32_to_cpu(desc[0].data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc[0].retval); - return hclge_get_mac_vlan_cmd_status(vport, desc[0].retval, resp_code, + return hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_LKUP); } @@ -3351,6 +3376,7 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; int cfg_status; u8 resp_code; + u16 retval; int ret; if (!mc_desc) { @@ -3362,8 +3388,10 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - resp_code = (desc.data[0] >> 8) & 0xff; - cfg_status = hclge_get_mac_vlan_cmd_status(vport, desc.retval, + resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc.retval); + + cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_ADD); } else { @@ -3376,9 +3404,10 @@ static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, memcpy(mc_desc[0].data, req, sizeof(struct hclge_mac_vlan_tbl_entry_cmd)); ret = hclge_cmd_send(&hdev->hw, mc_desc, 3); - resp_code = (mc_desc[0].data[0] >> 8) & 0xff; - cfg_status = hclge_get_mac_vlan_cmd_status(vport, - mc_desc[0].retval, + resp_code = (le32_to_cpu(mc_desc[0].data[0]) >> 8) & 0xff; + retval = le16_to_cpu(mc_desc[0].retval); + + cfg_status = hclge_get_mac_vlan_cmd_status(vport, retval, resp_code, HCLGE_MAC_VLAN_ADD); } @@ -3407,6 +3436,7 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_mac_vlan_tbl_entry_cmd req; enum hclge_cmd_status status; + u16 egress_port = 0; /* mac addr check */ if (is_zero_ether_addr(addr) || @@ -3426,15 +3456,15 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0); hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae_set_bit(req.egress_port, - HCLGE_MAC_EPORT_SW_EN_B, 0); - hnae_set_bit(req.egress_port, - HCLGE_MAC_EPORT_TYPE_B, 0); - hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_VFID_M, + + hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0); + hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0); + hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, HCLGE_MAC_EPORT_VFID_S, vport->vport_id); - hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_PFID_M, + hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M, HCLGE_MAC_EPORT_PFID_S, 0); - req.egress_port = cpu_to_le16(req.egress_port); + + req.egress_port = cpu_to_le16(egress_port); hclge_prepare_mac_addr(&req, addr); @@ -3667,7 +3697,7 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, req0 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[0].data; req1 = (struct hclge_vlan_filter_vf_cfg_cmd *)desc[1].data; - req0->vlan_id = vlan; + req0->vlan_id = cpu_to_le16(vlan); req0->vlan_cfg = is_kill; if (vf_byte_off < HCLGE_MAX_VF_BYTES) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 359ee670d1e17..1ae6eae82eb3e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -283,6 +283,7 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, struct hclge_pg_shapping_cmd *shap_cfg_cmd; enum hclge_opcode_type opcode; struct hclge_desc desc; + u32 shapping_para = 0; opcode = bucket ? HCLGE_OPC_TM_PG_P_SHAPPING : HCLGE_OPC_TM_PG_C_SHAPPING; @@ -292,11 +293,13 @@ static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pg_id = pg_id; - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b); - hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shapping_para, IR_B, ir_b); + hclge_tm_set_field(shapping_para, IR_U, ir_u); + hclge_tm_set_field(shapping_para, IR_S, ir_s); + hclge_tm_set_field(shapping_para, BS_B, bs_b); + hclge_tm_set_field(shapping_para, BS_S, bs_s); + + shap_cfg_cmd->pg_shapping_para = cpu_to_le32(shapping_para); return hclge_cmd_send(&hdev->hw, &desc, 1); } @@ -337,6 +340,7 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, struct hclge_pri_shapping_cmd *shap_cfg_cmd; enum hclge_opcode_type opcode; struct hclge_desc desc; + u32 shapping_para = 0; opcode = bucket ? HCLGE_OPC_TM_PRI_P_SHAPPING : HCLGE_OPC_TM_PRI_C_SHAPPING; @@ -347,11 +351,13 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, shap_cfg_cmd->pri_id = pri_id; - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b); - hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s); + hclge_tm_set_field(shapping_para, IR_B, ir_b); + hclge_tm_set_field(shapping_para, IR_U, ir_u); + hclge_tm_set_field(shapping_para, IR_S, ir_s); + hclge_tm_set_field(shapping_para, BS_B, bs_b); + hclge_tm_set_field(shapping_para, BS_S, bs_s); + + shap_cfg_cmd->pri_shapping_para = cpu_to_le32(shapping_para); return hclge_cmd_send(&hdev->hw, &desc, 1); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index c2a0537c649f8..aa73855366b30 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -761,7 +761,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, if (type == DESC_TYPE_SKB) { skb = (struct sk_buff *)priv; - paylen = cpu_to_le16(skb->len); + paylen = skb->len; if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_mac_len(skb); @@ -795,7 +795,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, cpu_to_le32(ol_type_vlan_len_msec); desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); - desc->tx.paylen = cpu_to_le16(paylen); + desc->tx.paylen = cpu_to_le32(paylen); desc->tx.mss = cpu_to_le16(mss); } -- GitLab From 1db9b1bf82b98cb265ed227dec3732aafae0eb0c Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 9 Oct 2017 15:44:01 +0800 Subject: [PATCH 1140/1507] net: hns3: Cleanup for non-static function in hns3 driver This patch fixes the following warning from sparse: warning: symbol 'hns3_set_multicast_list' was not declared. Should it be static. hns3_set_multicast_list turns out to be not used, so delete it. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hclge_cmd.c | 4 ++-- .../hisilicon/hns3/hns3pf/hclge_main.c | 14 ++++++------- .../hisilicon/hns3/hns3pf/hns3_enet.c | 20 ++++--------------- .../hisilicon/hns3/hns3pf/hns3_ethtool.c | 4 ++-- 4 files changed, 15 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 05985d81dda05..8ecd807447674 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -276,8 +276,8 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) return retval; } -enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw, - u32 *version) +static enum hclge_cmd_status hclge_cmd_query_firmware_version( + struct hclge_hw *hw, u32 *version) { struct hclge_query_version_cmd *resp; struct hclge_desc desc; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6115c2f730ce4..c91c779aeeed1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1550,8 +1550,8 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev, * @buf_alloc: pointer to buffer calculation data * @return: 0: calculate sucessful, negative: fail */ -int hclge_rx_buffer_calc(struct hclge_dev *hdev, - struct hclge_pkt_buf_alloc *buf_alloc) +static int hclge_rx_buffer_calc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) { u32 rx_all = hdev->pkt_buf_size; int no_pfc_priv_num, pfc_priv_num; @@ -2828,9 +2828,9 @@ int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, return 0; } -int hclge_map_handle_ring_to_vector(struct hnae3_handle *handle, - int vector, - struct hnae3_ring_chain_node *ring_chain) +static int hclge_map_handle_ring_to_vector( + struct hnae3_handle *handle, int vector, + struct hnae3_ring_chain_node *ring_chain) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -3206,8 +3206,8 @@ static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); } -u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, - const u8 *addr) +static u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, + const u8 *addr) { u16 high_val = addr[1] | (addr[0] << 8); struct hclge_dev *hdev = vport->back; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index aa73855366b30..26bbc91add651 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -24,7 +24,7 @@ #include "hnae3.h" #include "hns3_enet.h" -const char hns3_driver_name[] = "hns3"; +static const char hns3_driver_name[] = "hns3"; const char hns3_driver_version[] = VERMAGIC_STRING; static const char hns3_driver_string[] = "Hisilicon Ethernet Network Driver for Hip08 Family"; @@ -304,18 +304,6 @@ static int hns3_nic_net_stop(struct net_device *netdev) return 0; } -void hns3_set_multicast_list(struct net_device *netdev) -{ - struct hnae3_handle *h = hns3_get_handle(netdev); - struct netdev_hw_addr *ha = NULL; - - if (h->ae_algo->ops->set_mc_addr) { - netdev_for_each_mc_addr(ha, netdev) - if (h->ae_algo->ops->set_mc_addr(h, ha->addr)) - netdev_err(netdev, "set multicast fail\n"); - } -} - static int hns3_nic_uc_sync(struct net_device *netdev, const unsigned char *addr) { @@ -360,7 +348,7 @@ static int hns3_nic_mc_unsync(struct net_device *netdev, return 0; } -void hns3_nic_set_rx_mode(struct net_device *netdev) +static void hns3_nic_set_rx_mode(struct net_device *netdev) { struct hnae3_handle *h = hns3_get_handle(netdev); @@ -2596,7 +2584,7 @@ static void hns3_fini_ring(struct hns3_enet_ring *ring) ring->next_to_use = 0; } -int hns3_buf_size2type(u32 buf_size) +static int hns3_buf_size2type(u32 buf_size) { int bd_size_type; @@ -2908,7 +2896,7 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc) return ret; } -const struct hnae3_client_ops client_ops = { +static const struct hnae3_client_ops client_ops = { .init_instance = hns3_client_init, .uninit_instance = hns3_client_uninit, .link_status_change = hns3_link_status_change, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index a892a157f3462..060bacebf86a9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -215,8 +215,8 @@ static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data) * @stats: statistics info. * @data: statistics data. */ -void hns3_get_stats(struct net_device *netdev, struct ethtool_stats *stats, - u64 *data) +static void hns3_get_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) { struct hnae3_handle *h = hns3_get_handle(netdev); u64 *p = data; -- GitLab From 3a4b0129bf33caca5743891906393f17a2224d44 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:03 -0700 Subject: [PATCH 1141/1507] nfp: output control messages to trace_devlink_hwmsg() Use standard devlink trace point to allow tracing of control messages. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_app.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index af640b5c2108f..857bb33020ba9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -36,6 +36,8 @@ #include +#include + #include "nfp_net_repr.h" struct bpf_prog; @@ -271,11 +273,17 @@ static inline int nfp_app_xdp_offload(struct nfp_app *app, struct nfp_net *nn, static inline bool nfp_app_ctrl_tx(struct nfp_app *app, struct sk_buff *skb) { + trace_devlink_hwmsg(priv_to_devlink(app->pf), false, 0, + skb->data, skb->len); + return nfp_ctrl_tx(app->ctrl, skb); } static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb) { + trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, + skb->data, skb->len); + app->type->ctrl_msg_rx(app, skb); } -- GitLab From a52b35c39ec6f33592df634ef2d1afae23401fdd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:04 -0700 Subject: [PATCH 1142/1507] nfp: bpf: lift the single-port limitation Limiting the eBPF offload to a single port was a workaround required for the PoC application FW which has not been released externally. It's not necessary any more. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index be2cf10a2cd7a..074726980994d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -89,14 +89,6 @@ nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) struct nfp_net_bpf_priv *priv; int ret; - /* Limit to single port, otherwise it's just a NIC */ - if (id > 0) { - nfp_warn(app->cpp, - "BPF NIC doesn't support more than one port right now\n"); - nn->port = nfp_port_alloc(app, NFP_PORT_INVALID, nn->dp.netdev); - return PTR_ERR_OR_ZERO(nn->port); - } - priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; -- GitLab From b3f868df3c8904e964d7b257b47d7d90d93375e0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:05 -0700 Subject: [PATCH 1143/1507] nfp: bpf: use the power of sparse to check we encode registers right Define a new __bitwise type for software representation of registers. This will allow us to catch incorrect parameter types using sparse. Accessors we define also allow us to return correct enum type and therefore ensure all switches handle all register types. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 99 ++++++++++--------- drivers/net/ethernet/netronome/nfp/bpf/main.h | 24 +---- drivers/net/ethernet/netronome/nfp/nfp_asm.h | 45 +++++++++ 3 files changed, 99 insertions(+), 69 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 239dfbe8a0a13..7e8cdfb39607e 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -128,11 +128,11 @@ struct nfp_insn_re_regs { bool i8; }; -static u16 nfp_swreg_to_unreg(u32 swreg, bool is_dst) +static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) { - u16 val = FIELD_GET(NN_REG_VAL, swreg); + u16 val = swreg_value(reg); - switch (FIELD_GET(NN_REG_TYPE, swreg)) { + switch (swreg_type(reg)) { case NN_REG_GPR_A: case NN_REG_GPR_B: case NN_REG_GPR_BOTH: @@ -149,33 +149,34 @@ static u16 nfp_swreg_to_unreg(u32 swreg, bool is_dst) return UR_REG_IMM_encode(val); case NN_REG_NONE: return is_dst ? UR_REG_NO_DST : REG_NONE; - default: - pr_err("unrecognized reg encoding %08x\n", swreg); - return 0; } + + pr_err("unrecognized reg encoding %08x\n", reg); + return 0; } static int -swreg_to_unrestricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_ur_regs *reg) +swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_ur_regs *reg) { memset(reg, 0, sizeof(*reg)); /* Decode destination */ - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) + if (swreg_type(dst) == NN_REG_IMM) return -EFAULT; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B) + if (swreg_type(dst) == NN_REG_GPR_B) reg->dst_ab = ALU_DST_B; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH) + if (swreg_type(dst) == NN_REG_GPR_BOTH) reg->wr_both = true; reg->dst = nfp_swreg_to_unreg(dst, true); /* Decode source operands */ - if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg)) + if (swreg_type(lreg) == swreg_type(rreg)) return -EFAULT; - if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B || - FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) { + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { reg->areg = nfp_swreg_to_unreg(rreg, false); reg->breg = nfp_swreg_to_unreg(lreg, false); reg->swap = true; @@ -187,11 +188,11 @@ swreg_to_unrestricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_ur_regs *reg) return 0; } -static u16 nfp_swreg_to_rereg(u32 swreg, bool is_dst, bool has_imm8, bool *i8) +static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) { - u16 val = FIELD_GET(NN_REG_VAL, swreg); + u16 val = swreg_value(reg); - switch (FIELD_GET(NN_REG_TYPE, swreg)) { + switch (swreg_type(reg)) { case NN_REG_GPR_A: case NN_REG_GPR_B: case NN_REG_GPR_BOTH: @@ -207,34 +208,37 @@ static u16 nfp_swreg_to_rereg(u32 swreg, bool is_dst, bool has_imm8, bool *i8) return RE_REG_IMM_encode(val & 0x7f); case NN_REG_NONE: return is_dst ? RE_REG_NO_DST : REG_NONE; - default: - pr_err("unrecognized reg encoding\n"); + case NN_REG_NNR: + pr_err("NNRs used with restricted encoding\n"); return 0; } + + pr_err("unrecognized reg encoding\n"); + return 0; } static int -swreg_to_restricted(u32 dst, u32 lreg, u32 rreg, struct nfp_insn_re_regs *reg, - bool has_imm8) +swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_re_regs *reg, bool has_imm8) { memset(reg, 0, sizeof(*reg)); /* Decode destination */ - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) + if (swreg_type(dst) == NN_REG_IMM) return -EFAULT; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_B) + if (swreg_type(dst) == NN_REG_GPR_B) reg->dst_ab = ALU_DST_B; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_GPR_BOTH) + if (swreg_type(dst) == NN_REG_GPR_BOTH) reg->wr_both = true; reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL); /* Decode source operands */ - if (FIELD_GET(NN_REG_TYPE, lreg) == FIELD_GET(NN_REG_TYPE, rreg)) + if (swreg_type(lreg) == swreg_type(rreg)) return -EFAULT; - if (FIELD_GET(NN_REG_TYPE, lreg) == NN_REG_GPR_B || - FIELD_GET(NN_REG_TYPE, rreg) == NN_REG_GPR_A) { + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); reg->swap = true; @@ -281,7 +285,7 @@ __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, static void emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, - u8 mode, u8 xfer, u32 lreg, u32 rreg, u8 size, bool sync) + u8 mode, u8 xfer, swreg lreg, swreg rreg, u8 size, bool sync) { struct nfp_insn_re_regs reg; int err; @@ -364,7 +368,7 @@ __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8, static void emit_br_byte_neq(struct nfp_prog *nfp_prog, - u32 dst, u8 imm, u8 byte, u16 addr, u8 defer) + swreg dst, u8 imm, u8 byte, u16 addr, u8 defer) { struct nfp_insn_re_regs reg; int err; @@ -399,13 +403,13 @@ __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi, } static void -emit_immed(struct nfp_prog *nfp_prog, u32 dst, u16 imm, +emit_immed(struct nfp_prog *nfp_prog, swreg dst, u16 imm, enum immed_width width, bool invert, enum immed_shift shift) { struct nfp_insn_ur_regs reg; int err; - if (FIELD_GET(NN_REG_TYPE, dst) == NN_REG_IMM) { + if (swreg_type(dst) == NN_REG_IMM) { nfp_prog->error = -EFAULT; return; } @@ -451,8 +455,8 @@ __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, } static void -emit_shf(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum shf_op op, u32 rreg, - enum shf_sc sc, u8 shift) +emit_shf(struct nfp_prog *nfp_prog, swreg dst, + swreg lreg, enum shf_op op, swreg rreg, enum shf_sc sc, u8 shift) { struct nfp_insn_re_regs reg; int err; @@ -486,7 +490,8 @@ __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, } static void -emit_alu(struct nfp_prog *nfp_prog, u32 dst, u32 lreg, enum alu_op op, u32 rreg) +emit_alu(struct nfp_prog *nfp_prog, swreg dst, + swreg lreg, enum alu_op op, swreg rreg) { struct nfp_insn_ur_regs reg; int err; @@ -524,7 +529,7 @@ __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, static void emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, - u32 dst, u8 bmask, u32 src, bool zero) + swreg dst, u8 bmask, swreg src, bool zero) { struct nfp_insn_re_regs reg; int err; @@ -540,7 +545,7 @@ emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, } static void -emit_ld_field(struct nfp_prog *nfp_prog, u32 dst, u8 bmask, u32 src, +emit_ld_field(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, enum shf_sc sc, u8 shift) { emit_ld_field_any(nfp_prog, sc, shift, dst, bmask, src, false); @@ -565,7 +570,7 @@ static bool pack_immed(u32 imm, u16 *val, enum immed_shift *shift) return true; } -static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm) +static void wrp_immed(struct nfp_prog *nfp_prog, swreg dst, u32 imm) { enum immed_shift shift; u16 val; @@ -586,7 +591,7 @@ static void wrp_immed(struct nfp_prog *nfp_prog, u32 dst, u32 imm) * If the @imm is small enough encode it directly in operand and return * otherwise load @imm to a spare register and return its encoding. */ -static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) +static swreg ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg) { if (FIELD_FIT(UR_REG_IMM_MAX, imm)) return reg_imm(imm); @@ -599,7 +604,7 @@ static u32 ur_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) * If the @imm is small enough encode it directly in operand and return * otherwise load @imm to a spare register and return its encoding. */ -static u32 re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, u32 tmp_reg) +static swreg re_load_imm_any(struct nfp_prog *nfp_prog, u32 imm, swreg tmp_reg) { if (FIELD_FIT(RE_REG_IMM_MAX, imm)) return reg_imm(imm); @@ -629,7 +634,7 @@ construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, { unsigned int i; u16 shift, sz; - u32 tmp_reg; + swreg tmp_reg; /* We load the value from the address indicated in @offset and then * shift out the data we don't need. Note: this is big endian! @@ -697,7 +702,7 @@ static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src) static void wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm) { - u32 tmp_reg; + swreg tmp_reg; if (alu_op == ALU_OP_AND) { if (!imm) @@ -815,7 +820,7 @@ wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ u8 reg = insn->dst_reg * 2; - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1139,7 +1144,7 @@ static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - u32 dst = reg_both(meta->insn.dst_reg * 2); + swreg dst = reg_both(meta->insn.dst_reg * 2); if (meta->insn.off != offsetof(struct xdp_md, data) && meta->insn.off != offsetof(struct xdp_md, data_end)) @@ -1202,8 +1207,10 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 or1 = reg_a(insn->dst_reg * 2), or2 = reg_b(insn->dst_reg * 2 + 1); - u32 tmp_reg; + swreg or1, or2, tmp_reg; + + or1 = reg_a(insn->dst_reg * 2); + or2 = reg_b(insn->dst_reg * 2 + 1); if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1252,7 +1259,7 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1283,7 +1290,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ - u32 tmp_reg; + swreg tmp_reg; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 4051e943f3633..ccc3dbea25f62 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -39,6 +39,7 @@ #include #include +#include "../nfp_asm.h" #include "../nfp_net.h" /* For branch fixup logic use up-most byte of branch instruction as scratch @@ -65,29 +66,6 @@ enum nfp_bpf_action_type { NN_ACT_XDP, }; -/* Software register representation, hardware encoding in asm.h */ -#define NN_REG_TYPE GENMASK(31, 24) -#define NN_REG_VAL GENMASK(7, 0) - -enum nfp_bpf_reg_type { - NN_REG_GPR_A = BIT(0), - NN_REG_GPR_B = BIT(1), - NN_REG_NNR = BIT(2), - NN_REG_XFER = BIT(3), - NN_REG_IMM = BIT(4), - NN_REG_NONE = BIT(5), -}; - -#define NN_REG_GPR_BOTH (NN_REG_GPR_A | NN_REG_GPR_B) - -#define reg_both(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_BOTH)) -#define reg_a(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_A)) -#define reg_b(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_GPR_B)) -#define reg_nnr(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_NNR)) -#define reg_xfer(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_XFER)) -#define reg_imm(x) ((x) | FIELD_PREP(NN_REG_TYPE, NN_REG_IMM)) -#define reg_none() (FIELD_PREP(NN_REG_TYPE, NN_REG_NONE)) - #define pkt_reg(np) reg_a((np)->regs_per_thread - STATIC_REG_PKT) #define imm_a(np) reg_a((np)->regs_per_thread - STATIC_REG_IMM) #define imm_b(np) reg_b((np)->regs_per_thread - STATIC_REG_IMM) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index d2b535739d2b6..9b9d5d18ee20b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -34,6 +34,7 @@ #ifndef __NFP_ASM_H__ #define __NFP_ASM_H__ 1 +#include #include #define REG_NONE 0 @@ -230,4 +231,48 @@ enum lcsr_wr_src { #define OP_CARB_BASE 0x0e000000000ULL #define OP_CARB_OR 0x00000010000ULL +/* Software register representation, independent of operand type */ +#define NN_REG_TYPE GENMASK(31, 24) +#define NN_REG_VAL GENMASK(7, 0) + +enum nfp_bpf_reg_type { + NN_REG_GPR_A = BIT(0), + NN_REG_GPR_B = BIT(1), + NN_REG_GPR_BOTH = NN_REG_GPR_A | NN_REG_GPR_B, + NN_REG_NNR = BIT(2), + NN_REG_XFER = BIT(3), + NN_REG_IMM = BIT(4), + NN_REG_NONE = BIT(5), +}; + +#define reg_both(x) __enc_swreg((x), NN_REG_GPR_BOTH) +#define reg_a(x) __enc_swreg((x), NN_REG_GPR_A) +#define reg_b(x) __enc_swreg((x), NN_REG_GPR_B) +#define reg_nnr(x) __enc_swreg((x), NN_REG_NNR) +#define reg_xfer(x) __enc_swreg((x), NN_REG_XFER) +#define reg_imm(x) __enc_swreg((x), NN_REG_IMM) +#define reg_none() __enc_swreg(0, NN_REG_NONE) + +typedef __u32 __bitwise swreg; + +static inline swreg __enc_swreg(u16 id, u8 type) +{ + return (__force swreg)(id | FIELD_PREP(NN_REG_TYPE, type)); +} + +static inline u32 swreg_raw(swreg reg) +{ + return (__force u32)reg; +} + +static inline enum nfp_bpf_reg_type swreg_type(swreg reg) +{ + return FIELD_GET(NN_REG_TYPE, swreg_raw(reg)); +} + +static inline u16 swreg_value(swreg reg) +{ + return FIELD_GET(NN_REG_VAL, swreg_raw(reg)); +} + #endif -- GitLab From 2a15bb1aba2bfca0a69cdbb113def57afd5666ab Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:06 -0700 Subject: [PATCH 1144/1507] nfp: bpf: move software reg helpers and cmd table out of translator Move the software reg helpers and some static data to nfp_asm.c. They are related to the previous patch, but move is done in a separate commit for ease of review. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/Makefile | 1 + drivers/net/ethernet/netronome/nfp/bpf/jit.c | 147 ---------------- drivers/net/ethernet/netronome/nfp/nfp_asm.c | 167 +++++++++++++++++++ drivers/net/ethernet/netronome/nfp/nfp_asm.h | 24 +++ 4 files changed, 192 insertions(+), 147 deletions(-) create mode 100644 drivers/net/ethernet/netronome/nfp/nfp_asm.c diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index becaacf1554d8..bd3b2bd408bcf 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -14,6 +14,7 @@ nfp-objs := \ nfpcore/nfp_resource.o \ nfpcore/nfp_rtsym.o \ nfpcore/nfp_target.o \ + nfp_asm.o \ nfp_app.o \ nfp_app_nic.o \ nfp_devlink.o \ diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 7e8cdfb39607e..7bcff007075cf 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -110,154 +110,7 @@ nfp_prog_offset_to_index(struct nfp_prog *nfp_prog, unsigned int offset) return offset - nfp_prog->start_off; } -/* --- SW reg --- */ -struct nfp_insn_ur_regs { - enum alu_dst_ab dst_ab; - u16 dst; - u16 areg, breg; - bool swap; - bool wr_both; -}; - -struct nfp_insn_re_regs { - enum alu_dst_ab dst_ab; - u8 dst; - u8 areg, breg; - bool swap; - bool wr_both; - bool i8; -}; - -static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) -{ - u16 val = swreg_value(reg); - - switch (swreg_type(reg)) { - case NN_REG_GPR_A: - case NN_REG_GPR_B: - case NN_REG_GPR_BOTH: - return val; - case NN_REG_NNR: - return UR_REG_NN | val; - case NN_REG_XFER: - return UR_REG_XFR | val; - case NN_REG_IMM: - if (val & ~0xff) { - pr_err("immediate too large\n"); - return 0; - } - return UR_REG_IMM_encode(val); - case NN_REG_NONE: - return is_dst ? UR_REG_NO_DST : REG_NONE; - } - - pr_err("unrecognized reg encoding %08x\n", reg); - return 0; -} - -static int -swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, - struct nfp_insn_ur_regs *reg) -{ - memset(reg, 0, sizeof(*reg)); - - /* Decode destination */ - if (swreg_type(dst) == NN_REG_IMM) - return -EFAULT; - - if (swreg_type(dst) == NN_REG_GPR_B) - reg->dst_ab = ALU_DST_B; - if (swreg_type(dst) == NN_REG_GPR_BOTH) - reg->wr_both = true; - reg->dst = nfp_swreg_to_unreg(dst, true); - - /* Decode source operands */ - if (swreg_type(lreg) == swreg_type(rreg)) - return -EFAULT; - - if (swreg_type(lreg) == NN_REG_GPR_B || - swreg_type(rreg) == NN_REG_GPR_A) { - reg->areg = nfp_swreg_to_unreg(rreg, false); - reg->breg = nfp_swreg_to_unreg(lreg, false); - reg->swap = true; - } else { - reg->areg = nfp_swreg_to_unreg(lreg, false); - reg->breg = nfp_swreg_to_unreg(rreg, false); - } - - return 0; -} - -static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) -{ - u16 val = swreg_value(reg); - - switch (swreg_type(reg)) { - case NN_REG_GPR_A: - case NN_REG_GPR_B: - case NN_REG_GPR_BOTH: - return val; - case NN_REG_XFER: - return RE_REG_XFR | val; - case NN_REG_IMM: - if (val & ~(0x7f | has_imm8 << 7)) { - pr_err("immediate too large\n"); - return 0; - } - *i8 = val & 0x80; - return RE_REG_IMM_encode(val & 0x7f); - case NN_REG_NONE: - return is_dst ? RE_REG_NO_DST : REG_NONE; - case NN_REG_NNR: - pr_err("NNRs used with restricted encoding\n"); - return 0; - } - - pr_err("unrecognized reg encoding\n"); - return 0; -} - -static int -swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, - struct nfp_insn_re_regs *reg, bool has_imm8) -{ - memset(reg, 0, sizeof(*reg)); - - /* Decode destination */ - if (swreg_type(dst) == NN_REG_IMM) - return -EFAULT; - - if (swreg_type(dst) == NN_REG_GPR_B) - reg->dst_ab = ALU_DST_B; - if (swreg_type(dst) == NN_REG_GPR_BOTH) - reg->wr_both = true; - reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL); - - /* Decode source operands */ - if (swreg_type(lreg) == swreg_type(rreg)) - return -EFAULT; - - if (swreg_type(lreg) == NN_REG_GPR_B || - swreg_type(rreg) == NN_REG_GPR_A) { - reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); - reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); - reg->swap = true; - } else { - reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); - reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); - } - - return 0; -} - /* --- Emitters --- */ -static const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { - [CMD_TGT_WRITE8] = { 0x00, 0x42 }, - [CMD_TGT_READ8] = { 0x01, 0x43 }, - [CMD_TGT_READ_LE] = { 0x01, 0x40 }, - [CMD_TGT_READ_SWAP_LE] = { 0x03, 0x40 }, -}; - static void __emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, u8 mode, u8 xfer, u8 areg, u8 breg, u8 size, bool sync) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c new file mode 100644 index 0000000000000..4c9201bf93314 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -0,0 +1,167 @@ +/* + * Copyright (C) 2016-2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include +#include +#include +#include + +#include "nfp_asm.h" + +const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { + [CMD_TGT_WRITE8] = { 0x00, 0x42 }, + [CMD_TGT_READ8] = { 0x01, 0x43 }, + [CMD_TGT_READ_LE] = { 0x01, 0x40 }, + [CMD_TGT_READ_SWAP_LE] = { 0x03, 0x40 }, +}; + +static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) +{ + u16 val = swreg_value(reg); + + switch (swreg_type(reg)) { + case NN_REG_GPR_A: + case NN_REG_GPR_B: + case NN_REG_GPR_BOTH: + return val; + case NN_REG_NNR: + return UR_REG_NN | val; + case NN_REG_XFER: + return UR_REG_XFR | val; + case NN_REG_IMM: + if (val & ~0xff) { + pr_err("immediate too large\n"); + return 0; + } + return UR_REG_IMM_encode(val); + case NN_REG_NONE: + return is_dst ? UR_REG_NO_DST : REG_NONE; + } + + pr_err("unrecognized reg encoding %08x\n", reg); + return 0; +} + +int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_ur_regs *reg) +{ + memset(reg, 0, sizeof(*reg)); + + /* Decode destination */ + if (swreg_type(dst) == NN_REG_IMM) + return -EFAULT; + + if (swreg_type(dst) == NN_REG_GPR_B) + reg->dst_ab = ALU_DST_B; + if (swreg_type(dst) == NN_REG_GPR_BOTH) + reg->wr_both = true; + reg->dst = nfp_swreg_to_unreg(dst, true); + + /* Decode source operands */ + if (swreg_type(lreg) == swreg_type(rreg)) + return -EFAULT; + + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { + reg->areg = nfp_swreg_to_unreg(rreg, false); + reg->breg = nfp_swreg_to_unreg(lreg, false); + reg->swap = true; + } else { + reg->areg = nfp_swreg_to_unreg(lreg, false); + reg->breg = nfp_swreg_to_unreg(rreg, false); + } + + return 0; +} + +static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) +{ + u16 val = swreg_value(reg); + + switch (swreg_type(reg)) { + case NN_REG_GPR_A: + case NN_REG_GPR_B: + case NN_REG_GPR_BOTH: + return val; + case NN_REG_XFER: + return RE_REG_XFR | val; + case NN_REG_IMM: + if (val & ~(0x7f | has_imm8 << 7)) { + pr_err("immediate too large\n"); + return 0; + } + *i8 = val & 0x80; + return RE_REG_IMM_encode(val & 0x7f); + case NN_REG_NONE: + return is_dst ? RE_REG_NO_DST : REG_NONE; + case NN_REG_NNR: + pr_err("NNRs used with restricted encoding\n"); + return 0; + } + + pr_err("unrecognized reg encoding\n"); + return 0; +} + +int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_re_regs *reg, bool has_imm8) +{ + memset(reg, 0, sizeof(*reg)); + + /* Decode destination */ + if (swreg_type(dst) == NN_REG_IMM) + return -EFAULT; + + if (swreg_type(dst) == NN_REG_GPR_B) + reg->dst_ab = ALU_DST_B; + if (swreg_type(dst) == NN_REG_GPR_BOTH) + reg->wr_both = true; + reg->dst = nfp_swreg_to_rereg(dst, true, false, NULL); + + /* Decode source operands */ + if (swreg_type(lreg) == swreg_type(rreg)) + return -EFAULT; + + if (swreg_type(lreg) == NN_REG_GPR_B || + swreg_type(rreg) == NN_REG_GPR_A) { + reg->areg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); + reg->breg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); + reg->swap = true; + } else { + reg->areg = nfp_swreg_to_rereg(lreg, false, has_imm8, ®->i8); + reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); + } + + return 0; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index 9b9d5d18ee20b..8e87c0676c304 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -205,6 +205,8 @@ enum cmd_tgt_map { __CMD_TGT_MAP_SIZE, }; +extern const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE]; + enum cmd_mode { CMD_MODE_40b_AB = 0, CMD_MODE_40b_BA = 1, @@ -275,4 +277,26 @@ static inline u16 swreg_value(swreg reg) return FIELD_GET(NN_REG_VAL, swreg_raw(reg)); } +struct nfp_insn_ur_regs { + enum alu_dst_ab dst_ab; + u16 dst; + u16 areg, breg; + bool swap; + bool wr_both; +}; + +struct nfp_insn_re_regs { + enum alu_dst_ab dst_ab; + u8 dst; + u8 areg, breg; + bool swap; + bool wr_both; + bool i8; +}; + +int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_ur_regs *reg); +int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, + struct nfp_insn_re_regs *reg, bool has_imm8); + #endif -- GitLab From 3cae13193381fd4cb87791174d4c9fdf5b7025ff Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:07 -0700 Subject: [PATCH 1145/1507] nfp: bpf: encode all 64bit shifts Add encodings of all 64bit shift operations. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 48 +++++++++++++++----- 1 file changed, 36 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 7bcff007075cf..095cf50e84500 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -825,12 +825,24 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; - - if (insn->imm != 32) - return 1; /* TODO */ - - wrp_reg_mov(nfp_prog, insn->dst_reg * 2 + 1, insn->dst_reg * 2); - wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2), 0); + u8 dst = insn->dst_reg * 2; + + if (insn->imm < 32) { + emit_shf(nfp_prog, reg_both(dst + 1), + reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), + SHF_SC_R_DSHF, 32 - insn->imm); + emit_shf(nfp_prog, reg_both(dst), + reg_none(), SHF_OP_NONE, reg_b(dst), + SHF_SC_L_SHF, insn->imm); + } else if (insn->imm == 32) { + wrp_reg_mov(nfp_prog, dst + 1, dst); + wrp_immed(nfp_prog, reg_both(dst), 0); + } else if (insn->imm > 32) { + emit_shf(nfp_prog, reg_both(dst + 1), + reg_none(), SHF_OP_NONE, reg_b(dst), + SHF_SC_L_SHF, insn->imm - 32); + wrp_immed(nfp_prog, reg_both(dst), 0); + } return 0; } @@ -838,12 +850,24 @@ static int shl_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int shr_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; - - if (insn->imm != 32) - return 1; /* TODO */ - - wrp_reg_mov(nfp_prog, insn->dst_reg * 2, insn->dst_reg * 2 + 1); - wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0); + u8 dst = insn->dst_reg * 2; + + if (insn->imm < 32) { + emit_shf(nfp_prog, reg_both(dst), + reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), + SHF_SC_R_DSHF, insn->imm); + emit_shf(nfp_prog, reg_both(dst + 1), + reg_none(), SHF_OP_NONE, reg_b(dst + 1), + SHF_SC_R_SHF, insn->imm); + } else if (insn->imm == 32) { + wrp_reg_mov(nfp_prog, dst, dst + 1); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + } else if (insn->imm > 32) { + emit_shf(nfp_prog, reg_both(dst), + reg_none(), SHF_OP_NONE, reg_b(dst + 1), + SHF_SC_R_SHF, insn->imm - 32); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + } return 0; } -- GitLab From 226e0e94ce3575bd9ca85f90957516ac1dff5bf3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:08 -0700 Subject: [PATCH 1146/1507] nfp: bpf: remove register rename Remove the register renumbering optimization. To implement calling map and other helpers we need more strict register layout. We can't freely reassign register numbers. This will have the effect of running in 4 context/thread mode, which should be OK since we are moving towards integrating the BPF closer with FW app datapath anyway, and the target datapath itself runs in 4 context mode. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 46 ++------------------ 1 file changed, 3 insertions(+), 43 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 095cf50e84500..469dc8a055f2e 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1621,38 +1621,6 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog) } } -/* Try to rename registers so that program uses only low ones */ -static int nfp_bpf_opt_reg_rename(struct nfp_prog *nfp_prog) -{ - bool reg_used[MAX_BPF_REG] = {}; - u8 tgt_reg[MAX_BPF_REG] = {}; - struct nfp_insn_meta *meta; - unsigned int i, j; - - list_for_each_entry(meta, &nfp_prog->insns, l) { - if (meta->skip) - continue; - - reg_used[meta->insn.src_reg] = true; - reg_used[meta->insn.dst_reg] = true; - } - - for (i = 0, j = 0; i < ARRAY_SIZE(tgt_reg); i++) { - if (!reg_used[i]) - continue; - - tgt_reg[i] = j++; - } - nfp_prog->num_regs = j; - - list_for_each_entry(meta, &nfp_prog->insns, l) { - meta->insn.src_reg = tgt_reg[meta->insn.src_reg]; - meta->insn.dst_reg = tgt_reg[meta->insn.dst_reg]; - } - - return 0; -} - /* Remove masking after load since our load guarantees this is not needed */ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog) { @@ -1729,14 +1697,8 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog) static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) { - int ret; - nfp_bpf_opt_reg_init(nfp_prog); - ret = nfp_bpf_opt_reg_rename(nfp_prog); - if (ret) - return ret; - nfp_bpf_opt_ld_mask(nfp_prog); nfp_bpf_opt_ld_shift(nfp_prog); @@ -1783,10 +1745,8 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, if (ret) goto out; - if (nfp_prog->num_regs <= 7) - nfp_prog->regs_per_thread = 16; - else - nfp_prog->regs_per_thread = 32; + nfp_prog->num_regs = MAX_BPF_REG; + nfp_prog->regs_per_thread = 32; nfp_prog->prog = prog_mem; nfp_prog->__prog_alloc_len = prog_sz; @@ -1799,7 +1759,7 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, } res->n_instr = nfp_prog->prog_len; - res->dense_mode = nfp_prog->num_regs <= 7; + res->dense_mode = false; out: nfp_prog_free(nfp_prog); -- GitLab From 509144e25049831ffe94160b1f03cf1b900aaa3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:09 -0700 Subject: [PATCH 1147/1507] nfp: bpf: remove packet marking support Temporarily drop support for skb->mark. We are primarily focusing on XDP offload, and implementing skb->mark on the new datapath has lower priority. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 13 ------------- drivers/net/ethernet/netronome/nfp/bpf/main.h | 3 +-- 2 files changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 469dc8a055f2e..4fa220f710d2a 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -542,16 +542,6 @@ static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size) return construct_data_ind_ld(nfp_prog, offset, 0, false, size); } -static int wrp_set_mark(struct nfp_prog *nfp_prog, u8 src) -{ - emit_alu(nfp_prog, NFP_BPF_ABI_MARK, - reg_none(), ALU_OP_NONE, reg_b(src)); - emit_alu(nfp_prog, NFP_BPF_ABI_FLAGS, - NFP_BPF_ABI_FLAGS, ALU_OP_OR, reg_imm(NFP_BPF_ABI_FLAG_MARK)); - - return 0; -} - static void wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm) { @@ -1053,9 +1043,6 @@ static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - if (meta->insn.off == offsetof(struct sk_buff, mark)) - return wrp_set_mark(nfp_prog, meta->insn.src_reg * 2); - return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index ccc3dbea25f62..7d959757a51a9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -71,9 +71,8 @@ enum nfp_bpf_action_type { #define imm_b(np) reg_b((np)->regs_per_thread - STATIC_REG_IMM) #define imm_both(np) reg_both((np)->regs_per_thread - STATIC_REG_IMM) -#define NFP_BPF_ABI_FLAGS reg_nnr(0) +#define NFP_BPF_ABI_FLAGS reg_imm(0) #define NFP_BPF_ABI_FLAG_MARK 1 -#define NFP_BPF_ABI_MARK reg_nnr(1) #define NFP_BPF_ABI_PKT reg_nnr(2) #define NFP_BPF_ABI_LEN reg_nnr(3) -- GitLab From 8afd9c961e95b1529cbc2b2b9c063a488659b337 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:10 -0700 Subject: [PATCH 1148/1507] nfp: add more white space to the instruction defines We need to add longer OP_* defines, move the values away. Purely whitespace commit. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_asm.h | 156 +++++++++---------- 1 file changed, 78 insertions(+), 78 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index 8e87c0676c304..63cfd07da34ef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -53,14 +53,14 @@ #define UR_REG_IMM_encode(x) (UR_REG_IMM | (x)) #define UR_REG_IMM_MAX 0x0ffULL -#define OP_BR_BASE 0x0d800000020ULL -#define OP_BR_BASE_MASK 0x0f8000c3ce0ULL -#define OP_BR_MASK 0x0000000001fULL -#define OP_BR_EV_PIP 0x00000000300ULL -#define OP_BR_CSS 0x0000003c000ULL -#define OP_BR_DEFBR 0x00000300000ULL -#define OP_BR_ADDR_LO 0x007ffc00000ULL -#define OP_BR_ADDR_HI 0x10000000000ULL +#define OP_BR_BASE 0x0d800000020ULL +#define OP_BR_BASE_MASK 0x0f8000c3ce0ULL +#define OP_BR_MASK 0x0000000001fULL +#define OP_BR_EV_PIP 0x00000000300ULL +#define OP_BR_CSS 0x0000003c000ULL +#define OP_BR_DEFBR 0x00000300000ULL +#define OP_BR_ADDR_LO 0x007ffc00000ULL +#define OP_BR_ADDR_HI 0x10000000000ULL #define nfp_is_br(_insn) \ (((_insn) & OP_BR_BASE_MASK) == OP_BR_BASE) @@ -83,30 +83,30 @@ enum br_ctx_signal_state { BR_CSS_NONE = 2, }; -#define OP_BBYTE_BASE 0x0c800000000ULL -#define OP_BB_A_SRC 0x000000000ffULL -#define OP_BB_BYTE 0x00000000300ULL -#define OP_BB_B_SRC 0x0000003fc00ULL -#define OP_BB_I8 0x00000040000ULL -#define OP_BB_EQ 0x00000080000ULL -#define OP_BB_DEFBR 0x00000300000ULL -#define OP_BB_ADDR_LO 0x007ffc00000ULL -#define OP_BB_ADDR_HI 0x10000000000ULL - -#define OP_BALU_BASE 0x0e800000000ULL -#define OP_BA_A_SRC 0x000000003ffULL -#define OP_BA_B_SRC 0x000000ffc00ULL -#define OP_BA_DEFBR 0x00000300000ULL -#define OP_BA_ADDR_HI 0x0007fc00000ULL - -#define OP_IMMED_A_SRC 0x000000003ffULL -#define OP_IMMED_B_SRC 0x000000ffc00ULL -#define OP_IMMED_IMM 0x0000ff00000ULL -#define OP_IMMED_WIDTH 0x00060000000ULL -#define OP_IMMED_INV 0x00080000000ULL -#define OP_IMMED_SHIFT 0x00600000000ULL -#define OP_IMMED_BASE 0x0f000000000ULL -#define OP_IMMED_WR_AB 0x20000000000ULL +#define OP_BBYTE_BASE 0x0c800000000ULL +#define OP_BB_A_SRC 0x000000000ffULL +#define OP_BB_BYTE 0x00000000300ULL +#define OP_BB_B_SRC 0x0000003fc00ULL +#define OP_BB_I8 0x00000040000ULL +#define OP_BB_EQ 0x00000080000ULL +#define OP_BB_DEFBR 0x00000300000ULL +#define OP_BB_ADDR_LO 0x007ffc00000ULL +#define OP_BB_ADDR_HI 0x10000000000ULL + +#define OP_BALU_BASE 0x0e800000000ULL +#define OP_BA_A_SRC 0x000000003ffULL +#define OP_BA_B_SRC 0x000000ffc00ULL +#define OP_BA_DEFBR 0x00000300000ULL +#define OP_BA_ADDR_HI 0x0007fc00000ULL + +#define OP_IMMED_A_SRC 0x000000003ffULL +#define OP_IMMED_B_SRC 0x000000ffc00ULL +#define OP_IMMED_IMM 0x0000ff00000ULL +#define OP_IMMED_WIDTH 0x00060000000ULL +#define OP_IMMED_INV 0x00080000000ULL +#define OP_IMMED_SHIFT 0x00600000000ULL +#define OP_IMMED_BASE 0x0f000000000ULL +#define OP_IMMED_WR_AB 0x20000000000ULL enum immed_width { IMMED_WIDTH_ALL = 0, @@ -120,17 +120,17 @@ enum immed_shift { IMMED_SHIFT_2B = 2, }; -#define OP_SHF_BASE 0x08000000000ULL -#define OP_SHF_A_SRC 0x000000000ffULL -#define OP_SHF_SC 0x00000000300ULL -#define OP_SHF_B_SRC 0x0000003fc00ULL -#define OP_SHF_I8 0x00000040000ULL -#define OP_SHF_SW 0x00000080000ULL -#define OP_SHF_DST 0x0000ff00000ULL -#define OP_SHF_SHIFT 0x001f0000000ULL -#define OP_SHF_OP 0x00e00000000ULL -#define OP_SHF_DST_AB 0x01000000000ULL -#define OP_SHF_WR_AB 0x20000000000ULL +#define OP_SHF_BASE 0x08000000000ULL +#define OP_SHF_A_SRC 0x000000000ffULL +#define OP_SHF_SC 0x00000000300ULL +#define OP_SHF_B_SRC 0x0000003fc00ULL +#define OP_SHF_I8 0x00000040000ULL +#define OP_SHF_SW 0x00000080000ULL +#define OP_SHF_DST 0x0000ff00000ULL +#define OP_SHF_SHIFT 0x001f0000000ULL +#define OP_SHF_OP 0x00e00000000ULL +#define OP_SHF_DST_AB 0x01000000000ULL +#define OP_SHF_WR_AB 0x20000000000ULL enum shf_op { SHF_OP_NONE = 0, @@ -145,14 +145,14 @@ enum shf_sc { SHF_SC_R_DSHF = 3, }; -#define OP_ALU_A_SRC 0x000000003ffULL -#define OP_ALU_B_SRC 0x000000ffc00ULL -#define OP_ALU_DST 0x0003ff00000ULL -#define OP_ALU_SW 0x00040000000ULL -#define OP_ALU_OP 0x00f80000000ULL -#define OP_ALU_DST_AB 0x01000000000ULL -#define OP_ALU_BASE 0x0a000000000ULL -#define OP_ALU_WR_AB 0x20000000000ULL +#define OP_ALU_A_SRC 0x000000003ffULL +#define OP_ALU_B_SRC 0x000000ffc00ULL +#define OP_ALU_DST 0x0003ff00000ULL +#define OP_ALU_SW 0x00040000000ULL +#define OP_ALU_OP 0x00f80000000ULL +#define OP_ALU_DST_AB 0x01000000000ULL +#define OP_ALU_BASE 0x0a000000000ULL +#define OP_ALU_WR_AB 0x20000000000ULL enum alu_op { ALU_OP_NONE = 0x00, @@ -171,26 +171,26 @@ enum alu_dst_ab { ALU_DST_B = 1, }; -#define OP_LDF_BASE 0x0c000000000ULL -#define OP_LDF_A_SRC 0x000000000ffULL -#define OP_LDF_SC 0x00000000300ULL -#define OP_LDF_B_SRC 0x0000003fc00ULL -#define OP_LDF_I8 0x00000040000ULL -#define OP_LDF_SW 0x00000080000ULL -#define OP_LDF_ZF 0x00000100000ULL -#define OP_LDF_BMASK 0x0000f000000ULL -#define OP_LDF_SHF 0x001f0000000ULL -#define OP_LDF_WR_AB 0x20000000000ULL - -#define OP_CMD_A_SRC 0x000000000ffULL -#define OP_CMD_CTX 0x00000000300ULL -#define OP_CMD_B_SRC 0x0000003fc00ULL -#define OP_CMD_TOKEN 0x000000c0000ULL -#define OP_CMD_XFER 0x00001f00000ULL -#define OP_CMD_CNT 0x0000e000000ULL -#define OP_CMD_SIG 0x000f0000000ULL -#define OP_CMD_TGT_CMD 0x07f00000000ULL -#define OP_CMD_MODE 0x1c0000000000ULL +#define OP_LDF_BASE 0x0c000000000ULL +#define OP_LDF_A_SRC 0x000000000ffULL +#define OP_LDF_SC 0x00000000300ULL +#define OP_LDF_B_SRC 0x0000003fc00ULL +#define OP_LDF_I8 0x00000040000ULL +#define OP_LDF_SW 0x00000080000ULL +#define OP_LDF_ZF 0x00000100000ULL +#define OP_LDF_BMASK 0x0000f000000ULL +#define OP_LDF_SHF 0x001f0000000ULL +#define OP_LDF_WR_AB 0x20000000000ULL + +#define OP_CMD_A_SRC 0x000000000ffULL +#define OP_CMD_CTX 0x00000000300ULL +#define OP_CMD_B_SRC 0x0000003fc00ULL +#define OP_CMD_TOKEN 0x000000c0000ULL +#define OP_CMD_XFER 0x00001f00000ULL +#define OP_CMD_CNT 0x0000e000000ULL +#define OP_CMD_SIG 0x000f0000000ULL +#define OP_CMD_TGT_CMD 0x07f00000000ULL +#define OP_CMD_MODE 0x1c0000000000ULL struct cmd_tgt_act { u8 token; @@ -218,11 +218,11 @@ enum cmd_ctx_swap { CMD_CTX_NO_SWAP = 3, }; -#define OP_LCSR_BASE 0x0fc00000000ULL -#define OP_LCSR_A_SRC 0x000000003ffULL -#define OP_LCSR_B_SRC 0x000000ffc00ULL -#define OP_LCSR_WRITE 0x00000200000ULL -#define OP_LCSR_ADDR 0x001ffc00000ULL +#define OP_LCSR_BASE 0x0fc00000000ULL +#define OP_LCSR_A_SRC 0x000000003ffULL +#define OP_LCSR_B_SRC 0x000000ffc00ULL +#define OP_LCSR_WRITE 0x00000200000ULL +#define OP_LCSR_ADDR 0x001ffc00000ULL enum lcsr_wr_src { LCSR_WR_AREG, @@ -230,8 +230,8 @@ enum lcsr_wr_src { LCSR_WR_IMM, }; -#define OP_CARB_BASE 0x0e000000000ULL -#define OP_CARB_OR 0x00000010000ULL +#define OP_CARB_BASE 0x0e000000000ULL +#define OP_CARB_OR 0x00000010000ULL /* Software register representation, independent of operand type */ #define NN_REG_TYPE GENMASK(31, 24) -- GitLab From 9f15d0f438372986b0f9de36f805fe2dd83f9c27 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:11 -0700 Subject: [PATCH 1149/1507] nfp: bpf: encode LMEM accesses NFP LMEM is a large, indirectly accessed register file. There are two basic indirect access registers. Each access operation may either use offset (up to 8 or 16 words) or perform post decrement/increment. Add encodings of LMEM indexes as instruction operands. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_asm.c | 44 ++++++++++++++++++++ drivers/net/ethernet/netronome/nfp/nfp_asm.h | 41 ++++++++++++++++++ 2 files changed, 85 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 4c9201bf93314..4bcab43da16df 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -48,6 +48,7 @@ const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) { + bool lm_id, lm_dec = false; u16 val = swreg_value(reg); switch (swreg_type(reg)) { @@ -59,6 +60,33 @@ static u16 nfp_swreg_to_unreg(swreg reg, bool is_dst) return UR_REG_NN | val; case NN_REG_XFER: return UR_REG_XFR | val; + case NN_REG_LMEM: + lm_id = swreg_lm_idx(reg); + + switch (swreg_lm_mode(reg)) { + case NN_LM_MOD_NONE: + if (val & ~UR_REG_LM_IDX_MAX) { + pr_err("LM offset too large\n"); + return 0; + } + return UR_REG_LM | FIELD_PREP(UR_REG_LM_IDX, lm_id) | + val; + case NN_LM_MOD_DEC: + lm_dec = true; + /* fall through */ + case NN_LM_MOD_INC: + if (val) { + pr_err("LM offset in inc/dev mode\n"); + return 0; + } + return UR_REG_LM | UR_REG_LM_POST_MOD | + FIELD_PREP(UR_REG_LM_IDX, lm_id) | + FIELD_PREP(UR_REG_LM_POST_MOD_DEC, lm_dec); + default: + pr_err("bad LM mode for unrestricted operands %d\n", + swreg_lm_mode(reg)); + return 0; + } case NN_REG_IMM: if (val & ~0xff) { pr_err("immediate too large\n"); @@ -108,6 +136,7 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) { u16 val = swreg_value(reg); + bool lm_id; switch (swreg_type(reg)) { case NN_REG_GPR_A: @@ -116,6 +145,21 @@ static u16 nfp_swreg_to_rereg(swreg reg, bool is_dst, bool has_imm8, bool *i8) return val; case NN_REG_XFER: return RE_REG_XFR | val; + case NN_REG_LMEM: + lm_id = swreg_lm_idx(reg); + + if (swreg_lm_mode(reg) != NN_LM_MOD_NONE) { + pr_err("bad LM mode for restricted operands %d\n", + swreg_lm_mode(reg)); + return 0; + } + + if (val & ~RE_REG_LM_IDX_MAX) { + pr_err("LM offset too large\n"); + return 0; + } + + return RE_REG_LM | FIELD_PREP(RE_REG_LM_IDX, lm_id) | val; case NN_REG_IMM: if (val & ~(0x7f | has_imm8 << 7)) { pr_err("immediate too large\n"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index 63cfd07da34ef..d722f6878bd8f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -44,9 +44,17 @@ #define RE_REG_IMM_encode(x) \ (RE_REG_IMM | ((x) & 0x1f) | (((x) & 0x60) << 1)) #define RE_REG_IMM_MAX 0x07fULL +#define RE_REG_LM 0x050 +#define RE_REG_LM_IDX 0x008 +#define RE_REG_LM_IDX_MAX 0x7 #define RE_REG_XFR 0x080 #define UR_REG_XFR 0x180 +#define UR_REG_LM 0x200 +#define UR_REG_LM_IDX 0x020 +#define UR_REG_LM_POST_MOD 0x010 +#define UR_REG_LM_POST_MOD_DEC 0x001 +#define UR_REG_LM_IDX_MAX 0xf #define UR_REG_NN 0x280 #define UR_REG_NO_DST 0x300 #define UR_REG_IMM UR_REG_NO_DST @@ -235,6 +243,8 @@ enum lcsr_wr_src { /* Software register representation, independent of operand type */ #define NN_REG_TYPE GENMASK(31, 24) +#define NN_REG_LM_IDX BIT(22) +#define NN_REG_LM_MOD GENMASK(21, 20) #define NN_REG_VAL GENMASK(7, 0) enum nfp_bpf_reg_type { @@ -245,6 +255,13 @@ enum nfp_bpf_reg_type { NN_REG_XFER = BIT(3), NN_REG_IMM = BIT(4), NN_REG_NONE = BIT(5), + NN_REG_LMEM = BIT(6), +}; + +enum nfp_bpf_lm_mode { + NN_LM_MOD_NONE = 0, + NN_LM_MOD_INC, + NN_LM_MOD_DEC, }; #define reg_both(x) __enc_swreg((x), NN_REG_GPR_BOTH) @@ -254,6 +271,10 @@ enum nfp_bpf_reg_type { #define reg_xfer(x) __enc_swreg((x), NN_REG_XFER) #define reg_imm(x) __enc_swreg((x), NN_REG_IMM) #define reg_none() __enc_swreg(0, NN_REG_NONE) +#define reg_lm(x, off) __enc_swreg_lm((x), NN_LM_MOD_NONE, (off)) +#define reg_lm_inc(x) __enc_swreg_lm((x), NN_LM_MOD_INC, 0) +#define reg_lm_dec(x) __enc_swreg_lm((x), NN_LM_MOD_DEC, 0) +#define __reg_lm(x, mod, off) __enc_swreg_lm((x), (mod), (off)) typedef __u32 __bitwise swreg; @@ -262,6 +283,16 @@ static inline swreg __enc_swreg(u16 id, u8 type) return (__force swreg)(id | FIELD_PREP(NN_REG_TYPE, type)); } +static inline swreg __enc_swreg_lm(u8 id, enum nfp_bpf_lm_mode mode, u8 off) +{ + WARN_ON(id > 1 || (off && mode != NN_LM_MOD_NONE)); + + return (__force swreg)(FIELD_PREP(NN_REG_TYPE, NN_REG_LMEM) | + FIELD_PREP(NN_REG_LM_IDX, id) | + FIELD_PREP(NN_REG_LM_MOD, mode) | + off); +} + static inline u32 swreg_raw(swreg reg) { return (__force u32)reg; @@ -277,6 +308,16 @@ static inline u16 swreg_value(swreg reg) return FIELD_GET(NN_REG_VAL, swreg_raw(reg)); } +static inline bool swreg_lm_idx(swreg reg) +{ + return FIELD_GET(NN_REG_LM_IDX, swreg_raw(reg)); +} + +static inline enum nfp_bpf_lm_mode swreg_lm_mode(swreg reg) +{ + return FIELD_GET(NN_REG_LM_MOD, swreg_raw(reg)); +} + struct nfp_insn_ur_regs { enum alu_dst_ab dst_ab; u16 dst; -- GitLab From 995e101ffa71eff6ae5f5d5bf1ca8ec757b4ed21 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:12 -0700 Subject: [PATCH 1150/1507] nfp: bpf: encode extended LM pointer operands Most instructions have special fields which allow switching between base and extended Local Memory pointers. Introduce those to register encoding, we will use the extra LM pointers to access high addresses of the stack. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 56 ++++++++++++++------ drivers/net/ethernet/netronome/nfp/nfp_asm.c | 6 +++ drivers/net/ethernet/netronome/nfp/nfp_asm.h | 28 ++++++++-- 3 files changed, 70 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 4fa220f710d2a..d7dc19feba8dd 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -153,6 +153,11 @@ emit_cmd(struct nfp_prog *nfp_prog, enum cmd_tgt_map op, nfp_prog->error = -EFAULT; return; } + if (reg.dst_lmextn || reg.src_lmextn) { + pr_err("cmd can't use LMextn\n"); + nfp_prog->error = -EFAULT; + return; + } __emit_cmd(nfp_prog, op, mode, xfer, reg.areg, reg.breg, size, sync); } @@ -198,7 +203,7 @@ emit_br(struct nfp_prog *nfp_prog, enum br_mask mask, u16 addr, u8 defer) static void __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8, - u8 byte, bool equal, u16 addr, u8 defer) + u8 byte, bool equal, u16 addr, u8 defer, bool src_lmextn) { u16 addr_lo, addr_hi; u64 insn; @@ -214,32 +219,34 @@ __emit_br_byte(struct nfp_prog *nfp_prog, u8 areg, u8 breg, bool imm8, FIELD_PREP(OP_BB_EQ, equal) | FIELD_PREP(OP_BB_DEFBR, defer) | FIELD_PREP(OP_BB_ADDR_LO, addr_lo) | - FIELD_PREP(OP_BB_ADDR_HI, addr_hi); + FIELD_PREP(OP_BB_ADDR_HI, addr_hi) | + FIELD_PREP(OP_BB_SRC_LMEXTN, src_lmextn); nfp_prog_push(nfp_prog, insn); } static void emit_br_byte_neq(struct nfp_prog *nfp_prog, - swreg dst, u8 imm, u8 byte, u16 addr, u8 defer) + swreg src, u8 imm, u8 byte, u16 addr, u8 defer) { struct nfp_insn_re_regs reg; int err; - err = swreg_to_restricted(reg_none(), dst, reg_imm(imm), ®, true); + err = swreg_to_restricted(reg_none(), src, reg_imm(imm), ®, true); if (err) { nfp_prog->error = err; return; } __emit_br_byte(nfp_prog, reg.areg, reg.breg, reg.i8, byte, false, addr, - defer); + defer, reg.src_lmextn); } static void __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi, enum immed_width width, bool invert, - enum immed_shift shift, bool wr_both) + enum immed_shift shift, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -250,7 +257,9 @@ __emit_immed(struct nfp_prog *nfp_prog, u16 areg, u16 breg, u16 imm_hi, FIELD_PREP(OP_IMMED_WIDTH, width) | FIELD_PREP(OP_IMMED_INV, invert) | FIELD_PREP(OP_IMMED_SHIFT, shift) | - FIELD_PREP(OP_IMMED_WR_AB, wr_both); + FIELD_PREP(OP_IMMED_WR_AB, wr_both) | + FIELD_PREP(OP_IMMED_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_IMMED_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } @@ -274,13 +283,15 @@ emit_immed(struct nfp_prog *nfp_prog, swreg dst, u16 imm, } __emit_immed(nfp_prog, reg.areg, reg.breg, imm >> 8, width, - invert, shift, reg.wr_both); + invert, shift, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, enum shf_sc sc, u8 shift, - u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both) + u16 areg, enum shf_op op, u16 breg, bool i8, bool sw, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -302,7 +313,9 @@ __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, FIELD_PREP(OP_SHF_SHIFT, shift) | FIELD_PREP(OP_SHF_OP, op) | FIELD_PREP(OP_SHF_DST_AB, dst_ab) | - FIELD_PREP(OP_SHF_WR_AB, wr_both); + FIELD_PREP(OP_SHF_WR_AB, wr_both) | + FIELD_PREP(OP_SHF_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_SHF_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } @@ -321,12 +334,14 @@ emit_shf(struct nfp_prog *nfp_prog, swreg dst, } __emit_shf(nfp_prog, reg.dst, reg.dst_ab, sc, shift, - reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both); + reg.areg, op, reg.breg, reg.i8, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, - u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both) + u16 areg, enum alu_op op, u16 breg, bool swap, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -337,7 +352,9 @@ __emit_alu(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab, FIELD_PREP(OP_ALU_SW, swap) | FIELD_PREP(OP_ALU_OP, op) | FIELD_PREP(OP_ALU_DST_AB, dst_ab) | - FIELD_PREP(OP_ALU_WR_AB, wr_both); + FIELD_PREP(OP_ALU_WR_AB, wr_both) | + FIELD_PREP(OP_ALU_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_ALU_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } @@ -356,13 +373,15 @@ emit_alu(struct nfp_prog *nfp_prog, swreg dst, } __emit_alu(nfp_prog, reg.dst, reg.dst_ab, - reg.areg, op, reg.breg, reg.swap, reg.wr_both); + reg.areg, op, reg.breg, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8, - bool zero, bool swap, bool wr_both) + bool zero, bool swap, bool wr_both, + bool dst_lmextn, bool src_lmextn) { u64 insn; @@ -375,7 +394,9 @@ __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, FIELD_PREP(OP_LDF_ZF, zero) | FIELD_PREP(OP_LDF_BMASK, bmask) | FIELD_PREP(OP_LDF_SHF, shift) | - FIELD_PREP(OP_LDF_WR_AB, wr_both); + FIELD_PREP(OP_LDF_WR_AB, wr_both) | + FIELD_PREP(OP_LDF_SRC_LMEXTN, src_lmextn) | + FIELD_PREP(OP_LDF_DST_LMEXTN, dst_lmextn); nfp_prog_push(nfp_prog, insn); } @@ -394,7 +415,8 @@ emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, } __emit_ld_field(nfp_prog, sc, reg.areg, bmask, reg.breg, shift, - reg.i8, zero, reg.swap, reg.wr_both); + reg.i8, zero, reg.swap, reg.wr_both, + reg.dst_lmextn, reg.src_lmextn); } static void diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 4bcab43da16df..1decc638ea6f7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -130,6 +130,9 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, reg->breg = nfp_swreg_to_unreg(rreg, false); } + reg->dst_lmextn = swreg_lmextn(dst); + reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + return 0; } @@ -207,5 +210,8 @@ int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, reg->breg = nfp_swreg_to_rereg(rreg, false, has_imm8, ®->i8); } + reg->dst_lmextn = swreg_lmextn(dst); + reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index d722f6878bd8f..40a51a45afd79 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -100,6 +100,7 @@ enum br_ctx_signal_state { #define OP_BB_DEFBR 0x00000300000ULL #define OP_BB_ADDR_LO 0x007ffc00000ULL #define OP_BB_ADDR_HI 0x10000000000ULL +#define OP_BB_SRC_LMEXTN 0x40000000000ULL #define OP_BALU_BASE 0x0e800000000ULL #define OP_BA_A_SRC 0x000000003ffULL @@ -115,6 +116,8 @@ enum br_ctx_signal_state { #define OP_IMMED_SHIFT 0x00600000000ULL #define OP_IMMED_BASE 0x0f000000000ULL #define OP_IMMED_WR_AB 0x20000000000ULL +#define OP_IMMED_SRC_LMEXTN 0x40000000000ULL +#define OP_IMMED_DST_LMEXTN 0x80000000000ULL enum immed_width { IMMED_WIDTH_ALL = 0, @@ -139,6 +142,8 @@ enum immed_shift { #define OP_SHF_OP 0x00e00000000ULL #define OP_SHF_DST_AB 0x01000000000ULL #define OP_SHF_WR_AB 0x20000000000ULL +#define OP_SHF_SRC_LMEXTN 0x40000000000ULL +#define OP_SHF_DST_LMEXTN 0x80000000000ULL enum shf_op { SHF_OP_NONE = 0, @@ -161,6 +166,8 @@ enum shf_sc { #define OP_ALU_DST_AB 0x01000000000ULL #define OP_ALU_BASE 0x0a000000000ULL #define OP_ALU_WR_AB 0x20000000000ULL +#define OP_ALU_SRC_LMEXTN 0x40000000000ULL +#define OP_ALU_DST_LMEXTN 0x80000000000ULL enum alu_op { ALU_OP_NONE = 0x00, @@ -189,6 +196,8 @@ enum alu_dst_ab { #define OP_LDF_BMASK 0x0000f000000ULL #define OP_LDF_SHF 0x001f0000000ULL #define OP_LDF_WR_AB 0x20000000000ULL +#define OP_LDF_SRC_LMEXTN 0x40000000000ULL +#define OP_LDF_DST_LMEXTN 0x80000000000ULL #define OP_CMD_A_SRC 0x000000000ffULL #define OP_CMD_CTX 0x00000000300ULL @@ -231,6 +240,8 @@ enum cmd_ctx_swap { #define OP_LCSR_B_SRC 0x000000ffc00ULL #define OP_LCSR_WRITE 0x00000200000ULL #define OP_LCSR_ADDR 0x001ffc00000ULL +#define OP_LCSR_SRC_LMEXTN 0x40000000000ULL +#define OP_LCSR_DST_LMEXTN 0x80000000000ULL enum lcsr_wr_src { LCSR_WR_AREG, @@ -243,7 +254,9 @@ enum lcsr_wr_src { /* Software register representation, independent of operand type */ #define NN_REG_TYPE GENMASK(31, 24) -#define NN_REG_LM_IDX BIT(22) +#define NN_REG_LM_IDX GENMASK(23, 22) +#define NN_REG_LM_IDX_HI BIT(23) +#define NN_REG_LM_IDX_LO BIT(22) #define NN_REG_LM_MOD GENMASK(21, 20) #define NN_REG_VAL GENMASK(7, 0) @@ -285,7 +298,7 @@ static inline swreg __enc_swreg(u16 id, u8 type) static inline swreg __enc_swreg_lm(u8 id, enum nfp_bpf_lm_mode mode, u8 off) { - WARN_ON(id > 1 || (off && mode != NN_LM_MOD_NONE)); + WARN_ON(id > 3 || (off && mode != NN_LM_MOD_NONE)); return (__force swreg)(FIELD_PREP(NN_REG_TYPE, NN_REG_LMEM) | FIELD_PREP(NN_REG_LM_IDX, id) | @@ -310,7 +323,12 @@ static inline u16 swreg_value(swreg reg) static inline bool swreg_lm_idx(swreg reg) { - return FIELD_GET(NN_REG_LM_IDX, swreg_raw(reg)); + return FIELD_GET(NN_REG_LM_IDX_LO, swreg_raw(reg)); +} + +static inline bool swreg_lmextn(swreg reg) +{ + return FIELD_GET(NN_REG_LM_IDX_HI, swreg_raw(reg)); } static inline enum nfp_bpf_lm_mode swreg_lm_mode(swreg reg) @@ -324,6 +342,8 @@ struct nfp_insn_ur_regs { u16 areg, breg; bool swap; bool wr_both; + bool dst_lmextn; + bool src_lmextn; }; struct nfp_insn_re_regs { @@ -333,6 +353,8 @@ struct nfp_insn_re_regs { bool swap; bool wr_both; bool i8; + bool dst_lmextn; + bool src_lmextn; }; int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, -- GitLab From 18e53b6cb9ac157f4b2c7db698d4adc064df2fa0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:13 -0700 Subject: [PATCH 1151/1507] nfp: bpf: move to datapath ABI version 2 Datapath ABI version 2 stores the packet information in LMEM instead of NNRs. We also have strict restrictions on which GPRs we can use. Only GPRs 0-23 are reserved for BPF. Adjust the static register locations and "ABI" registers. Note that packet length is packed with other info so we have to extract it into one of the scratch registers, OTOH since LMEM can be used in restricted operands we don't have to extract packet pointer. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 19 ++++++++------- drivers/net/ethernet/netronome/nfp/bpf/main.h | 24 ++++++++++++------- .../net/ethernet/netronome/nfp/nfp_net_ctrl.h | 2 +- 3 files changed, 26 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index d7dc19feba8dd..9b6c98ccebfe9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -526,22 +526,22 @@ construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, emit_alu(nfp_prog, imm_a(nfp_prog), imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size)); emit_alu(nfp_prog, reg_none(), - NFP_BPF_ABI_LEN, ALU_OP_SUB, imm_a(nfp_prog)); + plen_reg(nfp_prog), ALU_OP_SUB, imm_a(nfp_prog)); wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); /* Load data */ emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pkt_reg(nfp_prog), imm_b(nfp_prog), sz - 1, true); + pptr_reg(nfp_prog), imm_b(nfp_prog), sz - 1, true); } else { /* Check packet length */ tmp_reg = ur_load_imm_any(nfp_prog, offset + size, imm_a(nfp_prog)); emit_alu(nfp_prog, reg_none(), - NFP_BPF_ABI_LEN, ALU_OP_SUB, tmp_reg); + plen_reg(nfp_prog), ALU_OP_SUB, tmp_reg); wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); /* Load data */ tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pkt_reg(nfp_prog), tmp_reg, sz - 1, true); + pptr_reg(nfp_prog), tmp_reg, sz - 1, true); } i = 0; @@ -1024,7 +1024,7 @@ static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { if (meta->insn.off == offsetof(struct sk_buff, len)) emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_LEN); + reg_none(), ALU_OP_NONE, plen_reg(nfp_prog)); else return -EOPNOTSUPP; @@ -1039,12 +1039,12 @@ static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) meta->insn.off != offsetof(struct xdp_md, data_end)) return -EOPNOTSUPP; - emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT); + emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, pptr_reg(nfp_prog)); if (meta->insn.off == offsetof(struct xdp_md, data)) return 0; - emit_alu(nfp_prog, dst, dst, ALU_OP_ADD, NFP_BPF_ABI_LEN); + emit_alu(nfp_prog, dst, dst, ALU_OP_ADD, plen_reg(nfp_prog)); return 0; } @@ -1403,8 +1403,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog) static void nfp_intro(struct nfp_prog *nfp_prog) { - emit_alu(nfp_prog, pkt_reg(nfp_prog), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_PKT); + wrp_immed(nfp_prog, plen_reg(nfp_prog), GENMASK(13, 0)); + emit_alu(nfp_prog, plen_reg(nfp_prog), + plen_reg(nfp_prog), ALU_OP_AND, pv_len(nfp_prog)); } static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 7d959757a51a9..b7a112acbdb72 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -54,9 +54,13 @@ enum br_special { }; enum static_regs { - STATIC_REG_PKT = 1, -#define REG_PKT_BANK ALU_DST_A - STATIC_REG_IMM = 2, /* Bank AB */ + STATIC_REG_IMM = 21, /* Bank AB */ + STATIC_REG_PKT_LEN = 22, /* Bank B */ +}; + +enum pkt_vec { + PKT_VEC_PKT_LEN = 0, + PKT_VEC_PKT_PTR = 2, }; enum nfp_bpf_action_type { @@ -66,15 +70,17 @@ enum nfp_bpf_action_type { NN_ACT_XDP, }; -#define pkt_reg(np) reg_a((np)->regs_per_thread - STATIC_REG_PKT) -#define imm_a(np) reg_a((np)->regs_per_thread - STATIC_REG_IMM) -#define imm_b(np) reg_b((np)->regs_per_thread - STATIC_REG_IMM) -#define imm_both(np) reg_both((np)->regs_per_thread - STATIC_REG_IMM) +#define pv_len(np) reg_lm(1, PKT_VEC_PKT_LEN) +#define pv_ctm_ptr(np) reg_lm(1, PKT_VEC_PKT_PTR) + +#define plen_reg(np) reg_b(STATIC_REG_PKT_LEN) +#define pptr_reg(np) pv_ctm_ptr(np) +#define imm_a(np) reg_a(STATIC_REG_IMM) +#define imm_b(np) reg_b(STATIC_REG_IMM) +#define imm_both(np) reg_both(STATIC_REG_IMM) #define NFP_BPF_ABI_FLAGS reg_imm(0) #define NFP_BPF_ABI_FLAG_MARK 1 -#define NFP_BPF_ABI_PKT reg_nnr(2) -#define NFP_BPF_ABI_LEN reg_nnr(3) struct nfp_prog; struct nfp_insn_meta; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index b0a452ba9039a..782d452e0fc22 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -255,7 +255,7 @@ * @NFP_NET_CFG_BPF_ADDR: DMA address of the buffer with JITed BPF code */ #define NFP_NET_CFG_BPF_ABI 0x0080 -#define NFP_NET_BPF_ABI 1 +#define NFP_NET_BPF_ABI 2 #define NFP_NET_CFG_BPF_CAP 0x0081 #define NFP_NET_BPF_CAP_RELO (1 << 0) /* seamless reload */ #define NFP_NET_CFG_BPF_MAX_LEN 0x0082 -- GitLab From fd068ddc888355dccd90ad610104e4addf23b7a3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:14 -0700 Subject: [PATCH 1152/1507] nfp: bpf: calculate code store ECC In the initial PoC firmware I simply disabled ECC on the instruction store. Do the ECC calculation for generated instructions in the driver. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 20 +++++++++++ drivers/net/ethernet/netronome/nfp/nfp_asm.c | 37 ++++++++++++++++++++ drivers/net/ethernet/netronome/nfp/nfp_asm.h | 3 ++ 3 files changed, 60 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 9b6c98ccebfe9..f4aedc89bfc8e 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1715,6 +1715,23 @@ static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) return 0; } +static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog) +{ + int i; + + for (i = 0; i < nfp_prog->prog_len; i++) { + int err; + + err = nfp_ustore_check_valid_no_ecc(nfp_prog->prog[i]); + if (err) + return err; + + nfp_prog->prog[i] = nfp_ustore_calc_ecc_insn(nfp_prog->prog[i]); + } + + return 0; +} + /** * nfp_bpf_jit() - translate BPF code into NFP assembly * @filter: kernel BPF filter struct @@ -1766,8 +1783,11 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, pr_err("Translation failed with error %d (translated: %u)\n", ret, nfp_prog->n_translated); ret = -EINVAL; + goto out; } + ret = nfp_bpf_ustore_calc(nfp_prog); + res->n_instr = nfp_prog->prog_len; res->dense_mode = false; out: diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 1decc638ea6f7..de76e7444fc23 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -215,3 +215,40 @@ int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, return 0; } + +#define NFP_USTORE_ECC_POLY_WORDS 7 +#define NFP_USTORE_OP_BITS 45 + +static const u64 nfp_ustore_ecc_polynomials[NFP_USTORE_ECC_POLY_WORDS] = { + 0x0ff800007fffULL, + 0x11f801ff801fULL, + 0x1e387e0781e1ULL, + 0x17cb8e388e22ULL, + 0x1af5b2c93244ULL, + 0x1f56d5525488ULL, + 0x0daf69a46910ULL, +}; + +static bool parity(u64 value) +{ + return hweight64(value) & 1; +} + +int nfp_ustore_check_valid_no_ecc(u64 insn) +{ + if (insn & ~GENMASK_ULL(NFP_USTORE_OP_BITS, 0)) + return -EINVAL; + + return 0; +} + +u64 nfp_ustore_calc_ecc_insn(u64 insn) +{ + u8 ecc = 0; + int i; + + for (i = 0; i < NFP_USTORE_ECC_POLY_WORDS; i++) + ecc |= parity(nfp_ustore_ecc_polynomials[i] & insn) << i; + + return insn | (u64)ecc << NFP_USTORE_OP_BITS; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index 40a51a45afd79..d95087e5fb732 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -362,4 +362,7 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, struct nfp_insn_re_regs *reg, bool has_imm8); +int nfp_ustore_check_valid_no_ecc(u64 insn); +u64 nfp_ustore_calc_ecc_insn(u64 insn); + #endif -- GitLab From 1c03e03f9b5278701d4a0e3444b2de3b9ddc244b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:15 -0700 Subject: [PATCH 1153/1507] nfp: bpf: pad code with valid nops We need to append up to 8 nops after last instruction to make sure the CPU will not fetch garbage instructions with invalid ECC if the code store was not initialized. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 12 +++++++++++- drivers/net/ethernet/netronome/nfp/nfp_asm.h | 2 ++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index f4aedc89bfc8e..e0600d0377738 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -426,6 +426,11 @@ emit_ld_field(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, emit_ld_field_any(nfp_prog, sc, shift, dst, bmask, src, false); } +static void emit_nop(struct nfp_prog *nfp_prog) +{ + __emit_immed(nfp_prog, UR_REG_IMM, UR_REG_IMM, 0, 0, 0, 0, 0, 0, 0); +} + /* --- Wrappers --- */ static bool pack_immed(u32 imm, u16 *val, enum immed_shift *shift) { @@ -1550,7 +1555,7 @@ static void nfp_outro(struct nfp_prog *nfp_prog) static int nfp_translate(struct nfp_prog *nfp_prog) { struct nfp_insn_meta *meta; - int err; + int i, err; nfp_intro(nfp_prog); if (nfp_prog->error) @@ -1582,6 +1587,11 @@ static int nfp_translate(struct nfp_prog *nfp_prog) if (nfp_prog->error) return nfp_prog->error; + for (i = 0; i < NFP_USTORE_PREFETCH_WINDOW; i++) + emit_nop(nfp_prog); + if (nfp_prog->error) + return nfp_prog->error; + return nfp_fixup_branches(nfp_prog); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index d95087e5fb732..c4c18dd5630a9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -362,6 +362,8 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, struct nfp_insn_re_regs *reg, bool has_imm8); +#define NFP_USTORE_PREFETCH_WINDOW 8 + int nfp_ustore_check_valid_no_ecc(u64 insn); u64 nfp_ustore_calc_ecc_insn(u64 insn); -- GitLab From 2e85d3884f25a0419a941676d1a7c25779884be2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:16 -0700 Subject: [PATCH 1154/1507] nfp: bpf: byte swap the instructions Device expects the instructions in little endian. Make sure we byte swap on big endian hosts. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index e0600d0377738..f68052367db70 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1725,7 +1725,7 @@ static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) return 0; } -static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog) +static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog, __le64 *ustore) { int i; @@ -1737,6 +1737,8 @@ static int nfp_bpf_ustore_calc(struct nfp_prog *nfp_prog) return err; nfp_prog->prog[i] = nfp_ustore_calc_ecc_insn(nfp_prog->prog[i]); + + ustore[i] = cpu_to_le64(nfp_prog->prog[i]); } return 0; @@ -1796,7 +1798,7 @@ nfp_bpf_jit(struct bpf_prog *filter, void *prog_mem, goto out; } - ret = nfp_bpf_ustore_calc(nfp_prog); + ret = nfp_bpf_ustore_calc(nfp_prog, (__force __le64 *)prog_mem); res->n_instr = nfp_prog->prog_len; res->dense_mode = false; -- GitLab From 2de1be1db25d3285f514920230790be20db92887 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 8 Oct 2017 21:04:17 -0700 Subject: [PATCH 1155/1507] nfp: bpf: pass dst register to ld_field instruction ld_field instruction is a bit special because the encoding uses two source registers and one of them becomes the output. We do need to pass the dst register to our encoding helpers though, otherwise the "write both banks" flag will not be observed. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index f68052367db70..13148f30fc4c1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -408,7 +408,8 @@ emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, struct nfp_insn_re_regs reg; int err; - err = swreg_to_restricted(reg_none(), dst, src, ®, true); + /* Note: ld_field is special as it uses one of the src regs as dst */ + err = swreg_to_restricted(dst, dst, src, ®, true); if (err) { nfp_prog->error = err; return; -- GitLab From 86e23494222f358138e3d2c337f57577b0893797 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 4 Sep 2017 20:40:22 +0200 Subject: [PATCH 1156/1507] ixgbe: add counter for times Rx pages gets allocated, not recycled The ixgbe driver have page recycle scheme based around the RX-ring queue, where a RX page is shared between two packets. Based on the refcnt, the driver can determine if the RX-page is currently only used by a single packet, if so it can then directly refill/recycle the RX-slot by with the opposite "side" of the page. While this is a clever trick, it is hard to determine when this recycling is successful and when it fails. Adding a counter, which is available via ethtool --statistics as 'alloc_rx_page'. Which counts the number of times the recycle fails and the real page allocator is invoked. When interpreting the stats, do remember that every alloc will serve two packets. The counter is collected per rx_ring, but is summed and ethtool exported as 'alloc_rx_page'. It would be relevant to know what rx_ring that cannot keep up, but that can be exported later if someone experience a need for this. Signed-off-by: Jesper Dangaard Brouer Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 ++ drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++++ 3 files changed, 7 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index dd5578756ae0f..008d0085e01f4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -275,6 +275,7 @@ struct ixgbe_rx_queue_stats { u64 rsc_count; u64 rsc_flush; u64 non_eop_descs; + u64 alloc_rx_page; u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; u64 csum_err; @@ -655,6 +656,7 @@ struct ixgbe_adapter { u64 rsc_total_count; u64 rsc_total_flush; u64 non_eop_descs; + u32 alloc_rx_page; u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 6d89f28cae062..de5704c7dd1bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -104,6 +104,7 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { {"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)}, {"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)}, {"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)}, + {"alloc_rx_page", IXGBE_STAT(alloc_rx_page)}, {"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)}, {"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)}, {"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)}, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d83cc9d34de33..211074934d5bd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1620,6 +1620,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, bi->page = page; bi->page_offset = ixgbe_rx_offset(rx_ring); bi->pagecnt_bias = 1; + rx_ring->rx_stats.alloc_rx_page++; return true; } @@ -6794,6 +6795,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot; u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0; u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; if (test_bit(__IXGBE_DOWN, &adapter->state) || @@ -6814,6 +6816,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct ixgbe_ring *rx_ring = adapter->rx_ring[i]; non_eop_descs += rx_ring->rx_stats.non_eop_descs; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; hw_csum_rx_error += rx_ring->rx_stats.csum_err; @@ -6821,6 +6824,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) packets += rx_ring->stats.packets; } adapter->non_eop_descs = non_eop_descs; + adapter->alloc_rx_page = alloc_rx_page; adapter->alloc_rx_page_failed = alloc_rx_page_failed; adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; adapter->hw_csum_rx_error = hw_csum_rx_error; -- GitLab From dcfd6b839c998bc9838e2a47f44f37afbdf3099c Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Mon, 11 Sep 2017 14:21:31 -0700 Subject: [PATCH 1157/1507] ixgbe: fix use of uninitialized padding This patch is resolving Coverity hits where padding in a structure could be used uninitialized. - Initialize fwd_cmd.pad/2 before ixgbe_calculate_checksum() - Initialize buffer.pad2/3 before ixgbe_hic_unlocked() Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 4 ++-- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 2c19070d2a0b0..041940c4bb2b6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3800,10 +3800,10 @@ s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, fw_cmd.ver_build = build; fw_cmd.ver_sub = sub; fw_cmd.hdr.checksum = 0; - fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, - (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); fw_cmd.pad = 0; fw_cmd.pad2 = 0; + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { ret_val = ixgbe_host_interface_command(hw, &fw_cmd, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 8cea53b62e1b7..cb7da5f9c4da7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -900,6 +900,8 @@ static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, /* convert offset from words to bytes */ buffer.address = cpu_to_be32((offset + current_word) * 2); buffer.length = cpu_to_be16(words_to_read * 2); + buffer.pad2 = 0; + buffer.pad3 = 0; status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), IXGBE_HI_COMMAND_TIMEOUT); -- GitLab From c3aec05dfe2cb1bc1fdf3593da82bc987211338a Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Mon, 11 Sep 2017 14:21:36 -0700 Subject: [PATCH 1158/1507] ixgbe: fix the FWSM.PT check in ixgbe_mng_present() Bits other than FWSM.PT can be set in IXGBE_SWFW_MODE_MASK making the previous check invalid. Change the check for MNG present to be only based on FWSM.PT bit. Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 041940c4bb2b6..4e5c92dea8693 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -4100,8 +4100,8 @@ bool ixgbe_mng_present(struct ixgbe_hw *hw) return false; fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); - fwsm &= IXGBE_FWSM_MODE_MASK; - return fwsm == IXGBE_FWSM_FW_MODE_PT; + + return !!(fwsm & IXGBE_FWSM_FW_MODE_PT); } /** -- GitLab From b4ded8327fea82b53fcec39e0845011246d020f4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 25 Sep 2017 14:55:36 -0700 Subject: [PATCH 1159/1507] ixgbe: Update adaptive ITR algorithm The following change is meant to update the adaptive ITR algorithm to better support the needs of the network. Specifically with this change what I have done is make it so that our ITR algorithm will try to prevent either starving a socket buffer for memory in the case of Tx, or overrunning an Rx socket buffer on receive. In addition a side effect of the calculations used is that we should function better with new features such as XDP which can handle small packets at high rates without needing to lock us into NAPI polling mode. Signed-off-by: Alexander Duyck Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 7 + drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 11 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 215 +++++++++++++----- 3 files changed, 178 insertions(+), 55 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 008d0085e01f4..468c3555a6298 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -435,8 +435,15 @@ static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) } #define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) +#define IXGBE_ITR_ADAPTIVE_MIN_INC 2 +#define IXGBE_ITR_ADAPTIVE_MIN_USECS 10 +#define IXGBE_ITR_ADAPTIVE_MAX_USECS 126 +#define IXGBE_ITR_ADAPTIVE_LATENCY 0x80 +#define IXGBE_ITR_ADAPTIVE_BULK 0x00 + struct ixgbe_ring_container { struct ixgbe_ring *ring; /* pointer to linked list of rings */ + unsigned long next_update; /* jiffies value of last update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ u16 work_limit; /* total work allowed per interrupt */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index f1bfae0c41d0c..8e2a957aca187 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -806,6 +806,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring, ring->next = head->ring; head->ring = ring; head->count++; + head->next_update = jiffies + 1; } /** @@ -879,8 +880,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, /* initialize work limits */ q_vector->tx.work_limit = adapter->tx_work_limit; - /* initialize pointer to rings */ - ring = q_vector->ring; + /* Initialize setting for adaptive ITR */ + q_vector->tx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; /* intialize ITR */ if (txr_count && !rxr_count) { @@ -897,6 +901,9 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, q_vector->itr = adapter->rx_itr_setting; } + /* initialize pointer to rings */ + ring = q_vector->ring; + while (txr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 211074934d5bd..5e2686d106dbb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2540,50 +2540,174 @@ enum latency_range { static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, struct ixgbe_ring_container *ring_container) { - int bytes = ring_container->total_bytes; - int packets = ring_container->total_packets; - u32 timepassed_us; - u64 bytes_perint; - u8 itr_setting = ring_container->itr; + unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + unsigned int avg_wire_size, packets, bytes; + unsigned long next_update = jiffies; - if (packets == 0) + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!ring_container->ring) return; - /* simple throttlerate management - * 0-10MB/s lowest (100000 ints/s) - * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (12000 ints/s) + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. */ - /* what was last interrupt timeslice? */ - timepassed_us = q_vector->itr >> 2; - if (timepassed_us == 0) - return; + if (time_after(next_update, ring_container->next_update)) + goto clear_counts; - bytes_perint = bytes / timepassed_us; /* bytes/usec */ + packets = ring_container->total_packets; - switch (itr_setting) { - case lowest_latency: - if (bytes_perint > 10) - itr_setting = low_latency; - break; - case low_latency: - if (bytes_perint > 20) - itr_setting = bulk_latency; - else if (bytes_perint <= 10) - itr_setting = lowest_latency; + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * When this occurs just tick up our delay by the minimum value + * and hope that this extra delay will prevent us from being called + * without any work on our queue. + */ + if (!packets) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY; + goto clear_counts; + } + + bytes = ring_container->total_bytes; + + /* If packets are less than 4 or bytes are less than 9000 assume + * insufficient data to use bulk rate limiting approach. We are + * likely latency driven. + */ + if (packets < 4 && bytes < 9000) { + itr = IXGBE_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + + /* Between 4 and 48 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. + */ + if (packets < 48) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + goto clear_counts; + } + + /* Between 48 and 96 is our "goldilocks" zone where we are working + * out "just right". Just report that our current ITR is good for us. + */ + if (packets < 96) { + itr = q_vector->itr >> 2; + goto clear_counts; + } + + /* If packet count is 96 or greater we are likely looking at a slight + * overrun of the delay we want. Try halving our delay to see if that + * will cut the number of packets in half per interrupt. + */ + if (packets < 256) { + itr = q_vector->itr >> 3; + if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS) + itr = IXGBE_ITR_ADAPTIVE_MIN_USECS; + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since number + * of packets is 256 or greater. We are just going to have to compute + * a value and try to bring the count under control, though for smaller + * packet sizes there isn't much we can do as NAPI polling will likely + * be kicking in sooner rather than later. + */ + itr = IXGBE_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. + */ + if (avg_wire_size <= 60) { + /* Start at 50k ints/sec */ + avg_wire_size = 5120; + } else if (avg_wire_size <= 316) { + /* 50K ints/sec to 16K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 2720; + } else if (avg_wire_size <= 1084) { + /* 16K ints/sec to 9.2K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size <= 1980) { + /* 9.2K ints/sec to 8K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 8K ints/sec */ + avg_wire_size = 32256; + } + + /* If we are in low latency mode half our delay which doubles the rate + * to somewhere between 100K to 16K ints/sec + */ + if (itr & IXGBE_ITR_ADAPTIVE_LATENCY) + avg_wire_size >>= 1; + + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + switch (q_vector->adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + case IXGBE_LINK_SPEED_100_FULL: + default: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 256) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; - case bulk_latency: - if (bytes_perint <= 20) - itr_setting = low_latency; + case IXGBE_LINK_SPEED_2_5GB_FULL: + case IXGBE_LINK_SPEED_1GB_FULL: + case IXGBE_LINK_SPEED_10_FULL: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 64) * + IXGBE_ITR_ADAPTIVE_MIN_INC; break; } - /* clear work counters since we have the values we need */ +clear_counts: + /* write back value */ + ring_container->itr = itr; + + /* next update should occur within next jiffy */ + ring_container->next_update = next_update + 1; + ring_container->total_bytes = 0; ring_container->total_packets = 0; - - /* write updated itr to ring container */ - ring_container->itr = itr_setting; } /** @@ -2625,34 +2749,19 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) { - u32 new_itr = q_vector->itr; - u8 current_itr; + u32 new_itr; ixgbe_update_itr(q_vector, &q_vector->tx); ixgbe_update_itr(q_vector, &q_vector->rx); - current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + /* use the smallest value of new ITR delay calculations */ + new_itr = min(q_vector->rx.itr, q_vector->tx.itr); - switch (current_itr) { - /* counts and packets in update_itr are dependent on these numbers */ - case lowest_latency: - new_itr = IXGBE_100K_ITR; - break; - case low_latency: - new_itr = IXGBE_20K_ITR; - break; - case bulk_latency: - new_itr = IXGBE_12K_ITR; - break; - default: - break; - } + /* Clear latency flag if set, shift into correct position */ + new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY; + new_itr <<= 2; if (new_itr != q_vector->itr) { - /* do an exponential smoothing */ - new_itr = (10 * new_itr * q_vector->itr) / - ((9 * new_itr) + q_vector->itr); - /* save the algorithm value here */ q_vector->itr = new_itr; -- GitLab From b64666ae00327efe53613fc180df6ffbeee1d8d1 Mon Sep 17 00:00:00 2001 From: Emil Tantilov Date: Fri, 29 Sep 2017 10:55:42 -0700 Subject: [PATCH 1160/1507] ixgbe: fix crash when injecting AER after failed reset In case where AER recovery fails the device is left in a down state. Consecutive AER error injection can lead to a double IRQ free. Signed-off-by: Emil Tantilov Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5e2686d106dbb..c6f9da7990c77 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10861,6 +10861,9 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) return PCI_ERS_RESULT_DISCONNECT; + if (!netif_device_present(netdev)) + return PCI_ERS_RESULT_DISCONNECT; + rtnl_lock(); netif_device_detach(netdev); -- GitLab From 77041420751fe6d4acf2103b245dcc2b4b7b8360 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 9 Oct 2017 11:15:31 +0200 Subject: [PATCH 1161/1507] net: bridge: Notify on bridge device mrouter state changes Add the SWITCHDEV_ATTR_ID_BRIDGE_MROUTER switchdev notification type, used to indicate whether the bridge is or isn't mrouter. Notify when the bridge changes its state, similarly to the already existing bridged port mrouter notifications. The notification uses the switchdev_attr.u.mrouter boolean flag to indicate the current bridge mrouter status. Thus, it only indicates whether the bridge is currently used as an mrouter or not, and does not indicate the exact mrouter state of the bridge (learning, permanent, etc.). Signed-off-by: Yotam Gigi Signed-off-by: Jiri Pirko Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + net/bridge/br_multicast.c | 38 +++++++++++++++++++++++++++++++++++--- 2 files changed, 36 insertions(+), 3 deletions(-) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d767b79918871..d756fbe46625d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -51,6 +51,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, + SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, }; struct switchdev_attr { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 8dc5c8d69bcd7..bd50550dd4caa 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -859,8 +859,32 @@ static void br_multicast_router_expired(unsigned long data) spin_unlock(&br->multicast_lock); } +static void br_mc_router_state_change(struct net_bridge *p, + bool is_mc_router) +{ + struct switchdev_attr attr = { + .orig_dev = p->dev, + .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, + .flags = SWITCHDEV_F_DEFER, + .u.mrouter = is_mc_router, + }; + + switchdev_port_attr_set(p->dev, &attr); +} + static void br_multicast_local_router_expired(unsigned long data) { + struct net_bridge *br = (struct net_bridge *)data; + + spin_lock(&br->multicast_lock); + if (br->multicast_router == MDB_RTR_TYPE_DISABLED || + br->multicast_router == MDB_RTR_TYPE_PERM || + timer_pending(&br->multicast_router_timer)) + goto out; + + br_mc_router_state_change(br, false); +out: + spin_unlock(&br->multicast_lock); } static void br_multicast_querier_expired(struct net_bridge *br, @@ -1364,9 +1388,12 @@ static void br_multicast_mark_router(struct net_bridge *br, unsigned long now = jiffies; if (!port) { - if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) + if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { + if (!timer_pending(&br->multicast_router_timer)) + br_mc_router_state_change(br, true); mod_timer(&br->multicast_router_timer, now + br->multicast_querier_interval); + } return; } @@ -1952,7 +1979,7 @@ void br_multicast_init(struct net_bridge *br) spin_lock_init(&br->multicast_lock); setup_timer(&br->multicast_router_timer, - br_multicast_local_router_expired, 0); + br_multicast_local_router_expired, (unsigned long)br); setup_timer(&br->ip4_other_query.timer, br_ip4_multicast_querier_expired, (unsigned long)br); setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, @@ -2042,9 +2069,14 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: + br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM); del_timer(&br->multicast_router_timer); - /* fall through */ + br->multicast_router = val; + err = 0; + break; case MDB_RTR_TYPE_TEMP_QUERY: + if (br->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) + br_mc_router_state_change(br, false); br->multicast_router = val; err = 0; break; -- GitLab From 0912bda436388a02c72164b4b490b578e64c012e Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 9 Oct 2017 11:15:32 +0200 Subject: [PATCH 1162/1507] net: bridge: Export bridge multicast router state Add an access function that, given a bridge netdevice, returns whether the bridge device is currently an mrouter or not. The function uses the already existing br_multicast_is_router function to check that. This function is needed in order to allow ports that join an already existing bridge to know the current mrouter state of the bridge device. Together with the bridge device mrouter ports switchdev notifications, it is possible to have full offloading of the semantics of the bridge device mcast router state. Due to the fact that the bridge multicast router status can change in packet RX path, take the multicast_router bridge spinlock to protect the read. Signed-off-by: Yotam Gigi Reviewed-by: Nogah Frankel Reviewed-by: Nikolay Aleksandrov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 5 +++++ net/bridge/br_multicast.c | 12 ++++++++++++ 2 files changed, 17 insertions(+) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 316ee113a2201..02639ebea2f06 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -64,6 +64,7 @@ int br_multicast_list_adjacent(struct net_device *dev, bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); +bool br_multicast_router(const struct net_device *dev); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -84,6 +85,10 @@ static inline bool br_multicast_enabled(const struct net_device *dev) { return false; } +static inline bool br_multicast_router(const struct net_device *dev) +{ + return false; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index bd50550dd4caa..7947e0436e186 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2216,6 +2216,18 @@ bool br_multicast_enabled(const struct net_device *dev) } EXPORT_SYMBOL_GPL(br_multicast_enabled); +bool br_multicast_router(const struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + bool is_router; + + spin_lock_bh(&br->multicast_lock); + is_router = br_multicast_is_router(br); + spin_unlock_bh(&br->multicast_lock); + return is_router; +} +EXPORT_SYMBOL_GPL(br_multicast_router); + int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { unsigned long max_delay; -- GitLab From b35750f19102271485af9092b800863164dd4be0 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 9 Oct 2017 11:15:33 +0200 Subject: [PATCH 1163/1507] mlxsw: spectrum: router: Export the mlxsw_sp_router_port function In Spectrum hardware, the router port is a virtual port that is the gateway to the routing mechanism. Hence, in order for a packet to be L3 forwarded, it must first be L2 forwarded to the router port inside the hardware. Further patches in this patchset are going to introduce support in bridge device used as an mrouter port. In this case, the router port index will be needed in order to update the MDB entries to include the router port. Thus, export the mlxsw_sp_router_port function, which returns the index of the Spectrum router port. Signed-off-by: Yotam Gigi Reviewed-by: Nogah Frankel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e0f8ea4ed7af2..a072903f2c4e0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -5957,7 +5957,7 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); } -static u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) +u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp) { return mlxsw_core_max_ports(mlxsw_sp->core) + 1; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 3d449180b035f..3f2d840cb2852 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -70,6 +70,7 @@ u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif); u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif); u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif); int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif); +u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp); const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif); int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, -- GitLab From c4db953f00f09003519ac1fb078f3b5f57b32e3c Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 9 Oct 2017 11:15:34 +0200 Subject: [PATCH 1164/1507] mlxsw: spectrum_switchdev: Add support for router port in SMID entries In Spectrum, MDB entries point to MID entries, that indicate which ports a packet should be forwarded to. Add the support in creating MID entries that forward the packet to the Spectrum router port. This will be later used to handle the bridge mrouter port switchdev notifications. Signed-off-by: Yotam Gigi Reviewed-by: Nogah Frankel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 2cfdf22a145ff..4b4584f8522aa 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -49,6 +49,7 @@ #include #include +#include "spectrum_router.h" #include "spectrum.h" #include "core.h" #include "reg.h" @@ -1243,7 +1244,8 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, } static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx, - long *ports_bitmap) + long *ports_bitmap, + bool set_router_port) { char *smid_pl; int err, i; @@ -1258,9 +1260,15 @@ static int mlxsw_sp_port_smid_full_entry(struct mlxsw_sp *mlxsw_sp, u16 mid_idx, mlxsw_reg_smid_port_mask_set(smid_pl, i, 1); } + mlxsw_reg_smid_port_mask_set(smid_pl, + mlxsw_sp_router_port(mlxsw_sp), 1); + for_each_set_bit(i, ports_bitmap, mlxsw_core_max_ports(mlxsw_sp->core)) mlxsw_reg_smid_port_set(smid_pl, i, 1); + mlxsw_reg_smid_port_set(smid_pl, mlxsw_sp_router_port(mlxsw_sp), + set_router_port); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl); kfree(smid_pl); return err; @@ -1364,7 +1372,8 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_mc_get_mrouters_bitmap(flood_bitmap, bridge_device, mlxsw_sp); mid->mid = mid_idx; - err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap); + err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap, + false); kfree(flood_bitmap); if (err) return false; -- GitLab From 593bc28ae211b864e7e0720ffc65a14cc5cff101 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Mon, 9 Oct 2017 11:15:35 +0200 Subject: [PATCH 1165/1507] mlxsw: spectrum_switchdev: Support bridge mrouter notifications Support the SWITCHDEV_ATTR_ID_BRIDGE_MROUTER port attribute switchdev notification. To do that, add the mrouter flag to struct mlxsw_sp_bridge_device, which indicates whether the bridge device was set to be mrouter port. This field is set when: - A new bridge is created, where the value is taken from the kernel bridge value. - A switchdev SWITCHDEV_ATTR_ID_BRIDGE_MROUTER notification is sent. In addition, change the bridge MID entries to include the router port when the bridge device is configured to be mrouter port. The MID entries are updated in the following cases: - When a new MID entry is created, update the router port according to the bridge mrouter state. - When a SWITCHDEV_ATTR_ID_BRIDGE_MROUTER notification is sent, update all the bridge's MID entries. This is aligned with the case where a bridge slave is configured to be mrouter port. Signed-off-by: Yotam Gigi Reviewed-by: Nogah Frankel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../mellanox/mlxsw/spectrum_switchdev.c | 65 ++++++++++++++++++- 1 file changed, 63 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 4b4584f8522aa..7b8548e25ae73 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -80,7 +80,8 @@ struct mlxsw_sp_bridge_device { struct list_head ports_list; struct list_head mids_list; u8 vlan_enabled:1, - multicast_enabled:1; + multicast_enabled:1, + mrouter:1; const struct mlxsw_sp_bridge_ops *ops; }; @@ -171,6 +172,7 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, bridge_device->dev = br_dev; bridge_device->vlan_enabled = vlan_enabled; bridge_device->multicast_enabled = br_multicast_enabled(br_dev); + bridge_device->mrouter = br_multicast_router(br_dev); INIT_LIST_HEAD(&bridge_device->ports_list); if (vlan_enabled) { bridge->vlan_enabled_exists = true; @@ -813,6 +815,60 @@ static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } +static int mlxsw_sp_smid_router_port_set(struct mlxsw_sp *mlxsw_sp, + u16 mid_idx, bool add) +{ + char *smid_pl; + int err; + + smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL); + if (!smid_pl) + return -ENOMEM; + + mlxsw_reg_smid_pack(smid_pl, mid_idx, + mlxsw_sp_router_port(mlxsw_sp), add); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(smid), smid_pl); + kfree(smid_pl); + return err; +} + +static void +mlxsw_sp_bridge_mrouter_update_mdb(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_bridge_device *bridge_device, + bool add) +{ + struct mlxsw_sp_mid *mid; + + list_for_each_entry(mid, &bridge_device->mids_list, list) + mlxsw_sp_smid_router_port_set(mlxsw_sp, mid->mid, add); +} + +static int +mlxsw_sp_port_attr_br_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port, + struct switchdev_trans *trans, + struct net_device *orig_dev, + bool is_mrouter) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_bridge_device *bridge_device; + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + /* It's possible we failed to enslave the port, yet this + * operation is executed due to it being deferred. + */ + bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, orig_dev); + if (!bridge_device) + return 0; + + if (bridge_device->mrouter != is_mrouter) + mlxsw_sp_bridge_mrouter_update_mdb(mlxsw_sp, bridge_device, + is_mrouter); + bridge_device->mrouter = is_mrouter; + return 0; +} + static int mlxsw_sp_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) @@ -850,6 +906,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, attr->orig_dev, attr->u.mc_disabled); break; + case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: + err = mlxsw_sp_port_attr_br_mrouter_set(mlxsw_sp_port, trans, + attr->orig_dev, + attr->u.mrouter); + break; default: err = -EOPNOTSUPP; break; @@ -1373,7 +1434,7 @@ mlxsw_sp_mc_write_mdb_entry(struct mlxsw_sp *mlxsw_sp, mid->mid = mid_idx; err = mlxsw_sp_port_smid_full_entry(mlxsw_sp, mid_idx, flood_bitmap, - false); + bridge_device->mrouter); kfree(flood_bitmap); if (err) return false; -- GitLab From f5823fe6897c444265ef3919d8684b647eef904f Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:43 +0300 Subject: [PATCH 1166/1507] qed: Add ll2 option to limit the number of bds per packet iWARP uses 3 ll2 connections, the maximum number of bds is known during connection setup. This patch modifies the static array in the ll2_tx_packet descriptor to be a flexible array and significantlly reduces memory size. In addition, some redundant fields in the ll2_tx_packet were removed, which also contributed to decreasing the descriptor size. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 29 ++++++++++++++++------- drivers/net/ethernet/qlogic/qed/qed_ll2.h | 9 +++---- 2 files changed, 24 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 250afa5486cfa..75af40a7690a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1105,6 +1105,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_info) { struct qed_ll2_tx_packet *p_descq; + u32 desc_size; u32 capacity; int rc = 0; @@ -1122,13 +1123,17 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn, goto out; capacity = qed_chain_get_capacity(&p_ll2_info->tx_queue.txq_chain); - p_descq = kcalloc(capacity, sizeof(struct qed_ll2_tx_packet), - GFP_KERNEL); + /* First element is part of the packet, rest are flexibly added */ + desc_size = (sizeof(*p_descq) + + (p_ll2_info->input.tx_max_bds_per_packet - 1) * + sizeof(p_descq->bds_set)); + + p_descq = kcalloc(capacity, desc_size, GFP_KERNEL); if (!p_descq) { rc = -ENOMEM; goto out; } - p_ll2_info->tx_queue.descq_array = p_descq; + p_ll2_info->tx_queue.descq_mem = p_descq; DP_VERBOSE(p_hwfn, QED_MSG_LL2, "Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n", @@ -1359,11 +1364,13 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) { struct qed_hwfn *p_hwfn = cxt; struct qed_ll2_info *p_ll2_conn; + struct qed_ll2_tx_packet *p_pkt; struct qed_ll2_rx_queue *p_rx; struct qed_ll2_tx_queue *p_tx; struct qed_ptt *p_ptt; int rc = -EINVAL; u32 i, capacity; + u32 desc_size; u8 qid; p_ptt = qed_ptt_acquire(p_hwfn); @@ -1397,9 +1404,15 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) INIT_LIST_HEAD(&p_tx->sending_descq); spin_lock_init(&p_tx->lock); capacity = qed_chain_get_capacity(&p_tx->txq_chain); - for (i = 0; i < capacity; i++) - list_add_tail(&p_tx->descq_array[i].list_entry, - &p_tx->free_descq); + /* First element is part of the packet, rest are flexibly added */ + desc_size = (sizeof(*p_pkt) + + (p_ll2_conn->input.tx_max_bds_per_packet - 1) * + sizeof(p_pkt->bds_set)); + + for (i = 0; i < capacity; i++) { + p_pkt = p_tx->descq_mem + desc_size * i; + list_add_tail(&p_pkt->list_entry, &p_tx->free_descq); + } p_tx->cur_completing_bd_idx = 0; p_tx->bds_idx = 0; p_tx->b_completing_packet = false; @@ -1698,7 +1711,7 @@ int qed_ll2_prepare_tx_packet(void *cxt, p_tx = &p_ll2_conn->tx_queue; p_tx_chain = &p_tx->txq_chain; - if (pkt->num_of_bds > CORE_LL2_TX_MAX_BDS_PER_PACKET) + if (pkt->num_of_bds > p_ll2_conn->input.tx_max_bds_per_packet) return -EIO; spin_lock_irqsave(&p_tx->lock, flags); @@ -1858,7 +1871,7 @@ void qed_ll2_release_connection(void *cxt, u8 connection_handle) qed_int_unregister_cb(p_hwfn, p_ll2_conn->tx_queue.tx_sb_index); } - kfree(p_ll2_conn->tx_queue.descq_array); + kfree(p_ll2_conn->tx_queue.descq_mem); qed_chain_free(p_hwfn->cdev, &p_ll2_conn->tx_queue.txq_chain); kfree(p_ll2_conn->rx_queue.descq_array); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index a822528e9c630..9bdd08f15c793 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -63,17 +63,14 @@ struct qed_ll2_rx_packet { struct qed_ll2_tx_packet { struct list_head list_entry; u16 bd_used; - u16 vlan; - u16 l4_hdr_offset_w; - u8 bd_flags; bool notify_fw; void *cookie; - + /* Flexible Array of bds_set determined by max_bds_per_packet */ struct { struct core_tx_bd *txq_bd; dma_addr_t tx_frag; u16 frag_len; - } bds_set[ETH_TX_MAX_BDS_PER_NON_LSO_PACKET]; + } bds_set[1]; }; struct qed_ll2_rx_queue { @@ -101,7 +98,7 @@ struct qed_ll2_tx_queue { struct list_head active_descq; struct list_head free_descq; struct list_head sending_descq; - struct qed_ll2_tx_packet *descq_array; + void *descq_mem; /* memory for variable sized qed_ll2_tx_packet*/ struct qed_ll2_tx_packet *cur_send_packet; struct qed_ll2_tx_packet cur_completing_packet; u16 cur_completing_bd_idx; -- GitLab From ed468ebee04ffba0231a8f50616bdb250752a891 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:44 +0300 Subject: [PATCH 1167/1507] qed: Add ll2 ability of opening a secondary queue When more than one ll2 queue is opened ( that is not an OOO queue ) ll2 code does not have enough information to determine whether the queue is the main one or not, so a new field is added to the acquire input data to expose the control of determining whether the queue is the main queue or a secondary queue. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 7 ++++++- drivers/net/ethernet/qlogic/qed/qed_ll2.h | 1 + include/linux/qed/qed_ll2_if.h | 1 + 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 75af40a7690a8..3c695da890dfd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -894,7 +894,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->drop_ttl0_flg = p_ll2_conn->input.rx_drop_ttl0_flg; p_ramrod->inner_vlan_removal_en = p_ll2_conn->input.rx_vlan_removal_en; p_ramrod->queue_id = p_ll2_conn->queue_id; - p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_OOO) ? 0 : 1; + p_ramrod->main_func_queue = p_ll2_conn->main_func_queue ? 1 : 0; if ((IS_MF_DEFAULT(p_hwfn) || IS_MF_SI(p_hwfn)) && p_ramrod->main_func_queue && (conn_type != QED_LL2_TYPE_ROCE) && @@ -1265,6 +1265,11 @@ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data) p_ll2_info->tx_dest = (data->input.tx_dest == QED_LL2_TX_DEST_NW) ? CORE_TX_DEST_NW : CORE_TX_DEST_LB; + if (data->input.conn_type == QED_LL2_TYPE_OOO || + data->input.secondary_queue) + p_ll2_info->main_func_queue = false; + else + p_ll2_info->main_func_queue = true; /* Correct maximum number of Tx BDs */ p_tx_max = &p_ll2_info->input.tx_max_bds_per_packet; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index 9bdd08f15c793..f65817012e972 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -121,6 +121,7 @@ struct qed_ll2_info { bool b_active; enum core_tx_dest tx_dest; u8 tx_stats_en; + bool main_func_queue; struct qed_ll2_rx_queue rx_queue; struct qed_ll2_tx_queue tx_queue; struct qed_ll2_cbs cbs; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 89fa0bbd54f32..d7cca590b743f 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -171,6 +171,7 @@ struct qed_ll2_acquire_data_inputs { enum qed_ll2_tx_dest tx_dest; enum qed_ll2_error_handle ai_err_packet_too_big; enum qed_ll2_error_handle ai_err_no_buf; + bool secondary_queue; u8 gsi_enable; }; -- GitLab From 77caa792f5d8e4ecc88eb1cf4b9c478c07e0ec57 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:45 +0300 Subject: [PATCH 1168/1507] qed: Add ll2 option for dropping a tx packet The option of sending a packet on the ll2 and dropping it exists in hardware and was not used until now, thus not exposed. The iWARP unaligned MPA flow requires this functionality for flushing the tx queue. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 16 ++++++++++++++-- include/linux/qed/qed_ll2_if.h | 1 + 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 3c695da890dfd..ad67d36956e84 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1597,8 +1597,20 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, roce_flavor = (pkt->qed_roce_flavor == QED_LL2_ROCE) ? CORE_ROCE : CORE_RROCE; - tx_dest = (pkt->tx_dest == QED_LL2_TX_DEST_NW) ? CORE_TX_DEST_NW - : CORE_TX_DEST_LB; + switch (pkt->tx_dest) { + case QED_LL2_TX_DEST_NW: + tx_dest = CORE_TX_DEST_NW; + break; + case QED_LL2_TX_DEST_LB: + tx_dest = CORE_TX_DEST_LB; + break; + case QED_LL2_TX_DEST_DROP: + tx_dest = CORE_TX_DEST_DROP; + break; + default: + tx_dest = CORE_TX_DEST_LB; + break; + } start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index d7cca590b743f..95fdf02a3bbe4 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -64,6 +64,7 @@ enum qed_ll2_roce_flavor_type { enum qed_ll2_tx_dest { QED_LL2_TX_DEST_NW, /* Light L2 TX Destination to the Network */ QED_LL2_TX_DEST_LB, /* Light L2 TX Destination to the Loopback */ + QED_LL2_TX_DEST_DROP, /* Light L2 Drop the TX packet */ QED_LL2_TX_DEST_MAX }; -- GitLab From 6df60fe703c348a507b0030b92c2947e68e1c589 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:46 +0300 Subject: [PATCH 1169/1507] qed: Fix initialization of ll2 offload feature enable_ip_cksum, enable_l4_cksum, calc_ip_len were added in commit stated below but not passed through to FW. This was OK until now as it wasn't used, but is required for the iWARP unaligned flow Fixes:7c7973b2ae27 ("qed: LL2 to use packed information for tx") Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index ad67d36956e84..6d144747111a0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1621,6 +1621,9 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, SET_FIELD(bd_data, CORE_TX_BD_DATA_START_BD, 0x1); SET_FIELD(bd_data, CORE_TX_BD_DATA_NBDS, pkt->num_of_bds); SET_FIELD(bd_data, CORE_TX_BD_DATA_ROCE_FLAV, roce_flavor); + SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_CSUM, !!(pkt->enable_ip_cksum)); + SET_FIELD(bd_data, CORE_TX_BD_DATA_L4_CSUM, !!(pkt->enable_l4_cksum)); + SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_LEN, !!(pkt->calc_ip_len)); start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data); DMA_REGPAIR_LE(start_bd->addr, pkt->first_frag); start_bd->nbytes = cpu_to_le16(pkt->first_frag_len); -- GitLab From 89d65113097072de7936a2aea2f819818a7c987a Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:47 +0300 Subject: [PATCH 1170/1507] qed: Add the source of a packet sent on an iWARP ll2 connection When a packet is sent back to iWARP FW via the tx ll2 connection the FW needs to know the source of the packet. Whether it is OOO or unaligned MPA related. Since OOO is implemented entirely inside the ll2 code (and shared with iSCSI), packets are marked as IN_ORDER inside the ll2 code. For unaligned mpa the value will be determined in the iWARP code and sent on the pkt->vlan field. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 6d144747111a0..8eb9645c880d2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1613,7 +1613,12 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, } start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); - start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); + if (QED_IS_IWARP_PERSONALITY(p_hwfn) && + p_ll2->input.conn_type == QED_LL2_TYPE_OOO) + start_bd->nw_vlan_or_lb_echo = + cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE); + else + start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, cpu_to_le16(pkt->l4_hdr_offset_w)); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest); -- GitLab From 6f34a284f36399501fcc034dc4522a2d8d9fa6c9 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:48 +0300 Subject: [PATCH 1171/1507] qed: Add LL2 slowpath handling For iWARP unaligned MPA flow, a slowpath event of flushing an MPA connection that entered an unaligned state is required. The flush ramrod is received on the ll2 queue, and a pre-registered callback function is called to handle the flush event. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 40 +++++++++++++++++++++-- include/linux/qed/qed_ll2_if.h | 5 +++ 2 files changed, 43 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 8eb9645c880d2..047f556ca62e7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -422,6 +422,41 @@ static void qed_ll2_rxq_parse_reg(struct qed_hwfn *p_hwfn, data->u.placement_offset = p_cqe->rx_cqe_fp.placement_offset; } +static int +qed_ll2_handle_slowpath(struct qed_hwfn *p_hwfn, + struct qed_ll2_info *p_ll2_conn, + union core_rx_cqe_union *p_cqe, + unsigned long *p_lock_flags) +{ + struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue; + struct core_rx_slow_path_cqe *sp_cqe; + + sp_cqe = &p_cqe->rx_cqe_sp; + if (sp_cqe->ramrod_cmd_id != CORE_RAMROD_RX_QUEUE_FLUSH) { + DP_NOTICE(p_hwfn, + "LL2 - unexpected Rx CQE slowpath ramrod_cmd_id:%d\n", + sp_cqe->ramrod_cmd_id); + return -EINVAL; + } + + if (!p_ll2_conn->cbs.slowpath_cb) { + DP_NOTICE(p_hwfn, + "LL2 - received RX_QUEUE_FLUSH but no callback was provided\n"); + return -EINVAL; + } + + spin_unlock_irqrestore(&p_rx->lock, *p_lock_flags); + + p_ll2_conn->cbs.slowpath_cb(p_ll2_conn->cbs.cookie, + p_ll2_conn->my_id, + le32_to_cpu(sp_cqe->opaque_data.data[0]), + le32_to_cpu(sp_cqe->opaque_data.data[1])); + + spin_lock_irqsave(&p_rx->lock, *p_lock_flags); + + return 0; +} + static int qed_ll2_rxq_handle_completion(struct qed_hwfn *p_hwfn, struct qed_ll2_info *p_ll2_conn, @@ -495,8 +530,8 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie) switch (cqe->rx_cqe_sp.type) { case CORE_RX_CQE_TYPE_SLOW_PATH: - DP_NOTICE(p_hwfn, "LL2 - unexpected Rx CQE slowpath\n"); - rc = -EINVAL; + rc = qed_ll2_handle_slowpath(p_hwfn, p_ll2_conn, + cqe, &flags); break; case CORE_RX_CQE_TYPE_GSI_OFFLOAD: case CORE_RX_CQE_TYPE_REGULAR: @@ -1214,6 +1249,7 @@ qed_ll2_set_cbs(struct qed_ll2_info *p_ll2_info, const struct qed_ll2_cbs *cbs) p_ll2_info->cbs.rx_release_cb = cbs->rx_release_cb; p_ll2_info->cbs.tx_comp_cb = cbs->tx_comp_cb; p_ll2_info->cbs.tx_release_cb = cbs->tx_release_cb; + p_ll2_info->cbs.slowpath_cb = cbs->slowpath_cb; p_ll2_info->cbs.cookie = cbs->cookie; return 0; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 95fdf02a3bbe4..e755954d85fd1 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -151,11 +151,16 @@ void (*qed_ll2_release_tx_packet_cb)(void *cxt, dma_addr_t first_frag_addr, bool b_last_fragment, bool b_last_packet); +typedef +void (*qed_ll2_slowpath_cb)(void *cxt, u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1); + struct qed_ll2_cbs { qed_ll2_complete_rx_packet_cb rx_comp_cb; qed_ll2_release_rx_packet_cb rx_release_cb; qed_ll2_complete_tx_packet_cb tx_comp_cb; qed_ll2_release_tx_packet_cb tx_release_cb; + qed_ll2_slowpath_cb slowpath_cb; void *cookie; }; -- GitLab From ae3488ff37dc4f21985111f442d26a8805e56d45 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:49 +0300 Subject: [PATCH 1172/1507] qed: Add ll2 connection for processing unaligned MPA packets This patch adds only the establishment and termination of the ll2 connection that handles unaligned MPA packets. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 65 +++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 1 + 2 files changed, 66 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 8fc9c811f6e32..f413621a67b0f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1713,6 +1713,19 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, return 0; } +/* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */ +#define QED_IWARP_MAX_BDS_PER_FPDU 3 +static void +qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) +{ + struct qed_iwarp_info *iwarp_info; + struct qed_hwfn *p_hwfn = cxt; + + iwarp_info = &p_hwfn->p_rdma_info->iwarp; + qed_iwarp_ll2_post_rx(p_hwfn, data->cookie, + iwarp_info->ll2_mpa_handle); +} + static void qed_iwarp_ll2_comp_syn_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) { @@ -1877,6 +1890,13 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, kfree(buffer); } +void +qed_iwarp_ll2_slowpath(void *cxt, + u8 connection_handle, + u32 opaque_data_0, u32 opaque_data_1) +{ +} + static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; @@ -1902,6 +1922,16 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; } + if (iwarp_info->ll2_mpa_handle != QED_IWARP_HANDLE_INVAL) { + rc = qed_ll2_terminate_connection(p_hwfn, + iwarp_info->ll2_mpa_handle); + if (rc) + DP_INFO(p_hwfn, "Failed to terminate mpa connection\n"); + + qed_ll2_release_connection(p_hwfn, iwarp_info->ll2_mpa_handle); + iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL; + } + qed_llh_remove_mac_filter(p_hwfn, p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr); return rc; @@ -1953,12 +1983,14 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; + u32 mpa_buff_size; u16 n_ooo_bufs; int rc = 0; iwarp_info = &p_hwfn->p_rdma_info->iwarp; iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL; iwarp_info->ll2_ooo_handle = QED_IWARP_HANDLE_INVAL; + iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL; iwarp_info->max_mtu = params->max_mtu; @@ -2029,6 +2061,39 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; + /* Start Unaligned MPA connection */ + cbs.rx_comp_cb = qed_iwarp_ll2_comp_mpa_pkt; + cbs.slowpath_cb = qed_iwarp_ll2_slowpath; + + memset(&data, 0, sizeof(data)); + data.input.conn_type = QED_LL2_TYPE_IWARP; + data.input.mtu = params->max_mtu; + /* FW requires that once a packet arrives OOO, it must have at + * least 2 rx buffers available on the unaligned connection + * for handling the case that it is a partial fpdu. + */ + data.input.rx_num_desc = n_ooo_bufs * 2; + data.input.tx_num_desc = data.input.rx_num_desc; + data.input.tx_max_bds_per_packet = QED_IWARP_MAX_BDS_PER_FPDU; + data.p_connection_handle = &iwarp_info->ll2_mpa_handle; + data.input.secondary_queue = true; + data.cbs = &cbs; + + rc = qed_ll2_acquire_connection(p_hwfn, &data); + if (rc) + goto err; + + rc = qed_ll2_establish_connection(p_hwfn, iwarp_info->ll2_mpa_handle); + if (rc) + goto err; + + mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); + rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, + data.input.rx_num_desc, + mpa_buff_size, + iwarp_info->ll2_mpa_handle); + if (rc) + goto err; return rc; err: qed_iwarp_ll2_stop(p_hwfn, p_ptt); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 9e2bfde894df1..9d33a1fa1758a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -73,6 +73,7 @@ struct qed_iwarp_info { u8 tcp_flags; u8 ll2_syn_handle; u8 ll2_ooo_handle; + u8 ll2_mpa_handle; u8 peer2peer; enum mpa_negotiation_mode mpa_rev; enum mpa_rtr_type rtr_type; -- GitLab From fcb39f6c10b24d2d16d4c2bdb4c256bc21b8a131 Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:50 +0300 Subject: [PATCH 1173/1507] qed: Add mpa buffer descriptors for storing and processing mpa fpdus The mpa buff is a descriptor for iwarp ll2 buffers that contains additional information required for aligining fpdu's. In some cases, an additional packet will arrive which will complete the alignment of a fpdu, but we won't be able to post the fpdu due to insufficient place on the tx ring. In this case we can't loose the data and require storing it for later. Processing is therefore done in two places, during rx completion, where we initialize a mpa buffer descriptor and add it to the pending list, and during tx-completion, since we free up an entry in the tx chain we can process any pending mpa packets. The mpa buff descriptors are pre-allocated since we have to ensure that we won't reach a state where we can't store an incoming unaligned packet. All packets received on the ll2 MUST be processed by the driver at some stage. Since they are preallocated, we hold a free list. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 116 ++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 11 ++ 2 files changed, 127 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index f413621a67b0f..efd4861c72e21 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1415,7 +1415,10 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn) void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn) { + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1); + kfree(iwarp_info->mpa_bufs); } int qed_iwarp_accept(void *rdma_cxt, struct qed_iwarp_accept_in *iparams) @@ -1715,13 +1718,104 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, /* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */ #define QED_IWARP_MAX_BDS_PER_FPDU 3 +static void +qed_iwarp_mpa_get_data(struct qed_hwfn *p_hwfn, + struct unaligned_opaque_data *curr_pkt, + u32 opaque_data0, u32 opaque_data1) +{ + u64 opaque_data; + + opaque_data = HILO_64(opaque_data1, opaque_data0); + *curr_pkt = *((struct unaligned_opaque_data *)&opaque_data); + + curr_pkt->first_mpa_offset = curr_pkt->tcp_payload_offset + + le16_to_cpu(curr_pkt->first_mpa_offset); + curr_pkt->cid = le32_to_cpu(curr_pkt->cid); +} + +/* This function is called when an unaligned or incomplete MPA packet arrives + * driver needs to align the packet, perhaps using previous data and send + * it down to FW once it is aligned. + */ +static int +qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_ll2_mpa_buf *mpa_buf) +{ + struct qed_iwarp_ll2_buff *buf = mpa_buf->ll2_buf; + int rc = -EINVAL; + + qed_iwarp_ll2_post_rx(p_hwfn, + buf, + p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle); + return rc; +} + +static void qed_iwarp_process_pending_pkts(struct qed_hwfn *p_hwfn) +{ + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + struct qed_iwarp_ll2_mpa_buf *mpa_buf = NULL; + int rc; + + while (!list_empty(&iwarp_info->mpa_buf_pending_list)) { + mpa_buf = list_first_entry(&iwarp_info->mpa_buf_pending_list, + struct qed_iwarp_ll2_mpa_buf, + list_entry); + + rc = qed_iwarp_process_mpa_pkt(p_hwfn, mpa_buf); + + /* busy means break and continue processing later, don't + * remove the buf from the pending list. + */ + if (rc == -EBUSY) + break; + + list_del(&mpa_buf->list_entry); + list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_list); + + if (rc) { /* different error, don't continue */ + DP_NOTICE(p_hwfn, "process pkts failed rc=%d\n", rc); + break; + } + } +} + static void qed_iwarp_ll2_comp_mpa_pkt(void *cxt, struct qed_ll2_comp_rx_data *data) { + struct qed_iwarp_ll2_mpa_buf *mpa_buf; struct qed_iwarp_info *iwarp_info; struct qed_hwfn *p_hwfn = cxt; iwarp_info = &p_hwfn->p_rdma_info->iwarp; + mpa_buf = list_first_entry(&iwarp_info->mpa_buf_list, + struct qed_iwarp_ll2_mpa_buf, list_entry); + if (!mpa_buf) { + DP_ERR(p_hwfn, "No free mpa buf\n"); + goto err; + } + + list_del(&mpa_buf->list_entry); + qed_iwarp_mpa_get_data(p_hwfn, &mpa_buf->data, + data->opaque_data_0, data->opaque_data_1); + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "LL2 MPA CompRx payload_len:0x%x\tfirst_mpa_offset:0x%x\ttcp_payload_offset:0x%x\tflags:0x%x\tcid:0x%x\n", + data->length.packet_length, mpa_buf->data.first_mpa_offset, + mpa_buf->data.tcp_payload_offset, mpa_buf->data.flags, + mpa_buf->data.cid); + + mpa_buf->ll2_buf = data->cookie; + mpa_buf->tcp_payload_len = data->length.packet_length - + mpa_buf->data.first_mpa_offset; + mpa_buf->data.first_mpa_offset += data->u.placement_offset; + mpa_buf->placement_offset = data->u.placement_offset; + + list_add_tail(&mpa_buf->list_entry, &iwarp_info->mpa_buf_pending_list); + + qed_iwarp_process_pending_pkts(p_hwfn); + return; +err: qed_iwarp_ll2_post_rx(p_hwfn, data->cookie, iwarp_info->ll2_mpa_handle); } @@ -1872,6 +1966,11 @@ static void qed_iwarp_ll2_comp_tx_pkt(void *cxt, u8 connection_handle, /* this was originally an rx packet, post it back */ qed_iwarp_ll2_post_rx(p_hwfn, buffer, connection_handle); + + if (connection_handle == p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle) + qed_iwarp_process_pending_pkts(p_hwfn); + + return; } static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, @@ -1986,6 +2085,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, u32 mpa_buff_size; u16 n_ooo_bufs; int rc = 0; + int i; iwarp_info = &p_hwfn->p_rdma_info->iwarp; iwarp_info->ll2_syn_handle = QED_IWARP_HANDLE_INVAL; @@ -2094,6 +2194,22 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->ll2_mpa_handle); if (rc) goto err; + /* The mpa_bufs array serves for pending RX packets received on the + * mpa ll2 that don't have place on the tx ring and require later + * processing. We can't fail on allocation of such a struct therefore + * we allocate enough to take care of all rx packets + */ + iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc, + sizeof(*iwarp_info->mpa_bufs), + GFP_KERNEL); + if (!iwarp_info->mpa_bufs) + goto err; + + INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list); + INIT_LIST_HEAD(&iwarp_info->mpa_buf_list); + for (i = 0; i < data.input.rx_num_desc; i++) + list_add_tail(&iwarp_info->mpa_bufs[i].list_entry, + &iwarp_info->mpa_buf_list); return rc; err: qed_iwarp_ll2_stop(p_hwfn, p_ptt); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 9d33a1fa1758a..2c53fe46345ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -60,10 +60,20 @@ struct qed_iwarp_ll2_buff { u32 buff_size; }; +struct qed_iwarp_ll2_mpa_buf { + struct list_head list_entry; + struct qed_iwarp_ll2_buff *ll2_buf; + struct unaligned_opaque_data data; + u16 tcp_payload_len; + u8 placement_offset; +}; + struct qed_iwarp_info { struct list_head listen_list; /* qed_iwarp_listener */ struct list_head ep_list; /* qed_iwarp_ep */ struct list_head ep_free_list; /* pre-allocated ep's */ + struct list_head mpa_buf_list; /* list of mpa_bufs */ + struct list_head mpa_buf_pending_list; spinlock_t iw_lock; /* for iwarp resources */ spinlock_t qp_lock; /* for teardown races */ u32 rcv_wnd_scale; @@ -77,6 +87,7 @@ struct qed_iwarp_info { u8 peer2peer; enum mpa_negotiation_mode mpa_rev; enum mpa_rtr_type rtr_type; + struct qed_iwarp_ll2_mpa_buf *mpa_bufs; }; enum qed_iwarp_ep_state { -- GitLab From 469981b17a4f8ddac91837bd74ebc98578f2ddbf Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:51 +0300 Subject: [PATCH 1174/1507] qed: Add unaligned and packed packet processing The fpdu data structure is preallocated per connection. Each connection stores the current status of the connection: either nothing pending, or there is a partial fpdu that is waiting for the rest of the fpdu (incomplete bytes != 0). The same structure is also used for splitting a packet when there are packed fpdus. The structure is initialized with all data required for sending the fpdu back to the FW. A fpdu will always be spanned across a maximum of 3 tx bds. One for the header, one for the partial fdpu received and one for the remainder (unaligned) packet. In case of packed fpdu's, two fragments are used, one for the header and one for the data. Corner cases are not handled in the patch for clarity, and will be added as a separate patch. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 257 ++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 13 + 2 files changed, 270 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index efd4861c72e21..83b147fdacdeb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1419,6 +1419,7 @@ void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn) qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1); kfree(iwarp_info->mpa_bufs); + kfree(iwarp_info->partial_fpdus); } int qed_iwarp_accept(void *rdma_cxt, struct qed_iwarp_accept_in *iparams) @@ -1716,8 +1717,170 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, return 0; } +static struct qed_iwarp_fpdu *qed_iwarp_get_curr_fpdu(struct qed_hwfn *p_hwfn, + u16 cid) +{ + struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp; + struct qed_iwarp_fpdu *partial_fpdu; + u32 idx; + + idx = cid - qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_IWARP); + if (idx >= iwarp_info->max_num_partial_fpdus) { + DP_ERR(p_hwfn, "Invalid cid %x max_num_partial_fpdus=%x\n", cid, + iwarp_info->max_num_partial_fpdus); + return NULL; + } + + partial_fpdu = &iwarp_info->partial_fpdus[idx]; + + return partial_fpdu; +} + +enum qed_iwarp_mpa_pkt_type { + QED_IWARP_MPA_PKT_PACKED, + QED_IWARP_MPA_PKT_PARTIAL, + QED_IWARP_MPA_PKT_UNALIGNED +}; + +#define QED_IWARP_MPA_FPDU_LENGTH_SIZE (2) +#define QED_IWARP_MPA_CRC32_DIGEST_SIZE (4) + +/* Pad to multiple of 4 */ +#define QED_IWARP_PDU_DATA_LEN_WITH_PAD(data_len) ALIGN(data_len, 4) +#define QED_IWARP_FPDU_LEN_WITH_PAD(_mpa_len) \ + (QED_IWARP_PDU_DATA_LEN_WITH_PAD((_mpa_len) + \ + QED_IWARP_MPA_FPDU_LENGTH_SIZE) + \ + QED_IWARP_MPA_CRC32_DIGEST_SIZE) + /* fpdu can be fragmented over maximum 3 bds: header, partial mpa, unaligned */ #define QED_IWARP_MAX_BDS_PER_FPDU 3 + +char *pkt_type_str[] = { + "QED_IWARP_MPA_PKT_PACKED", + "QED_IWARP_MPA_PKT_PARTIAL", + "QED_IWARP_MPA_PKT_UNALIGNED" +}; + +static enum qed_iwarp_mpa_pkt_type +qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + u16 tcp_payload_len, u8 *mpa_data) +{ + enum qed_iwarp_mpa_pkt_type pkt_type; + u16 mpa_len; + + if (fpdu->incomplete_bytes) { + pkt_type = QED_IWARP_MPA_PKT_UNALIGNED; + goto out; + } + + mpa_len = ntohs(*((u16 *)(mpa_data))); + fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); + + if (fpdu->fpdu_length <= tcp_payload_len) + pkt_type = QED_IWARP_MPA_PKT_PACKED; + else + pkt_type = QED_IWARP_MPA_PKT_PARTIAL; + +out: + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "MPA_ALIGN: %s: fpdu_length=0x%x tcp_payload_len:0x%x\n", + pkt_type_str[pkt_type], fpdu->fpdu_length, tcp_payload_len); + + return pkt_type; +} + +static void +qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *pkt_data, + u16 tcp_payload_size, u8 placement_offset) +{ + fpdu->mpa_buf = buf; + fpdu->pkt_hdr = buf->data_phys_addr + placement_offset; + fpdu->pkt_hdr_size = pkt_data->tcp_payload_offset; + fpdu->mpa_frag = buf->data_phys_addr + pkt_data->first_mpa_offset; + fpdu->mpa_frag_virt = (u8 *)(buf->data) + pkt_data->first_mpa_offset; + + if (tcp_payload_size < fpdu->fpdu_length) + fpdu->incomplete_bytes = fpdu->fpdu_length - tcp_payload_size; + else + fpdu->incomplete_bytes = 0; /* complete fpdu */ + + fpdu->mpa_frag_len = fpdu->fpdu_length - fpdu->incomplete_bytes; +} + +static int +qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *curr_pkt, + struct qed_iwarp_ll2_buff *buf, + u16 tcp_payload_size, enum qed_iwarp_mpa_pkt_type pkt_type) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + + /* An unaligned packet means it's split over two tcp segments. So the + * complete packet requires 3 bds, one for the header, one for the + * part of the fpdu of the first tcp segment, and the last fragment + * will point to the remainder of the fpdu. A packed pdu, requires only + * two bds, one for the header and one for the data. + */ + tx_pkt.num_of_bds = (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED) ? 3 : 2; + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; /* offset in words */ + + /* Send the mpa_buf only with the last fpdu (in case of packed) */ + if (pkt_type == QED_IWARP_MPA_PKT_UNALIGNED || + tcp_payload_size <= fpdu->fpdu_length) + tx_pkt.cookie = fpdu->mpa_buf; + + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + tx_pkt.enable_ip_cksum = true; + tx_pkt.enable_l4_cksum = true; + tx_pkt.calc_ip_len = true; + /* vlan overload with enum iwarp_ll2_tx_queues */ + tx_pkt.vlan = IWARP_LL2_ALIGNED_TX_QUEUE; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + /* Set first fragment to header */ + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + goto out; + + /* Set second fragment to first part of packet */ + rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn, ll2_handle, + fpdu->mpa_frag, + fpdu->mpa_frag_len); + if (rc) + goto out; + + if (!fpdu->incomplete_bytes) + goto out; + + /* Set third fragment to second part of the packet */ + rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn, + ll2_handle, + buf->data_phys_addr + + curr_pkt->first_mpa_offset, + fpdu->incomplete_bytes); +out: + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Sent FPDU num_bds=%d first_frag_len=%x, mpa_frag_len=0x%x, incomplete_bytes:0x%x rc=%d\n", + tx_pkt.num_of_bds, + tx_pkt.first_frag_len, + fpdu->mpa_frag_len, + fpdu->incomplete_bytes, rc); + + return rc; +} + static void qed_iwarp_mpa_get_data(struct qed_hwfn *p_hwfn, struct unaligned_opaque_data *curr_pkt, @@ -1741,9 +1904,79 @@ static int qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, struct qed_iwarp_ll2_mpa_buf *mpa_buf) { + struct unaligned_opaque_data *curr_pkt = &mpa_buf->data; struct qed_iwarp_ll2_buff *buf = mpa_buf->ll2_buf; + enum qed_iwarp_mpa_pkt_type pkt_type; + struct qed_iwarp_fpdu *fpdu; int rc = -EINVAL; + u8 *mpa_data; + + fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, curr_pkt->cid & 0xffff); + if (!fpdu) { /* something corrupt with cid, post rx back */ + DP_ERR(p_hwfn, "Invalid cid, drop and post back to rx cid=%x\n", + curr_pkt->cid); + goto err; + } + do { + mpa_data = ((u8 *)(buf->data) + curr_pkt->first_mpa_offset); + + pkt_type = qed_iwarp_mpa_classify(p_hwfn, fpdu, + mpa_buf->tcp_payload_len, + mpa_data); + + switch (pkt_type) { + case QED_IWARP_MPA_PKT_PARTIAL: + qed_iwarp_init_fpdu(buf, fpdu, + curr_pkt, + mpa_buf->tcp_payload_len, + mpa_buf->placement_offset); + + mpa_buf->tcp_payload_len = 0; + break; + case QED_IWARP_MPA_PKT_PACKED: + qed_iwarp_init_fpdu(buf, fpdu, + curr_pkt, + mpa_buf->tcp_payload_len, + mpa_buf->placement_offset); + + rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, + mpa_buf->tcp_payload_len, + pkt_type); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:reset rc=%d\n", rc); + memset(fpdu, 0, sizeof(*fpdu)); + break; + } + + mpa_buf->tcp_payload_len -= fpdu->fpdu_length; + curr_pkt->first_mpa_offset += fpdu->fpdu_length; + break; + case QED_IWARP_MPA_PKT_UNALIGNED: + rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, + mpa_buf->tcp_payload_len, + pkt_type); + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:delay rc=%d\n", rc); + /* don't reset fpdu -> we need it for next + * classify + */ + break; + } + + mpa_buf->tcp_payload_len -= fpdu->incomplete_bytes; + curr_pkt->first_mpa_offset += fpdu->incomplete_bytes; + /* The framed PDU was sent - no more incomplete bytes */ + fpdu->incomplete_bytes = 0; + break; + } + } while (mpa_buf->tcp_payload_len && !rc); + + return rc; + +err: qed_iwarp_ll2_post_rx(p_hwfn, buf, p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle); @@ -1989,11 +2222,27 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, kfree(buffer); } +/* The only slowpath for iwarp ll2 is unalign flush. When this completion + * is received, need to reset the FPDU. + */ void qed_iwarp_ll2_slowpath(void *cxt, u8 connection_handle, u32 opaque_data_0, u32 opaque_data_1) { + struct unaligned_opaque_data unalign_data; + struct qed_hwfn *p_hwfn = cxt; + struct qed_iwarp_fpdu *fpdu; + + qed_iwarp_mpa_get_data(p_hwfn, &unalign_data, + opaque_data_0, opaque_data_1); + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "(0x%x) Flush fpdu\n", + unalign_data.cid); + + fpdu = qed_iwarp_get_curr_fpdu(p_hwfn, (u16)unalign_data.cid); + if (fpdu) + memset(fpdu, 0, sizeof(*fpdu)); } static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -2194,6 +2443,14 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->ll2_mpa_handle); if (rc) goto err; + + iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps, + sizeof(*iwarp_info->partial_fpdus), + GFP_KERNEL); + if (!iwarp_info->partial_fpdus) + goto err; + + iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; /* The mpa_bufs array serves for pending RX packets received on the * mpa ll2 that don't have place on the tx ring and require later * processing. We can't fail on allocation of such a struct therefore diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 2c53fe46345ce..858755cafd2bc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -68,6 +68,17 @@ struct qed_iwarp_ll2_mpa_buf { u8 placement_offset; }; +struct qed_iwarp_fpdu { + struct qed_iwarp_ll2_buff *mpa_buf; + void *mpa_frag_virt; + dma_addr_t mpa_frag; + dma_addr_t pkt_hdr; + u16 mpa_frag_len; + u16 fpdu_length; + u16 incomplete_bytes; + u8 pkt_hdr_size; +}; + struct qed_iwarp_info { struct list_head listen_list; /* qed_iwarp_listener */ struct list_head ep_list; /* qed_iwarp_ep */ @@ -87,7 +98,9 @@ struct qed_iwarp_info { u8 peer2peer; enum mpa_negotiation_mode mpa_rev; enum mpa_rtr_type rtr_type; + struct qed_iwarp_fpdu *partial_fpdus; struct qed_iwarp_ll2_mpa_buf *mpa_bufs; + u16 max_num_partial_fpdus; }; enum qed_iwarp_ep_state { -- GitLab From d531038eeb6dd25dbf88402f932bf0ea524de82e Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:52 +0300 Subject: [PATCH 1175/1507] qed: Add support for freeing two ll2 buffers for corner cases When posting a packet on the ll2 tx, we can provide a cookie that will be returned upon tx completion. This cookie is the ll2 iwarp buffer which is then reposted to the rx ring. Part of the unaligned mpa flow is determining when a buffer can be reposted. Each buffer needs to be sent only once as a cookie for on the tx ring. In packed fpdu case, only the last packet will be sent with the buffer, meaning we need to handle the case that a cookie can be NULL on tx complete. In addition, when a fpdu splits over two buffers, but there are no more fpdus on the second buffer, two buffers need to be provided as a cookie. To avoid changing the ll2 interface to provide two cookies, we introduce a piggy buf pointer, relevant for iWARP only, that holds a pointer to a second buffer that needs to be released during tx completion. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 25 +++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 1 + 2 files changed, 26 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 83b147fdacdeb..8b17369af9ef4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1846,6 +1846,12 @@ qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn, /* vlan overload with enum iwarp_ll2_tx_queues */ tx_pkt.vlan = IWARP_LL2_ALIGNED_TX_QUEUE; + /* special case of unaligned packet and not packed, need to send + * both buffers as cookie to release. + */ + if (tcp_payload_size == fpdu->incomplete_bytes) + fpdu->mpa_buf->piggy_buf = buf; + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; /* Set first fragment to header */ @@ -2195,9 +2201,19 @@ static void qed_iwarp_ll2_comp_tx_pkt(void *cxt, u8 connection_handle, bool b_last_fragment, bool b_last_packet) { struct qed_iwarp_ll2_buff *buffer = cookie; + struct qed_iwarp_ll2_buff *piggy; struct qed_hwfn *p_hwfn = cxt; + if (!buffer) /* can happen in packed mpa unaligned... */ + return; + /* this was originally an rx packet, post it back */ + piggy = buffer->piggy_buf; + if (piggy) { + buffer->piggy_buf = NULL; + qed_iwarp_ll2_post_rx(p_hwfn, piggy, connection_handle); + } + qed_iwarp_ll2_post_rx(p_hwfn, buffer, connection_handle); if (connection_handle == p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle) @@ -2216,6 +2232,15 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle, if (!buffer) return; + if (buffer->piggy_buf) { + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + buffer->piggy_buf->buff_size, + buffer->piggy_buf->data, + buffer->piggy_buf->data_phys_addr); + + kfree(buffer->piggy_buf); + } + dma_free_coherent(&p_hwfn->cdev->pdev->dev, buffer->buff_size, buffer->data, buffer->data_phys_addr); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 858755cafd2bc..58db51af26bda 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -55,6 +55,7 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_HANDLE_INVAL (0xff) struct qed_iwarp_ll2_buff { + struct qed_iwarp_ll2_buff *piggy_buf; void *data; dma_addr_t data_phys_addr; u32 buff_size; -- GitLab From c7d1d839999476aac0d7e16732722285a9c30cce Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:53 +0300 Subject: [PATCH 1176/1507] qed: Add support for MPA header being split over two tcp packets There is a special case where an MPA header is split over to tcp packets, in this case we need to wait for the next packet to get the fpdu length. We use the incomplete_bytes to mark this fpdu as a "special" one which requires updating the length with the next packet Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 36 ++++++++++++++++++++- drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 6 ++++ 2 files changed, 41 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 8b17369af9ef4..299494225f44a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1742,6 +1742,7 @@ enum qed_iwarp_mpa_pkt_type { QED_IWARP_MPA_PKT_UNALIGNED }; +#define QED_IWARP_INVALID_FPDU_LENGTH 0xffff #define QED_IWARP_MPA_FPDU_LENGTH_SIZE (2) #define QED_IWARP_MPA_CRC32_DIGEST_SIZE (4) @@ -1774,6 +1775,15 @@ qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn, goto out; } + /* special case of one byte remaining... + * lower byte will be read next packet + */ + if (tcp_payload_len == 1) { + fpdu->fpdu_length = *mpa_data << BITS_PER_BYTE; + pkt_type = QED_IWARP_MPA_PKT_PARTIAL; + goto out; + } + mpa_len = ntohs(*((u16 *)(mpa_data))); fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); @@ -1802,7 +1812,9 @@ qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf, fpdu->mpa_frag = buf->data_phys_addr + pkt_data->first_mpa_offset; fpdu->mpa_frag_virt = (u8 *)(buf->data) + pkt_data->first_mpa_offset; - if (tcp_payload_size < fpdu->fpdu_length) + if (tcp_payload_size == 1) + fpdu->incomplete_bytes = QED_IWARP_INVALID_FPDU_LENGTH; + else if (tcp_payload_size < fpdu->fpdu_length) fpdu->incomplete_bytes = fpdu->fpdu_length - tcp_payload_size; else fpdu->incomplete_bytes = 0; /* complete fpdu */ @@ -1810,6 +1822,27 @@ qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf, fpdu->mpa_frag_len = fpdu->fpdu_length - fpdu->incomplete_bytes; } +static void +qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, u8 *mpa_data) +{ + u16 mpa_len; + + /* Update incomplete packets if needed */ + if (fpdu->incomplete_bytes == QED_IWARP_INVALID_FPDU_LENGTH) { + /* Missing lower byte is now available */ + mpa_len = fpdu->fpdu_length | *mpa_data; + fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); + fpdu->mpa_frag_len = fpdu->fpdu_length; + /* one byte of hdr */ + fpdu->incomplete_bytes = fpdu->fpdu_length - 1; + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Partial header mpa_len=%x fpdu_length=%x incomplete_bytes=%x\n", + mpa_len, fpdu->fpdu_length, fpdu->incomplete_bytes); + } +} + static int qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu, @@ -1960,6 +1993,7 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, curr_pkt->first_mpa_offset += fpdu->fpdu_length; break; case QED_IWARP_MPA_PKT_UNALIGNED: + qed_iwarp_update_fpdu_length(p_hwfn, fpdu, mpa_data); rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, mpa_buf->tcp_payload_len, pkt_type); diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index 58db51af26bda..c58793a477748 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -69,6 +69,12 @@ struct qed_iwarp_ll2_mpa_buf { u8 placement_offset; }; +/* In some cases a fpdu will arrive with only one byte of the header, in this + * case the fpdu_length will be partial (contain only higher byte and + * incomplete bytes will contain the invalid value + */ +#define QED_IWARP_INVALID_INCOMPLETE_BYTES 0xffff + struct qed_iwarp_fpdu { struct qed_iwarp_ll2_buff *mpa_buf; void *mpa_frag_virt; -- GitLab From 1e28eaad07ea1e2d6537586529e87cbc1d698ffd Mon Sep 17 00:00:00 2001 From: Michal Kalderon Date: Mon, 9 Oct 2017 12:37:54 +0300 Subject: [PATCH 1177/1507] qed: Add iWARP support for fpdu spanned over more than two tcp packets We continue to maintain a maximum of three buffers per fpdu, to ensure that there are enough buffers for additional unaligned mpa packets. To support this, if a fpdu is split over more than two tcp packets, we use an intermediate buffer to copy the data to the previous buffer, then we can release the data. We need an intermediate buffer as the initial buffer partial packet could be located at the end of the packet, not leaving room for additional data. This is a corner case, and will usually not be the case. Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 193 ++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_iwarp.h | 1 + 2 files changed, 194 insertions(+) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 299494225f44a..b2b1f87864ef6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1420,6 +1420,7 @@ void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn) qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1); kfree(iwarp_info->mpa_bufs); kfree(iwarp_info->partial_fpdus); + kfree(iwarp_info->mpa_intermediate_buf); } int qed_iwarp_accept(void *rdma_cxt, struct qed_iwarp_accept_in *iparams) @@ -1762,6 +1763,11 @@ char *pkt_type_str[] = { "QED_IWARP_MPA_PKT_UNALIGNED" }; +static int +qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct qed_iwarp_ll2_buff *buf); + static enum qed_iwarp_mpa_pkt_type qed_iwarp_mpa_classify(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu, @@ -1822,6 +1828,68 @@ qed_iwarp_init_fpdu(struct qed_iwarp_ll2_buff *buf, fpdu->mpa_frag_len = fpdu->fpdu_length - fpdu->incomplete_bytes; } +static int +qed_iwarp_cp_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct unaligned_opaque_data *pkt_data, + struct qed_iwarp_ll2_buff *buf, u16 tcp_payload_size) +{ + u8 *tmp_buf = p_hwfn->p_rdma_info->iwarp.mpa_intermediate_buf; + int rc; + + /* need to copy the data from the partial packet stored in fpdu + * to the new buf, for this we also need to move the data currently + * placed on the buf. The assumption is that the buffer is big enough + * since fpdu_length <= mss, we use an intermediate buffer since + * we may need to copy the new data to an overlapping location + */ + if ((fpdu->mpa_frag_len + tcp_payload_size) > (u16)buf->buff_size) { + DP_ERR(p_hwfn, + "MPA ALIGN: Unexpected: buffer is not large enough for split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n", + buf->buff_size, fpdu->mpa_frag_len, + tcp_payload_size, fpdu->incomplete_bytes); + return -EINVAL; + } + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "MPA ALIGN Copying fpdu: [%p, %d] [%p, %d]\n", + fpdu->mpa_frag_virt, fpdu->mpa_frag_len, + (u8 *)(buf->data) + pkt_data->first_mpa_offset, + tcp_payload_size); + + memcpy(tmp_buf, fpdu->mpa_frag_virt, fpdu->mpa_frag_len); + memcpy(tmp_buf + fpdu->mpa_frag_len, + (u8 *)(buf->data) + pkt_data->first_mpa_offset, + tcp_payload_size); + + rc = qed_iwarp_recycle_pkt(p_hwfn, fpdu, fpdu->mpa_buf); + if (rc) + return rc; + + /* If we managed to post the buffer copy the data to the new buffer + * o/w this will occur in the next round... + */ + memcpy((u8 *)(buf->data), tmp_buf, + fpdu->mpa_frag_len + tcp_payload_size); + + fpdu->mpa_buf = buf; + /* fpdu->pkt_hdr remains as is */ + /* fpdu->mpa_frag is overridden with new buf */ + fpdu->mpa_frag = buf->data_phys_addr; + fpdu->mpa_frag_virt = buf->data; + fpdu->mpa_frag_len += tcp_payload_size; + + fpdu->incomplete_bytes -= tcp_payload_size; + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA ALIGN: split fpdu buff_size = %d mpa_frag_len = %d, tcp_payload_size = %d, incomplete_bytes = %d\n", + buf->buff_size, fpdu->mpa_frag_len, tcp_payload_size, + fpdu->incomplete_bytes); + + return 0; +} + static void qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu, u8 *mpa_data) @@ -1843,6 +1911,90 @@ qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn, } } +#define QED_IWARP_IS_RIGHT_EDGE(_curr_pkt) \ + (GET_FIELD((_curr_pkt)->flags, \ + UNALIGNED_OPAQUE_DATA_PKT_REACHED_WIN_RIGHT_EDGE)) + +/* This function is used to recycle a buffer using the ll2 drop option. It + * uses the mechanism to ensure that all buffers posted to tx before this one + * were completed. The buffer sent here will be sent as a cookie in the tx + * completion function and can then be reposted to rx chain when done. The flow + * that requires this is the flow where a FPDU splits over more than 3 tcp + * segments. In this case the driver needs to re-post a rx buffer instead of + * the one received, but driver can't simply repost a buffer it copied from + * as there is a case where the buffer was originally a packed FPDU, and is + * partially posted to FW. Driver needs to ensure FW is done with it. + */ +static int +qed_iwarp_recycle_pkt(struct qed_hwfn *p_hwfn, + struct qed_iwarp_fpdu *fpdu, + struct qed_iwarp_ll2_buff *buf) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + tx_pkt.num_of_bds = 1; + tx_pkt.tx_dest = QED_LL2_TX_DEST_DROP; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + buf->piggy_buf = NULL; + tx_pkt.cookie = buf; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't drop packet rc=%d\n", rc); + + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: send drop tx packet [%lx, 0x%x], buf=%p, rc=%d\n", + (unsigned long int)tx_pkt.first_frag, + tx_pkt.first_frag_len, buf, rc); + + return rc; +} + +static int +qed_iwarp_win_right_edge(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu) +{ + struct qed_ll2_tx_pkt_info tx_pkt; + u8 ll2_handle; + int rc; + + memset(&tx_pkt, 0, sizeof(tx_pkt)); + tx_pkt.num_of_bds = 1; + tx_pkt.tx_dest = QED_LL2_TX_DEST_LB; + tx_pkt.l4_hdr_offset_w = fpdu->pkt_hdr_size >> 2; + + tx_pkt.first_frag = fpdu->pkt_hdr; + tx_pkt.first_frag_len = fpdu->pkt_hdr_size; + tx_pkt.enable_ip_cksum = true; + tx_pkt.enable_l4_cksum = true; + tx_pkt.calc_ip_len = true; + /* vlan overload with enum iwarp_ll2_tx_queues */ + tx_pkt.vlan = IWARP_LL2_ALIGNED_RIGHT_TRIMMED_TX_QUEUE; + + ll2_handle = p_hwfn->p_rdma_info->iwarp.ll2_mpa_handle; + + rc = qed_ll2_prepare_tx_packet(p_hwfn, ll2_handle, &tx_pkt, true); + if (rc) + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send right edge rc=%d\n", rc); + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "MPA_ALIGN: Sent right edge FPDU num_bds=%d [%lx, 0x%x], rc=%d\n", + tx_pkt.num_of_bds, + (unsigned long int)tx_pkt.first_frag, + tx_pkt.first_frag_len, rc); + + return rc; +} + static int qed_iwarp_send_fpdu(struct qed_hwfn *p_hwfn, struct qed_iwarp_fpdu *fpdu, @@ -1971,6 +2123,20 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, mpa_buf->tcp_payload_len, mpa_buf->placement_offset); + if (!QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) { + mpa_buf->tcp_payload_len = 0; + break; + } + + rc = qed_iwarp_win_right_edge(p_hwfn, fpdu); + + if (rc) { + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, + "Can't send FPDU:reset rc=%d\n", rc); + memset(fpdu, 0, sizeof(*fpdu)); + break; + } + mpa_buf->tcp_payload_len = 0; break; case QED_IWARP_MPA_PKT_PACKED: @@ -1994,6 +2160,28 @@ qed_iwarp_process_mpa_pkt(struct qed_hwfn *p_hwfn, break; case QED_IWARP_MPA_PKT_UNALIGNED: qed_iwarp_update_fpdu_length(p_hwfn, fpdu, mpa_data); + if (mpa_buf->tcp_payload_len < fpdu->incomplete_bytes) { + /* special handling of fpdu split over more + * than 2 segments + */ + if (QED_IWARP_IS_RIGHT_EDGE(curr_pkt)) { + rc = qed_iwarp_win_right_edge(p_hwfn, + fpdu); + /* packet will be re-processed later */ + if (rc) + return rc; + } + + rc = qed_iwarp_cp_pkt(p_hwfn, fpdu, curr_pkt, + buf, + mpa_buf->tcp_payload_len); + if (rc) /* packet will be re-processed later */ + return rc; + + mpa_buf->tcp_payload_len = 0; + break; + } + rc = qed_iwarp_send_fpdu(p_hwfn, fpdu, curr_pkt, buf, mpa_buf->tcp_payload_len, pkt_type); @@ -2510,6 +2698,11 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, goto err; iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; + + iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL); + if (!iwarp_info->mpa_intermediate_buf) + goto err; + /* The mpa_bufs array serves for pending RX packets received on the * mpa ll2 that don't have place on the tx ring and require later * processing. We can't fail on allocation of such a struct therefore diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index c58793a477748..c1ecd743305f1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -107,6 +107,7 @@ struct qed_iwarp_info { enum mpa_rtr_type rtr_type; struct qed_iwarp_fpdu *partial_fpdus; struct qed_iwarp_ll2_mpa_buf *mpa_bufs; + u8 *mpa_intermediate_buf; u16 max_num_partial_fpdus; }; -- GitLab From 41c87425a1ac9b633e0fcc78eb1f19640c8fb5a0 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 9 Oct 2017 14:14:51 +0200 Subject: [PATCH 1178/1507] netlink: do not set cb_running if dump's start() errs It turns out that multiple places can call netlink_dump(), which means it's still possible to dereference partially initialized values in dump() that were the result of a faulty returned start(). This fixes the issue by calling start() _before_ setting cb_running to true, so that there's no chance at all of hitting the dump() function through any indirect paths. It also moves the call to start() to be when the mutex is held. This has the nice side effect of serializing invocations to start(), which is likely desirable anyway. It also prevents any possible other races that might come out of this logic. In testing this with several different pieces of tricky code to trigger these issues, this commit fixes all avenues that I'm aware of. Signed-off-by: Jason A. Donenfeld Cc: Johannes Berg Reviewed-by: Johannes Berg Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 94c11cf0459d3..f34750691c5c0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2266,16 +2266,17 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; + if (cb->start) { + ret = cb->start(cb); + if (ret) + goto error_unlock; + } + nlk->cb_running = true; mutex_unlock(nlk->cb_mutex); - ret = 0; - if (cb->start) - ret = cb->start(cb); - - if (!ret) - ret = netlink_dump(sk); + ret = netlink_dump(sk); sock_put(sk); -- GitLab From 996b44fcef8f216ea0b6b6e74468c5a77b5e341f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 9 Oct 2017 14:52:10 +0200 Subject: [PATCH 1179/1507] udp: fix bcast packet reception The commit bc044e8db796 ("udp: perform source validation for mcast early demux") does not take into account that broadcast packets lands in the same code path and they need different checks for the source address - notably, zero source address are valid for bcast and invalid for mcast. As a result, 2nd and later broadcast packets with 0 source address landing to the same socket are dropped. This breaks dhcp servers. Since we don't have stringent performance requirements for ingress broadcast traffic, fix it by disabling UDP early demux such traffic. Reported-by: Hannes Frederic Sowa Fixes: bc044e8db796 ("udp: perform source validation for mcast early demux") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/udp.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5676237d2b0f8..e45177ceb0ee5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2240,20 +2240,16 @@ int udp_v4_early_demux(struct sk_buff *skb) iph = ip_hdr(skb); uh = udp_hdr(skb); - if (skb->pkt_type == PACKET_BROADCAST || - skb->pkt_type == PACKET_MULTICAST) { + if (skb->pkt_type == PACKET_MULTICAST) { in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; - /* we are supposed to accept bcast packets */ - if (skb->pkt_type == PACKET_MULTICAST) { - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return 0; - } + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, -- GitLab From bfd8e5a407133e58a92a38ccf3d0ba6db81f22d8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 Oct 2017 06:01:37 -0700 Subject: [PATCH 1180/1507] ipv6: avoid zeroing per cpu data again per cpu allocations are already zeroed, no need to clear them again. Fixes: d52d3997f843f ("ipv6: Create percpu rt6_info") Signed-off-by: Eric Dumazet Cc: Martin KaFai Lau Cc: Tejun Heo Acked-by: Tejun Heo Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv6/route.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 606e80325b21c..3d7d4e09301ef 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -377,17 +377,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, if (rt) { rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (rt->rt6i_pcpu) { - int cpu; - - for_each_possible_cpu(cpu) { - struct rt6_info **p; - - p = per_cpu_ptr(rt->rt6i_pcpu, cpu); - /* no one shares rt */ - *p = NULL; - } - } else { + if (!rt->rt6i_pcpu) { dst_release_immediate(&rt->dst); return NULL; } -- GitLab From acb40d8412572b2a79216a98acdbac10e620da1b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 9 Oct 2017 16:22:34 +0300 Subject: [PATCH 1181/1507] thunderbolt: Initialize Thunderbolt bus earlier The 0day kbuild robot reports following crash: BUG: unable to handle kernel NULL pointer dereference at 00000004 IP: tb_property_find+0xe/0x41 *pde = 00000000 Oops: 0000 [#1] CPU: 0 PID: 1 Comm: swapper Not tainted 4.14.0-rc1-00741-ge69b6c0 #412 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 task: 89c80000 task.stack: 89c7c000 EIP: tb_property_find+0xe/0x41 EFLAGS: 00210246 CPU: 0 EAX: 00000000 EBX: 7a368f47 ECX: 00000044 EDX: 7a368f47 ESI: 8851d340 EDI: 7a368f47 EBP: 89c7df0c ESP: 89c7defc DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068 CR0: 80050033 CR2: 00000004 CR3: 027a2000 CR4: 00000690 Call Trace: tb_register_property_dir+0x49/0xb9 ? cdc_mbim_driver_init+0x1b/0x1b tbnet_init+0x77/0x9f ? cdc_mbim_driver_init+0x1b/0x1b do_one_initcall+0x7e/0x145 ? parse_args+0x10c/0x1b3 ? kernel_init_freeable+0xbe/0x159 kernel_init_freeable+0xd1/0x159 ? rest_init+0x110/0x110 kernel_init+0xd/0xd0 ret_from_fork+0x19/0x30 The reason is that both Thunderbolt bus and thunderbolt-net are build into the kernel image, and the latter is linked first because drivers/net comes before drivers/thunderbolt. Since both use module_init() thunderbolt-net ends up calling Thunderbolt bus functions too early triggering the above crash. Fix this by moving Thunderbolt bus initialization to happen earlier to make sure all the data structures are ready when Thunderbolt service drivers are initialized. To be on the safe side also add a check for properly initialized xdomain_property_dir to tb_register_property_dir(). Reported-by: kernel test robot Signed-off-by: Mika Westerberg Signed-off-by: David S. Miller --- drivers/thunderbolt/nhi.c | 2 +- drivers/thunderbolt/xdomain.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 0e79eebfcbb7a..419a7a90bce0e 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1144,5 +1144,5 @@ static void __exit nhi_unload(void) tb_domain_exit(); } -module_init(nhi_init); +fs_initcall(nhi_init); module_exit(nhi_unload); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index f2d06f6f7be97..138027537d29c 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1487,6 +1487,9 @@ int tb_register_property_dir(const char *key, struct tb_property_dir *dir) { int ret; + if (WARN_ON(!xdomain_property_dir)) + return -EAGAIN; + if (!key || strlen(key) > 8) return -EINVAL; -- GitLab From bb428a5c4df5f50acdce89449e476faa0b295e95 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 9 Oct 2017 16:59:48 +0300 Subject: [PATCH 1182/1507] net/mlx4: Fix endianness issue in qp context params Should take care of the endianness before assigning to params2 field. Fixes: 53f33ae295a5 ("net/mlx4_core: Port aggregation upper layer interface") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_resources.c | 2 +- drivers/net/ethernet/mellanox/mlx4/qp.c | 2 +- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 5a47f9669621c..6883ac75d37f6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -53,7 +53,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, if (is_tx) { context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4); if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP) - context->params2 |= MLX4_QP_BIT_FPP; + context->params2 |= cpu_to_be32(MLX4_QP_BIT_FPP); } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 728a2fb1f5c09..203320923340e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -925,7 +925,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt, context->flags &= cpu_to_be32(~(0xf << 28)); context->flags |= cpu_to_be32(states[i + 1] << 28); if (states[i + 1] != MLX4_QP_STATE_RTR) - context->params2 &= ~MLX4_QP_BIT_FPP; + context->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP); err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1], context, 0, 0, qp); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index fabb533797275..04304dd894c6c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3185,7 +3185,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, optpar = be32_to_cpu(*(__be32 *) inbox->buf); if (slave != mlx4_master_func_num(dev)) { - qp_ctx->params2 &= ~MLX4_QP_BIT_FPP; + qp_ctx->params2 &= ~cpu_to_be32(MLX4_QP_BIT_FPP); /* setting QP rate-limit is disallowed for VFs */ if (qp_ctx->rate_limit_params) return -EPERM; -- GitLab From b71322d9db924e1ae33b9fd00a2e37aee09df81f Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 9 Oct 2017 16:59:49 +0300 Subject: [PATCH 1183/1507] net/mlx4_core: Fix cast warning in fw.c Fix the following SPARSE warning, in MLX4_GET() macro: drivers/net/ethernet/mellanox/mlx4/fw.c:233:9: warning: cast to restricted __be64 Fixes: 17d5ceb6e43e ("net/mlx4_core: Fix unaligned accesses") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/fw.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 16c09949afd5b..634f603f941c4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -57,12 +57,12 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)"); #define MLX4_GET(dest, source, offset) \ do { \ void *__p = (char *) (source) + (offset); \ - u64 val; \ - switch (sizeof(dest)) { \ + __be64 val; \ + switch (sizeof(dest)) { \ case 1: (dest) = *(u8 *) __p; break; \ case 2: (dest) = be16_to_cpup(__p); break; \ case 4: (dest) = be32_to_cpup(__p); break; \ - case 8: val = get_unaligned((u64 *)__p); \ + case 8: val = get_unaligned((__be64 *)__p); \ (dest) = be64_to_cpu(val); break; \ default: __buggy_use_of_MLX4_GET(); \ } \ -- GitLab From 7ba5e7bd64a5715f624d39815f567842178afb72 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 9 Oct 2017 16:59:50 +0300 Subject: [PATCH 1184/1507] net/mlx4_en: Use __force to fix a sparse warning in TX datapath In TX data-path, we intentionally do not byte-swap, as documented in code and in the cited commit log. This fixes sparse warning: en_tx.c:720:23: warning: incorrect type in argument 1 (different base types) en_tx.c:720:23: expected unsigned int [unsigned] [usertype] en_tx.c:720:23: got restricted __be32 [usertype] doorbell_qpn Fixes: 492f5add4be8 ("net/mlx4_en: Doorbell is byteswapped in Little Endian archs") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8a32a8f7f9c0c..2cc82dc073974 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -718,7 +718,7 @@ void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring) #else iowrite32be( #endif - ring->doorbell_qpn, + (__force u32)ring->doorbell_qpn, ring->bf.uar->map + MLX4_SEND_DOORBELL); } -- GitLab From 1a2ace56cea2d752b212e198c5e70ff0c0f39b59 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 9 Oct 2017 11:44:53 -0500 Subject: [PATCH 1185/1507] net: thunderx: mark expected switch fall-throughs in nicvf_main() In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Cc: Sunil Goutham Cc: Robert Richter Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da51ba73..805ab45e9b5ac 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -565,8 +565,10 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, return true; default: bpf_warn_invalid_xdp_action(action); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(nic->netdev, prog, action); + /* fall through */ case XDP_DROP: /* Check if it's a recycled page, if not * unmap the DMA mapping. -- GitLab From 66c77ff3a049a1d182c9c78cc6286bb1ceee70db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 Oct 2017 09:52:24 -0700 Subject: [PATCH 1186/1507] ipv6: addrlabel: rework ip6addrlbl_get() If we allocate skb before the lookup, we can use RCU without the need of ip6addrlbl_hold() This means that the following patch can get rid of refcounting. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrlabel.c | 36 +++++++++++++----------------------- 1 file changed, 13 insertions(+), 23 deletions(-) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index c6311d7108f65..f31489652c4ae 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -546,38 +546,28 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); - rcu_read_lock(); - p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && !ip6addrlbl_hold(p)) - p = NULL; - lseq = net->ipv6.ip6addrlbl_table.seq; - rcu_read_unlock(); - - if (!p) { - err = -ESRCH; - goto out; - } - skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); - if (!skb) { - ip6addrlbl_put(p); + if (!skb) return -ENOBUFS; - } - err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWADDRLABEL, 0); + err = -ESRCH; - ip6addrlbl_put(p); + rcu_read_lock(); + p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); + lseq = net->ipv6.ip6addrlbl_table.seq; + if (p) + err = ip6addrlbl_fill(skb, p, lseq, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, + RTM_NEWADDRLABEL, 0); + rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - goto out; + } else { + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } - - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); -out: return err; } -- GitLab From 2809c0957dbbd56d3a92e9ede27b19943fef7236 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 Oct 2017 09:52:25 -0700 Subject: [PATCH 1187/1507] ipv6: addrlabel: remove refcounting After previous patch ("ipv6: addrlabel: rework ip6addrlbl_get()") we can remove the refcount from struct ip6addrlbl_entry, since it is no longer elevated in p6addrlbl_get() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/addrlabel.c | 33 ++++----------------------------- 1 file changed, 4 insertions(+), 29 deletions(-) diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f31489652c4ae..2606d2fa3ac4c 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -18,7 +18,6 @@ #include #include #include -#include #if 0 #define ADDRLABEL(x...) printk(x) @@ -36,7 +35,6 @@ struct ip6addrlbl_entry { int addrtype; u32 label; struct hlist_node list; - refcount_t refcnt; struct rcu_head rcu; }; @@ -111,28 +109,6 @@ static const __net_initconst struct ip6addrlbl_init_table } }; -/* Object management */ -static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p) -{ - kfree(p); -} - -static void ip6addrlbl_free_rcu(struct rcu_head *h) -{ - ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu)); -} - -static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p) -{ - return refcount_inc_not_zero(&p->refcnt); -} - -static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) -{ - if (refcount_dec_and_test(&p->refcnt)) - call_rcu(&p->rcu, ip6addrlbl_free_rcu); -} - /* Find label */ static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, @@ -219,7 +195,6 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); - refcount_set(&newp->refcnt, 1); return newp; } @@ -243,7 +218,7 @@ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, goto out; } hlist_replace_rcu(&p->list, &newp->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { @@ -281,7 +256,7 @@ static int ip6addrlbl_add(struct net *net, ret = __ip6addrlbl_add(net, newp, replace); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) - ip6addrlbl_free(newp); + kfree(newp); return ret; } @@ -302,7 +277,7 @@ static int __ip6addrlbl_del(struct net *net, p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); ret = 0; break; } @@ -360,7 +335,7 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) spin_lock(&net->ipv6.ip6addrlbl_table.lock); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); - ip6addrlbl_put(p); + kfree_rcu(p, rcu); } spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } -- GitLab From b48be9978e4b21b28b7349f57574dae21378ddd5 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 15:19:12 -0700 Subject: [PATCH 1188/1507] i40e: fix flags declaration Since we don't yet have more than 32 flags, we'll use a u32 for both the hw_features and flag field. Should we gain more flags in the future, we may need to convert to a u64 or separate flags out into two fields. This was overlooked in the previous commit 2781de2134c4 ("i40e/i40evf: organize and re-number feature flags"), where the feature flag was not converted form u64 to u32. Signed-off-by: Jacob Keller Reviewed-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 18c453a3e7286..7baf6d8a84dd0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -424,7 +424,7 @@ struct i40e_pf { #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) - u64 flags; + u32 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT(0) #define I40E_FLAG_MSI_ENABLED BIT(1) #define I40E_FLAG_MSIX_ENABLED BIT(2) -- GitLab From 784548c40d6f43eff2297220ad7800dc04be03c6 Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Thu, 7 Sep 2017 08:05:46 -0400 Subject: [PATCH 1189/1507] i40e: use the safe hash table iterator when deleting mac filters This patch replaces hash_for_each function with hash_for_each_safe when calling __i40e_del_filter. The hash_for_each_safe function is the right one to use when iterating over a hash table to safely remove a hash entry. Otherwise, incorrect values may be read from freed memory. Detected by CoverityScan, CID 1402048 Read from pointer after free Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 04568137e029d..c062d74d21f32 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2883,6 +2883,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct i40e_mac_filter *f; struct i40e_vf *vf; int ret = 0; + struct hlist_node *h; int bkt; /* validate the request */ @@ -2921,7 +2922,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Delete all the filters for this VSI - we're going to kill it * anyway. */ - hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) __i40e_del_filter(vsi, f); spin_unlock_bh(&vsi->mac_filter_hash_lock); -- GitLab From c766b9af9abe897eb5480ef9ef3914fc07b815c5 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Thu, 7 Sep 2017 08:05:47 -0400 Subject: [PATCH 1190/1507] i40evf: fix mac filter removal timing issue Due to the asynchronous nature in which mac filters are added and deleted, there exists a bug in which filters are erroneously removed if removed then added again quickly. The events are as such: - filter marked for removal - same filter is re-added before watchdog that cleans up filters - we skip re-adding the filter because we have it already in the list - watchdog filter cleanup kicks off and filter is removed So when we were re-adding the same filter, it didn't actually get added because it already existed in the list, but was marked for removal and had yet to actually be removed. This patch fixes the issue by making sure that when adding a filter, if we find it already existing in our list, make sure it is not marked to be removed. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 1d2fc898b6645..f62d9565c7b59 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -880,6 +880,8 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; + } else { + f->remove = false; } clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); -- GitLab From 427025592955d245997b12923111e85f07850d5f Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:48 -0400 Subject: [PATCH 1191/1507] i40e/i40evf: fix incorrect default ITR values on driver load The ITR register expects to be programmed in units of 2 microseconds. Because of this, all of the drivers I40E_ITR_* constants are in terms of this 2 microsecond register. Unfortunately, the rx_itr_default value is expected to be programmed in microseconds. Effectively the driver defaults to an ITR value of half the expected value (in terms of minimum microseconds between interrupts). Fix this by changing the default values to be calculated using ITR_REG_TO_USEC macro which indicates that we're converting from the register units into microseconds. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 6 ++++-- drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 6 ++++-- drivers/net/ethernet/intel/i40evf/i40evf_main.c | 4 ++-- 4 files changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 60b11fdeca2d5..d4b0cc36afb18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8983,8 +8983,8 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_FLAG_MSIX_ENABLED; /* Set default ITR */ - pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF; - pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF; + pf->rx_itr_default = I40E_ITR_RX_DEF; + pf->tx_itr_default = I40E_ITR_TX_DEF; /* Depending on PF configurations, it is possible that the RSS * maximum might end up larger than the available queues diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index a4e3e665a1a14..c3156aa3f709f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index d8ca802a71a92..8f9830d7649a7 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -38,8 +38,10 @@ #define I40E_ITR_8K 0x003E #define I40E_ITR_4K 0x007A #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ -#define I40E_ITR_RX_DEF I40E_ITR_20K -#define I40E_ITR_TX_DEF I40E_ITR_20K +#define I40E_ITR_RX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) +#define I40E_ITR_TX_DEF (ITR_REG_TO_USEC(I40E_ITR_20K) | \ + I40E_ITR_DYNAMIC) #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_MIN_INT_RATE 250 /* ~= 1000000 / (I40E_MAX_ITR * 2) */ #define I40E_MAX_INT_RATE 500000 /* == 1000000 / (I40E_MIN_ITR * 2) */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f62d9565c7b59..5bcbd46e2f6c4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1223,7 +1223,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF); + tx_ring->tx_itr_setting = I40E_ITR_TX_DEF; if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; @@ -1232,7 +1232,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->rx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF); + rx_ring->rx_itr_setting = I40E_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; -- GitLab From dbadbbe235f82f13224c85d29e65cf859afaa18c Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:49 -0400 Subject: [PATCH 1192/1507] i40e/i40evf: always set the CLEARPBA flag when re-enabling interrupts In the past we changed driver behavior to not clear the PBA when re-enabling interrupts. This change was motivated by the flawed belief that clearing the PBA would cause a lost interrupt if a receive interrupt occurred while interrupts were disabled. According to empirical testing this isn't the case. Additionally, the data sheet specifically says that we should set the CLEARPBA bit when re-enabling interrupts in a polling setup. This reverts commit 40d72a509862 ("i40e/i40evf: don't lose interrupts") Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 5 +---- drivers/net/ethernet/intel/i40e/i40e_main.c | 11 +++++------ drivers/net/ethernet/intel/i40e/i40e_txrx.c | 6 ++---- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 4 +--- 5 files changed, 10 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 7baf6d8a84dd0..8139b4ee1dc32 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -949,9 +949,6 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) struct i40e_hw *hw = &pf->hw; u32 val; - /* definitely clear the PBA here, as this function is meant to - * clean out all previous interrupts AND enable the interrupt - */ val = I40E_PFINT_DYN_CTLN_INTENA_MASK | I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT); @@ -960,7 +957,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) } void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf); -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba); +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf); int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); int i40e_open(struct net_device *netdev); int i40e_close(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d4b0cc36afb18..00a83afb02e9d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3403,15 +3403,14 @@ void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf) /** * i40e_irq_dynamic_enable_icr0 - Enable default interrupt generation for icr0 * @pf: board private structure - * @clearpba: true when all pending interrupt events should be cleared **/ -void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba) +void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; u32 val; val = I40E_PFINT_DYN_CTL0_INTENA_MASK | - (clearpba ? I40E_PFINT_DYN_CTL0_CLEARPBA_MASK : 0) | + I40E_PFINT_DYN_CTL0_CLEARPBA_MASK | (I40E_ITR_NONE << I40E_PFINT_DYN_CTL0_ITR_INDX_SHIFT); wr32(hw, I40E_PFINT_DYN_CTL0, val); @@ -3597,7 +3596,7 @@ static int i40e_vsi_enable_irq(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_q_vectors; i++) i40e_irq_dynamic_enable(vsi, i); } else { - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); } i40e_flush(&pf->hw); @@ -3746,7 +3745,7 @@ static irqreturn_t i40e_intr(int irq, void *data) wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask); if (!test_bit(__I40E_DOWN, pf->state)) { i40e_service_event_schedule(pf); - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); } return ret; @@ -8455,7 +8454,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) i40e_flush(hw); - i40e_irq_dynamic_enable_icr0(pf, true); + i40e_irq_dynamic_enable_icr0(pf); return err; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 3bd176606c094..616abf79253e8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2202,9 +2202,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_PFINT_DYN_CTLN_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_PFINT_DYN_CTLN_CLEARPBA_MASK | (type << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT) | (itr << I40E_PFINT_DYN_CTLN_INTERVAL_SHIFT); @@ -2241,7 +2239,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* If we don't have MSIX, then we only need to re-enable icr0 */ if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { - i40e_irq_dynamic_enable_icr0(vsi->back, false); + i40e_irq_dynamic_enable_icr0(vsi->back); return; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c062d74d21f32..10298956a81be 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1358,7 +1358,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) i40e_free_vfs(pf); err_iov: /* Re-enable interrupt 0. */ - i40e_irq_dynamic_enable_icr0(pf, false); + i40e_irq_dynamic_enable_icr0(pf); return ret; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 37e1de886d480..fe817e2b6fef4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1409,9 +1409,7 @@ static u32 i40e_buildreg_itr(const int type, const u16 itr) u32 val; val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - /* Don't clear PBA because that can cause lost interrupts that - * came in while we were cleaning/polling - */ + I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK | (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | (itr << I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT); -- GitLab From 7362be9eeed01980bfa03cf49737703a0e43fe50 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:50 -0400 Subject: [PATCH 1193/1507] i40e: reduce lrxqthresh from 2 to 1 The lrxq thresh value tells hardware to immediately interrupt when there are fewer than N*64 packets left in the ring. Counter intuitively, empirical testing has shown that decreasing this value from 2 to 1, and thus changing from an immediate interrupt at fewer than 128 descriptors down to 64 descriptors causes a small increase in the maximum total packets per second we can receive. This increase occurs even when we're polling with interrupts masked, as the hardware must still handle interrupts internally even if we've disabled them in software. Also reduce the value for any VFs we allocate. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 00a83afb02e9d..74875ddaeb330 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3030,7 +3030,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (hw->revision_id == 0) rx_ctx.lrxqthresh = 0; else - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.l2tsel = 1; /* this controls whether VLAN is stripped from inner headers */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 10298956a81be..83727906a3868 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -639,7 +639,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, rx_ctx.dsize = 1; /* default values */ - rx_ctx.lrxqthresh = 2; + rx_ctx.lrxqthresh = 1; rx_ctx.crcstrip = 1; rx_ctx.prefena = 1; rx_ctx.l2tsel = 1; -- GitLab From 11f29003d6376fb123b7c3779dba49bb56fb0815 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:51 -0400 Subject: [PATCH 1194/1507] i40e/i40evf: bump tail only in multiples of 8 Hardware only fetches descriptors on cachelines of 8, essentially ignoring the lower 3 bits of the tail register. Thus, it is pointless to bump tail by an unaligned access as the hardware will ignore some of the new descriptors we allocated. Thus, it's ideal if we can ensure tail writes are always aligned to 8. At first, it seems like we'd already do this, since we allocate descriptors in batches which are a multiple of 8. Since we'd always increment by a multiple of 8, it seems like the value should always be aligned. However, this ignores allocation failures. If we fail to allocate a buffer, our tail register will become unaligned. Once it has become unaligned it will essentially be stuck unaligned until a buffer allocation happens to fail at the exact amount necessary to re-align it. We can do better, by simply rounding down the number of buffers we're about to allocate (cleaned_count) such that "next_to_clean + cleaned_count" is rounded to the nearest multiple of 8. We do this by calculating how far off that value is and subtracting it from the cleaned_count. This essentially defers allocation of buffers if they're going to be ignored by hardware anyways, and re-aligns our next_to_use and tail values after a failure to allocate a descriptor. This calculation ensures that we always align the tail writes in a way the hardware expects and don't unnecessarily allocate buffers which won't be fetched immediately. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 9 +++++++++ drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 9 +++++++++ 2 files changed, 18 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 616abf79253e8..a23306f04e004 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1372,6 +1372,15 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index fe817e2b6fef4..6806ada11490a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -711,6 +711,15 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) union i40e_rx_desc *rx_desc; struct i40e_rx_buffer *bi; + /* Hardware only fetches new descriptors in cache lines of 8, + * essentially ignoring the lower 3 bits of the tail register. We want + * to ensure our tail writes are aligned to avoid unnecessary work. We + * can't simply round down the cleaned count, since we might fail to + * allocate some buffers. What we really want is to ensure that + * next_to_used + cleaned_count produces an aligned value. + */ + cleaned_count -= (ntu + cleaned_count) & 0x7; + /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; -- GitLab From 95bc2fb4c6c7d23db6dc54a3d49bdbadb13c392b Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:52 -0400 Subject: [PATCH 1195/1507] i40e/i40evf: bundle more descriptors when allocating buffers Double the number of descriptors we'll bundle into one tail bump when receiving. Empirical testing has shown that we reduce CPU utilization and don't appear to reduce throughput or packet rate. 32 seems to be the sweet spot, as it's half the default polling budget, so we'd essentially reduce from 4 tail writes when polling down to 2. Increasing this up to 64 appears to have negative impacts as it may become possible that we don't bump the tail each time we get polled, which could cause a long delay between returning descriptors to the hardware. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 +- drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index c3156aa3f709f..ff57ae451524f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -208,7 +208,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 8f9830d7649a7..8d26c85d12e13 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -191,7 +191,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ #define I40E_RX_INCREMENT(r, i) \ do { \ (i)++; \ -- GitLab From 6f853d4f8e93eeace504b021e05dfdbeb4d3b40f Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 7 Sep 2017 08:05:53 -0400 Subject: [PATCH 1196/1507] i40e: allow XPS with QoS enabled Recently, the kernel gained support for enabling XPS and QoS at the same time. Thus, we no longer need to worry about the number of traffic classes when enabling XPS. Signed-off-by: Jacob Keller Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 74875ddaeb330..b26f615bed5a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2879,23 +2879,18 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) **/ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { - struct i40e_vsi *vsi = ring->vsi; int cpu; if (!ring->q_vector || !ring->netdev) return; - if ((vsi->tc_config.numtc <= 1) && - !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) { - cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); - netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), - ring->queue_index); - } + /* We only initialize XPS once, so as not to overwrite user settings */ + if (test_and_set_bit(__I40E_TX_XPS_INIT_DONE, ring->state)) + return; - /* schedule our worker thread which will take care of - * applying the new filter changes - */ - i40e_service_event_schedule(vsi->back); + cpu = cpumask_local_spread(ring->q_vector->v_idx, -1); + netif_set_xps_queue(ring->netdev, get_cpu_mask(cpu), + ring->queue_index); } /** -- GitLab From b861fb762a26144593387b84cd078ef86d99cf6f Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Thu, 7 Sep 2017 08:05:54 -0400 Subject: [PATCH 1197/1507] i40e: add check for return from find_first_bit call The find_first_bit function will return the size passed to search if the first set bit is not found. This patch adds the check in case that happens as the return value would be used as the index in an array and that would have caused the out-of-bounds access. Detected by CoverityScan, CID 1295969 Out-of-bounds access Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 83727906a3868..125dcd1d2233d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -306,6 +306,10 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, next_q = find_first_bit(&linklistmap, (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)); + if (unlikely(next_q == (I40E_MAX_VSI_QP * + I40E_VIRTCHNL_SUPPORTED_QTYPES))) + goto irq_list_done; + vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); -- GitLab From 4988410f8d3a6fa04381072e2406a1d3979ffb95 Mon Sep 17 00:00:00 2001 From: Jayaprakash Shanmugam Date: Thu, 7 Sep 2017 08:05:55 -0400 Subject: [PATCH 1198/1507] i40e: Retry AQC GetPhyAbilities to overcome I2CRead hangs - When the I2C is busy, the PHY reads are delayed. The firmware will return EGAIN in these cases with an expectation that the SW will trigger the reads again - This patch retries the operation for a maximum period of 500ms Signed-off-by: Jayaprakash Shanmugam Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_common.c | 42 +++++++++++++------ drivers/net/ethernet/intel/i40e/i40e_type.h | 3 ++ drivers/net/ethernet/intel/i40evf/i40e_type.h | 3 ++ 3 files changed, 35 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 60542beda7ade..53aad378d49c1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1567,30 +1567,46 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, struct i40e_aq_desc desc; i40e_status status; u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp); + u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0; if (!abilities) return I40E_ERR_PARAM; - i40e_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_phy_abilities); + do { + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_phy_abilities); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - if (abilities_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (abilities_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - if (qualified_modules) - desc.params.external.param0 |= + if (qualified_modules) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES); - if (report_init) - desc.params.external.param0 |= + if (report_init) + desc.params.external.param0 |= cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES); - status = i40e_asq_send_command(hw, &desc, abilities, abilities_size, - cmd_details); + status = i40e_asq_send_command(hw, &desc, abilities, + abilities_size, cmd_details); - if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) - status = I40E_ERR_UNKNOWN_PHY; + if (status) + break; + + if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) { + status = I40E_ERR_UNKNOWN_PHY; + break; + } else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) { + usleep_range(1000, 2000); + total_delay++; + status = I40E_ERR_TIMEOUT; + } + } while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) && + (total_delay < max_delay)); + + if (status) + return status; if (report_init) { if (hw->mac.type == I40E_MAC_XL710 && diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 4b32b1d38a661..0410fcbdbb942 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 9364b67fff9c4..213b773dfad63 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -46,6 +46,9 @@ /* Max default timeout in ms, */ #define I40E_MAX_NVM_TIMEOUT 18000 +/* Max timeout in ms for the phy to respond */ +#define I40E_MAX_PHY_TIMEOUT 500 + /* Switch from ms to the 1usec global time (this is the GTIME resolution) */ #define I40E_MS_TO_GTIME(time) ((time) * 1000) -- GitLab From 9bcc07f0651b3078f1c3164c710f72a558665345 Mon Sep 17 00:00:00 2001 From: Lihong Yang Date: Thu, 7 Sep 2017 08:05:56 -0400 Subject: [PATCH 1199/1507] i40e: use a local variable instead of calculating multiple times The computed result of I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES is used more than three times in function i40e_config_irq_link_list. Simply declare a local variable to store it to improve readability. Signed-off-by: Lihong Yang Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 20 +++++++------------ 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 125dcd1d2233d..0c4fa225c7bee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -273,7 +273,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, struct i40e_hw *hw = &pf->hw; u16 vsi_queue_id, pf_queue_id; enum i40e_queue_type qtype; - u16 next_q, vector_id; + u16 next_q, vector_id, size; u32 reg, reg_idx; u16 itr_idx = 0; @@ -303,11 +303,9 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, vsi_queue_id + 1)); } - next_q = find_first_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES)); - if (unlikely(next_q == (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES))) + size = I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES; + next_q = find_first_bit(&linklistmap, size); + if (unlikely(next_q == size)) goto irq_list_done; vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; @@ -317,7 +315,7 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, wr32(hw, reg_idx, reg); - while (next_q < (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + while (next_q < size) { switch (qtype) { case I40E_QUEUE_TYPE_RX: reg_idx = I40E_QINT_RQCTL(pf_queue_id); @@ -331,12 +329,8 @@ static void i40e_config_irq_link_list(struct i40e_vf *vf, u16 vsi_id, break; } - next_q = find_next_bit(&linklistmap, - (I40E_MAX_VSI_QP * - I40E_VIRTCHNL_SUPPORTED_QTYPES), - next_q + 1); - if (next_q < - (I40E_MAX_VSI_QP * I40E_VIRTCHNL_SUPPORTED_QTYPES)) { + next_q = find_next_bit(&linklistmap, size, next_q + 1); + if (next_q < size) { vsi_queue_id = next_q / I40E_VIRTCHNL_SUPPORTED_QTYPES; qtype = next_q % I40E_VIRTCHNL_SUPPORTED_QTYPES; pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, -- GitLab From 3d7d7a86ec6ea5abaea30194eeb175e2a3d0bdc7 Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Sat, 16 Sep 2017 05:49:48 +0300 Subject: [PATCH 1200/1507] i40e: fix a typo This patch fixes a typo in i40e_vsi_alloc_arrays() documentation. The first parameter name should be "vsi" instead of "type". Signed-off-by: Rami Rosen Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b26f615bed5a1..4de52001a2b9d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7688,7 +7688,7 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) /** * i40e_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the vsi - * @type: VSI pointer + * @vsi: VSI pointer * @alloc_qvectors: a bool to specify if q_vectors need to be allocated. * * On error: returns error code (negative) -- GitLab From 2c4d36b7087538704fc9e3464d185dcc4d04e863 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 6 Sep 2017 10:11:39 +0200 Subject: [PATCH 1201/1507] i40e: Avoid some useless variables and initializers in NVM functions Fixes: 09f79fd49d94 ("i40e: avoid NVM acquire deadlock during NVM update") Signed-off-by: Stefano Brivio Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_nvm.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 57505b1df98df..151d9cfb6ea46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -311,13 +311,10 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_word_aq(hw, offset, data); - else - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); - return ret_code; + return i40e_read_nvm_word_aq(hw, offset, data); + + return i40e_read_nvm_word_srctl(hw, offset, data); } /** @@ -331,7 +328,7 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - i40e_status ret_code = 0; + i40e_status ret_code; ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (ret_code) @@ -446,13 +443,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, u16 *words, u16 *data) { - i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) - ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data); - else - ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); - return ret_code; + return i40e_read_nvm_buffer_aq(hw, offset, words, data); + + return i40e_read_nvm_buffer_srctl(hw, offset, words, data); } /** -- GitLab From fdfbad3256918fc5736d68384331d2dbf45ccbd6 Mon Sep 17 00:00:00 2001 From: Aleksander Morgado Date: Mon, 9 Oct 2017 14:05:12 +0200 Subject: [PATCH 1202/1507] cdc_ether: flag the u-blox TOBY-L2 and SARA-U2 as wwan The u-blox TOBY-L2 is a LTE Cat 4 module with HSPA+ and 2G fallback. This module allows switching to different USB profiles with the 'AT+UUSBCONF' command, and provides a ECM network interface when the 'AT+UUSBCONF=2' profile is selected. The u-blox SARA-U2 is a HSPA module with 2G fallback. The default USB configuration includes a ECM network interface. Both these modules are controlled via AT commands through one of the TTYs exposed. Connecting these modules may be done just by activating the desired PDP context with 'AT+CGACT=1,' and then running DHCP on the ECM interface. Signed-off-by: Aleksander Morgado Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ether.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 29c7e2ec0dcbe..52ea80bcd6392 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -560,6 +560,7 @@ static const struct driver_info wwan_info = { #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 #define MICROSOFT_VENDOR_ID 0x045e +#define UBLOX_VENDOR_ID 0x1546 static const struct usb_device_id products[] = { /* BLACKLIST !! @@ -868,6 +869,18 @@ static const struct usb_device_id products[] = { USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&zte_cdc_info, +}, { + /* U-blox TOBY-L2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1143, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { + /* U-blox SARA-U2 */ + USB_DEVICE_AND_INTERFACE_INFO(UBLOX_VENDOR_ID, 0x1104, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, }, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), -- GitLab From d0e60206bea2dec46c0a28fd6b116646aa67c5ae Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 9 Oct 2017 17:17:26 -0700 Subject: [PATCH 1203/1507] ipv6: use rcu_dereference_bh() in ipv6_route_seq_next() This patch replaces rcu_deference() with rcu_dereference_bh() in ipv6_route_seq_next() to avoid the following warning: [ 19.431685] WARNING: suspicious RCU usage [ 19.433451] 4.14.0-rc3-00914-g66f5d6c #118 Not tainted [ 19.435509] ----------------------------- [ 19.437267] net/ipv6/ip6_fib.c:2259 suspicious rcu_dereference_check() usage! [ 19.440790] [ 19.440790] other info that might help us debug this: [ 19.440790] [ 19.444734] [ 19.444734] rcu_scheduler_active = 2, debug_locks = 1 [ 19.447757] 2 locks held by odhcpd/3720: [ 19.449480] #0: (&p->lock){+.+.}, at: [] seq_read+0x3c/0x333 [ 19.452720] #1: (rcu_read_lock_bh){....}, at: [] ipv6_route_seq_start+0x5/0xfd [ 19.456323] [ 19.456323] stack backtrace: [ 19.458812] CPU: 0 PID: 3720 Comm: odhcpd Not tainted 4.14.0-rc3-00914-g66f5d6c #118 [ 19.462042] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 19.465414] Call Trace: [ 19.466788] dump_stack+0x86/0xc0 [ 19.468358] lockdep_rcu_suspicious+0xea/0xf3 [ 19.470183] ipv6_route_seq_next+0x71/0x164 [ 19.471963] seq_read+0x244/0x333 [ 19.473522] proc_reg_read+0x48/0x67 [ 19.475152] ? proc_reg_write+0x67/0x67 [ 19.476862] __vfs_read+0x26/0x10b [ 19.478463] ? __might_fault+0x37/0x84 [ 19.480148] vfs_read+0xba/0x146 [ 19.481690] SyS_read+0x51/0x8e [ 19.483197] do_int80_syscall_32+0x66/0x15a [ 19.484969] entry_INT80_compat+0x32/0x50 [ 19.486707] RIP: 0023:0xf7f0be8e [ 19.488244] RSP: 002b:00000000ffa75d04 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 [ 19.491431] RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 0000000008056068 [ 19.493886] RDX: 0000000000001000 RSI: 0000000008056008 RDI: 0000000000001000 [ 19.496331] RBP: 00000000000001ff R08: 0000000000000000 R09: 0000000000000000 [ 19.498768] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [ 19.501217] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Xiaolong Ye Signed-off-by: Wei Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 52a29ba329285..c2ecd5ec638aa 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2262,7 +2262,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference(((struct rt6_info *)v)->dst.rt6_next); + n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next); if (n) { ++*pos; return n; -- GitLab From cf4c950b87ee2f547ad3abd3aca6ae3f3eb3443f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 9 Oct 2017 14:30:52 -0700 Subject: [PATCH 1204/1507] once: switch to new jump label API Switch the DO_ONCE() macro from the deprecated jump label API to the new one. The new one is more readable, and for DO_ONCE() it also makes the generated code more icache-friendly: now the one-time initialization code is placed out-of-line at the jump target, rather than at the inline fallthrough case. Acked-by: Hannes Frederic Sowa Signed-off-by: Eric Biggers Signed-off-by: David S. Miller --- include/linux/once.h | 6 +++--- lib/once.c | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/linux/once.h b/include/linux/once.h index 9c98aaa87cbcd..724724918e8bc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,7 +5,7 @@ #include bool __do_once_start(bool *done, unsigned long *flags); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags); /* Call a function exactly once. The idea of DO_ONCE() is to perform @@ -38,8 +38,8 @@ void __do_once_done(bool *done, struct static_key *once_key, ({ \ bool ___ret = false; \ static bool ___done = false; \ - static struct static_key ___once_key = STATIC_KEY_INIT_TRUE; \ - if (static_key_true(&___once_key)) { \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ ___ret = __do_once_start(&___done, &___flags); \ if (unlikely(___ret)) { \ diff --git a/lib/once.c b/lib/once.c index 05c8604627eb0..831c5a6b0bb2d 100644 --- a/lib/once.c +++ b/lib/once.c @@ -5,7 +5,7 @@ struct once_work { struct work_struct work; - struct static_key *key; + struct static_key_true *key; }; static void once_deferred(struct work_struct *w) @@ -14,11 +14,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); - static_key_slow_dec(work->key); + static_branch_disable(work->key); kfree(work); } -static void once_disable_jump(struct static_key *key) +static void once_disable_jump(struct static_key_true *key) { struct once_work *w; @@ -51,7 +51,7 @@ bool __do_once_start(bool *done, unsigned long *flags) } EXPORT_SYMBOL(__do_once_start); -void __do_once_done(bool *done, struct static_key *once_key, +void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags) __releases(once_lock) { -- GitLab From ceaa001a170e43608854d5290a48064f57b565ed Mon Sep 17 00:00:00 2001 From: William Tu Date: Wed, 4 Oct 2017 17:03:12 -0700 Subject: [PATCH 1205/1507] openvswitch: Add erspan tunnel support. Add erspan netlink interface for OVS. Signed-off-by: William Tu Cc: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + net/openvswitch/flow_netlink.c | 51 +++++++++++++++++++++++++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 156ee4cab82e5..efdbfbfd3ee2a 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -359,6 +359,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, + OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index e8eb427ce6d1f..fc0ca9a89b8e6 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "flow_netlink.h" @@ -319,7 +320,8 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ } size_t ovs_key_attr_size(void) @@ -371,6 +373,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -593,6 +596,33 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } +static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + unsigned long opt_key_offset; + struct erspan_metadata opts; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + memset(&opts, 0, sizeof(opts)); + opts.index = nla_get_be32(attr); + + /* Index has only 20-bit */ + if (ntohl(opts.index) & ~INDEX_MASK) { + OVS_NLERR(log, "ERSPAN index number %x too large.", + ntohl(opts.index)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + + return 0; +} + static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -700,6 +730,19 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_ERSPAN_OPT; + opts_type = type; + break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -824,6 +867,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, + ((struct erspan_metadata *)tun_opts)->index)) + return -EMSGSIZE; } return 0; @@ -2195,6 +2242,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + break; } }; -- GitLab From 1e6f74536de08b5e50cf0e37e735911c2cef7c62 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 6 Oct 2017 13:22:31 -0400 Subject: [PATCH 1206/1507] vhost_net: do not stall on zerocopy depletion Vhost-net has a hard limit on the number of zerocopy skbs in flight. When reached, transmission stalls. Stalls cause latency, as well as head-of-line blocking of other flows that do not use zerocopy. Instead of stalling, revert to copy-based transmission. Tested by sending two udp flows from guest to host, one with payload of VHOST_GOODCOPY_LEN, the other too small for zerocopy (1B). The large flow is redirected to a netem instance with 1MBps rate limit and deep 1000 entry queue. modprobe ifb ip link set dev ifb0 up tc qdisc add dev ifb0 root netem limit 1000 rate 1MBit tc qdisc add dev tap0 ingress tc filter add dev tap0 parent ffff: protocol ip \ u32 match ip dport 8000 0xffff \ action mirred egress redirect dev ifb0 Before the delay, both flows process around 80K pps. With the delay, before this patch, both process around 400. After this patch, the large flow is still rate limited, while the small reverts to its original rate. See also discussion in the first link, below. Without rate limiting, {1, 10, 100}x TCP_STREAM tests continued to send at 100% zerocopy. The limit in vhost_exceeds_maxpend must be carefully chosen. With vq->num >> 1, the flows remain correlated. This value happens to correspond to VHOST_MAX_PENDING for vq->num == 256. Allow smaller fractions and ensure correctness also for much smaller values of vq->num, by testing the min() of both explicitly. See also the discussion in the second link below. Changes v1 -> v2 - replaced min with typed min_t - avoid unnecessary whitespace change Link:http://lkml.kernel.org/r/CAF=yD-+Wk9sc9dXMUq1+x_hh=3ThTXa6BnZkygP3tgVpjbp93g@mail.gmail.com Link:http://lkml.kernel.org/r/20170819064129.27272-1-den@klaipeden.com Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/vhost/net.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 58585ec8699e8..68677d930e201 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -436,8 +436,8 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net) struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; struct vhost_virtqueue *vq = &nvq->vq; - return (nvq->upend_idx + vq->num - VHOST_MAX_PEND) % UIO_MAXIOV - == nvq->done_idx; + return (nvq->upend_idx + UIO_MAXIOV - nvq->done_idx) % UIO_MAXIOV > + min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2); } /* Expects to be always run from workqueue - which acts as @@ -480,11 +480,6 @@ static void handle_tx(struct vhost_net *net) if (zcopy) vhost_zerocopy_signal_used(net, vq); - /* If more outstanding DMAs, queue the work. - * Handle upend_idx wrap around - */ - if (unlikely(vhost_exceeds_maxpend(net))) - break; head = vhost_net_tx_get_vq_desc(net, vq, vq->iov, ARRAY_SIZE(vq->iov), @@ -519,8 +514,7 @@ static void handle_tx(struct vhost_net *net) len = msg_data_left(&msg); zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN - && (nvq->upend_idx + 1) % UIO_MAXIOV != - nvq->done_idx + && !vhost_exceeds_maxpend(net) && vhost_net_tx_select_zcopy(net); /* use msg_control to pass vhost zerocopy ubuf info to skb */ -- GitLab From 812b5ca7d376e7e008ac0c897d1ef94eb05ddc3b Mon Sep 17 00:00:00 2001 From: Bernd Edlinger Date: Sun, 8 Oct 2017 13:40:08 +0000 Subject: [PATCH 1207/1507] Add a driver for Renesas uPD60620 and uPD60620A PHYs Signed-off-by: Bernd Edlinger Signed-off-by: David S. Miller --- drivers/net/phy/Kconfig | 5 ++ drivers/net/phy/Makefile | 1 + drivers/net/phy/uPD60620.c | 109 +++++++++++++++++++++++++++++++++++++ 3 files changed, 115 insertions(+) create mode 100644 drivers/net/phy/uPD60620.c diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index cd931cf9dcc26..e2cf8ffc5c6f2 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -366,6 +366,11 @@ config REALTEK_PHY ---help--- Supports the Realtek 821x PHY. +config RENESAS_PHY + tristate "Driver for Renesas PHYs" + ---help--- + Supports the Renesas PHYs uPD60620 and uPD60620A. + config ROCKCHIP_PHY tristate "Driver for Rockchip Ethernet PHYs" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 416df92fbf4f6..1404ad3b77c79 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -72,6 +72,7 @@ obj-$(CONFIG_MICROSEMI_PHY) += mscc.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o obj-$(CONFIG_REALTEK_PHY) += realtek.o +obj-$(CONFIG_RENESAS_PHY) += uPD60620.o obj-$(CONFIG_ROCKCHIP_PHY) += rockchip.o obj-$(CONFIG_SMSC_PHY) += smsc.o obj-$(CONFIG_STE10XP) += ste10Xp.o diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c new file mode 100644 index 0000000000000..96b33475ea5ef --- /dev/null +++ b/drivers/net/phy/uPD60620.c @@ -0,0 +1,109 @@ +/* + * Driver for the Renesas PHY uPD60620. + * + * Copyright (C) 2015 Softing Industrial Automation GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + */ + +#include +#include +#include + +#define UPD60620_PHY_ID 0xb8242824 + +/* Extended Registers and values */ +/* PHY Special Control/Status */ +#define PHY_PHYSCR 0x1F /* PHY.31 */ +#define PHY_PHYSCR_10MB 0x0004 /* PHY speed = 10mb */ +#define PHY_PHYSCR_100MB 0x0008 /* PHY speed = 100mb */ +#define PHY_PHYSCR_DUPLEX 0x0010 /* PHY Duplex */ + +/* PHY Special Modes */ +#define PHY_SPM 0x12 /* PHY.18 */ + +/* Init PHY */ + +static int upd60620_config_init(struct phy_device *phydev) +{ + /* Enable support for passive HUBs (could be a strap option) */ + /* PHYMODE: All speeds, HD in parallel detect */ + return phy_write(phydev, PHY_SPM, 0x0180 | phydev->mdio.addr); +} + +/* Get PHY status from common registers */ + +static int upd60620_read_status(struct phy_device *phydev) +{ + int phy_state; + + /* Read negotiated state */ + phy_state = phy_read(phydev, MII_BMSR); + if (phy_state < 0) + return phy_state; + + phydev->link = 0; + phydev->lp_advertising = 0; + phydev->pause = 0; + phydev->asym_pause = 0; + + if (phy_state & (BMSR_ANEGCOMPLETE | BMSR_LSTATUS)) { + phy_state = phy_read(phydev, PHY_PHYSCR); + if (phy_state < 0) + return phy_state; + + if (phy_state & (PHY_PHYSCR_10MB | PHY_PHYSCR_100MB)) { + phydev->link = 1; + phydev->speed = SPEED_10; + phydev->duplex = DUPLEX_HALF; + + if (phy_state & PHY_PHYSCR_100MB) + phydev->speed = SPEED_100; + if (phy_state & PHY_PHYSCR_DUPLEX) + phydev->duplex = DUPLEX_FULL; + + phy_state = phy_read(phydev, MII_LPA); + if (phy_state < 0) + return phy_state; + + phydev->lp_advertising + = mii_lpa_to_ethtool_lpa_t(phy_state); + + if (phydev->duplex == DUPLEX_FULL) { + if (phy_state & LPA_PAUSE_CAP) + phydev->pause = 1; + if (phy_state & LPA_PAUSE_ASYM) + phydev->asym_pause = 1; + } + } + } + return 0; +} + +MODULE_DESCRIPTION("Renesas uPD60620 PHY driver"); +MODULE_AUTHOR("Bernd Edlinger "); +MODULE_LICENSE("GPL"); + +static struct phy_driver upd60620_driver[1] = { { + .phy_id = UPD60620_PHY_ID, + .phy_id_mask = 0xfffffffe, + .name = "Renesas uPD60620", + .features = PHY_BASIC_FEATURES, + .flags = 0, + .config_init = upd60620_config_init, + .config_aneg = genphy_config_aneg, + .read_status = upd60620_read_status, +} }; + +module_phy_driver(upd60620_driver); + +static struct mdio_device_id __maybe_unused upd60620_tbl[] = { + { UPD60620_PHY_ID, 0xfffffffe }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, upd60620_tbl); -- GitLab From c4c40e51f9c32c6dd8adf606624c930a1c4d9bbb Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 21 Jul 2017 11:36:23 -0700 Subject: [PATCH 1208/1507] e1000e: Fix error path in link detection In case of error from e1e_rphy(), the loop will exit early and "success" will be set to true erroneously. Signed-off-by: Benjamin Poirier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/phy.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index d78d47b41a716..86ff0969efb6e 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1744,6 +1744,7 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, s32 ret_val = 0; u16 i, phy_status; + *success = false; for (i = 0; i < iterations; i++) { /* Some PHYs require the MII_BMSR register to be read * twice due to the link bit being sticky. No harm doing @@ -1763,16 +1764,16 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, ret_val = e1e_rphy(hw, MII_BMSR, &phy_status); if (ret_val) break; - if (phy_status & BMSR_LSTATUS) + if (phy_status & BMSR_LSTATUS) { + *success = true; break; + } if (usec_interval >= 1000) msleep(usec_interval / 1000); else udelay(usec_interval); } - *success = (i < iterations); - return ret_val; } -- GitLab From 65a29da1f5fd20fdebef3b959bef9b3660807b20 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 21 Jul 2017 11:36:24 -0700 Subject: [PATCH 1209/1507] e1000e: Fix wrong comment related to link detection Reading e1000e_check_for_copper_link() shows that get_link_status is set to false after link has been detected. Therefore, it stays TRUE until then. Signed-off-by: Benjamin Poirier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 8436c5f2c3e81..ead4c112580e6 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5074,7 +5074,7 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) /* get_link_status is set on LSC (link status) interrupt or * Rx sequence error interrupt. get_link_status will stay - * false until the check_for_link establishes link + * true until the check_for_link establishes link * for copper adapters ONLY */ switch (hw->phy.media_type) { @@ -5092,7 +5092,7 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) break; case e1000_media_type_internal_serdes: ret_val = hw->mac.ops.check_for_link(hw); - link_active = adapter->hw.mac.serdes_has_link; + link_active = hw->mac.serdes_has_link; break; default: case e1000_media_type_unknown: -- GitLab From d3509f8bc7b0560044c15f0e3ecfde1d9af757a6 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 21 Jul 2017 11:36:25 -0700 Subject: [PATCH 1210/1507] e1000e: Fix return value test All the helpers return -E1000_ERR_PHY. Signed-off-by: Benjamin Poirier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index ead4c112580e6..a740de6a30b03 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5099,7 +5099,7 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) break; } - if ((ret_val == E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && + if ((ret_val == -E1000_ERR_PHY) && (hw->phy.type == e1000_phy_igp_3) && (er32(CTRL) & E1000_PHY_CTRL_GBE_DISABLE)) { /* See e1000_kmrn_lock_loss_workaround_ich8lan() */ e_info("Gigabit has been disabled, downgrading speed\n"); -- GitLab From 19110cfbb34d4af0cdfe14cd243f3b09dc95b013 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 21 Jul 2017 11:36:26 -0700 Subject: [PATCH 1211/1507] e1000e: Separate signaling for link check/link up Lennart reported the following race condition: \ e1000_watchdog_task \ e1000e_has_link \ hw->mac.ops.check_for_link() === e1000e_check_for_copper_link /* link is up */ mac->get_link_status = false; /* interrupt */ \ e1000_msix_other hw->mac.get_link_status = true; link_active = !hw->mac.get_link_status /* link_active is false, wrongly */ This problem arises because the single flag get_link_status is used to signal two different states: link status needs checking and link status is down. Avoid the problem by using the return value of .check_for_link to signal the link status to e1000e_has_link(). Reported-by: Lennart Sorensen Signed-off-by: Benjamin Poirier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/mac.c | 11 ++++++++--- drivers/net/ethernet/intel/e1000e/netdev.c | 2 +- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index b322011ec2828..f457c5703d0c4 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -410,6 +410,9 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw) * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. + * + * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link + * up). **/ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) { @@ -423,7 +426,7 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 0; + return 1; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex @@ -461,10 +464,12 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) + if (ret_val) { e_dbg("Error configuring flow control\n"); + return ret_val; + } - return ret_val; + return 1; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a740de6a30b03..0a5f95ab0d3c5 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5081,7 +5081,7 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) case e1000_media_type_copper: if (hw->mac.get_link_status) { ret_val = hw->mac.ops.check_for_link(hw); - link_active = !hw->mac.get_link_status; + link_active = ret_val > 0; } else { link_active = true; } -- GitLab From 4aea7a5c5e940c1723add439f4088844cd26196d Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 21 Jul 2017 11:36:27 -0700 Subject: [PATCH 1212/1507] e1000e: Avoid receiver overrun interrupt bursts When e1000e_poll() is not fast enough to keep up with incoming traffic, the adapter (when operating in msix mode) raises the Other interrupt to signal Receiver Overrun. This is a double problem because 1) at the moment e1000_msix_other() assumes that it is only called in case of Link Status Change and 2) if the condition persists, the interrupt is repeatedly raised again in quick succession. Ideally we would configure the Other interrupt to not be raised in case of receiver overrun but this doesn't seem possible on this adapter. Instead, we handle the first part of the problem by reverting to the practice of reading ICR in the other interrupt handler, like before commit 16ecba59bc33 ("e1000e: Do not read ICR in Other interrupt"). Thanks to commit 0a8047ac68e5 ("e1000e: Fix msi-x interrupt automask") which cleared IAME from CTRL_EXT, reading ICR doesn't interfere with RxQ0, TxQ0 interrupts anymore. We handle the second part of the problem by not re-enabling the Other interrupt right away when there is overrun. Instead, we wait until traffic subsides, napi polling mode is exited and interrupts are re-enabled. Reported-by: Lennart Sorensen Fixes: 16ecba59bc33 ("e1000e: Do not read ICR in Other interrupt") Signed-off-by: Benjamin Poirier Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/defines.h | 1 + drivers/net/ethernet/intel/e1000e/netdev.c | 33 ++++++++++++++++----- 2 files changed, 26 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 0641c00987380..afb7ebe20b243 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -398,6 +398,7 @@ #define E1000_ICR_LSC 0x00000004 /* Link Status Change */ #define E1000_ICR_RXSEQ 0x00000008 /* Rx sequence error */ #define E1000_ICR_RXDMT0 0x00000010 /* Rx desc min. threshold (0) */ +#define E1000_ICR_RXO 0x00000040 /* Receiver Overrun */ #define E1000_ICR_RXT0 0x00000080 /* Rx timer intr (ring 0) */ #define E1000_ICR_ECCER 0x00400000 /* Uncorrectable ECC Error */ /* If this bit asserted, the driver should claim the interrupt */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 0a5f95ab0d3c5..ee9de35003314 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1910,14 +1910,30 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 icr; + bool enable = true; + + icr = er32(ICR); + if (icr & E1000_ICR_RXO) { + ew32(ICR, E1000_ICR_RXO); + enable = false; + /* napi poll will re-enable Other, make sure it runs */ + if (napi_schedule_prep(&adapter->napi)) { + adapter->total_rx_bytes = 0; + adapter->total_rx_packets = 0; + __napi_schedule(&adapter->napi); + } + } + if (icr & E1000_ICR_LSC) { + ew32(ICR, E1000_ICR_LSC); + hw->mac.get_link_status = true; + /* guard against interrupt when we're going down */ + if (!test_bit(__E1000_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); + } - hw->mac.get_link_status = true; - - /* guard against interrupt when we're going down */ - if (!test_bit(__E1000_DOWN, &adapter->state)) { - mod_timer(&adapter->watchdog_timer, jiffies + 1); + if (enable && !test_bit(__E1000_DOWN, &adapter->state)) ew32(IMS, E1000_IMS_OTHER); - } return IRQ_HANDLED; } @@ -2687,7 +2703,8 @@ static int e1000e_poll(struct napi_struct *napi, int weight) napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) - ew32(IMS, adapter->rx_ring->ims_val); + ew32(IMS, adapter->rx_ring->ims_val | + E1000_IMS_OTHER); else e1000_irq_enable(adapter); } @@ -4204,7 +4221,7 @@ static void e1000e_trigger_lsc(struct e1000_adapter *adapter) struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) - ew32(ICS, E1000_ICS_OTHER); + ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER); else ew32(ICS, E1000_ICS_LSC); } -- GitLab From b10effb92e272051dd1ec0d7be56bf9ca85ab927 Mon Sep 17 00:00:00 2001 From: Sasha Neftin Date: Sun, 6 Aug 2017 16:49:18 +0300 Subject: [PATCH 1213/1507] e1000e: fix buffer overrun while the I219 is processing DMA transactions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Intel® 100/200 Series Chipset platforms reduced the round-trip latency for the LAN Controller DMA accesses, causing in some high performance cases a buffer overrun while the I219 LAN Connected Device is processing the DMA transactions. I219LM and I219V devices can fall into unrecovered Tx hang under very stressfully UDP traffic and multiple reconnection of Ethernet cable. This Tx hang of the LAN Controller is only recovered if the system is rebooted. Slightly slow down DMA access by reducing the number of outstanding requests. This workaround could have an impact on TCP traffic performance on the platform. Disabling TSO eliminates performance loss for TCP traffic without a noticeable impact on CPU performance. Please, refer to I218/I219 specification update: https://www.intel.com/content/www/us/en/embedded/products/networking/ ethernet-connection-i218-family-documentation.html Signed-off-by: Sasha Neftin Reviewed-by: Dima Ruinskiy Reviewed-by: Raanan Avargil Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index ee9de35003314..14b096f3d1da4 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3021,8 +3021,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) hw->mac.ops.config_collision_dist(hw); - /* SPT and CNP Si errata workaround to avoid data corruption */ - if (hw->mac.type >= e1000_pch_spt) { + /* SPT and KBL Si errata workaround to avoid data corruption */ + if (hw->mac.type == e1000_pch_spt) { u32 reg_val; reg_val = er32(IOSFPC); @@ -3030,7 +3030,9 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) ew32(IOSFPC, reg_val); reg_val = er32(TARC(0)); - reg_val |= E1000_TARC0_CB_MULTIQ_3_REQ; + /* SPT and KBL Si errata workaround to avoid Tx hang */ + reg_val &= ~BIT(28); + reg_val |= BIT(29); ew32(TARC(0), reg_val); } } -- GitLab From 48072ae1ec7a1c778771cad8c1b8dd803c4992ab Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 25 Aug 2017 11:06:26 -0400 Subject: [PATCH 1214/1507] e1000e: apply burst mode settings only on default Devices that support FLAG2_DMA_BURST have different default values for RDTR and RADV. Apply burst mode default settings only when no explicit value was passed at module load. The RDTR default is zero. If the module is loaded for low latency operation with RxIntDelay=0, do not override this value with a burst default of 32. Move the decision to apply burst values earlier, where explicitly initialized module variables can be distinguished from defaults. Signed-off-by: Willem de Bruijn Acked-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/e1000.h | 4 ---- drivers/net/ethernet/intel/e1000e/netdev.c | 8 -------- drivers/net/ethernet/intel/e1000e/param.c | 16 +++++++++++++++- 3 files changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 98e68888abb1d..2311b31bdcac9 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -94,10 +94,6 @@ struct e1000_info; */ #define E1000_CHECK_RESET_COUNT 25 -#define DEFAULT_RDTR 0 -#define DEFAULT_RADV 8 -#define BURST_RDTR 0x20 -#define BURST_RADV 0x20 #define PCICFG_DESC_RING_STATUS 0xe4 #define FLUSH_DESC_REQUIRED 0x100 diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 14b096f3d1da4..00f48d4cabec0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3242,14 +3242,6 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) */ ew32(RXDCTL(0), E1000_RXDCTL_DMA_BURST_ENABLE); ew32(RXDCTL(1), E1000_RXDCTL_DMA_BURST_ENABLE); - - /* override the delay timers for enabling bursting, only if - * the value was not set by the user via module options - */ - if (adapter->rx_int_delay == DEFAULT_RDTR) - adapter->rx_int_delay = BURST_RDTR; - if (adapter->rx_abs_int_delay == DEFAULT_RADV) - adapter->rx_abs_int_delay = BURST_RADV; } /* set the Receive Delay Timer Register */ diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index 6d8c39abee167..47da518645437 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -73,17 +73,25 @@ E1000_PARAM(TxAbsIntDelay, "Transmit Absolute Interrupt Delay"); /* Receive Interrupt Delay in units of 1.024 microseconds * hardware will likely hang if you set this to anything but zero. * + * Burst variant is used as default if device has FLAG2_DMA_BURST. + * * Valid Range: 0-65535 */ E1000_PARAM(RxIntDelay, "Receive Interrupt Delay"); +#define DEFAULT_RDTR 0 +#define BURST_RDTR 0x20 #define MAX_RXDELAY 0xFFFF #define MIN_RXDELAY 0 /* Receive Absolute Interrupt Delay in units of 1.024 microseconds + * + * Burst variant is used as default if device has FLAG2_DMA_BURST. * * Valid Range: 0-65535 */ E1000_PARAM(RxAbsIntDelay, "Receive Absolute Interrupt Delay"); +#define DEFAULT_RADV 8 +#define BURST_RADV 0x20 #define MAX_RXABSDELAY 0xFFFF #define MIN_RXABSDELAY 0 @@ -297,6 +305,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RDTR; + if (num_RxIntDelay > bd) { adapter->rx_int_delay = RxIntDelay[bd]; e1000_validate_option(&adapter->rx_int_delay, &opt, @@ -307,7 +318,7 @@ void e1000e_check_options(struct e1000_adapter *adapter) } /* Receive Absolute Interrupt Delay */ { - static const struct e1000_option opt = { + static struct e1000_option opt = { .type = range_option, .name = "Receive Absolute Interrupt Delay", .err = "using default of " @@ -317,6 +328,9 @@ void e1000e_check_options(struct e1000_adapter *adapter) .max = MAX_RXABSDELAY } } }; + if (adapter->flags2 & FLAG2_DMA_BURST) + opt.def = BURST_RADV; + if (num_RxAbsIntDelay > bd) { adapter->rx_abs_int_delay = RxAbsIntDelay[bd]; e1000_validate_option(&adapter->rx_abs_int_delay, &opt, -- GitLab From 377b62736c01f14309141c69caa6d84363c12e12 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 25 Aug 2017 18:14:24 -0700 Subject: [PATCH 1215/1507] e1000e: Be drop monitor friendly e1000e_put_txbuf() can be called from normal reclamation path as well as when a DMA mapping failure, so we need to differentiate these two cases when freeing SKBs to be drop monitor friendly. e1000e_tx_hwtstamp_work() and e1000_remove() are processing TX timestamped SKBs and those should not be accounted as drops either. Signed-off-by: Florian Fainelli Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/e1000e/netdev.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 00f48d4cabec0..bf8f38f769534 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1071,7 +1071,8 @@ static bool e1000_clean_rx_irq(struct e1000_ring *rx_ring, int *work_done, } static void e1000_put_txbuf(struct e1000_ring *tx_ring, - struct e1000_buffer *buffer_info) + struct e1000_buffer *buffer_info, + bool drop) { struct e1000_adapter *adapter = tx_ring->adapter; @@ -1085,7 +1086,10 @@ static void e1000_put_txbuf(struct e1000_ring *tx_ring, buffer_info->dma = 0; } if (buffer_info->skb) { - dev_kfree_skb_any(buffer_info->skb); + if (drop) + dev_kfree_skb_any(buffer_info->skb); + else + dev_consume_skb_any(buffer_info->skb); buffer_info->skb = NULL; } buffer_info->time_stamp = 0; @@ -1199,7 +1203,7 @@ static void e1000e_tx_hwtstamp_work(struct work_struct *work) wmb(); /* force write prior to skb_tstamp_tx */ skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } else if (time_after(jiffies, adapter->tx_hwtstamp_start + adapter->tx_timeout_factor * HZ)) { dev_kfree_skb_any(adapter->tx_hwtstamp_skb); @@ -1254,7 +1258,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring) } } - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); tx_desc->upper.data = 0; i++; @@ -2437,7 +2441,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring) for (i = 0; i < tx_ring->count; i++) { buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, false); } netdev_reset_queue(adapter->netdev); @@ -5625,7 +5629,7 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, i += tx_ring->count; i--; buffer_info = &tx_ring->buffer_info[i]; - e1000_put_txbuf(tx_ring, buffer_info); + e1000_put_txbuf(tx_ring, buffer_info, true); } return 0; @@ -7419,7 +7423,7 @@ static void e1000_remove(struct pci_dev *pdev) if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { cancel_work_sync(&adapter->tx_hwtstamp_work); if (adapter->tx_hwtstamp_skb) { - dev_kfree_skb_any(adapter->tx_hwtstamp_skb); + dev_consume_skb_any(adapter->tx_hwtstamp_skb); adapter->tx_hwtstamp_skb = NULL; } } -- GitLab From 18eb86362a52f0af933cc0fd5e37027317eb2d1c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 27 Aug 2017 08:39:51 +0200 Subject: [PATCH 1216/1507] igb: check memory allocation failure Check memory allocation failures and return -ENOMEM in such cases, as already done for other memory allocations in this function. This avoids NULL pointers dereference. Signed-off-by: Christophe JAILLET Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fd4a46b03cc83..837d9b46a3905 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3162,6 +3162,8 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Setup and initialize a copy of the hw vlan table array */ adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), GFP_ATOMIC); + if (!adapter->shadow_vfta) + return -ENOMEM; /* This call may decrease the number of queues */ if (igb_init_interrupt_scheme(adapter, true)) { -- GitLab From b2427e671766c51379bc882fdf809d905c6f9619 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 10 Oct 2017 18:01:16 +0100 Subject: [PATCH 1217/1507] ipv6: fix dereference of rt6_ex before null check error Currently rt6_ex is being dereferenced before it is null checked hence there is a possible null dereference bug. Fix this by only dereferencing rt6_ex after it has been null checked. Detected by CoverityScan, CID#1457749 ("Dereference before null check") Fixes: 81eb8447daae ("ipv6: take care of rt6_stats") Signed-off-by: Colin Ian King Reviewed-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv6/route.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 13b0d6d1cc303..c1c44f484286c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1142,10 +1142,12 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { - struct net *net = dev_net(rt6_ex->rt6i->dst.dev); + struct net *net; if (!bucket || !rt6_ex) return; + + net = dev_net(rt6_ex->rt6i->dst.dev); rt6_ex->rt6i->rt6i_node = NULL; hlist_del_rcu(&rt6_ex->hlist); rt6_release(rt6_ex->rt6i); -- GitLab From 442d713baa33db0f78adadee6125c215f10f5a75 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 10 Oct 2017 19:10:30 +0100 Subject: [PATCH 1218/1507] ipv6: fix incorrect bitwise operator used on rt6i_flags The use of the | operator always leads to true which looks rather suspect to me. Fix this by using & instead to just check the RTF_CACHE entry bit. Detected by CoverityScan, CID#1457734, #1457747 ("Wrong operator used") Fixes: 35732d01fe31 ("ipv6: introduce a hash table to store dst cache") Signed-off-by: Colin Ian King Acked-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv6/route.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c1c44f484286c..2e8842fa6450d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1415,7 +1415,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt) int err; if (!from || - !(rt->rt6i_flags | RTF_CACHE)) + !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (!rcu_access_pointer(from->rt6i_exception_bucket)) @@ -1459,7 +1459,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) struct rt6_exception *rt6_ex; if (!from || - !(rt->rt6i_flags | RTF_CACHE)) + !(rt->rt6i_flags & RTF_CACHE)) return; rcu_read_lock(); -- GitLab From a99ca6dbf429fe6c035cfb880d91bf6a223fcd3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:09 -0700 Subject: [PATCH 1219/1507] selftests/bpf: add a test for verifier logs Add a test for verifier log handling. Check bad attr combinations but focus on cases when log is truncated. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/Makefile | 2 +- .../testing/selftests/bpf/test_verifier_log.c | 171 ++++++++++++++++++ 2 files changed, 172 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/test_verifier_log.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 924af8d79bded..2e7880ea0addd 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -12,7 +12,7 @@ CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../i LDLIBS += -lcap -lelf TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align + test_align test_verifier_log TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c new file mode 100644 index 0000000000000..3cc0b561489ea --- /dev/null +++ b/tools/testing/selftests/bpf/test_verifier_log.c @@ -0,0 +1,171 @@ +#include +#include +#include +#include +#include + +#include +#include +#include + +#include + +#define LOG_SIZE (1 << 20) + +#define err(str...) printf("ERROR: " str) + +static const struct bpf_insn code_sample[] = { + /* We need a few instructions to pass the min log length */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static int load(char *log, size_t log_len, int log_level) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn)); + attr.insns = ptr_to_u64(code_sample); + attr.license = ptr_to_u64("GPL"); + attr.log_buf = ptr_to_u64(log); + attr.log_size = log_len; + attr.log_level = log_level; + + return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); +} + +static void check_ret(int ret, int exp_errno) +{ + if (ret > 0) { + close(ret); + err("broken sample loaded successfully!?\n"); + exit(1); + } + + if (!ret || errno != exp_errno) { + err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n", + ret, errno, -1, exp_errno); + exit(1); + } +} + +static void check_ones(const char *buf, size_t len, const char *msg) +{ + while (len--) + if (buf[len] != 1) { + err("%s", msg); + exit(1); + } +} + +static void test_log_good(char *log, size_t buf_len, size_t log_len, + size_t exp_len, int exp_errno, const char *full_log) +{ + size_t len; + int ret; + + memset(log, 1, buf_len); + + ret = load(log, log_len, 1); + check_ret(ret, exp_errno); + + len = strnlen(log, buf_len); + if (len == buf_len) { + err("verifier did not NULL terminate the log\n"); + exit(1); + } + if (exp_len && len != exp_len) { + err("incorrect log length expected:%zd have:%zd\n", + exp_len, len); + exit(1); + } + + if (strchr(log, 1)) { + err("verifier leaked a byte through\n"); + exit(1); + } + + check_ones(log + len + 1, buf_len - len - 1, + "verifier wrote bytes past NULL termination\n"); + + if (memcmp(full_log, log, LOG_SIZE)) { + err("log did not match expected output\n"); + exit(1); + } +} + +static void test_log_bad(char *log, size_t log_len, int log_level) +{ + int ret; + + ret = load(log, log_len, log_level); + check_ret(ret, EINVAL); + if (log) + check_ones(log, LOG_SIZE, + "verifier touched log with bad parameters\n"); +} + +int main(int argc, char **argv) +{ + char full_log[LOG_SIZE]; + char log[LOG_SIZE]; + size_t want_len; + int i; + + memset(log, 1, LOG_SIZE); + + /* Test incorrect attr */ + printf("Test log_level 0...\n"); + test_log_bad(log, LOG_SIZE, 0); + + printf("Test log_size < 128...\n"); + test_log_bad(log, 15, 1); + + printf("Test log_buff = NULL...\n"); + test_log_bad(NULL, LOG_SIZE, 1); + + /* Test with log big enough */ + printf("Test oversized buffer...\n"); + test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log); + + want_len = strlen(full_log); + + printf("Test exact buffer...\n"); + test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log); + + printf("Test undersized buffers...\n"); + for (i = 0; i < 64; i++) { + full_log[want_len - i + 1] = 1; + full_log[want_len - i] = 0; + + test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i, + ENOSPC, full_log); + } + + printf("test_verifier_log: OK\n"); + return 0; +} -- GitLab From e7bf8249e8f1bac64885eeccb55bcf6111901a81 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:10 -0700 Subject: [PATCH 1220/1507] bpf: encapsulate verifier log state into a structure Put the loose log_* variables into a structure. This will make it simpler to remove the global verifier state in following patches. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 13 ++++++++ kernel/bpf/verifier.c | 57 +++++++++++++++++++----------------- 2 files changed, 43 insertions(+), 27 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b8d200f60a409..163541ba70d97 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -115,6 +115,19 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +struct bpf_verifer_log { + u32 level; + char *kbuf; + char __user *ubuf; + u32 len_used; + u32 len_total; +}; + +static inline bool bpf_verifier_log_full(const struct bpf_verifer_log *log) +{ + return log->len_used >= log->len_total - 1; +} + struct bpf_verifier_env; struct bpf_ext_analyzer_ops { int (*insn_hook)(struct bpf_verifier_env *env, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6352a88ca6d16..e53458b022493 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -156,8 +156,7 @@ struct bpf_call_arg_meta { /* verbose verifier prints what it's seeing * bpf_check() is called under lock, so no race to access these global vars */ -static u32 log_level, log_size, log_len; -static char *log_buf; +static struct bpf_verifer_log verifier_log; static DEFINE_MUTEX(bpf_verifier_lock); @@ -167,13 +166,15 @@ static DEFINE_MUTEX(bpf_verifier_lock); */ static __printf(1, 2) void verbose(const char *fmt, ...) { + struct bpf_verifer_log *log = &verifier_log; va_list args; - if (log_level == 0 || log_len >= log_size - 1) + if (!log->level || bpf_verifier_log_full(log)) return; va_start(args, fmt); - log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + log->len_used += vscnprintf(log->kbuf + log->len_used, + log->len_total - log->len_used, fmt, args); va_end(args); } @@ -886,7 +887,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (log_level) + if (verifier_log.level) print_verifier_state(state); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a @@ -2956,7 +2957,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; } - if (log_level) + if (verifier_log.level) print_verifier_state(this_branch); return 0; } @@ -3712,7 +3713,7 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (log_level) { + if (verifier_log.level) { if (do_print_state) verbose("\nfrom %d to %d: safe\n", prev_insn_idx, insn_idx); @@ -3725,8 +3726,9 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (log_level > 1 || (log_level && do_print_state)) { - if (log_level > 1) + if (verifier_log.level > 1 || + (verifier_log.level && do_print_state)) { + if (verifier_log.level > 1) verbose("%d:", insn_idx); else verbose("\nfrom %d to %d:", @@ -3735,7 +3737,7 @@ static int do_check(struct bpf_verifier_env *env) do_print_state = false; } - if (log_level) { + if (verifier_log.level) { verbose("%d: ", insn_idx); print_bpf_insn(env, insn); } @@ -4389,7 +4391,7 @@ static void free_states(struct bpf_verifier_env *env) int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { - char __user *log_ubuf = NULL; + struct bpf_verifer_log *log = &verifier_log; struct bpf_verifier_env *env; int ret = -EINVAL; @@ -4414,23 +4416,23 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* user requested verbose verifier output * and supplied buffer to store the verification trace */ - log_level = attr->log_level; - log_ubuf = (char __user *) (unsigned long) attr->log_buf; - log_size = attr->log_size; - log_len = 0; + log->level = attr->log_level; + log->ubuf = (char __user *) (unsigned long) attr->log_buf; + log->len_total = attr->log_size; + log->len_used = 0; ret = -EINVAL; - /* log_* values have to be sane */ - if (log_size < 128 || log_size > UINT_MAX >> 8 || - log_level == 0 || log_ubuf == NULL) + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) goto err_unlock; ret = -ENOMEM; - log_buf = vmalloc(log_size); - if (!log_buf) + log->kbuf = vmalloc(log->len_total); + if (!log->kbuf) goto err_unlock; } else { - log_level = 0; + log->level = 0; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); @@ -4467,15 +4469,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (ret == 0) ret = fixup_bpf_calls(env); - if (log_level && log_len >= log_size - 1) { - BUG_ON(log_len >= log_size); + if (log->level && bpf_verifier_log_full(log)) { + BUG_ON(log->len_used >= log->len_total); /* verifier log exceeded user supplied buffer */ ret = -ENOSPC; /* fall through to return what was recorded */ } /* copy verifier log back to user space including trailing zero */ - if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + if (log->level && copy_to_user(log->ubuf, log->kbuf, + log->len_used + 1) != 0) { ret = -EFAULT; goto free_log_buf; } @@ -4502,8 +4505,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) } free_log_buf: - if (log_level) - vfree(log_buf); + if (log->level) + vfree(log->kbuf); if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. @@ -4540,7 +4543,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); - log_level = 0; + verifier_log.level = 0; env->strict_alignment = false; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) -- GitLab From 61bd5218eef349fcacc4976a251bc83a4748b4af Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:11 -0700 Subject: [PATCH 1221/1507] bpf: move global verifier log into verifier environment The biggest piece of global state protected by the verifier lock is the verifier_log. Move that log to struct bpf_verifier_env. struct bpf_verifier_env has to be passed now to all invocations of verbose(). Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 2 + kernel/bpf/verifier.c | 491 ++++++++++++++++++----------------- 2 files changed, 261 insertions(+), 232 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 163541ba70d97..5ddb9a626a51e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -152,6 +152,8 @@ struct bpf_verifier_env { bool allow_ptr_leaks; bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ + + struct bpf_verifer_log log; }; int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e53458b022493..a352f93cd4b2f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -153,20 +153,16 @@ struct bpf_call_arg_meta { int access_size; }; -/* verbose verifier prints what it's seeing - * bpf_check() is called under lock, so no race to access these global vars - */ -static struct bpf_verifer_log verifier_log; - static DEFINE_MUTEX(bpf_verifier_lock); /* log_level controls verbosity level of eBPF verifier. * verbose() is used to dump the verification trace to the log, so the user * can figure out what's wrong with the program */ -static __printf(1, 2) void verbose(const char *fmt, ...) +static __printf(2, 3) void verbose(struct bpf_verifier_env *env, + const char *fmt, ...) { - struct bpf_verifer_log *log = &verifier_log; + struct bpf_verifer_log *log = &env->log; va_list args; if (!log->level || bpf_verifier_log_full(log)) @@ -214,7 +210,8 @@ static const char *func_id_name(int id) return "unknown"; } -static void print_verifier_state(struct bpf_verifier_state *state) +static void print_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state *state) { struct bpf_reg_state *reg; enum bpf_reg_type t; @@ -225,21 +222,21 @@ static void print_verifier_state(struct bpf_verifier_state *state) t = reg->type; if (t == NOT_INIT) continue; - verbose(" R%d=%s", i, reg_type_str[t]); + verbose(env, " R%d=%s", i, reg_type_str[t]); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ - verbose("%lld", reg->var_off.value + reg->off); + verbose(env, "%lld", reg->var_off.value + reg->off); } else { - verbose("(id=%d", reg->id); + verbose(env, "(id=%d", reg->id); if (t != SCALAR_VALUE) - verbose(",off=%d", reg->off); + verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) - verbose(",r=%d", reg->range); + verbose(env, ",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || t == PTR_TO_MAP_VALUE_OR_NULL) - verbose(",ks=%d,vs=%d", + verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); if (tnum_is_const(reg->var_off)) { @@ -247,38 +244,38 @@ static void print_verifier_state(struct bpf_verifier_state *state) * could be a pointer whose offset is too big * for reg->off */ - verbose(",imm=%llx", reg->var_off.value); + verbose(env, ",imm=%llx", reg->var_off.value); } else { if (reg->smin_value != reg->umin_value && reg->smin_value != S64_MIN) - verbose(",smin_value=%lld", + verbose(env, ",smin_value=%lld", (long long)reg->smin_value); if (reg->smax_value != reg->umax_value && reg->smax_value != S64_MAX) - verbose(",smax_value=%lld", + verbose(env, ",smax_value=%lld", (long long)reg->smax_value); if (reg->umin_value != 0) - verbose(",umin_value=%llu", + verbose(env, ",umin_value=%llu", (unsigned long long)reg->umin_value); if (reg->umax_value != U64_MAX) - verbose(",umax_value=%llu", + verbose(env, ",umax_value=%llu", (unsigned long long)reg->umax_value); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(",var_off=%s", tn_buf); + verbose(env, ",var_off=%s", tn_buf); } } - verbose(")"); + verbose(env, ")"); } } for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] == STACK_SPILL) - verbose(" fp%d=%s", -MAX_BPF_STACK + i, + verbose(env, " fp%d=%s", -MAX_BPF_STACK + i, reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]); } - verbose("\n"); + verbose(env, "\n"); } static const char *const bpf_class_string[] = { @@ -333,15 +330,15 @@ static const char *const bpf_jmp_string[16] = { [BPF_EXIT >> 4] = "exit", }; -static void print_bpf_end_insn(const struct bpf_verifier_env *env, +static void print_bpf_end_insn(struct bpf_verifier_env *env, const struct bpf_insn *insn) { - verbose("(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", insn->imm, insn->dst_reg); } -static void print_bpf_insn(const struct bpf_verifier_env *env, +static void print_bpf_insn(struct bpf_verifier_env *env, const struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); @@ -349,23 +346,23 @@ static void print_bpf_insn(const struct bpf_verifier_env *env, if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) - verbose("BUG_alu64_%02x\n", insn->code); + verbose(env, "BUG_alu64_%02x\n", insn->code); else print_bpf_end_insn(env, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { - verbose("(%02x) r%d = %s-r%d\n", + verbose(env, "(%02x) r%d = %s-r%d\n", insn->code, insn->dst_reg, class == BPF_ALU ? "(u32) " : "", insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { - verbose("(%02x) %sr%d %s %sr%d\n", + verbose(env, "(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->src_reg); } else { - verbose("(%02x) %sr%d %s %s%d\n", + verbose(env, "(%02x) %sr%d %s %s%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], @@ -374,46 +371,46 @@ static void print_bpf_insn(const struct bpf_verifier_env *env, } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) - verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", + verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); else if (BPF_MODE(insn->code) == BPF_XADD) - verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", + verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); else - verbose("BUG_%02x\n", insn->code); + verbose(env, "BUG_%02x\n", insn->code); } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_st_%02x\n", insn->code); + verbose(env, "BUG_st_%02x\n", insn->code); return; } - verbose("(%02x) *(%s *)(r%d %+d) = %d\n", + verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->imm); } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_ldx_%02x\n", insn->code); + verbose(env, "BUG_ldx_%02x\n", insn->code); return; } - verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", + verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (class == BPF_LD) { if (BPF_MODE(insn->code) == BPF_ABS) { - verbose("(%02x) r0 = *(%s *)skb[%d]\n", + verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->imm); } else if (BPF_MODE(insn->code) == BPF_IND) { - verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", + verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->imm); @@ -428,36 +425,37 @@ static void print_bpf_insn(const struct bpf_verifier_env *env, if (map_ptr && !env->allow_ptr_leaks) imm = 0; - verbose("(%02x) r%d = 0x%llx\n", insn->code, + verbose(env, "(%02x) r%d = 0x%llx\n", insn->code, insn->dst_reg, (unsigned long long)imm); } else { - verbose("BUG_ld_%02x\n", insn->code); + verbose(env, "BUG_ld_%02x\n", insn->code); return; } } else if (class == BPF_JMP) { u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { - verbose("(%02x) call %s#%d\n", insn->code, + verbose(env, "(%02x) call %s#%d\n", insn->code, func_id_name(insn->imm), insn->imm); } else if (insn->code == (BPF_JMP | BPF_JA)) { - verbose("(%02x) goto pc%+d\n", + verbose(env, "(%02x) goto pc%+d\n", insn->code, insn->off); } else if (insn->code == (BPF_JMP | BPF_EXIT)) { - verbose("(%02x) exit\n", insn->code); + verbose(env, "(%02x) exit\n", insn->code); } else if (BPF_SRC(insn->code) == BPF_X) { - verbose("(%02x) if r%d %s r%d goto pc%+d\n", + verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n", insn->code, insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], insn->src_reg, insn->off); } else { - verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", + verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n", insn->code, insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], insn->imm, insn->off); } } else { - verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); + verbose(env, "(%02x) %s\n", + insn->code, bpf_class_string[class]); } } @@ -496,7 +494,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { - verbose("BPF program is too complex\n"); + verbose(env, "BPF program is too complex\n"); goto err; } return &elem->st; @@ -534,10 +532,11 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_known_zero(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_known_zero(regs, %u)\n", regno); + verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -647,10 +646,11 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) __mark_reg_unbounded(reg); } -static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_unknown(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_unknown(regs, %u)\n", regno); + verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -665,10 +665,11 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg) reg->type = NOT_INIT; } -static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_not_init(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_not_init(regs, %u)\n", regno); + verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -677,22 +678,23 @@ static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) __mark_reg_not_init(regs + regno); } -static void init_reg_state(struct bpf_reg_state *regs) +static void init_reg_state(struct bpf_verifier_env *env, + struct bpf_reg_state *regs) { int i; for (i = 0; i < MAX_BPF_REG; i++) { - mark_reg_not_init(regs, i); + mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; - mark_reg_known_zero(regs, BPF_REG_FP); + mark_reg_known_zero(env, regs, BPF_REG_FP); /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; - mark_reg_known_zero(regs, BPF_REG_1); + mark_reg_known_zero(env, regs, BPF_REG_1); } enum reg_arg_type { @@ -726,26 +728,26 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, struct bpf_reg_state *regs = env->cur_state.regs; if (regno >= MAX_BPF_REG) { - verbose("R%d is invalid\n", regno); + verbose(env, "R%d is invalid\n", regno); return -EINVAL; } if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (regs[regno].type == NOT_INIT) { - verbose("R%d !read_ok\n", regno); + verbose(env, "R%d !read_ok\n", regno); return -EACCES; } mark_reg_read(&env->cur_state, regno); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { - verbose("frame pointer is read only\n"); + verbose(env, "frame pointer is read only\n"); return -EACCES; } regs[regno].live |= REG_LIVE_WRITTEN; if (t == DST_OP) - mark_reg_unknown(regs, regno); + mark_reg_unknown(env, regs, regno); } return 0; } @@ -770,7 +772,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ -static int check_stack_write(struct bpf_verifier_state *state, int off, +static int check_stack_write(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; @@ -783,7 +786,7 @@ static int check_stack_write(struct bpf_verifier_state *state, int off, /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } @@ -818,7 +821,8 @@ static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slo } } -static int check_stack_read(struct bpf_verifier_state *state, int off, int size, +static int check_stack_read(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { u8 *slot_type; @@ -828,12 +832,12 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, if (slot_type[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } for (i = 1; i < BPF_REG_SIZE; i++) { if (slot_type[i] != STACK_SPILL) { - verbose("corrupted spill memory\n"); + verbose(env, "corrupted spill memory\n"); return -EACCES; } } @@ -849,14 +853,14 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, } else { for (i = 0; i < size; i++) { if (slot_type[i] != STACK_MISC) { - verbose("invalid read from stack off %d+%d size %d\n", + verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } } if (value_regno >= 0) /* have read misc data from the stack */ - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); return 0; } } @@ -868,7 +872,7 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, struct bpf_map *map = env->cur_state.regs[regno].map_ptr; if (off < 0 || size <= 0 || off + size > map->value_size) { - verbose("invalid access to map value, value_size=%d off=%d size=%d\n", + verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } @@ -887,8 +891,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (verifier_log.level) - print_verifier_state(state); + if (env->log.level) + print_verifier_state(env, state); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our @@ -896,13 +900,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * will have a set floor within our range. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->smin_value + off, size); if (err) { - verbose("R%d min value is outside of the array range\n", regno); + verbose(env, "R%d min value is outside of the array range\n", + regno); return err; } @@ -911,13 +916,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { - verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n", + verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->umax_value + off, size); if (err) - verbose("R%d max value is outside of the array range\n", regno); + verbose(env, "R%d max value is outside of the array range\n", + regno); return err; } @@ -956,7 +962,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, struct bpf_reg_state *reg = ®s[regno]; if (off < 0 || size <= 0 || (u64)off + size > reg->range) { - verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", + verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, reg->off, reg->range); return -EACCES; } @@ -979,13 +985,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, * detail to prove they're safe. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_packet_access(env, regno, off, size); if (err) { - verbose("R%d offset is outside of the packet\n", regno); + verbose(env, "R%d offset is outside of the packet\n", regno); return err; } return err; @@ -1021,7 +1027,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return 0; } - verbose("invalid bpf_context access off=%d size=%d\n", off, size); + verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } @@ -1039,7 +1045,8 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); } -static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, +static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; @@ -1064,7 +1071,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned packet access off %d+%s+%d+%d size %d\n", + verbose(env, + "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } @@ -1072,7 +1080,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, return 0; } -static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, +static int check_generic_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { @@ -1087,7 +1096,7 @@ static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned %saccess off %s+%d+%d size %d\n", + verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } @@ -1108,7 +1117,7 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ - return check_pkt_ptr_alignment(reg, off, size, strict); + return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1121,7 +1130,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, default: break; } - return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict); + return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, + strict); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -1153,20 +1163,20 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (reg->type == PTR_TO_MAP_VALUE) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into map\n", value_regno); + verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into ctx\n", value_regno); + verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } /* ctx accesses must be at a fixed offset, so that we can @@ -1176,7 +1186,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable ctx access var_off=%s off=%d size=%d", + verbose(env, + "variable ctx access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } @@ -1188,9 +1199,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); else - mark_reg_known_zero(state->regs, value_regno); + mark_reg_known_zero(env, state->regs, + value_regno); state->regs[value_regno].id = 0; state->regs[value_regno].off = 0; state->regs[value_regno].range = 0; @@ -1206,13 +1218,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable stack access var_off=%s off=%d size=%d", + verbose(env, "variable stack access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } off += reg->var_off.value; if (off >= 0 || off < -MAX_BPF_STACK) { - verbose("invalid stack off=%d size=%d\n", off, size); + verbose(env, "invalid stack off=%d size=%d\n", off, + size); return -EACCES; } @@ -1223,29 +1236,32 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!env->allow_ptr_leaks && state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && size != BPF_REG_SIZE) { - verbose("attempt to corrupt spilled pointer on stack\n"); + verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } - err = check_stack_write(state, off, size, value_regno); + err = check_stack_write(env, state, off, size, + value_regno); } else { - err = check_stack_read(state, off, size, value_regno); + err = check_stack_read(env, state, off, size, + value_regno); } } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { - verbose("cannot write into packet\n"); + verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into packet\n", value_regno); + verbose(env, "R%d leaks addr into packet\n", + value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); } else { - verbose("R%d invalid mem access '%s'\n", - regno, reg_type_str[reg->type]); + verbose(env, "R%d invalid mem access '%s'\n", regno, + reg_type_str[reg->type]); return -EACCES; } @@ -1265,7 +1281,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || insn->imm != 0) { - verbose("BPF_XADD uses reserved fields\n"); + verbose(env, "BPF_XADD uses reserved fields\n"); return -EINVAL; } @@ -1280,7 +1296,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d leaks addr into mem\n", insn->src_reg); + verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } @@ -1321,7 +1337,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, register_is_null(regs[regno])) return 0; - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[regs[regno].type], reg_type_str[PTR_TO_STACK]); return -EACCES; @@ -1332,13 +1348,13 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off); - verbose("invalid variable stack read R%d var_off=%s\n", + verbose(env, "invalid variable stack read R%d var_off=%s\n", regno, tn_buf); } off = regs[regno].off + regs[regno].var_off.value; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || access_size <= 0) { - verbose("invalid stack type R%d off=%d access_size=%d\n", + verbose(env, "invalid stack type R%d off=%d access_size=%d\n", regno, off, access_size); return -EACCES; } @@ -1354,7 +1370,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, for (i = 0; i < access_size; i++) { if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) { - verbose("invalid indirect read from stack off %d+%d size %d\n", + verbose(env, "invalid indirect read from stack off %d+%d size %d\n", off, i, access_size); return -EACCES; } @@ -1397,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { - verbose("R%d leaks addr into helper function\n", regno); + verbose(env, "R%d leaks addr into helper function\n", + regno); return -EACCES; } return 0; @@ -1405,7 +1422,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { - verbose("helper access to the packet is not allowed\n"); + verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } @@ -1443,7 +1460,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; } else { - verbose("unsupported arg_type %d\n", arg_type); + verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; } @@ -1461,7 +1478,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->key\n"); + verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } if (type_is_pkt_pointer(type)) @@ -1477,7 +1494,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->value\n"); + verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } if (type_is_pkt_pointer(type)) @@ -1497,7 +1514,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (regno == 0) { /* kernel subsystem misconfigured verifier */ - verbose("ARG_CONST_SIZE cannot be first argument\n"); + verbose(env, + "ARG_CONST_SIZE cannot be first argument\n"); return -EACCES; } @@ -1514,7 +1532,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta = NULL; if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned or 'var &= const'\n", + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } @@ -1528,7 +1546,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } @@ -1539,12 +1557,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return err; err_type: - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[type], reg_type_str[expected_type]); return -EACCES; } -static int check_map_func_compatibility(struct bpf_map *map, int func_id) +static int check_map_func_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, int func_id) { if (!map) return 0; @@ -1632,7 +1651,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) return 0; error: - verbose("cannot pass map_type %d into func %s#%d\n", + verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } @@ -1666,7 +1685,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) for (i = 0; i < MAX_BPF_REG; i++) if (reg_is_pkt_pointer_any(®s[i])) - mark_reg_unknown(regs, i); + mark_reg_unknown(env, regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) @@ -1688,7 +1707,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) /* find function prototype */ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose("invalid func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "invalid func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } @@ -1696,13 +1716,14 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) fn = env->prog->aux->ops->get_func_proto(func_id); if (!fn) { - verbose("unknown func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "unknown func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose("cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL only function from proprietary program\n"); return -EINVAL; } @@ -1716,7 +1737,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) */ err = check_raw_mode(fn); if (err) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } @@ -1749,14 +1770,14 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { @@ -1764,14 +1785,15 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ - mark_reg_known_zero(regs, BPF_REG_0); + mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { - verbose("kernel subsystem misconfigured verifier\n"); + verbose(env, + "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; @@ -1782,12 +1804,12 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) else if (insn_aux->map_ptr != meta.map_ptr) insn_aux->map_ptr = BPF_MAP_PTR_POISON; } else { - verbose("unknown return type %d of func %s#%d\n", + verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } - err = check_map_func_compatibility(meta.map_ptr, func_id); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; @@ -1846,39 +1868,42 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad sbounds\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, + "verifier internal error: known but bad sbounds\n"); return -EINVAL; } if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad ubounds\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, + "verifier internal error: known but bad ubounds\n"); return -EINVAL; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (!env->allow_ptr_leaks) - verbose("R%d 32-bit pointer arithmetic prohibited\n", + verbose(env, + "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", dst); return -EACCES; } @@ -1943,7 +1968,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ if (!env->allow_ptr_leaks) - verbose("R%d tried to subtract pointer from scalar\n", + verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } @@ -1953,7 +1978,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, */ if (ptr_reg->type == PTR_TO_STACK) { if (!env->allow_ptr_leaks) - verbose("R%d subtraction from stack pointer prohibited\n", + verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } @@ -2008,13 +2033,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * ptr &= ~3 which would reduce min_value by 3.) */ if (!env->allow_ptr_leaks) - verbose("R%d bitwise operator %s on pointer prohibited\n", + verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic with %s operator prohibited\n", + verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } @@ -2180,7 +2205,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* We lose all sign bit information (except what we can pick @@ -2208,7 +2233,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* BPF_RSH is an unsigned shift, so make the appropriate casts */ @@ -2236,7 +2261,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); break; default: - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } @@ -2268,12 +2293,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. */ if (!env->allow_ptr_leaks) { - verbose("R%d pointer %s pointer prohibited\n", + verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); return 0; } else { /* scalar += pointer @@ -2325,13 +2350,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: unexpected ptr_reg\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: no src_reg\n"); + print_verifier_state(env, &env->cur_state); + verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); @@ -2349,14 +2374,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) != 0 || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { - verbose("BPF_NEG uses reserved fields\n"); + verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || BPF_CLASS(insn->code) == BPF_ALU64) { - verbose("BPF_END uses reserved fields\n"); + verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } @@ -2367,7 +2392,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer arithmetic prohibited\n", + verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } @@ -2381,7 +2406,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } @@ -2391,7 +2416,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } @@ -2411,11 +2436,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d partial copy of pointer\n", + verbose(env, + "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); /* high 32 bits are known zero. */ regs[insn->dst_reg].var_off = tnum_cast( regs[insn->dst_reg].var_off, 4); @@ -2430,14 +2456,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } } else if (opcode > BPF_END) { - verbose("invalid BPF_ALU opcode %x\n", opcode); + verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ @@ -2446,7 +2472,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } @@ -2458,7 +2484,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { - verbose("div by zero\n"); + verbose(env, "div by zero\n"); return -EINVAL; } @@ -2467,7 +2493,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { - verbose("invalid shift %d\n", insn->imm); + verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } @@ -2820,13 +2846,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, int err; if (opcode > BPF_JSLE) { - verbose("invalid BPF_JMP opcode %x\n", opcode); + verbose(env, "invalid BPF_JMP opcode %x\n", opcode); return -EINVAL; } if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } @@ -2836,13 +2862,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d pointer comparison prohibited\n", + verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } } else { if (insn->src_reg != BPF_REG_0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } } @@ -2954,11 +2980,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, find_good_pkt_pointers(this_branch, ®s[insn->src_reg], PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer comparison prohibited\n", insn->dst_reg); + verbose(env, "R%d pointer comparison prohibited\n", + insn->dst_reg); return -EACCES; } - if (verifier_log.level) - print_verifier_state(this_branch); + if (env->log.level) + print_verifier_state(env, this_branch); return 0; } @@ -2977,11 +3004,11 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) int err; if (BPF_SIZE(insn->code) != BPF_DW) { - verbose("invalid BPF_LD_IMM insn\n"); + verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { - verbose("BPF_LD_IMM64 uses reserved fields\n"); + verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } @@ -3039,14 +3066,14 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) int i, err; if (!may_access_skb(env->prog->type)) { - verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); + verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { - verbose("BPF_LD_[ABS|IND] uses reserved fields\n"); + verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } @@ -3056,7 +3083,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (regs[BPF_REG_6].type != PTR_TO_CTX) { - verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); + verbose(env, + "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } @@ -3069,7 +3097,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } @@ -3077,7 +3105,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * the value fetched from the packet. * Already marked as written above. */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); return 0; } @@ -3097,22 +3125,22 @@ static int check_return_code(struct bpf_verifier_env *env) reg = &env->cur_state.regs[BPF_REG_0]; if (reg->type != SCALAR_VALUE) { - verbose("At program exit the register R0 is not a known value (%s)\n", + verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str[reg->type]); return -EINVAL; } if (!tnum_in(range, reg->var_off)) { - verbose("At program exit the register R0 "); + verbose(env, "At program exit the register R0 "); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("has value %s", tn_buf); + verbose(env, "has value %s", tn_buf); } else { - verbose("has unknown scalar value"); + verbose(env, "has unknown scalar value"); } - verbose(" should have been 0 or 1\n"); + verbose(env, " should have been 0 or 1\n"); return -EINVAL; } return 0; @@ -3178,7 +3206,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) return 0; if (w < 0 || w >= env->prog->len) { - verbose("jump out of range from insn %d to %d\n", t, w); + verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } @@ -3195,13 +3223,13 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - verbose("back-edge from insn %d to %d\n", t, w); + verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { - verbose("insn state internal bug\n"); + verbose(env, "insn state internal bug\n"); return -EFAULT; } return 0; @@ -3295,7 +3323,7 @@ static int check_cfg(struct bpf_verifier_env *env) mark_explored: insn_state[t] = EXPLORED; if (cur_stack-- <= 0) { - verbose("pop stack internal bug\n"); + verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } @@ -3304,7 +3332,7 @@ static int check_cfg(struct bpf_verifier_env *env) check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { - verbose("unreachable insn %d\n", i); + verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } @@ -3685,7 +3713,7 @@ static int do_check(struct bpf_verifier_env *env) int insn_processed = 0; bool do_print_state = false; - init_reg_state(regs); + init_reg_state(env, regs); state->parent = NULL; insn_idx = 0; for (;;) { @@ -3694,7 +3722,7 @@ static int do_check(struct bpf_verifier_env *env) int err; if (insn_idx >= insn_cnt) { - verbose("invalid insn idx %d insn_cnt %d\n", + verbose(env, "invalid insn idx %d insn_cnt %d\n", insn_idx, insn_cnt); return -EFAULT; } @@ -3703,7 +3731,8 @@ static int do_check(struct bpf_verifier_env *env) class = BPF_CLASS(insn->code); if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { - verbose("BPF program is too large. Processed %d insn\n", + verbose(env, + "BPF program is too large. Processed %d insn\n", insn_processed); return -E2BIG; } @@ -3713,12 +3742,12 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (verifier_log.level) { + if (env->log.level) { if (do_print_state) - verbose("\nfrom %d to %d: safe\n", + verbose(env, "\nfrom %d to %d: safe\n", prev_insn_idx, insn_idx); else - verbose("%d: safe\n", insn_idx); + verbose(env, "%d: safe\n", insn_idx); } goto process_bpf_exit; } @@ -3726,19 +3755,18 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (verifier_log.level > 1 || - (verifier_log.level && do_print_state)) { - if (verifier_log.level > 1) - verbose("%d:", insn_idx); + if (env->log.level > 1 || (env->log.level && do_print_state)) { + if (env->log.level > 1) + verbose(env, "%d:", insn_idx); else - verbose("\nfrom %d to %d:", + verbose(env, "\nfrom %d to %d:", prev_insn_idx, insn_idx); - print_verifier_state(&env->cur_state); + print_verifier_state(env, &env->cur_state); do_print_state = false; } - if (verifier_log.level) { - verbose("%d: ", insn_idx); + if (env->log.level) { + verbose(env, "%d: ", insn_idx); print_bpf_insn(env, insn); } @@ -3795,7 +3823,7 @@ static int do_check(struct bpf_verifier_env *env) * src_reg == stack|map in some other branch. * Reject it. */ - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -3835,14 +3863,14 @@ static int do_check(struct bpf_verifier_env *env) } else if (dst_reg_type != *prev_dst_type && (dst_reg_type == PTR_TO_CTX || *prev_dst_type == PTR_TO_CTX)) { - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { - verbose("BPF_ST uses reserved fields\n"); + verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ @@ -3865,7 +3893,7 @@ static int do_check(struct bpf_verifier_env *env) insn->off != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_CALL uses reserved fields\n"); + verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } @@ -3878,7 +3906,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_JA uses reserved fields\n"); + verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } @@ -3890,7 +3918,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_EXIT uses reserved fields\n"); + verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } @@ -3905,7 +3933,7 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_pointer_value(env, BPF_REG_0)) { - verbose("R0 leaks addr as return value\n"); + verbose(env, "R0 leaks addr as return value\n"); return -EACCES; } @@ -3940,19 +3968,19 @@ static int do_check(struct bpf_verifier_env *env) insn_idx++; } else { - verbose("invalid BPF_LD mode\n"); + verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { - verbose("unknown insn class %d\n", class); + verbose(env, "unknown insn class %d\n", class); return -EINVAL; } insn_idx++; } - verbose("processed %d insns, stack depth %d\n", - insn_processed, env->prog->aux->stack_depth); + verbose(env, "processed %d insns, stack depth %d\n", insn_processed, + env->prog->aux->stack_depth); return 0; } @@ -3964,7 +3992,8 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } -static int check_map_prog_compatibility(struct bpf_map *map, +static int check_map_prog_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, struct bpf_prog *prog) { @@ -3975,12 +4004,12 @@ static int check_map_prog_compatibility(struct bpf_map *map, */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { if (!check_map_prealloc(map)) { - verbose("perf_event programs can only use preallocated hash map\n"); + verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) { - verbose("perf_event programs can only use preallocated inner hash map\n"); + verbose(env, "perf_event programs can only use preallocated inner hash map\n"); return -EINVAL; } } @@ -4003,14 +4032,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { - verbose("BPF_LDX uses reserved fields\n"); + verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (BPF_CLASS(insn->code) == BPF_STX && ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { - verbose("BPF_STX uses reserved fields\n"); + verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } @@ -4021,7 +4050,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { - verbose("invalid bpf_ld_imm64 insn\n"); + verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -4030,19 +4059,20 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) goto next_insn; if (insn->src_reg != BPF_PSEUDO_MAP_FD) { - verbose("unrecognized bpf_ld_imm64 insn\n"); + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } f = fdget(insn->imm); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose("fd %d is not pointing to valid bpf_map\n", + verbose(env, "fd %d is not pointing to valid bpf_map\n", insn->imm); return PTR_ERR(map); } - err = check_map_prog_compatibility(map, env->prog); + err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; @@ -4164,7 +4194,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); @@ -4212,7 +4242,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) u8 size_code; if (type == BPF_WRITE) { - verbose("bpf verifier narrow ctx access misconfigured\n"); + verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } @@ -4231,7 +4261,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4313,7 +4343,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4357,7 +4387,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) * programs to call them, must be real in-kernel functions */ if (!fn->func) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, + "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } @@ -4391,8 +4422,8 @@ static void free_states(struct bpf_verifier_env *env) int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { - struct bpf_verifer_log *log = &verifier_log; struct bpf_verifier_env *env; + struct bpf_verifer_log *log; int ret = -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, @@ -4401,6 +4432,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; + log = &env->log; env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * (*prog)->len); @@ -4419,7 +4451,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) log->level = attr->log_level; log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; - log->len_used = 0; ret = -EINVAL; /* log attributes have to be sane */ @@ -4431,8 +4462,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) log->kbuf = vmalloc(log->len_total); if (!log->kbuf) goto err_unlock; - } else { - log->level = 0; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); @@ -4543,8 +4572,6 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); - verifier_log.level = 0; - env->strict_alignment = false; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; -- GitLab From f4ac7e0b5cc8d16004ac57ff679266d573f30f77 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:12 -0700 Subject: [PATCH 1222/1507] bpf: move instruction printing into a separate file Separate the instruction printing into a standalone source file. This way sneaky code from tools/ can compile it in directly. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/Makefile | 1 + kernel/bpf/disasm.c | 214 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/disasm.h | 32 +++++++ kernel/bpf/verifier.c | 202 +-------------------------------------- 4 files changed, 251 insertions(+), 198 deletions(-) create mode 100644 kernel/bpf/disasm.c create mode 100644 kernel/bpf/disasm.h diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 897daa005b239..53fb09f92e3fc 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,6 +2,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o ifeq ($(CONFIG_STREAM_PARSER),y) diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c new file mode 100644 index 0000000000000..e682850c97150 --- /dev/null +++ b/kernel/bpf/disasm.c @@ -0,0 +1,214 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include + +#include "disasm.h" + +#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) +static const char * const func_id_str[] = { + __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) +}; +#undef __BPF_FUNC_STR_FN + +const char *func_id_name(int id) +{ + BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); + + if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) + return func_id_str[id]; + else + return "unknown"; +} + +const char *const bpf_class_string[8] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +const char *const bpf_alu_string[16] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[16] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JLT >> 4] = "<", + [BPF_JGE >> 4] = ">=", + [BPF_JLE >> 4] = "<=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSLT >> 4] = "s<", + [BPF_JSGE >> 4] = "s>=", + [BPF_JSLE >> 4] = "s<=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_end_insn(bpf_insn_print_cb verbose, + struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", + insn->imm, insn->dst_reg); +} + +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose(env, "BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(verbose, env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose(env, "(%02x) r%d = %s-r%d\n", + insn->code, insn->dst_reg, + class == BPF_ALU ? "(u32) " : "", + insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose(env, "(%02x) %sr%d %s %sr%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->src_reg); + } else { + verbose(env, "(%02x) %sr%d %s %s%d\n", + insn->code, class == BPF_ALU ? "(u32) " : "", + insn->dst_reg, + bpf_alu_string[BPF_OP(insn->code) >> 4], + class == BPF_ALU ? "(u32) " : "", + insn->imm); + } + } else if (class == BPF_STX) { + if (BPF_MODE(insn->code) == BPF_MEM) + verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose(env, "BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_st_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_ldx_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM && + BPF_SIZE(insn->code) == BPF_DW) { + /* At this point, we already made sure that the second + * part of the ldimm64 insn is accessible. + */ + u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; + bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + + if (map_ptr && !allow_ptr_leaks) + imm = 0; + + verbose(env, "(%02x) r%d = 0x%llx\n", insn->code, + insn->dst_reg, (unsigned long long)imm); + } else { + verbose(env, "BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose(env, "(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose(env, "(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose(env, "(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose(env, "(%02x) %s\n", + insn->code, bpf_class_string[class]); + } +} diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h new file mode 100644 index 0000000000000..8de977e420b64 --- /dev/null +++ b/kernel/bpf/disasm.h @@ -0,0 +1,32 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef __BPF_DISASM_H__ +#define __BPF_DISASM_H__ + +#include +#include +#include + +extern const char *const bpf_alu_string[16]; +extern const char *const bpf_class_string[8]; + +const char *func_id_name(int id); + +struct bpf_verifier_env; +typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env, + const char *, ...); +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks); + +#endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a352f93cd4b2f..274c6582ec398 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21,6 +21,8 @@ #include #include +#include "disasm.h" + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -194,22 +196,6 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; -#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) -static const char * const func_id_str[] = { - __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) -}; -#undef __BPF_FUNC_STR_FN - -static const char *func_id_name(int id) -{ - BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); - - if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) - return func_id_str[id]; - else - return "unknown"; -} - static void print_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *state) { @@ -278,187 +264,6 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, "\n"); } -static const char *const bpf_class_string[] = { - [BPF_LD] = "ld", - [BPF_LDX] = "ldx", - [BPF_ST] = "st", - [BPF_STX] = "stx", - [BPF_ALU] = "alu", - [BPF_JMP] = "jmp", - [BPF_RET] = "BUG", - [BPF_ALU64] = "alu64", -}; - -static const char *const bpf_alu_string[16] = { - [BPF_ADD >> 4] = "+=", - [BPF_SUB >> 4] = "-=", - [BPF_MUL >> 4] = "*=", - [BPF_DIV >> 4] = "/=", - [BPF_OR >> 4] = "|=", - [BPF_AND >> 4] = "&=", - [BPF_LSH >> 4] = "<<=", - [BPF_RSH >> 4] = ">>=", - [BPF_NEG >> 4] = "neg", - [BPF_MOD >> 4] = "%=", - [BPF_XOR >> 4] = "^=", - [BPF_MOV >> 4] = "=", - [BPF_ARSH >> 4] = "s>>=", - [BPF_END >> 4] = "endian", -}; - -static const char *const bpf_ldst_string[] = { - [BPF_W >> 3] = "u32", - [BPF_H >> 3] = "u16", - [BPF_B >> 3] = "u8", - [BPF_DW >> 3] = "u64", -}; - -static const char *const bpf_jmp_string[16] = { - [BPF_JA >> 4] = "jmp", - [BPF_JEQ >> 4] = "==", - [BPF_JGT >> 4] = ">", - [BPF_JLT >> 4] = "<", - [BPF_JGE >> 4] = ">=", - [BPF_JLE >> 4] = "<=", - [BPF_JSET >> 4] = "&", - [BPF_JNE >> 4] = "!=", - [BPF_JSGT >> 4] = "s>", - [BPF_JSLT >> 4] = "s<", - [BPF_JSGE >> 4] = "s>=", - [BPF_JSLE >> 4] = "s<=", - [BPF_CALL >> 4] = "call", - [BPF_EXIT >> 4] = "exit", -}; - -static void print_bpf_end_insn(struct bpf_verifier_env *env, - const struct bpf_insn *insn) -{ - verbose(env, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, - BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", - insn->imm, insn->dst_reg); -} - -static void print_bpf_insn(struct bpf_verifier_env *env, - const struct bpf_insn *insn) -{ - u8 class = BPF_CLASS(insn->code); - - if (class == BPF_ALU || class == BPF_ALU64) { - if (BPF_OP(insn->code) == BPF_END) { - if (class == BPF_ALU64) - verbose(env, "BUG_alu64_%02x\n", insn->code); - else - print_bpf_end_insn(env, insn); - } else if (BPF_OP(insn->code) == BPF_NEG) { - verbose(env, "(%02x) r%d = %s-r%d\n", - insn->code, insn->dst_reg, - class == BPF_ALU ? "(u32) " : "", - insn->dst_reg); - } else if (BPF_SRC(insn->code) == BPF_X) { - verbose(env, "(%02x) %sr%d %s %sr%d\n", - insn->code, class == BPF_ALU ? "(u32) " : "", - insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], - class == BPF_ALU ? "(u32) " : "", - insn->src_reg); - } else { - verbose(env, "(%02x) %sr%d %s %s%d\n", - insn->code, class == BPF_ALU ? "(u32) " : "", - insn->dst_reg, - bpf_alu_string[BPF_OP(insn->code) >> 4], - class == BPF_ALU ? "(u32) " : "", - insn->imm); - } - } else if (class == BPF_STX) { - if (BPF_MODE(insn->code) == BPF_MEM) - verbose(env, "(%02x) *(%s *)(r%d %+d) = r%d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_XADD) - verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, insn->off, - insn->src_reg); - else - verbose(env, "BUG_%02x\n", insn->code); - } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose(env, "BUG_st_%02x\n", insn->code); - return; - } - verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); - } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose(env, "BUG_ldx_%02x\n", insn->code); - return; - } - verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n", - insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->off); - } else if (class == BPF_LD) { - if (BPF_MODE(insn->code) == BPF_ABS) { - verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IND) { - verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IMM && - BPF_SIZE(insn->code) == BPF_DW) { - /* At this point, we already made sure that the second - * part of the ldimm64 insn is accessible. - */ - u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; - - if (map_ptr && !env->allow_ptr_leaks) - imm = 0; - - verbose(env, "(%02x) r%d = 0x%llx\n", insn->code, - insn->dst_reg, (unsigned long long)imm); - } else { - verbose(env, "BUG_ld_%02x\n", insn->code); - return; - } - } else if (class == BPF_JMP) { - u8 opcode = BPF_OP(insn->code); - - if (opcode == BPF_CALL) { - verbose(env, "(%02x) call %s#%d\n", insn->code, - func_id_name(insn->imm), insn->imm); - } else if (insn->code == (BPF_JMP | BPF_JA)) { - verbose(env, "(%02x) goto pc%+d\n", - insn->code, insn->off); - } else if (insn->code == (BPF_JMP | BPF_EXIT)) { - verbose(env, "(%02x) exit\n", insn->code); - } else if (BPF_SRC(insn->code) == BPF_X) { - verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->src_reg, insn->off); - } else { - verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->imm, insn->off); - } - } else { - verbose(env, "(%02x) %s\n", - insn->code, bpf_class_string[class]); - } -} - static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx) { struct bpf_verifier_stack_elem *elem; @@ -3767,7 +3572,8 @@ static int do_check(struct bpf_verifier_env *env) if (env->log.level) { verbose(env, "%d: ", insn_idx); - print_bpf_insn(env, insn); + print_bpf_insn(verbose, env, insn, + env->allow_ptr_leaks); } err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx); -- GitLab From c9c35995bcf812ee8136f634c25bc6ccc3021d4c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:13 -0700 Subject: [PATCH 1223/1507] tools: bpftool: use the kernel's instruction printer Compile the instruction printer from kernel/bpf and use it for disassembling "translated" eBPF code. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- .../bpftool/Documentation/bpftool-prog.rst | 11 +++-- tools/bpf/bpftool/Makefile | 7 ++- tools/bpf/bpftool/main.h | 10 ++--- tools/bpf/bpftool/prog.c | 44 +++++++++++++++---- 4 files changed, 51 insertions(+), 21 deletions(-) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 57fc4b9924ea6..04d12f768f06a 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -11,7 +11,7 @@ SYNOPSIS ======== | **bpftool** prog show [*PROG*] -| **bpftool** prog dump xlated *PROG* file *FILE* +| **bpftool** prog dump xlated *PROG* [file *FILE*] [opcodes] | **bpftool** prog dump jited *PROG* [file *FILE*] [opcodes] | **bpftool** prog pin *PROG* *FILE* | **bpftool** prog help @@ -28,9 +28,12 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). - **bpftool prog dump xlated** *PROG* **file** *FILE* - Dump eBPF instructions of the program from the kernel to a - file. + **bpftool prog dump xlated** *PROG* [**file** *FILE*] [**opcodes**] + Dump eBPF instructions of the program from the kernel. + If *FILE* is specified image will be written to a file, + otherwise it will be disassembled and printed to stdout. + + **opcodes** controls if raw opcodes will be printed. **bpftool prog dump jited** *PROG* [**file** *FILE*] [**opcodes**] Dump jited image (host machine code) of the program. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 8705ee44664d8..4f339824ca572 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -51,7 +51,7 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf +CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ LIBS = -lelf -lbfd -lopcodes $(LIBBPF) include $(wildcard *.d) @@ -59,7 +59,10 @@ include $(wildcard *.d) all: $(OUTPUT)bpftool SRCS=$(wildcard *.c) -OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) +OBJS=$(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o + +$(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(COMPILE.c) -MMD -o $@ $< $(OUTPUT)bpftool: $(OBJS) $(LIBBPF) $(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^ $(LIBS) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 85d2d7870a582..8e809b2bb3111 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -36,11 +36,12 @@ #ifndef __BPF_TOOL_H #define __BPF_TOOL_H +/* BFD and kernel.h both define GCC_VERSION, differently */ +#undef GCC_VERSION #include #include #include - -#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0])) +#include #define err(msg...) fprintf(stderr, "Error: " msg) #define warn(msg...) fprintf(stderr, "Warning: " msg) @@ -48,11 +49,6 @@ #define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) -#define min(a, b) \ - ({ typeof(a) _a = (a); typeof(b) _b = (b); _a > _b ? _b : _a; }) -#define max(a, b) \ - ({ typeof(a) _a = (a); typeof(b) _b = (b); _a < _b ? _b : _a; }) - #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) #define BAD_ARG() ({ err("what is '%s'?\n", *argv); -1; }) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 421ba89ce86a8..9e2681c837179 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -35,6 +35,7 @@ #include #include +#include #include #include #include @@ -46,6 +47,7 @@ #include #include "main.h" +#include "disasm.h" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -297,11 +299,39 @@ static int do_show(int argc, char **argv) return 0; } +static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vprintf(fmt, args); + va_end(args); +} + +static void dump_xlated(void *buf, unsigned int len, bool opcodes) +{ + struct bpf_insn *insn = buf; + unsigned int i; + + for (i = 0; i < len / sizeof(*insn); i++) { + printf("% 4d: ", i); + print_bpf_insn(print_insn, NULL, insn + i, true); + + if (opcodes) { + printf(" "); + print_hex(insn + i, 8, " "); + printf("\n"); + } + + if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) + i++; + } +} + static int do_dump(int argc, char **argv) { struct bpf_prog_info info = {}; __u32 len = sizeof(info); - bool can_disasm = false; unsigned int buf_size; char *filepath = NULL; bool opcodes = false; @@ -315,7 +345,6 @@ static int do_dump(int argc, char **argv) if (is_prefix(*argv, "jited")) { member_len = &info.jited_prog_len; member_ptr = &info.jited_prog_insns; - can_disasm = true; } else if (is_prefix(*argv, "xlated")) { member_len = &info.xlated_prog_len; member_ptr = &info.xlated_prog_insns; @@ -346,10 +375,6 @@ static int do_dump(int argc, char **argv) NEXT_ARG(); } - if (!filepath && !can_disasm) { - err("expected 'file' got %s\n", *argv); - return -1; - } if (argc) { usage(); return -1; @@ -409,7 +434,10 @@ static int do_dump(int argc, char **argv) goto err_free; } } else { - disasm_print_insn(buf, *member_len, opcodes); + if (member_len == &info.jited_prog_len) + disasm_print_insn(buf, *member_len, opcodes); + else + dump_xlated(buf, *member_len, opcodes); } free(buf); @@ -430,7 +458,7 @@ static int do_help(int argc, char **argv) { fprintf(stderr, "Usage: %s %s show [PROG]\n" - " %s %s dump xlated PROG file FILE\n" + " %s %s dump xlated PROG [file FILE] [opcodes]\n" " %s %s dump jited PROG [file FILE] [opcodes]\n" " %s %s pin PROG FILE\n" " %s %s help\n" -- GitLab From d66f2b91f95b56e31772b9faa0d036cd2e53cb02 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:14 -0700 Subject: [PATCH 1224/1507] bpf: don't rely on the verifier lock for metadata_dst allocation bpf_skb_set_tunnel_*() functions require allocation of per-cpu metadata_dst. The allocation happens upon verification of the first program using those helpers. In preparation for removing the verifier lock, use cmpxchg() to make sure we only allocate the metadata_dsts once. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 1 + net/core/dst.c | 16 ++++++++++++++++ net/core/filter.c | 16 +++++++++------- 3 files changed, 26 insertions(+), 7 deletions(-) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 9fba2ebf6ddaa..87a0bb8d449f2 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -87,6 +87,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags); +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst); struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); diff --git a/net/core/dst.c b/net/core/dst.c index a6c47da7d0f8b..8b2eafac984de 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -322,3 +322,19 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + +void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) +{ + int cpu; + +#ifdef CONFIG_DST_CACHE + for_each_possible_cpu(cpu) { + struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); + + if (one_md_dst->type == METADATA_IP_TUNNEL) + dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); + } +#endif + free_percpu(md_dst); +} +EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); diff --git a/net/core/filter.c b/net/core/filter.c index b7e8caa1e790e..140fa9f9c0f41 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -2987,14 +2988,15 @@ static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { - /* Race is not possible, since it's called from verifier - * that is holding verifier mutex. - */ - md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, - METADATA_IP_TUNNEL, - GFP_KERNEL); - if (!md_dst) + struct metadata_dst __percpu *tmp; + + tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + METADATA_IP_TUNNEL, + GFP_KERNEL); + if (!tmp) return NULL; + if (cmpxchg(&md_dst, NULL, tmp)) + metadata_dst_free_percpu(tmp); } switch (which) { -- GitLab From a2a7d5701052542cd2260e7659b12443e0a74733 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 Oct 2017 10:30:15 -0700 Subject: [PATCH 1225/1507] bpf: write back the verifier log buffer as it gets filled Verifier log buffer can be quite large (up to 16MB currently). As Eric Dumazet points out if we allow multiple verification requests to proceed simultaneously, malicious user may use the verifier as a way of allocating large amounts of unswappable memory to OOM the host. Switch to a strategy of allocating a smaller buffer (1024B) and writing it out into the user buffer after every print. While at it remove the old BUG_ON(). This is in preparation of the global verifier lock removal. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 4 +++- kernel/bpf/verifier.c | 41 +++++++++++++++++------------------- 2 files changed, 22 insertions(+), 23 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5ddb9a626a51e..f00ef751c1c52 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -115,9 +115,11 @@ struct bpf_insn_aux_data { #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define BPF_VERIFIER_TMP_LOG_SIZE 1024 + struct bpf_verifer_log { u32 level; - char *kbuf; + char kbuf[BPF_VERIFIER_TMP_LOG_SIZE]; char __user *ubuf; u32 len_used; u32 len_total; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 274c6582ec398..2cdbcc4f8f6b2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -165,15 +165,26 @@ static __printf(2, 3) void verbose(struct bpf_verifier_env *env, const char *fmt, ...) { struct bpf_verifer_log *log = &env->log; + unsigned int n; va_list args; - if (!log->level || bpf_verifier_log_full(log)) + if (!log->level || !log->ubuf || bpf_verifier_log_full(log)) return; va_start(args, fmt); - log->len_used += vscnprintf(log->kbuf + log->len_used, - log->len_total - log->len_used, fmt, args); + n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); va_end(args); + + WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, + "verifier log line truncated - local buffer too short\n"); + + n = min(log->len_total - log->len_used - 1, n); + log->kbuf[n] = '\0'; + + if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) + log->len_used += n; + else + log->ubuf = NULL; } static bool type_is_pkt_pointer(enum bpf_reg_type type) @@ -4263,11 +4274,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || !log->level || !log->ubuf) goto err_unlock; - - ret = -ENOMEM; - log->kbuf = vmalloc(log->len_total); - if (!log->kbuf) - goto err_unlock; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); @@ -4304,18 +4310,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (ret == 0) ret = fixup_bpf_calls(env); - if (log->level && bpf_verifier_log_full(log)) { - BUG_ON(log->len_used >= log->len_total); - /* verifier log exceeded user supplied buffer */ + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; - /* fall through to return what was recorded */ - } - - /* copy verifier log back to user space including trailing zero */ - if (log->level && copy_to_user(log->ubuf, log->kbuf, - log->len_used + 1) != 0) { + if (log->level && !log->ubuf) { ret = -EFAULT; - goto free_log_buf; + goto err_release_maps; } if (ret == 0 && env->used_map_cnt) { @@ -4326,7 +4325,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->prog->aux->used_maps) { ret = -ENOMEM; - goto free_log_buf; + goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, @@ -4339,9 +4338,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) convert_pseudo_ld_imm64(env); } -free_log_buf: - if (log->level) - vfree(log->kbuf); +err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. -- GitLab From 9f77fad3c2e3b923984fc617ea45b60264115fc3 Mon Sep 17 00:00:00 2001 From: Tim Hansen Date: Mon, 9 Oct 2017 11:37:59 -0400 Subject: [PATCH 1226/1507] net/core: Fix BUG to BUG_ON conditionals. Fix BUG() calls to use BUG_ON(conditional) macros. This was found using make coccicheck M=net/core on linux next tag next-2017092 Signed-off-by: Tim Hansen Signed-off-by: David S. Miller --- net/core/skbuff.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 822a90e56aea2..40717501cbdd2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1350,8 +1350,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) /* Set the tail pointer and length */ skb_put(n, skb->len); - if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); copy_skb_header(n, skb); return n; @@ -1449,8 +1448,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, BUG_ON(nhead < 0); - if (skb_shared(skb)) - BUG(); + BUG_ON(skb_shared(skb)); size = SKB_DATA_ALIGN(size); @@ -1595,9 +1593,8 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, head_copy_off = newheadroom - head_copy_len; /* Copy the linear header and data. */ - if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, - skb->len + head_copy_len)) - BUG(); + BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, + skb->len + head_copy_len)); copy_skb_header(n, skb); @@ -1878,8 +1875,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) return NULL; } - if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)) - BUG(); + BUG_ON(skb_copy_bits(skb, skb_headlen(skb), + skb_tail_pointer(skb), delta)); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. -- GitLab From 96ac18f14a5a721dc4233f1c6ebd07e103ae5a63 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Tue, 10 Oct 2017 12:44:13 +0530 Subject: [PATCH 1227/1507] cxgb4: Add support for new flash parts Add support for new flash parts identification, and also cleanup the flash Part identifying and decoding code. Based on the original work of Casey Leedom Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 136 ++++++++++++++++++--- 1 file changed, 116 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index b65ce26ff72f8..b3fd1f4576390 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -8205,7 +8205,7 @@ struct flash_desc { u32 size_mb; }; -static int get_flash_params(struct adapter *adap) +static int t4_get_flash_params(struct adapter *adap) { /* Table for non-Numonix supported flash parts. Numonix parts are left * to the preexisting code. All flash parts have 64KB sectors. @@ -8214,40 +8214,136 @@ static int get_flash_params(struct adapter *adap) { 0x150201, 4 << 20 }, /* Spansion 4MB S25FL032P */ }; + unsigned int part, manufacturer; + unsigned int density, size; + u32 flashid = 0; int ret; - u32 info; + + /* Issue a Read ID Command to the Flash part. We decode supported + * Flash parts and their sizes from this. There's a newer Query + * Command which can retrieve detailed geometry information but many + * Flash parts don't support it. + */ ret = sf1_write(adap, 1, 1, 0, SF_RD_ID); if (!ret) - ret = sf1_read(adap, 3, 0, 1, &info); + ret = sf1_read(adap, 3, 0, 1, &flashid); t4_write_reg(adap, SF_OP_A, 0); /* unlock SF */ if (ret) return ret; - for (ret = 0; ret < ARRAY_SIZE(supported_flash); ++ret) - if (supported_flash[ret].vendor_and_model_id == info) { - adap->params.sf_size = supported_flash[ret].size_mb; + /* Check to see if it's one of our non-standard supported Flash parts. + */ + for (part = 0; part < ARRAY_SIZE(supported_flash); part++) + if (supported_flash[part].vendor_and_model_id == flashid) { + adap->params.sf_size = supported_flash[part].size_mb; adap->params.sf_nsec = adap->params.sf_size / SF_SEC_SIZE; - return 0; + goto found; } - if ((info & 0xff) != 0x20) /* not a Numonix flash */ + /* Decode Flash part size. The code below looks repetative with + * common encodings, but that's not guaranteed in the JEDEC + * specification for the Read JADEC ID command. The only thing that + * we're guaranteed by the JADEC specification is where the + * Manufacturer ID is in the returned result. After that each + * Manufacturer ~could~ encode things completely differently. + * Note, all Flash parts must have 64KB sectors. + */ + manufacturer = flashid & 0xff; + switch (manufacturer) { + case 0x20: { /* Micron/Numonix */ + /* This Density -> Size decoding table is taken from Micron + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x14: /* 1MB */ + size = 1 << 20; + break; + case 0x15: /* 2MB */ + size = 1 << 21; + break; + case 0x16: /* 4MB */ + size = 1 << 22; + break; + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + case 0x19: /* 32MB */ + size = 1 << 25; + break; + case 0x20: /* 64MB */ + size = 1 << 26; + break; + case 0x21: /* 128MB */ + size = 1 << 27; + break; + case 0x22: /* 256MB */ + size = 1 << 28; + break; + + default: + dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); return -EINVAL; - info >>= 16; /* log2 of size */ - if (info >= 0x14 && info < 0x18) - adap->params.sf_nsec = 1 << (info - 16); - else if (info == 0x18) - adap->params.sf_nsec = 64; - else + } + break; + } + case 0xc2: { /* Macronix */ + /* This Density -> Size decoding table is taken from Macronix + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + default: + dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); + return -EINVAL; + } + } + case 0xef: { /* Winbond */ + /* This Density -> Size decoding table is taken from Winbond + * Data Sheets. + */ + density = (flashid >> 16) & 0xff; + switch (density) { + case 0x17: /* 8MB */ + size = 1 << 23; + break; + case 0x18: /* 16MB */ + size = 1 << 24; + break; + default: + dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n", + flashid, density); return -EINVAL; - adap->params.sf_size = 1 << info; - adap->params.sf_fw_start = - t4_read_reg(adap, CIM_BOOT_CFG_A) & BOOTADDR_M; + } + break; + } + default: + dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n", + flashid); + return -EINVAL; + } + + /* Store decoded Flash size and fall through into vetting code. */ + adap->params.sf_size = size; + adap->params.sf_nsec = size / SF_SEC_SIZE; +found: if (adap->params.sf_size < FLASH_MIN_SIZE) - dev_warn(adap->pdev_dev, "WARNING!!! FLASH size %#x < %#x!!!\n", - adap->params.sf_size, FLASH_MIN_SIZE); + dev_warn(adap->pdev_dev, "WARNING: Flash Part ID %#x, size %#x < %#x\n", + flashid, adap->params.sf_size, FLASH_MIN_SIZE); return 0; } @@ -8285,7 +8381,7 @@ int t4_prep_adapter(struct adapter *adapter) get_pci_mode(adapter, &adapter->params.pci); pl_rev = REV_G(t4_read_reg(adapter, PL_REV_A)); - ret = get_flash_params(adapter); + ret = t4_get_flash_params(adapter); if (ret < 0) { dev_err(adapter->pdev_dev, "error %d identifying flash\n", ret); return ret; -- GitLab From 652faa98ec383c25296fb8493f17060a2c7e3438 Mon Sep 17 00:00:00 2001 From: Ganesh Goudar Date: Tue, 10 Oct 2017 12:45:02 +0530 Subject: [PATCH 1228/1507] cxgb4: add new T5 pci device id's Add 0x50aa and 0x50ab T5 device id's. Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 633e9751a25e7..8c22bb8c9fbf2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -181,6 +181,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50a7), /* Custom T580-CR */ CH_PCI_ID_TABLE_FENTRY(0x50a8), /* Custom T580-KR */ CH_PCI_ID_TABLE_FENTRY(0x50a9), /* Custom T580-KR */ + CH_PCI_ID_TABLE_FENTRY(0x50aa), /* Custom T580-CR */ + CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */ /* T6 adapters: */ -- GitLab From ee83f77645332ce86863e5cef8dd3372b8ee4b87 Mon Sep 17 00:00:00 2001 From: Lipeng Date: Tue, 10 Oct 2017 16:42:03 +0800 Subject: [PATCH 1229/1507] net: hns3: fixes the ring index in hns3_fini_ring This patch fixes the ring index in hns3_fini_ring. Signed-off-by: Lipeng Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index 26bbc91add651..acb82cfc1b9a2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -2661,7 +2661,7 @@ static int hns3_init_all_ring(struct hns3_nic_priv *priv) out_when_alloc_ring_memory: for (j = i - 1; j >= 0; j--) - hns3_fini_ring(priv->ring_data[i].ring); + hns3_fini_ring(priv->ring_data[j].ring); return -ENOMEM; } -- GitLab From 5668abda0931c61f823b21b1612e1c77b617a734 Mon Sep 17 00:00:00 2001 From: Lipeng Date: Tue, 10 Oct 2017 16:42:04 +0800 Subject: [PATCH 1230/1507] net: hns3: add support for set_ringparam This patch supports the ethtool's set_ringparam(). Signed-off-by: Lipeng Signed-off-by: David S. Miller --- .../hisilicon/hns3/hns3pf/hns3_enet.c | 4 +- .../hisilicon/hns3/hns3pf/hns3_enet.h | 4 + .../hisilicon/hns3/hns3pf/hns3_ethtool.c | 75 +++++++++++++++++++ 3 files changed, 81 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c index acb82cfc1b9a2..ba550c1b5b013 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -2637,7 +2637,7 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring) } } -static int hns3_init_all_ring(struct hns3_nic_priv *priv) +int hns3_init_all_ring(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; int ring_num = h->kinfo.num_tqps * 2; @@ -2666,7 +2666,7 @@ static int hns3_init_all_ring(struct hns3_nic_priv *priv) return -ENOMEM; } -static int hns3_uninit_all_ring(struct hns3_nic_priv *priv) +int hns3_uninit_all_ring(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; int i; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h index dd8d40ca1dcce..66599890b4d44 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -76,6 +76,8 @@ enum hns3_nic_state { #define HNS3_RING_NAME_LEN 16 #define HNS3_BUFFER_SIZE_2048 2048 #define HNS3_RING_MAX_PENDING 32768 +#define HNS3_RING_MIN_PENDING 8 +#define HNS3_RING_BD_MULTIPLE 8 #define HNS3_MAX_MTU 9728 #define HNS3_BD_SIZE_512_TYPE 0 @@ -593,6 +595,8 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) void hns3_ethtool_set_ops(struct net_device *netdev); int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); +int hns3_init_all_ring(struct hns3_nic_priv *priv); +int hns3_uninit_all_ring(struct hns3_nic_priv *priv); #ifdef CONFIG_HNS3_DCB void hns3_dcbnl_setup(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index 060bacebf86a9..1c5d003ecf294 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -459,10 +459,85 @@ static int hns3_get_rxnfc(struct net_device *netdev, return 0; } +int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, u32 new_desc_num) +{ + struct hnae3_handle *h = priv->ae_handle; + int i; + + h->kinfo.num_desc = new_desc_num; + + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + priv->ring_data[i].ring->desc_num = new_desc_num; + + return hns3_init_all_ring(priv); +} + +int hns3_set_ringparam(struct net_device *ndev, struct ethtool_ringparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + bool if_running = netif_running(ndev); + u32 old_desc_num, new_desc_num; + int ret; + + if (param->rx_mini_pending || param->rx_jumbo_pending) + return -EINVAL; + + if (param->tx_pending != param->rx_pending) { + netdev_err(ndev, + "Descriptors of tx and rx must be equal"); + return -EINVAL; + } + + if (param->tx_pending > HNS3_RING_MAX_PENDING || + param->tx_pending < HNS3_RING_MIN_PENDING) { + netdev_err(ndev, + "Descriptors requested (Tx/Rx: %d) out of range [%d-%d]\n", + param->tx_pending, HNS3_RING_MIN_PENDING, + HNS3_RING_MAX_PENDING); + return -EINVAL; + } + + new_desc_num = param->tx_pending; + + /* Hardware requires that its descriptors must be multiple of eight */ + new_desc_num = ALIGN(new_desc_num, HNS3_RING_BD_MULTIPLE); + old_desc_num = h->kinfo.num_desc; + if (old_desc_num == new_desc_num) + return 0; + + netdev_info(ndev, + "Changing descriptor count from %d to %d.\n", + old_desc_num, new_desc_num); + + if (if_running) + dev_close(ndev); + + ret = hns3_uninit_all_ring(priv); + if (ret) + return ret; + + ret = hns3_change_all_ring_bd_num(priv, new_desc_num); + if (ret) { + ret = hns3_change_all_ring_bd_num(priv, old_desc_num); + if (ret) { + netdev_err(ndev, + "Revert to old bd num fail, ret=%d.\n", ret); + return ret; + } + } + + if (if_running) + ret = dev_open(ndev); + + return ret; +} + static const struct ethtool_ops hns3_ethtool_ops = { .get_drvinfo = hns3_get_drvinfo, .get_link = hns3_get_link, .get_ringparam = hns3_get_ringparam, + .set_ringparam = hns3_set_ringparam, .get_pauseparam = hns3_get_pauseparam, .get_strings = hns3_get_strings, .get_ethtool_stats = hns3_get_stats, -- GitLab From f7db940afc0a70f72ffcb6bb9c0ad15e6c5349c1 Mon Sep 17 00:00:00 2001 From: Lipeng Date: Tue, 10 Oct 2017 16:42:05 +0800 Subject: [PATCH 1231/1507] net: hns3: add support for set_rxnfc This patch supports the ethtool's set_rxnfc(). Signed-off-by: Lipeng Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 + .../hisilicon/hns3/hns3pf/hclge_cmd.c | 9 ++ .../hisilicon/hns3/hns3pf/hclge_cmd.h | 1 + .../hisilicon/hns3/hns3pf/hclge_main.c | 95 ++++++++++++++++++- .../hisilicon/hns3/hns3pf/hclge_main.h | 8 ++ .../hisilicon/hns3/hns3pf/hns3_ethtool.c | 16 ++++ 6 files changed, 129 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index c677530841cf6..d952d6213024e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -339,6 +339,8 @@ struct hnae3_ae_ops { u8 *hfunc); int (*set_rss)(struct hnae3_handle *handle, const u32 *indir, const u8 *key, const u8 hfunc); + int (*set_rss_tuple)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); int (*get_tc_size)(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 8ecd807447674..60960e588b5fc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -85,6 +85,15 @@ static int hclge_init_cmd_queue(struct hclge_dev *hdev, int ring_type) return 0; } +void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read) +{ + desc->flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN); + if (is_read) + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR); + else + desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); +} + void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, enum hclge_opcode_type opcode, bool is_read) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 8f3ba02aea3ce..b4373345c2b4d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -739,6 +739,7 @@ struct hclge_hw; int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num); void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, enum hclge_opcode_type opcode, bool is_read); +void hclge_cmd_reuse_desc(struct hclge_desc *desc, bool is_read); int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, struct hclge_promisc_param *param); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c91c779aeeed1..5b5e52c7fde0f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2595,8 +2595,6 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, static int hclge_set_rss_input_tuple(struct hclge_dev *hdev) { -#define HCLGE_RSS_INPUT_TUPLE_OTHER 0xf -#define HCLGE_RSS_INPUT_TUPLE_SCTP 0x1f struct hclge_rss_input_tuple_cmd *req; struct hclge_desc desc; int ret; @@ -2677,6 +2675,98 @@ static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, return ret; } +static u8 hclge_get_rss_hash_bits(struct ethtool_rxnfc *nfc) +{ + u8 hash_sets = nfc->data & RXH_L4_B_0_1 ? HCLGE_S_PORT_BIT : 0; + + if (nfc->data & RXH_L4_B_2_3) + hash_sets |= HCLGE_D_PORT_BIT; + else + hash_sets &= ~HCLGE_D_PORT_BIT; + + if (nfc->data & RXH_IP_SRC) + hash_sets |= HCLGE_S_IP_BIT; + else + hash_sets &= ~HCLGE_S_IP_BIT; + + if (nfc->data & RXH_IP_DST) + hash_sets |= HCLGE_D_IP_BIT; + else + hash_sets &= ~HCLGE_D_IP_BIT; + + if (nfc->flow_type == SCTP_V4_FLOW || nfc->flow_type == SCTP_V6_FLOW) + hash_sets |= HCLGE_V_TAG_BIT; + + return hash_sets; +} + +static int hclge_set_rss_tuple(struct hnae3_handle *handle, + struct ethtool_rxnfc *nfc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_rss_input_tuple_cmd *req; + struct hclge_desc desc; + u8 tuple_sets; + int ret; + + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + req = (struct hclge_rss_input_tuple_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Read rss tuple fail, status = %d\n", ret); + return ret; + } + + hclge_cmd_reuse_desc(&desc, false); + + tuple_sets = hclge_get_rss_hash_bits(nfc); + switch (nfc->flow_type) { + case TCP_V4_FLOW: + req->ipv4_tcp_en = tuple_sets; + break; + case TCP_V6_FLOW: + req->ipv6_tcp_en = tuple_sets; + break; + case UDP_V4_FLOW: + req->ipv4_udp_en = tuple_sets; + break; + case UDP_V6_FLOW: + req->ipv6_udp_en = tuple_sets; + break; + case SCTP_V4_FLOW: + req->ipv4_sctp_en = tuple_sets; + break; + case SCTP_V6_FLOW: + if ((nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + + req->ipv6_sctp_en = tuple_sets; + break; + case IPV4_FLOW: + req->ipv4_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + break; + case IPV6_FLOW: + req->ipv6_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + break; + default: + return -EINVAL; + } + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "Set rss tuple fail, status = %d\n", ret); + + return ret; +} + static int hclge_get_tc_size(struct hnae3_handle *handle) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -4344,6 +4434,7 @@ static const struct hnae3_ae_ops hclge_ops = { .get_rss_indir_size = hclge_get_rss_indir_size, .get_rss = hclge_get_rss, .set_rss = hclge_set_rss, + .set_rss_tuple = hclge_set_rss_tuple, .get_tc_size = hclge_get_tc_size, .get_mac_addr = hclge_get_mac_addr, .set_mac_addr = hclge_set_mac_addr, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 79c1a06cb941b..a7c018c7b0eca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -41,6 +41,14 @@ #define HCLGE_RSS_CFG_TBL_NUM \ (HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE) +#define HCLGE_RSS_INPUT_TUPLE_OTHER GENMASK(3, 0) +#define HCLGE_RSS_INPUT_TUPLE_SCTP GENMASK(4, 0) +#define HCLGE_D_PORT_BIT BIT(0) +#define HCLGE_S_PORT_BIT BIT(1) +#define HCLGE_D_IP_BIT BIT(2) +#define HCLGE_S_IP_BIT BIT(3) +#define HCLGE_V_TAG_BIT BIT(4) + #define HCLGE_RSS_TC_SIZE_0 1 #define HCLGE_RSS_TC_SIZE_1 2 #define HCLGE_RSS_TC_SIZE_2 4 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index 1c5d003ecf294..f0e88e00a1f6f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -533,6 +533,21 @@ int hns3_set_ringparam(struct net_device *ndev, struct ethtool_ringparam *param) return ret; } +static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss_tuple) + return -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXFH: + return h->ae_algo->ops->set_rss_tuple(h, cmd); + default: + return -EOPNOTSUPP; + } +} + static const struct ethtool_ops hns3_ethtool_ops = { .get_drvinfo = hns3_get_drvinfo, .get_link = hns3_get_link, @@ -543,6 +558,7 @@ static const struct ethtool_ops hns3_ethtool_ops = { .get_ethtool_stats = hns3_get_stats, .get_sset_count = hns3_get_sset_count, .get_rxnfc = hns3_get_rxnfc, + .set_rxnfc = hns3_set_rxnfc, .get_rxfh_key_size = hns3_get_rss_key_size, .get_rxfh_indir_size = hns3_get_rss_indir_size, .get_rxfh = hns3_get_rss, -- GitLab From 07d2995425eb8eb4874b94bf62fb1490a2014d76 Mon Sep 17 00:00:00 2001 From: Lipeng Date: Tue, 10 Oct 2017 16:42:06 +0800 Subject: [PATCH 1232/1507] net: hns3: add support for ETHTOOL_GRXFH This patch add support for ethtool's ETHTOOL_GRXFH in hns3_get_rxnfc(). Signed-off-by: Lipeng Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 + .../hisilicon/hns3/hns3pf/hclge_main.c | 64 +++++++++++++++++++ .../hisilicon/hns3/hns3pf/hns3_ethtool.c | 2 + 3 files changed, 68 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index d952d6213024e..575f50df340c4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -341,6 +341,8 @@ struct hnae3_ae_ops { const u8 *key, const u8 hfunc); int (*set_rss_tuple)(struct hnae3_handle *handle, struct ethtool_rxnfc *cmd); + int (*get_rss_tuple)(struct hnae3_handle *handle, + struct ethtool_rxnfc *cmd); int (*get_tc_size)(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5b5e52c7fde0f..c322b45341482 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2767,6 +2767,69 @@ static int hclge_set_rss_tuple(struct hnae3_handle *handle, return ret; } +static int hclge_get_rss_tuple(struct hnae3_handle *handle, + struct ethtool_rxnfc *nfc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_rss_input_tuple_cmd *req; + struct hclge_desc desc; + u8 tuple_sets; + int ret; + + nfc->data = 0; + + req = (struct hclge_rss_input_tuple_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Read rss tuple fail, status = %d\n", ret); + return ret; + } + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + tuple_sets = req->ipv4_tcp_en; + break; + case UDP_V4_FLOW: + tuple_sets = req->ipv4_udp_en; + break; + case TCP_V6_FLOW: + tuple_sets = req->ipv6_tcp_en; + break; + case UDP_V6_FLOW: + tuple_sets = req->ipv6_udp_en; + break; + case SCTP_V4_FLOW: + tuple_sets = req->ipv4_sctp_en; + break; + case SCTP_V6_FLOW: + tuple_sets = req->ipv6_sctp_en; + break; + case IPV4_FLOW: + case IPV6_FLOW: + tuple_sets = HCLGE_S_IP_BIT | HCLGE_D_IP_BIT; + break; + default: + return -EINVAL; + } + + if (!tuple_sets) + return 0; + + if (tuple_sets & HCLGE_D_PORT_BIT) + nfc->data |= RXH_L4_B_2_3; + if (tuple_sets & HCLGE_S_PORT_BIT) + nfc->data |= RXH_L4_B_0_1; + if (tuple_sets & HCLGE_D_IP_BIT) + nfc->data |= RXH_IP_DST; + if (tuple_sets & HCLGE_S_IP_BIT) + nfc->data |= RXH_IP_SRC; + + return 0; +} + static int hclge_get_tc_size(struct hnae3_handle *handle) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -4435,6 +4498,7 @@ static const struct hnae3_ae_ops hclge_ops = { .get_rss = hclge_get_rss, .set_rss = hclge_set_rss, .set_rss_tuple = hclge_set_rss_tuple, + .get_rss_tuple = hclge_get_rss_tuple, .get_tc_size = hclge_get_tc_size, .get_mac_addr = hclge_get_mac_addr, .set_mac_addr = hclge_set_mac_addr, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index f0e88e00a1f6f..b64fbd3c369ad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -452,6 +452,8 @@ static int hns3_get_rxnfc(struct net_device *netdev, case ETHTOOL_GRXRINGS: cmd->data = h->ae_algo->ops->get_tc_size(h); break; + case ETHTOOL_GRXFH: + return h->ae_algo->ops->get_rss_tuple(h, cmd); default: return -EOPNOTSUPP; } -- GitLab From abf11d04fd9dbec778219d76a9d38c36f65fbc24 Mon Sep 17 00:00:00 2001 From: Lipeng Date: Tue, 10 Oct 2017 16:42:07 +0800 Subject: [PATCH 1233/1507] net: hns3: fix the ring count for ETHTOOL_GRXRINGS This patch fix the ring count for ETHTOOL_GRXRINGS. Ring count not TC size should be return for command "ethtool -n ethx". Signed-off-by: Lipeng Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index b64fbd3c369ad..9b36ce081f620 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -450,7 +450,7 @@ static int hns3_get_rxnfc(struct net_device *netdev, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = h->ae_algo->ops->get_tc_size(h); + cmd->data = h->kinfo.num_tc * h->kinfo.rss_size; break; case ETHTOOL_GRXFH: return h->ae_algo->ops->get_rss_tuple(h, cmd); -- GitLab From 7e1dc5e926d57a5bc4ac97d6e061e2fe29c266c0 Mon Sep 17 00:00:00 2001 From: Inbar Karmy Date: Tue, 10 Oct 2017 12:28:33 +0300 Subject: [PATCH 1234/1507] net/mlx4_en: Limit the number of TX rings Limit the number of TX rings per UP by the number of cores in the system. Signed-off-by: Inbar Karmy Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/en_main.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 3d4e4a5d00d1c..e9432bc1c1bcc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1748,7 +1748,7 @@ static void mlx4_en_get_channels(struct net_device *dev, struct mlx4_en_priv *priv = netdev_priv(dev); channel->max_rx = MAX_RX_RINGS; - channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP; + channel->max_tx = priv->mdev->profile.max_num_tx_rings_p_up; channel->rx_count = priv->rx_ring_num; channel->tx_count = priv->tx_ring_num[TX] / @@ -1777,7 +1777,7 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; if (channel->tx_count * priv->prof->num_up + xdp_count > - MAX_TX_RINGS) { + priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 686e18de9a97b..2c2965497ed35 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -153,7 +153,7 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) int i; params->udp_rss = udp_rss; - params->num_tx_rings_p_up = mlx4_low_memory_profile() ? + params->max_num_tx_rings_p_up = mlx4_low_memory_profile() ? MLX4_EN_MIN_TX_RING_P_UP : min_t(int, num_online_cpus(), MLX4_EN_MAX_TX_RING_P_UP); @@ -170,8 +170,8 @@ static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) params->prof[i].tx_ring_size = MLX4_EN_DEF_TX_RING_SIZE; params->prof[i].rx_ring_size = MLX4_EN_DEF_RX_RING_SIZE; params->prof[i].num_up = MLX4_EN_NUM_UP_LOW; - params->prof[i].num_tx_rings_p_up = params->num_tx_rings_p_up; - params->prof[i].tx_ring_num[TX] = params->num_tx_rings_p_up * + params->prof[i].num_tx_rings_p_up = params->max_num_tx_rings_p_up; + params->prof[i].tx_ring_num[TX] = params->max_num_tx_rings_p_up * params->prof[i].num_up; params->prof[i].rss_rings = 0; params->prof[i].inline_thold = inline_thold; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 9c218f1cfc6ca..e4c7a80ef5a81 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3305,7 +3305,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->pflags = MLX4_EN_PRIV_FLAGS_BLUEFLAME; priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE | MLX4_WQE_CTRL_SOLICITED); - priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up; + priv->num_tx_rings_p_up = mdev->profile.max_num_tx_rings_p_up; priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK; netdev_rss_key_fill(priv->rss_key, sizeof(priv->rss_key)); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index fdb3ad0cbe542..245e9ea09ab29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -399,7 +399,7 @@ struct mlx4_en_profile { u32 active_ports; u32 small_pkt_int; u8 no_reset; - u8 num_tx_rings_p_up; + u8 max_num_tx_rings_p_up; struct mlx4_en_port_profile prof[MLX4_MAX_PORTS + 1]; }; -- GitLab From b8d394367a631c2d749b3114e04dfb4d09624ddf Mon Sep 17 00:00:00 2001 From: Inbar Karmy Date: Tue, 10 Oct 2017 12:28:34 +0300 Subject: [PATCH 1235/1507] net/mlx4_en: Limit the number of RX rings Limit the number of RX rings by the number of cores in the system. Signed-off-by: Inbar Karmy Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index e9432bc1c1bcc..bf1f041648855 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1742,12 +1742,17 @@ static int mlx4_en_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } +static int mlx4_en_get_max_num_rx_rings(struct net_device *dev) +{ + return min_t(int, num_online_cpus(), MAX_RX_RINGS); +} + static void mlx4_en_get_channels(struct net_device *dev, struct ethtool_channels *channel) { struct mlx4_en_priv *priv = netdev_priv(dev); - channel->max_rx = MAX_RX_RINGS; + channel->max_rx = mlx4_en_get_max_num_rx_rings(dev); channel->max_tx = priv->mdev->profile.max_num_tx_rings_p_up; channel->rx_count = priv->rx_ring_num; -- GitLab From 80a8dc75ee674a111fea2ae1d02ff96535a309c2 Mon Sep 17 00:00:00 2001 From: Inbar Karmy Date: Tue, 10 Oct 2017 12:28:35 +0300 Subject: [PATCH 1236/1507] net/mlx4_en: Increase number of default RX rings Remove limitation of netif_get_num_default_rss_queues() from logic of RX rings default number. Signed-off-by: Inbar Karmy Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 8f9cb8abc4970..a7866954d1063 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -254,8 +254,7 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) DEF_RX_RINGS)); num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS : - min_t(int, num_of_eqs, - netif_get_num_default_rss_queues()); + min_t(int, num_of_eqs, num_online_cpus()); mdev->profile.prof[i].rx_ring_num = rounddown_pow_of_two(num_rx_rings); } -- GitLab From 8f88f74a1641f57607a2417669e0e02b768796b4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 10 Oct 2017 16:18:05 +0200 Subject: [PATCH 1237/1507] selftests: rtnetlink: test RTM_GETNETCONF exercise RTM_GETNETCONF call path for unspec, inet and inet6 families, they are DOIT_UNLOCKED candidates. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 28 ++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index e8c86c416ed04..a8a8cdf726b20 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -37,6 +37,26 @@ kci_del_dummy() check_err $? } +kci_test_netconf() +{ + dev="$1" + r=$ret + + ip netconf show dev "$dev" > /dev/null + check_err $? + + for f in 4 6; do + ip -$f netconf show dev "$dev" > /dev/null + check_err $? + done + + if [ $ret -ne 0 ] ;then + echo "FAIL: ip netconf show $dev" + test $r -eq 0 && ret=0 + return 1 + fi +} + # add a bridge with vlans on top kci_test_bridge() { @@ -63,6 +83,11 @@ kci_test_bridge() check_err $? ip r s t all > /dev/null check_err $? + + for name in "$devbr" "$vlandev" "$devdummy" ; do + kci_test_netconf "$name" + done + ip -6 addr del dev "$vlandev" dead:42::1234/64 check_err $? @@ -100,6 +125,9 @@ kci_test_gre() check_err $? ip addr > /dev/null check_err $? + + kci_test_netconf "$gredev" + ip addr del dev "$devdummy" 10.23.7.11/24 check_err $? -- GitLab From b88d12e4a4ff5b99dcaf9b35a30ad2597cb2fd8a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 10 Oct 2017 17:10:04 +0200 Subject: [PATCH 1238/1507] rtnetlink: bridge: use ext_ack instead of printk We can now piggyback error strings to userspace via extended acks rather than using printk. Before: bridge fdb add 01:02:03:04:05:06 dev br0 vlan 4095 RTNETLINK answers: Invalid argument After: bridge fdb add 01:02:03:04:05:06 dev br0 vlan 4095 Error: invalid vlan id. v3: drop 'RTM_' prefixes, suggested by David Ahern, they are not useful, the add/del in bridge command line is enough. Also reword error in response to malformed/bad vlan id attribute size. Cc: David Ahern Signed-off-by: Florian Westphal Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e84d108cfee4c..6a09f3d575afc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3066,21 +3066,21 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, } EXPORT_SYMBOL(ndo_dflt_fdb_add); -static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid) +static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid, + struct netlink_ext_ack *extack) { u16 vid = 0; if (vlan_attr) { if (nla_len(vlan_attr) != sizeof(u16)) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n"); + NL_SET_ERR_MSG(extack, "invalid vlan attribute size"); return -EINVAL; } vid = nla_get_u16(vlan_attr); if (!vid || vid >= VLAN_VID_MASK) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n", - vid); + NL_SET_ERR_MSG(extack, "invalid vlan id"); return -EINVAL; } } @@ -3105,24 +3105,24 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3209,24 +3209,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + NL_SET_ERR_MSG(extack, "invalid ifindex"); return -EINVAL; } dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { - pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + NL_SET_ERR_MSG(extack, "invalid address"); return -EINVAL; } addr = nla_data(tb[NDA_LLADDR]); - err = fdb_vid_parse(tb[NDA_VLAN], &vid); + err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); if (err) return err; @@ -3666,7 +3666,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } @@ -3741,7 +3741,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, dev = __dev_get_by_index(net, ifm->ifi_index); if (!dev) { - pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + NL_SET_ERR_MSG(extack, "unknown ifindex"); return -ENODEV; } -- GitLab From 833e0e2f24fd0525090878f71e129a8a4cb8bf78 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 10 Oct 2017 15:05:39 -0700 Subject: [PATCH 1239/1507] net: dst: move cpu inside ifdef to avoid compilation warning If CONFIG_DST_CACHE is not selected cpu variable will be unused and we will see a compilation warning. Move it under the ifdef. Reported-by: kbuild test robot Fixes: d66f2b91f95b ("bpf: don't rely on the verifier lock for metadata_dst allocation") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/core/dst.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dst.c b/net/core/dst.c index 8b2eafac984de..662a2d4a3d19b 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -325,9 +325,9 @@ EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) { +#ifdef CONFIG_DST_CACHE int cpu; -#ifdef CONFIG_DST_CACHE for_each_possible_cpu(cpu) { struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); -- GitLab From b8226962b1c49c784aeddb9d2fafbf53dfdc2190 Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Tue, 10 Oct 2017 16:54:44 -0400 Subject: [PATCH 1240/1507] openvswitch: add ct_clear action This adds a ct_clear action for clearing conntrack state. ct_clear is currently implemented in OVS userspace, but is not backed by an action in the kernel datapath. This is useful for flows that may modify a packet tuple after a ct lookup has already occurred. Signed-off-by: Eric Garver Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/actions.c | 4 ++++ net/openvswitch/conntrack.c | 11 +++++++++++ net/openvswitch/conntrack.h | 7 +++++++ net/openvswitch/flow_netlink.c | 5 +++++ 5 files changed, 29 insertions(+) diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efdbfbfd3ee2a..0cd6f88331471 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -807,6 +807,7 @@ struct ovs_action_push_eth { * packet. * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. + * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -836,6 +837,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ + OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a54a556fcdb57..a551232daf61d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1203,6 +1203,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err == -EINPROGRESS ? 0 : err; break; + case OVS_ACTION_ATTR_CT_CLEAR: + err = ovs_ct_clear(skb, key); + break; + case OVS_ACTION_ATTR_PUSH_ETH: err = push_eth(skb, key, nla_data(a)); break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d558e882ca0c5..fe861e2f0deb8 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1129,6 +1129,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) +{ + if (skb_nfct(skb)) { + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key); + } + + return 0; +} + static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, const struct sw_flow_key *key, bool log) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index bc7efd1867ab4..399dfdd2c4f97 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -30,6 +30,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *); int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *swkey, @@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, return -ENOTSUPP; } +static inline int ovs_ct_clear(struct sk_buff *skb, + struct sw_flow_key *key) +{ + return -ENOTSUPP; +} + static inline void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index fc0ca9a89b8e6..dc0d79092e742 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -76,6 +76,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) break; case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: @@ -2528,6 +2529,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, + [OVS_ACTION_ATTR_CT_CLEAR] = 0, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, @@ -2669,6 +2671,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_CT_CLEAR: + break; + case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ -- GitLab From 8c03145a2e2d98d44dba4bf16ab34636eb60b834 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 Oct 2017 09:57:59 +0200 Subject: [PATCH 1241/1507] MAINTAINERS: update Johannes Berg's entries Update my MAINTAINERS file entries to list all the right files. Since I'm also the de-facto wireless extensions maintainer, there's little point in excluding those. Signed-off-by: Johannes Berg --- MAINTAINERS | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index f0c37be4e04a6..e90cdecd7b5d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3329,17 +3329,22 @@ S: Maintained F: drivers/auxdisplay/cfag12864bfb.c F: include/linux/cfag12864b.h -CFG80211 and NL80211 +802.11 (including CFG80211/NL80211) M: Johannes Berg L: linux-wireless@vger.kernel.org W: http://wireless.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained +F: net/wireless/ F: include/uapi/linux/nl80211.h +F: include/linux/ieee80211.h +F: include/net/wext.h F: include/net/cfg80211.h -F: net/wireless/* -X: net/wireless/wext* +F: include/net/iw_handler.h +F: include/net/ieee80211_radiotap.h +F: Documentation/driver-api/80211/cfg80211.rst +F: Documentation/networking/regulatory.txt CHAR and MISC DRIVERS M: Arnd Bergmann @@ -8207,6 +8212,7 @@ F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h F: net/mac80211/ F: drivers/net/wireless/mac80211_hwsim.[ch] +F: Documentation/networking/mac80211_hwsim/README MAILBOX API M: Jassi Brar @@ -11491,6 +11497,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: Documentation/rfkill.txt +F: Documentation/ABI/stable/sysfs-class-rfkill F: net/rfkill/ RHASHTABLE -- GitLab From 4133da73067af0417c623eb4ad5e85081ccbf4b4 Mon Sep 17 00:00:00 2001 From: Xiang Gao Date: Tue, 10 Oct 2017 22:31:49 -0400 Subject: [PATCH 1242/1507] mac80211: aead api to reduce redundancy Currently, the aes_ccm.c and aes_gcm.c are almost line by line copy of each other. This patch reduce code redundancy by moving the code in these two files to crypto/aead_api.c to make it a higher level aead api. The file aes_ccm.c and aes_gcm.c are removed and all the functions there are now implemented in their headers using the newly added aead api. Signed-off-by: Xiang Gao Signed-off-by: Johannes Berg --- net/mac80211/Makefile | 3 +- net/mac80211/{aes_ccm.c => aead_api.c} | 40 ++++----- net/mac80211/aead_api.h | 27 ++++++ net/mac80211/aes_ccm.h | 42 +++++++--- net/mac80211/aes_gcm.c | 109 ------------------------- net/mac80211/aes_gcm.h | 38 +++++++-- net/mac80211/wpa.c | 4 +- 7 files changed, 111 insertions(+), 152 deletions(-) rename net/mac80211/{aes_ccm.c => aead_api.c} (67%) create mode 100644 net/mac80211/aead_api.h delete mode 100644 net/mac80211/aes_gcm.c diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 2829122459387..80f25ff2f24be 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -6,6 +6,7 @@ mac80211-y := \ driver-ops.o \ sta_info.o \ wep.o \ + aead_api.o \ wpa.o \ scan.o offchannel.o \ ht.o agg-tx.o agg-rx.o \ @@ -15,8 +16,6 @@ mac80211-y := \ rate.o \ michael.o \ tkip.o \ - aes_ccm.o \ - aes_gcm.o \ aes_cmac.o \ aes_gmac.o \ fils_aead.o \ diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aead_api.c similarity index 67% rename from net/mac80211/aes_ccm.c rename to net/mac80211/aead_api.c index a4e0d59a40dd5..347f13953b2cb 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aead_api.c @@ -1,6 +1,7 @@ /* * Copyright 2003-2004, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. + * Copyright 2014-2015, Qualcomm Atheros, Inc. * * Rewrite: Copyright (C) 2013 Linaro Ltd * @@ -12,30 +13,29 @@ #include #include #include +#include #include -#include -#include "key.h" -#include "aes_ccm.h" +#include "aead_api.h" -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = tfm->authsize; struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); u8 *__aad; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -49,10 +49,10 @@ int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return 0; } -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len) +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, + u8 *data, size_t data_len, u8 *mic) { + size_t mic_len = tfm->authsize; struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); @@ -62,15 +62,15 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, if (data_len == 0) return -EINVAL; - aead_req = kzalloc(reqsize + CCM_AAD_LEN, GFP_ATOMIC); + aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) return -ENOMEM; __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, CCM_AAD_LEN); + memcpy(__aad, aad, aad_len); sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); + sg_set_buf(&sg[0], __aad, aad_len); sg_set_buf(&sg[1], data, data_len); sg_set_buf(&sg[2], mic, mic_len); @@ -84,14 +84,14 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, return err; } -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len) +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len) { struct crypto_aead *tfm; int err; - tfm = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_aead(alg, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -109,7 +109,7 @@ struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], return ERR_PTR(err); } -void ieee80211_aes_key_free(struct crypto_aead *tfm) +void aead_key_free(struct crypto_aead *tfm) { crypto_free_aead(tfm); } diff --git a/net/mac80211/aead_api.h b/net/mac80211/aead_api.h new file mode 100644 index 0000000000000..5e39ea843bbfe --- /dev/null +++ b/net/mac80211/aead_api.h @@ -0,0 +1,27 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _AEAD_API_H +#define _AEAD_API_H + +#include +#include + +struct crypto_aead * +aead_key_setup_encrypt(const char *alg, const u8 key[], + size_t key_len, size_t mic_len); + +int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, + size_t aad_len, u8 *data, + size_t data_len, u8 *mic); + +void aead_key_free(struct crypto_aead *tfm); + +#endif /* _AEAD_API_H */ diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h index fcd3254c5cf08..e9b7ca0bde5b9 100644 --- a/net/mac80211/aes_ccm.h +++ b/net/mac80211/aes_ccm.h @@ -10,19 +10,39 @@ #ifndef AES_CCM_H #define AES_CCM_H -#include +#include "aead_api.h" #define CCM_AAD_LEN 32 -struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[], - size_t key_len, - size_t mic_len); -int ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic, - size_t mic_len); -void ieee80211_aes_key_free(struct crypto_aead *tfm); +static inline struct crypto_aead * +ieee80211_aes_key_setup_encrypt(const u8 key[], size_t key_len, size_t mic_len) +{ + return aead_key_setup_encrypt("ccm(aes)", key, key_len, mic_len); +} + +static inline int +ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int +ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, + u8 *b_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, b_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline void ieee80211_aes_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_CCM_H */ diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c deleted file mode 100644 index 8a4397cc1b08b..0000000000000 --- a/net/mac80211/aes_gcm.c +++ /dev/null @@ -1,109 +0,0 @@ -/* - * Copyright 2014-2015, Qualcomm Atheros, Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include - -#include -#include "key.h" -#include "aes_gcm.h" - -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, data_len, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - crypto_aead_encrypt(aead_req); - kzfree(aead_req); - return 0; -} - -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic) -{ - struct scatterlist sg[3]; - struct aead_request *aead_req; - int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); - u8 *__aad; - int err; - - if (data_len == 0) - return -EINVAL; - - aead_req = kzalloc(reqsize + GCM_AAD_LEN, GFP_ATOMIC); - if (!aead_req) - return -ENOMEM; - - __aad = (u8 *)aead_req + reqsize; - memcpy(__aad, aad, GCM_AAD_LEN); - - sg_init_table(sg, 3); - sg_set_buf(&sg[0], &__aad[2], be16_to_cpup((__be16 *)__aad)); - sg_set_buf(&sg[1], data, data_len); - sg_set_buf(&sg[2], mic, IEEE80211_GCMP_MIC_LEN); - - aead_request_set_tfm(aead_req, tfm); - aead_request_set_crypt(aead_req, sg, sg, - data_len + IEEE80211_GCMP_MIC_LEN, j_0); - aead_request_set_ad(aead_req, sg[0].length); - - err = crypto_aead_decrypt(aead_req); - kzfree(aead_req); - - return err; -} - -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len) -{ - struct crypto_aead *tfm; - int err; - - tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return tfm; - - err = crypto_aead_setkey(tfm, key, key_len); - if (err) - goto free_aead; - err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN); - if (err) - goto free_aead; - - return tfm; - -free_aead: - crypto_free_aead(tfm); - return ERR_PTR(err); -} - -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) -{ - crypto_free_aead(tfm); -} diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h index 55aed5352494f..d2b0960330092 100644 --- a/net/mac80211/aes_gcm.h +++ b/net/mac80211/aes_gcm.h @@ -9,16 +9,38 @@ #ifndef AES_GCM_H #define AES_GCM_H -#include +#include "aead_api.h" #define GCM_AAD_LEN 32 -int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad, - u8 *data, size_t data_len, u8 *mic); -struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], - size_t key_len); -void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm); +static inline int ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_encrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, + u8 *j_0, u8 *aad, u8 *data, + size_t data_len, u8 *mic) +{ + return aead_decrypt(tfm, j_0, aad + 2, + be16_to_cpup((__be16 *)aad), + data, data_len, mic); +} + +static inline struct crypto_aead * +ieee80211_aes_gcm_key_setup_encrypt(const u8 key[], size_t key_len) +{ + return aead_key_setup_encrypt("gcm(aes)", key, + key_len, IEEE80211_GCMP_MIC_LEN); +} + +static inline void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm) +{ + return aead_key_free(tfm); +} #endif /* AES_GCM_H */ diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 0d722ea98a1b3..b58722d9de379 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -464,7 +464,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, pos += IEEE80211_CCMP_HDR_LEN; ccmp_special_blocks(skb, pn, b_0, aad); return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, - skb_put(skb, mic_len), mic_len); + skb_put(skb, mic_len)); } @@ -543,7 +543,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, key->u.ccmp.tfm, b_0, aad, skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, data_len, - skb->data + skb->len - mic_len, mic_len)) + skb->data + skb->len - mic_len)) return RX_DROP_UNUSABLE; } -- GitLab From 8c418b5b15747eda05d086e80fa0a767982fbf37 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 6 Oct 2017 11:53:32 +0200 Subject: [PATCH 1243/1507] fq: support filtering a given tin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add to the FQ API a way to filter a given tin, in order to remove frames that fulfil certain criteria according to a filter function. This will be used by mac80211 to remove frames belonging to an AP VLAN interface that's being removed. Signed-off-by: Johannes Berg Acked-by: Toke Høiland-Jørgensen Signed-off-by: Johannes Berg --- include/net/fq.h | 7 +++++ include/net/fq_impl.h | 72 +++++++++++++++++++++++++++++++++++++------ 2 files changed, 69 insertions(+), 10 deletions(-) diff --git a/include/net/fq.h b/include/net/fq.h index 6d8521a30c5cf..ac944a686840f 100644 --- a/include/net/fq.h +++ b/include/net/fq.h @@ -90,6 +90,13 @@ typedef void fq_skb_free_t(struct fq *, struct fq_flow *, struct sk_buff *); +/* Return %true to filter (drop) the frame. */ +typedef bool fq_skb_filter_t(struct fq *, + struct fq_tin *, + struct fq_flow *, + struct sk_buff *, + void *); + typedef struct fq_flow *fq_flow_get_default_t(struct fq *, struct fq_tin *, int idx, diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 4e6131cd3f43d..8b237e4afee6f 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -12,24 +12,22 @@ /* functions that are embedded into includer */ -static struct sk_buff *fq_flow_dequeue(struct fq *fq, - struct fq_flow *flow) +static void fq_adjust_removal(struct fq *fq, + struct fq_flow *flow, + struct sk_buff *skb) { struct fq_tin *tin = flow->tin; - struct fq_flow *i; - struct sk_buff *skb; - - lockdep_assert_held(&fq->lock); - - skb = __skb_dequeue(&flow->queue); - if (!skb) - return NULL; tin->backlog_bytes -= skb->len; tin->backlog_packets--; flow->backlog -= skb->len; fq->backlog--; fq->memory_usage -= skb->truesize; +} + +static void fq_rejigger_backlog(struct fq *fq, struct fq_flow *flow) +{ + struct fq_flow *i; if (flow->backlog == 0) { list_del_init(&flow->backlogchain); @@ -43,6 +41,21 @@ static struct sk_buff *fq_flow_dequeue(struct fq *fq, list_move_tail(&flow->backlogchain, &i->backlogchain); } +} + +static struct sk_buff *fq_flow_dequeue(struct fq *fq, + struct fq_flow *flow) +{ + struct sk_buff *skb; + + lockdep_assert_held(&fq->lock); + + skb = __skb_dequeue(&flow->queue); + if (!skb) + return NULL; + + fq_adjust_removal(fq, flow, skb); + fq_rejigger_backlog(fq, flow); return skb; } @@ -188,6 +201,45 @@ static void fq_tin_enqueue(struct fq *fq, } } +static void fq_flow_filter(struct fq *fq, + struct fq_flow *flow, + fq_skb_filter_t filter_func, + void *filter_data, + fq_skb_free_t free_func) +{ + struct fq_tin *tin = flow->tin; + struct sk_buff *skb, *tmp; + + lockdep_assert_held(&fq->lock); + + skb_queue_walk_safe(&flow->queue, skb, tmp) { + if (!filter_func(fq, tin, flow, skb, filter_data)) + continue; + + __skb_unlink(skb, &flow->queue); + fq_adjust_removal(fq, flow, skb); + free_func(fq, tin, flow, skb); + } + + fq_rejigger_backlog(fq, flow); +} + +static void fq_tin_filter(struct fq *fq, + struct fq_tin *tin, + fq_skb_filter_t filter_func, + void *filter_data, + fq_skb_free_t free_func) +{ + struct fq_flow *flow; + + lockdep_assert_held(&fq->lock); + + list_for_each_entry(flow, &tin->new_flows, flowchain) + fq_flow_filter(fq, flow, filter_func, filter_data, free_func); + list_for_each_entry(flow, &tin->old_flows, flowchain) + fq_flow_filter(fq, flow, filter_func, filter_data, free_func); +} + static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) -- GitLab From 2a9e25796b289f71c0802eca46005c750c57af95 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 6 Oct 2017 11:53:33 +0200 Subject: [PATCH 1244/1507] mac80211: only remove AP VLAN frames from TXQ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When removing an AP VLAN interface, mac80211 currently purges the entire TXQ for the AP interface. Fix this by using the FQ API introduced in the previous patch to filter frames. Signed-off-by: Johannes Berg Acked-by: Toke Høiland-Jørgensen Signed-off-by: Johannes Berg --- net/mac80211/ieee80211_i.h | 2 ++ net/mac80211/iface.c | 25 +++---------------------- net/mac80211/tx.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+), 22 deletions(-) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 9675814f64dbc..68f874e73561e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2009,6 +2009,8 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct txq_info *txq, int tid); void ieee80211_txq_purge(struct ieee80211_local *local, struct txq_info *txqi); +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 2619daa299613..13b16f90e1cf4 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -793,9 +793,7 @@ static int ieee80211_open(struct net_device *dev) static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_down) { - struct ieee80211_sub_if_data *txq_sdata = sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; unsigned long flags; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; @@ -939,9 +937,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP_VLAN: - txq_sdata = container_of(sdata->bss, - struct ieee80211_sub_if_data, u.ap); - mutex_lock(&local->mtx); list_del(&sdata->u.vlan.list); mutex_unlock(&local->mtx); @@ -998,8 +993,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, skb_queue_purge(&sdata->skb_queue); } - sdata->bss = NULL; - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_walk_safe(&local->pending[i], skb, tmp) { @@ -1012,22 +1005,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - if (txq_sdata->vif.txq) { - struct txq_info *txqi = to_txq_info(txq_sdata->vif.txq); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + ieee80211_txq_remove_vlan(local, sdata); - /* - * FIXME FIXME - * - * We really shouldn't purge the *entire* txqi since that - * contains frames for the other AP_VLANs (and possibly - * the AP itself) as well, but there's no API in FQ now - * to be able to filter. - */ - - spin_lock_bh(&fq->lock); - ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); - } + sdata->bss = NULL; if (local->open_count == 0) ieee80211_clear_tx_pending(local); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 94826680cf2b5..7b8154474b9e6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1396,6 +1396,40 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, fq_flow_get_default_func); } +static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin, + struct fq_flow *flow, struct sk_buff *skb, + void *data) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + return info->control.vif == data; +} + +void ieee80211_txq_remove_vlan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + struct fq *fq = &local->fq; + struct txq_info *txqi; + struct fq_tin *tin; + struct ieee80211_sub_if_data *ap; + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP_VLAN)) + return; + + ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); + + if (!ap->vif.txq) + return; + + txqi = to_txq_info(ap->vif.txq); + tin = &txqi->tin; + + spin_lock_bh(&fq->lock); + fq_tin_filter(fq, tin, fq_vlan_filter_func, &sdata->vif, + fq_skb_free_func); + spin_unlock_bh(&fq->lock); +} + void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct txq_info *txqi, int tid) -- GitLab From 007f6c5e6eb45c81ee89368a5f226572ae638831 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 15 Oct 2015 11:22:58 +0200 Subject: [PATCH 1245/1507] cfg80211: support loading regulatory database as firmware file As the current regulatory database is only about 4k big, and already difficult to extend, we decided that overall it would be better to get rid of the complications with CRDA and load the database into the kernel directly, but in a new format that is extensible. The new file format can be extended since it carries a length field on all the structs that need to be extensible. In order to be able to request firmware when the module initializes, move cfg80211 from subsys_initcall() to the later fs_initcall(); the firmware loader is at the same level but linked earlier, so it can be called from there. Otherwise, when both the firmware loader and cfg80211 are built-in, the request will crash the kernel. We also need to be before device_initcall() so that cfg80211 is available for devices when they initialize. Signed-off-by: Johannes Berg --- Documentation/networking/regulatory.txt | 8 + net/wireless/Kconfig | 4 +- net/wireless/core.c | 2 +- net/wireless/reg.c | 294 ++++++++++++++++++++++-- 4 files changed, 284 insertions(+), 24 deletions(-) diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index 7818b5fe448b6..46c8d8b1cc66a 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -19,6 +19,14 @@ core regulatory domain all wireless devices should adhere to. How to get regulatory domains to the kernel ------------------------------------------- +When the regulatory domain is first set up, the kernel will request a +database file (regulatory.db) containing all the regulatory rules. It +will then use that database when it needs to look up the rules for a +given country. + +How to get regulatory domains to the kernel (old CRDA solution) +--------------------------------------------------------------- + Userspace gets a regulatory domain in the kernel by having a userspace agent build it and send it via nl80211. Only expected regulatory domains will be respected by the kernel. diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 6c606120abfed..24eec55166495 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -19,6 +19,7 @@ config WEXT_PRIV config CFG80211 tristate "cfg80211 - wireless configuration API" depends on RFKILL || !RFKILL + select FW_LOADER ---help--- cfg80211 is the Linux wireless LAN (802.11) configuration API. Enable this if you have a wireless device. @@ -167,7 +168,8 @@ config CFG80211_CRDA_SUPPORT depends on CFG80211 help You should enable this option unless you know for sure you have no - need for it, for example when using internal regdb (above.) + need for it, for example when using internal regdb (above) or the + database loaded as a firmware file. If unsure, say Y. diff --git a/net/wireless/core.c b/net/wireless/core.c index 7b33e8c366bc1..fdde0d98fde16 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1384,7 +1384,7 @@ static int __init cfg80211_init(void) out_fail_pernet: return err; } -subsys_initcall(cfg80211_init); +fs_initcall(cfg80211_init); static void __exit cfg80211_exit(void) { diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 6e94f6934a0e7..e9aeb05aaf3ea 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include "core.h" #include "reg.h" @@ -100,7 +101,7 @@ static struct regulatory_request core_request_world = { static struct regulatory_request __rcu *last_request = (void __force __rcu *)&core_request_world; -/* To trigger userspace events */ +/* To trigger userspace events and load firmware */ static struct platform_device *reg_pdev; /* @@ -443,7 +444,6 @@ reg_copy_regd(const struct ieee80211_regdomain *src_regd) return regd; } -#ifdef CONFIG_CFG80211_INTERNAL_REGDB struct reg_regdb_apply_request { struct list_head list; const struct ieee80211_regdomain *regdom; @@ -475,41 +475,44 @@ static void reg_regdb_apply(struct work_struct *work) static DECLARE_WORK(reg_regdb_work, reg_regdb_apply); -static int reg_query_builtin(const char *alpha2) +static int reg_schedule_apply(const struct ieee80211_regdomain *regdom) { - const struct ieee80211_regdomain *regdom = NULL; struct reg_regdb_apply_request *request; - unsigned int i; - - for (i = 0; i < reg_regdb_size; i++) { - if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { - regdom = reg_regdb[i]; - break; - } - } - - if (!regdom) - return -ENODATA; request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL); - if (!request) - return -ENOMEM; - - request->regdom = reg_copy_regd(regdom); - if (IS_ERR_OR_NULL(request->regdom)) { - kfree(request); + if (!request) { + kfree(regdom); return -ENOMEM; } + request->regdom = regdom; + mutex_lock(®_regdb_apply_mutex); list_add_tail(&request->list, ®_regdb_apply_list); mutex_unlock(®_regdb_apply_mutex); schedule_work(®_regdb_work); - return 0; } +#ifdef CONFIG_CFG80211_INTERNAL_REGDB +static int reg_query_builtin(const char *alpha2) +{ + const struct ieee80211_regdomain *regdom = NULL; + unsigned int i; + + for (i = 0; i < reg_regdb_size; i++) { + if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { + regdom = reg_copy_regd(reg_regdb[i]); + break; + } + } + if (!regdom) + return -ENODATA; + + return reg_schedule_apply(regdom); +} + /* Feel free to add any other sanity checks here */ static void reg_regdb_size_check(void) { @@ -599,12 +602,256 @@ static inline int call_crda(const char *alpha2) } #endif /* CONFIG_CFG80211_CRDA_SUPPORT */ +/* code to directly load a firmware database through request_firmware */ +static const struct fwdb_header *regdb; + +struct fwdb_country { + u8 alpha2[2]; + __be16 coll_ptr; + /* this struct cannot be extended */ +} __packed __aligned(4); + +struct fwdb_collection { + u8 len; + u8 n_rules; + u8 dfs_region; + /* no optional data yet */ + /* aligned to 2, then followed by __be16 array of rule pointers */ +} __packed __aligned(4); + +enum fwdb_flags { + FWDB_FLAG_NO_OFDM = BIT(0), + FWDB_FLAG_NO_OUTDOOR = BIT(1), + FWDB_FLAG_DFS = BIT(2), + FWDB_FLAG_NO_IR = BIT(3), + FWDB_FLAG_AUTO_BW = BIT(4), +}; + +struct fwdb_rule { + u8 len; + u8 flags; + __be16 max_eirp; + __be32 start, end, max_bw; + /* start of optional data */ + __be16 cac_timeout; +} __packed __aligned(4); + +#define FWDB_MAGIC 0x52474442 +#define FWDB_VERSION 20 + +struct fwdb_header { + __be32 magic; + __be32 version; + struct fwdb_country country[]; +} __packed __aligned(4); + +static bool valid_rule(const u8 *data, unsigned int size, u16 rule_ptr) +{ + struct fwdb_rule *rule = (void *)(data + (rule_ptr << 2)); + + if ((u8 *)rule + sizeof(rule->len) > data + size) + return false; + + /* mandatory fields */ + if (rule->len < offsetofend(struct fwdb_rule, max_bw)) + return false; + + return true; +} + +static bool valid_country(const u8 *data, unsigned int size, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)(data + ptr); + __be16 *rules_ptr; + unsigned int i; + + /* make sure we can read len/n_rules */ + if ((u8 *)coll + offsetofend(typeof(*coll), n_rules) > data + size) + return false; + + /* make sure base struct and all rules fit */ + if ((u8 *)coll + ALIGN(coll->len, 2) + + (coll->n_rules * 2) > data + size) + return false; + + /* mandatory fields must exist */ + if (coll->len < offsetofend(struct fwdb_collection, dfs_region)) + return false; + + rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + + for (i = 0; i < coll->n_rules; i++) { + u16 rule_ptr = be16_to_cpu(rules_ptr[i]); + + if (!valid_rule(data, size, rule_ptr)) + return false; + } + + return true; +} + +static bool valid_regdb(const u8 *data, unsigned int size) +{ + const struct fwdb_header *hdr = (void *)data; + const struct fwdb_country *country; + + if (size < sizeof(*hdr)) + return false; + + if (hdr->magic != cpu_to_be32(FWDB_MAGIC)) + return false; + + if (hdr->version != cpu_to_be32(FWDB_VERSION)) + return false; + + country = &hdr->country[0]; + while ((u8 *)(country + 1) <= data + size) { + if (!country->coll_ptr) + break; + if (!valid_country(data, size, country)) + return false; + country++; + } + + return true; +} + +static int regdb_query_country(const struct fwdb_header *db, + const struct fwdb_country *country) +{ + unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; + struct fwdb_collection *coll = (void *)((u8 *)db + ptr); + struct ieee80211_regdomain *regdom; + unsigned int size_of_regd; + unsigned int i; + + size_of_regd = + sizeof(struct ieee80211_regdomain) + + coll->n_rules * sizeof(struct ieee80211_reg_rule); + + regdom = kzalloc(size_of_regd, GFP_KERNEL); + if (!regdom) + return -ENOMEM; + + regdom->n_reg_rules = coll->n_rules; + regdom->alpha2[0] = country->alpha2[0]; + regdom->alpha2[1] = country->alpha2[1]; + regdom->dfs_region = coll->dfs_region; + + for (i = 0; i < regdom->n_reg_rules; i++) { + __be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); + unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2; + struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr); + struct ieee80211_reg_rule *rrule = ®dom->reg_rules[i]; + + rrule->freq_range.start_freq_khz = be32_to_cpu(rule->start); + rrule->freq_range.end_freq_khz = be32_to_cpu(rule->end); + rrule->freq_range.max_bandwidth_khz = be32_to_cpu(rule->max_bw); + + rrule->power_rule.max_antenna_gain = 0; + rrule->power_rule.max_eirp = be16_to_cpu(rule->max_eirp); + + rrule->flags = 0; + if (rule->flags & FWDB_FLAG_NO_OFDM) + rrule->flags |= NL80211_RRF_NO_OFDM; + if (rule->flags & FWDB_FLAG_NO_OUTDOOR) + rrule->flags |= NL80211_RRF_NO_OUTDOOR; + if (rule->flags & FWDB_FLAG_DFS) + rrule->flags |= NL80211_RRF_DFS; + if (rule->flags & FWDB_FLAG_NO_IR) + rrule->flags |= NL80211_RRF_NO_IR; + if (rule->flags & FWDB_FLAG_AUTO_BW) + rrule->flags |= NL80211_RRF_AUTO_BW; + + rrule->dfs_cac_ms = 0; + + /* handle optional data */ + if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout)) + rrule->dfs_cac_ms = + 1000 * be16_to_cpu(rule->cac_timeout); + } + + return reg_schedule_apply(regdom); +} + +static int query_regdb(const char *alpha2) +{ + const struct fwdb_header *hdr = regdb; + const struct fwdb_country *country; + + if (IS_ERR(regdb)) + return PTR_ERR(regdb); + + country = &hdr->country[0]; + while (country->coll_ptr) { + if (alpha2_equal(alpha2, country->alpha2)) + return regdb_query_country(regdb, country); + country++; + } + + return -ENODATA; +} + +static void regdb_fw_cb(const struct firmware *fw, void *context) +{ + void *db; + + if (!fw) { + pr_info("failed to load regulatory.db\n"); + regdb = ERR_PTR(-ENODATA); + goto restore; + } + + if (!valid_regdb(fw->data, fw->size)) { + pr_info("loaded regulatory.db is malformed\n"); + release_firmware(fw); + regdb = ERR_PTR(-EINVAL); + goto restore; + } + + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + release_firmware(fw); + + if (!db) + goto restore; + regdb = db; + + if (query_regdb(context)) + goto restore; + goto free; + restore: + rtnl_lock(); + restore_regulatory_settings(true); + rtnl_unlock(); + free: + kfree(context); +} + +static int query_regdb_file(const char *alpha2) +{ + if (regdb) + return query_regdb(alpha2); + + alpha2 = kmemdup(alpha2, 2, GFP_KERNEL); + if (!alpha2) + return -ENOMEM; + + return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); +} + static bool reg_query_database(struct regulatory_request *request) { /* query internal regulatory database (if it exists) */ if (reg_query_builtin(request->alpha2) == 0) return true; + if (query_regdb_file(request->alpha2) == 0) + return true; + if (call_crda(request->alpha2) == 0) return true; @@ -3360,4 +3607,7 @@ void regulatory_exit(void) list_del(®_request->list); kfree(reg_request); } + + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); } -- GitLab From 1ea4ff3e9f0b8d53e680a2bb9e8e644bf03aeb4d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Sep 2017 16:07:22 +0200 Subject: [PATCH 1246/1507] cfg80211: support reloading regulatory database If the regulatory database is loaded, and then updated, it may be necessary to reload it. Add an nl80211 command to do this. Note that this just reloads the database, it doesn't re-apply the rules from it immediately. Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 ++ net/wireless/nl80211.c | 11 +++++ net/wireless/reg.c | 80 +++++++++++++++++++++++++++--------- net/wireless/reg.h | 6 +++ 4 files changed, 81 insertions(+), 20 deletions(-) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 95832ce03a440..f882fe1f9709d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -990,6 +990,8 @@ * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed * &NL80211_CMD_DISCONNECT should be indicated instead. * + * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1194,6 +1196,8 @@ enum nl80211_commands { NL80211_CMD_PORT_AUTHORIZED, + NL80211_CMD_RELOAD_REGDB, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5129342151e6d..67a03f2885a4e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5678,6 +5678,11 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) } } +static int nl80211_reload_regdb(struct sk_buff *skb, struct genl_info *info) +{ + return reg_reload_regdb(); +} + static int nl80211_get_mesh_config(struct sk_buff *skb, struct genl_info *info) { @@ -12708,6 +12713,12 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = NL80211_CMD_RELOAD_REGDB, + .doit = nl80211_reload_regdb, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, { .cmd = NL80211_CMD_GET_MESH_CONFIG, .doit = nl80211_get_mesh_config, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e9aeb05aaf3ea..180addda52aff 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -781,6 +781,8 @@ static int query_regdb(const char *alpha2) const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; + ASSERT_RTNL(); + if (IS_ERR(regdb)) return PTR_ERR(regdb); @@ -796,41 +798,47 @@ static int query_regdb(const char *alpha2) static void regdb_fw_cb(const struct firmware *fw, void *context) { + int set_error = 0; + bool restore = true; void *db; if (!fw) { pr_info("failed to load regulatory.db\n"); - regdb = ERR_PTR(-ENODATA); - goto restore; - } - - if (!valid_regdb(fw->data, fw->size)) { + set_error = -ENODATA; + } else if (!valid_regdb(fw->data, fw->size)) { pr_info("loaded regulatory.db is malformed\n"); - release_firmware(fw); - regdb = ERR_PTR(-EINVAL); - goto restore; + set_error = -EINVAL; } - db = kmemdup(fw->data, fw->size, GFP_KERNEL); - release_firmware(fw); + rtnl_lock(); + if (WARN_ON(regdb && !IS_ERR(regdb))) { + /* just restore and free new db */ + } else if (set_error) { + regdb = ERR_PTR(set_error); + } else if (fw) { + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (db) { + regdb = db; + restore = context && query_regdb(context); + } else { + restore = true; + } + } - if (!db) - goto restore; - regdb = db; + if (restore) + restore_regulatory_settings(true); - if (query_regdb(context)) - goto restore; - goto free; - restore: - rtnl_lock(); - restore_regulatory_settings(true); rtnl_unlock(); - free: + kfree(context); + + release_firmware(fw); } static int query_regdb_file(const char *alpha2) { + ASSERT_RTNL(); + if (regdb) return query_regdb(alpha2); @@ -843,6 +851,38 @@ static int query_regdb_file(const char *alpha2) (void *)alpha2, regdb_fw_cb); } +int reg_reload_regdb(void) +{ + const struct firmware *fw; + void *db; + int err; + + err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); + if (err) + return err; + + if (!valid_regdb(fw->data, fw->size)) { + err = -ENODATA; + goto out; + } + + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!db) { + err = -ENOMEM; + goto out; + } + + rtnl_lock(); + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + regdb = db; + rtnl_unlock(); + + out: + release_firmware(fw); + return err; +} + static bool reg_query_database(struct regulatory_request *request) { /* query internal regulatory database (if it exists) */ diff --git a/net/wireless/reg.h b/net/wireless/reg.h index ca7fedf2e7a16..9529c522611a7 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -179,4 +179,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1 */ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); + +/** + * reg_reload_regdb - reload the regulatory.db firmware file + */ +int reg_reload_regdb(void); + #endif /* __NET_WIRELESS_REG_H */ -- GitLab From c8c240e284b3d821011b4f680b3eaa99569b3756 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 15 Oct 2015 14:35:41 +0200 Subject: [PATCH 1247/1507] cfg80211: reg: remove support for built-in regdb Parsing and building C structures from a regdb is no longer needed since the "firmware" file (regulatory.db) can be linked into the kernel image to achieve the same effect. Signed-off-by: Johannes Berg --- Documentation/networking/regulatory.txt | 22 +--- net/wireless/.gitignore | 1 - net/wireless/Kconfig | 24 +--- net/wireless/Makefile | 6 - net/wireless/db.txt | 17 --- net/wireless/genregdb.awk | 158 ------------------------ net/wireless/reg.c | 39 ------ net/wireless/regdb.h | 23 ---- 8 files changed, 3 insertions(+), 287 deletions(-) delete mode 100644 net/wireless/.gitignore delete mode 100644 net/wireless/db.txt delete mode 100644 net/wireless/genregdb.awk delete mode 100644 net/wireless/regdb.h diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index 46c8d8b1cc66a..381e5b23d61d8 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -200,23 +200,5 @@ Then in some part of your code after your wiphy has been registered: Statically compiled regulatory database --------------------------------------- -In most situations the userland solution using CRDA as described -above is the preferred solution. However in some cases a set of -rules built into the kernel itself may be desirable. To account -for this situation, a configuration option has been provided -(i.e. CONFIG_CFG80211_INTERNAL_REGDB). With this option enabled, -the wireless database information contained in net/wireless/db.txt is -used to generate a data structure encoded in net/wireless/regdb.c. -That option also enables code in net/wireless/reg.c which queries -the data in regdb.c as an alternative to using CRDA. - -The file net/wireless/db.txt should be kept up-to-date with the db.txt -file available in the git repository here: - - git://git.kernel.org/pub/scm/linux/kernel/git/sforshee/wireless-regdb.git - -Again, most users in most situations should be using the CRDA package -provided with their distribution, and in most other situations users -should be building and using CRDA on their own rather than using -this option. If you are not absolutely sure that you should be using -CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_. +When a database should be fixed into the kernel, it can be provided as a +firmware file at build time that is then linked into the kernel. diff --git a/net/wireless/.gitignore b/net/wireless/.gitignore deleted file mode 100644 index c33451b896d94..0000000000000 --- a/net/wireless/.gitignore +++ /dev/null @@ -1 +0,0 @@ -regdb.c diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 24eec55166495..f050030055c50 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -140,30 +140,8 @@ config CFG80211_DEBUGFS If unsure, say N. -config CFG80211_INTERNAL_REGDB - bool "use statically compiled regulatory rules database" if EXPERT - default n - depends on CFG80211 - ---help--- - This option generates an internal data structure representing - the wireless regulatory rules described in net/wireless/db.txt - and includes code to query that database. This is an alternative - to using CRDA for defining regulatory rules for the kernel. - - Using this option requires some parsing of the db.txt at build time, - the parser will be upkept with the latest wireless-regdb updates but - older wireless-regdb formats will be ignored. The parser may later - be replaced to avoid issues with conflicts on versions of - wireless-regdb. - - For details see: - - http://wireless.kernel.org/en/developers/Regulatory - - Most distributions have a CRDA package. So if unsure, say N. - config CFG80211_CRDA_SUPPORT - bool "support CRDA" if CFG80211_INTERNAL_REGDB + bool "support CRDA" if EXPERT default y depends on CFG80211 help diff --git a/net/wireless/Makefile b/net/wireless/Makefile index d06e5015751a4..5f20dac5d8c6b 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -14,11 +14,5 @@ cfg80211-y += mlme.o ibss.o sme.o chan.o ethtool.o mesh.o ap.o trace.o ocb.o cfg80211-$(CONFIG_OF) += of.o cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o -cfg80211-$(CONFIG_CFG80211_INTERNAL_REGDB) += regdb.o CFLAGS_trace.o := -I$(src) - -$(obj)/regdb.c: $(src)/db.txt $(src)/genregdb.awk - @$(AWK) -f $(srctree)/$(src)/genregdb.awk < $< > $@ - -clean-files := regdb.c diff --git a/net/wireless/db.txt b/net/wireless/db.txt deleted file mode 100644 index a2fc3a09ccdc7..0000000000000 --- a/net/wireless/db.txt +++ /dev/null @@ -1,17 +0,0 @@ -# -# This file is a placeholder to prevent accidental build breakage if someone -# enables CONFIG_CFG80211_INTERNAL_REGDB. Almost no one actually needs to -# enable that build option. -# -# You should be using CRDA instead. It is even better if you use the CRDA -# package provided by your distribution, since they will probably keep it -# up-to-date on your behalf. -# -# If you _really_ intend to use CONFIG_CFG80211_INTERNAL_REGDB then you will -# need to replace this file with one containing appropriately formatted -# regulatory rules that cover the regulatory domains you will be using. Your -# best option is to extract the db.txt file from the wireless-regdb git -# repository: -# -# git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git -# diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk deleted file mode 100644 index baf2426b555a3..0000000000000 --- a/net/wireless/genregdb.awk +++ /dev/null @@ -1,158 +0,0 @@ -#!/usr/bin/awk -f -# -# genregdb.awk -- generate regdb.c from db.txt -# -# Actually, it reads from stdin (presumed to be db.txt) and writes -# to stdout (presumed to be regdb.c), but close enough... -# -# Copyright 2009 John W. Linville -# -# Permission to use, copy, modify, and/or distribute this software for any -# purpose with or without fee is hereby granted, provided that the above -# copyright notice and this permission notice appear in all copies. -# -# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES -# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF -# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR -# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES -# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN -# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF -# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - -BEGIN { - active = 0 - rules = 0; - print "/*" - print " * DO NOT EDIT -- file generated from data in db.txt" - print " */" - print "" - print "#include " - print "#include " - print "#include \"regdb.h\"" - print "" - regdb = "const struct ieee80211_regdomain *reg_regdb[] = {\n" -} - -function parse_country_head() { - country=$2 - sub(/:/, "", country) - printf "static const struct ieee80211_regdomain regdom_%s = {\n", country - printf "\t.alpha2 = \"%s\",\n", country - if ($NF ~ /DFS-ETSI/) - printf "\t.dfs_region = NL80211_DFS_ETSI,\n" - else if ($NF ~ /DFS-FCC/) - printf "\t.dfs_region = NL80211_DFS_FCC,\n" - else if ($NF ~ /DFS-JP/) - printf "\t.dfs_region = NL80211_DFS_JP,\n" - printf "\t.reg_rules = {\n" - active = 1 - regdb = regdb "\t®dom_" country ",\n" -} - -function parse_reg_rule() -{ - flag_starts_at = 7 - - start = $1 - sub(/\(/, "", start) - end = $3 - bw = $5 - sub(/\),/, "", bw) - gain = 0 - power = $6 - # power might be in mW... - units = $7 - dfs_cac = 0 - - sub(/\(/, "", power) - sub(/\),/, "", power) - sub(/\),/, "", units) - sub(/\)/, "", units) - - if (units == "mW") { - flag_starts_at = 8 - power = 10 * log(power)/log(10) - if ($8 ~ /[[:digit:]]/) { - flag_starts_at = 9 - dfs_cac = $8 - } - } else { - if ($7 ~ /[[:digit:]]/) { - flag_starts_at = 8 - dfs_cac = $7 - } - } - sub(/\(/, "", dfs_cac) - sub(/\),/, "", dfs_cac) - flagstr = "" - for (i=flag_starts_at; i<=NF; i++) - flagstr = flagstr $i - split(flagstr, flagarray, ",") - flags = "" - for (arg in flagarray) { - if (flagarray[arg] == "NO-OFDM") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OFDM | " - } else if (flagarray[arg] == "NO-CCK") { - flags = flags "\n\t\t\tNL80211_RRF_NO_CCK | " - } else if (flagarray[arg] == "NO-INDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_INDOOR | " - } else if (flagarray[arg] == "NO-OUTDOOR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_OUTDOOR | " - } else if (flagarray[arg] == "DFS") { - flags = flags "\n\t\t\tNL80211_RRF_DFS | " - } else if (flagarray[arg] == "PTP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTP_ONLY | " - } else if (flagarray[arg] == "PTMP-ONLY") { - flags = flags "\n\t\t\tNL80211_RRF_PTMP_ONLY | " - } else if (flagarray[arg] == "PASSIVE-SCAN") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IBSS") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "NO-IR") { - flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " - } else if (flagarray[arg] == "AUTO-BW") { - flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | " - } - - } - flags = flags "0" - printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags - rules++ -} - -function print_tail_country() -{ - active = 0 - printf "\t},\n" - printf "\t.n_reg_rules = %d\n", rules - printf "};\n\n" - rules = 0; -} - -/^[ \t]*#/ { - # Ignore -} - -!active && /^[ \t]*$/ { - # Ignore -} - -!active && /country/ { - parse_country_head() -} - -active && /^[ \t]*\(/ { - parse_reg_rule() -} - -active && /^[ \t]*$/ { - print_tail_country() -} - -END { - if (active) - print_tail_country() - print regdb "};" - print "" - print "int reg_regdb_size = ARRAY_SIZE(reg_regdb);" -} diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 180addda52aff..ebf8267ffbc91 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -59,7 +59,6 @@ #include "core.h" #include "reg.h" #include "rdev-ops.h" -#include "regdb.h" #include "nl80211.h" /* @@ -495,38 +494,6 @@ static int reg_schedule_apply(const struct ieee80211_regdomain *regdom) return 0; } -#ifdef CONFIG_CFG80211_INTERNAL_REGDB -static int reg_query_builtin(const char *alpha2) -{ - const struct ieee80211_regdomain *regdom = NULL; - unsigned int i; - - for (i = 0; i < reg_regdb_size; i++) { - if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { - regdom = reg_copy_regd(reg_regdb[i]); - break; - } - } - if (!regdom) - return -ENODATA; - - return reg_schedule_apply(regdom); -} - -/* Feel free to add any other sanity checks here */ -static void reg_regdb_size_check(void) -{ - /* We should ideally BUILD_BUG_ON() but then random builds would fail */ - WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it..."); -} -#else -static inline void reg_regdb_size_check(void) {} -static inline int reg_query_builtin(const char *alpha2) -{ - return -ENODATA; -} -#endif /* CONFIG_CFG80211_INTERNAL_REGDB */ - #ifdef CONFIG_CFG80211_CRDA_SUPPORT /* Max number of consecutive attempts to communicate with CRDA */ #define REG_MAX_CRDA_TIMEOUTS 10 @@ -885,10 +852,6 @@ int reg_reload_regdb(void) static bool reg_query_database(struct regulatory_request *request) { - /* query internal regulatory database (if it exists) */ - if (reg_query_builtin(request->alpha2) == 0) - return true; - if (query_regdb_file(request->alpha2) == 0) return true; @@ -3580,8 +3543,6 @@ int __init regulatory_init(void) spin_lock_init(®_pending_beacons_lock); spin_lock_init(®_indoor_lock); - reg_regdb_size_check(); - rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); user_alpha2[0] = '9'; diff --git a/net/wireless/regdb.h b/net/wireless/regdb.h deleted file mode 100644 index 3279cfcefb0c5..0000000000000 --- a/net/wireless/regdb.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __REGDB_H__ -#define __REGDB_H__ - -/* - * Copyright 2009 John W. Linville - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR - * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ - -extern const struct ieee80211_regdomain *reg_regdb[]; -extern int reg_regdb_size; - -#endif /* __REGDB_H__ */ -- GitLab From 90a53e4432b12288316efaa5f308adafb8d304b0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Sep 2017 22:21:08 +0200 Subject: [PATCH 1248/1507] cfg80211: implement regdb signature checking Currently CRDA implements the signature checking, and the previous commits added the ability to load the whole regulatory database into the kernel. However, we really can't lose the signature checking, so implement it in the kernel by loading a detached signature (regulatory.db.p7s) and check it against built-in keys. Signed-off-by: Johannes Berg --- net/wireless/.gitignore | 2 + net/wireless/Kconfig | 30 ++++++++ net/wireless/Makefile | 22 ++++++ net/wireless/certs/sforshee.x509 | Bin 0 -> 680 bytes net/wireless/reg.c | 121 ++++++++++++++++++++++++++++++- net/wireless/reg.h | 8 ++ 6 files changed, 182 insertions(+), 1 deletion(-) create mode 100644 net/wireless/.gitignore create mode 100644 net/wireless/certs/sforshee.x509 diff --git a/net/wireless/.gitignore b/net/wireless/.gitignore new file mode 100644 index 0000000000000..61cbc304a3d37 --- /dev/null +++ b/net/wireless/.gitignore @@ -0,0 +1,2 @@ +shipped-certs.c +extra-certs.c diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index f050030055c50..da91bb547db3e 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -83,6 +83,36 @@ config CFG80211_CERTIFICATION_ONUS you are a wireless researcher and are working in a controlled and approved environment by your local regulatory agency. +config CFG80211_REQUIRE_SIGNED_REGDB + bool "require regdb signature" if CFG80211_CERTIFICATION_ONUS + default y + select SYSTEM_DATA_VERIFICATION + help + Require that in addition to the "regulatory.db" file a + "regulatory.db.p7s" can be loaded with a valid PKCS#7 + signature for the regulatory.db file made by one of the + keys in the certs/ directory. + +config CFG80211_USE_KERNEL_REGDB_KEYS + bool "allow regdb keys shipped with the kernel" if CFG80211_CERTIFICATION_ONUS + default y + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + Allow the regulatory database to be signed by one of the keys for + which certificates are part of the kernel sources + (in net/wireless/certs/). + + This is currently only Seth Forshee's key, who is the regulatory + database maintainer. + +config CFG80211_EXTRA_REGDB_KEYDIR + string "additional regdb key directory" if CFG80211_CERTIFICATION_ONUS + depends on CFG80211_REQUIRE_SIGNED_REGDB + help + If selected, point to a directory with DER-encoded X.509 + certificates like in the kernel sources (net/wireless/certs/) + that shall be accepted for a signed regulatory database. + config CFG80211_REG_CELLULAR_HINTS bool "cfg80211 regulatory support for cellular base station hints" depends on CFG80211_CERTIFICATION_ONUS diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 5f20dac5d8c6b..219baea57e4e0 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -16,3 +16,25 @@ cfg80211-$(CONFIG_CFG80211_DEBUGFS) += debugfs.o cfg80211-$(CONFIG_CFG80211_WEXT) += wext-compat.o wext-sme.o CFLAGS_trace.o := -I$(src) + +cfg80211-$(CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS) += shipped-certs.o +ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) +cfg80211-y += extra-certs.o +endif + +$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) + @echo " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 shipped_regdb_certs[] = {' >> $@ + @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done + @echo '};' >> $@ + @echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);' >> $@ + +$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ + $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) + @echo " GEN $@" + @echo '#include "reg.h"' > $@ + @echo 'const u8 extra_regdb_certs[] = {' >> $@ + @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done + @echo '};' >> $@ + @echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);' >> $@ diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509 new file mode 100644 index 0000000000000000000000000000000000000000..c6f8f9d6b98839048822ebbe27ecb831614ccf3d GIT binary patch literal 680 zcmXqLVp?L*#Mr~c$*`&SzWchL=aw7rvTPs z1zb!`jEoFh9UjloXt8AeWO+SJ$I(J`P2JMwLe;tnH5qsF?QdR>w3uI$6?BMMOSdlV zi`-_R0)^-+(~WEkyRD@;#6_|bkA!zm6O;L?a+RC&XNF+Q?^A(17hNT93Al9K{8zT} zZ-TA_x5m^>y01EB?6?@F_#s&SBUAoMx7m~9H74+{G5eLFTo@kq?abx-wOTi&i(Oyu zQg3}-}=;a=vvvRoQQq5|7x<;&pS~YD#Y&_6&F5Z@hi_o39R~2i%lCEQp;`DZKFij>Y=beQfq8 zwmr$x_+%2JY;Sbn*;@WJ=R-@}i!U>_Zs%4CQ>mTLxstDKo_X|~T&9~nCjzn_MSd1z zd$q}FYs9}@7aPN+-fyz#i1@bZh+cP;`je$EmYhnDSyPmLIA8d%u4(1nTO z{kHgKW!NWvf$y~!0w?Rc|ETrmY6%tMs`ay$*Vg}|u{qP^VMD|2N9%W9Gx#VQ(ylyn seju}tYb{f1@#??lr<~!nO89FdqAzB=Qc?bNz{Y;&cMH;1idBjL01XcsegFUf literal 0 HcmV?d00001 diff --git a/net/wireless/reg.c b/net/wireless/reg.c index ebf8267ffbc91..58319c82ecb34 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -659,6 +660,115 @@ static bool valid_country(const u8 *data, unsigned int size, return true; } +#ifdef CONFIG_CFG80211_REQUIRE_SIGNED_REGDB +static struct key *builtin_regdb_keys; + +static void __init load_keys_from_buffer(const u8 *p, unsigned int buflen) +{ + const u8 *end = p + buflen; + size_t plen; + key_ref_t key; + + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(builtin_regdb_keys, 1), + "asymmetric", NULL, p, plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN | + KEY_ALLOC_BYPASS_RESTRICTION); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); +} + +static int __init load_builtin_regdb_keys(void) +{ + builtin_regdb_keys = + keyring_alloc(".builtin_regdb_keys", + KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), + KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); + if (IS_ERR(builtin_regdb_keys)) + return PTR_ERR(builtin_regdb_keys); + + pr_notice("Loading compiled-in X.509 certificates for regulatory database\n"); + +#ifdef CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS + load_keys_from_buffer(shipped_regdb_certs, shipped_regdb_certs_len); +#endif +#ifdef CFG80211_EXTRA_REGDB_KEYDIR + if (CONFIG_CFG80211_EXTRA_REGDB_KEYDIR[0] != '\0') + load_keys_from_buffer(extra_regdb_certs, extra_regdb_certs_len); +#endif + + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + const struct firmware *sig; + bool result; + + if (request_firmware(&sig, "regulatory.db.p7s", ®_pdev->dev)) + return false; + + result = verify_pkcs7_signature(data, size, sig->data, sig->size, + builtin_regdb_keys, + VERIFYING_UNSPECIFIED_SIGNATURE, + NULL, NULL) == 0; + + release_firmware(sig); + + return result; +} + +static void free_regdb_keyring(void) +{ + key_put(builtin_regdb_keys); +} +#else +static int load_builtin_regdb_keys(void) +{ + return 0; +} + +static bool regdb_has_valid_signature(const u8 *data, unsigned int size) +{ + return true; +} + +static void free_regdb_keyring(void) +{ +} +#endif /* CONFIG_CFG80211_REQUIRE_SIGNED_REGDB */ + static bool valid_regdb(const u8 *data, unsigned int size) { const struct fwdb_header *hdr = (void *)data; @@ -673,6 +783,9 @@ static bool valid_regdb(const u8 *data, unsigned int size) if (hdr->version != cpu_to_be32(FWDB_VERSION)) return false; + if (!regdb_has_valid_signature(data, size)) + return false; + country = &hdr->country[0]; while ((u8 *)(country + 1) <= data + size) { if (!country->coll_ptr) @@ -773,7 +886,7 @@ static void regdb_fw_cb(const struct firmware *fw, void *context) pr_info("failed to load regulatory.db\n"); set_error = -ENODATA; } else if (!valid_regdb(fw->data, fw->size)) { - pr_info("loaded regulatory.db is malformed\n"); + pr_info("loaded regulatory.db is malformed or signature is missing/invalid\n"); set_error = -EINVAL; } @@ -3535,6 +3648,10 @@ int __init regulatory_init(void) { int err = 0; + err = load_builtin_regdb_keys(); + if (err) + return err; + reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0); if (IS_ERR(reg_pdev)) return PTR_ERR(reg_pdev); @@ -3611,4 +3728,6 @@ void regulatory_exit(void) if (!IS_ERR_OR_NULL(regdb)) kfree(regdb); + + free_regdb_keyring(); } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 9529c522611a7..9ceeb5f3a7cbc 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -1,5 +1,8 @@ #ifndef __NET_WIRELESS_REG_H #define __NET_WIRELESS_REG_H + +#include + /* * Copyright 2008-2011 Luis R. Rodriguez * @@ -185,4 +188,9 @@ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); */ int reg_reload_regdb(void); +extern const u8 shipped_regdb_certs[]; +extern unsigned int shipped_regdb_certs_len; +extern const u8 extra_regdb_certs[]; +extern unsigned int extra_regdb_certs_len; + #endif /* __NET_WIRELESS_REG_H */ -- GitLab From 9e97964d5e500d8d0df94e1a79ad715ad4f9c995 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 11 Oct 2017 15:46:45 +0200 Subject: [PATCH 1249/1507] mac80211: use crypto_aead_authsize() Evidently this API is intended to be used to isolate against API changes, so use it instead of accessing ->authsize. Signed-off-by: Johannes Berg --- net/mac80211/aead_api.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/aead_api.c b/net/mac80211/aead_api.c index 347f13953b2cb..160f9df304027 100644 --- a/net/mac80211/aead_api.c +++ b/net/mac80211/aead_api.c @@ -21,7 +21,7 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, u8 *data, size_t data_len, u8 *mic) { - size_t mic_len = tfm->authsize; + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); @@ -52,7 +52,7 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, u8 *data, size_t data_len, u8 *mic) { - size_t mic_len = tfm->authsize; + size_t mic_len = crypto_aead_authsize(tfm); struct scatterlist sg[3]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); -- GitLab From 4a269818a7eb8577d32d8b2879099c689ddbd856 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Oct 2017 13:27:29 -0700 Subject: [PATCH 1250/1507] tcp: fix tcp_unlink_write_queue() Yury reported crash with this signature : [ 554.034021] [] 0xffff80003ccd5a58 [ 554.034156] [] skb_release_all+0x14/0x30 [ 554.034288] [] __kfree_skb+0x14/0x28 [ 554.034409] [] tcp_sendmsg_locked+0x4dc/0xcc8 [ 554.034541] [] tcp_sendmsg+0x34/0x58 [ 554.034659] [] inet_sendmsg+0x2c/0xf8 [ 554.034783] [] sock_sendmsg+0x18/0x30 [ 554.034928] [] SyS_sendto+0x84/0xf8 Problem is that skb->destructor contains garbage, and this is because I accidentally removed tcp_skb_tsorted_anchor_cleanup() from tcp_unlink_write_queue() This would trigger with a write(fd, , len) attempt, and we will add to packetdrill this capability to avoid future regressions. Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue") Reported-by: Yury Norov Tested-by: Yury Norov Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/net/tcp.h b/include/net/tcp.h index 5a95e5886b55e..15163454174ba 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1712,6 +1712,7 @@ static inline void tcp_insert_write_queue_before(struct sk_buff *new, static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { + tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } -- GitLab From f7e3bfa14daa35ea393ad6389c9e01e61196e93f Mon Sep 17 00:00:00 2001 From: Egil Hjelmeland Date: Tue, 10 Oct 2017 14:49:52 +0200 Subject: [PATCH 1251/1507] net: dsa: lan9303: Move tag setup to new lan9303_setup_tagging Prepare for next patch: Move tag setup from lan9303_separate_ports() to new function lan9303_setup_tagging() Signed-off-by: Egil Hjelmeland Signed-off-by: David S. Miller --- drivers/net/dsa/lan9303-core.c | 42 ++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 17 deletions(-) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 07355db2ad81e..2215ec1fbe1e9 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -157,6 +157,7 @@ # define LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING BIT(1) # define LAN9303_SWE_PORT_MIRROR_ENABLE_TX_MIRRORING BIT(0) #define LAN9303_SWE_INGRESS_PORT_TYPE 0x1847 +#define LAN9303_SWE_INGRESS_PORT_TYPE_VLAN 3 #define LAN9303_BM_CFG 0x1c00 #define LAN9303_BM_EGRSS_PORT_TYPE 0x1c0c # define LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT2 (BIT(17) | BIT(16)) @@ -510,11 +511,30 @@ static int lan9303_enable_processing_port(struct lan9303 *chip, LAN9303_MAC_TX_CFG_X_TX_ENABLE); } +/* forward special tagged packets from port 0 to port 1 *or* port 2 */ +static int lan9303_setup_tagging(struct lan9303 *chip) +{ + int ret; + u32 val; + /* enable defining the destination port via special VLAN tagging + * for port 0 + */ + ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE, + LAN9303_SWE_INGRESS_PORT_TYPE_VLAN); + if (ret) + return ret; + + /* tag incoming packets at port 1 and 2 on their way to port 0 to be + * able to discover their source port + */ + val = LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0; + return lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE, val); +} + /* We want a special working switch: * - do not forward packets between port 1 and 2 * - forward everything from port 1 to port 0 * - forward everything from port 2 to port 0 - * - forward special tagged packets from port 0 to port 1 *or* port 2 */ static int lan9303_separate_ports(struct lan9303 *chip) { @@ -529,22 +549,6 @@ static int lan9303_separate_ports(struct lan9303 *chip) if (ret) return ret; - /* enable defining the destination port via special VLAN tagging - * for port 0 - */ - ret = lan9303_write_switch_reg(chip, LAN9303_SWE_INGRESS_PORT_TYPE, - 0x03); - if (ret) - return ret; - - /* tag incoming packets at port 1 and 2 on their way to port 0 to be - * able to discover their source port - */ - ret = lan9303_write_switch_reg(chip, LAN9303_BM_EGRSS_PORT_TYPE, - LAN9303_BM_EGRSS_PORT_TYPE_SPECIAL_TAG_PORT0); - if (ret) - return ret; - /* prevent port 1 and 2 from forwarding packets by their own */ return lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 | @@ -644,6 +648,10 @@ static int lan9303_setup(struct dsa_switch *ds) return -EINVAL; } + ret = lan9303_setup_tagging(chip); + if (ret) + dev_err(chip->dev, "failed to setup port tagging %d\n", ret); + ret = lan9303_separate_ports(chip); if (ret) dev_err(chip->dev, "failed to separate ports %d\n", ret); -- GitLab From d99a86ae83d28ad08bcd46570d81033b48db2ca0 Mon Sep 17 00:00:00 2001 From: Egil Hjelmeland Date: Tue, 10 Oct 2017 14:49:53 +0200 Subject: [PATCH 1252/1507] net: dsa: lan9303: Add basic offloading of unicast traffic When both user ports are joined to the same bridge, the normal HW MAC learning is enabled. This means that unicast traffic is forwarded in HW. If one of the user ports leave the bridge, the ports goes back to the initial separated operation. Port separation relies on disabled HW MAC learning. Hence the condition that both ports must join same bridge. Add brigde methods port_bridge_join, port_bridge_leave and port_stp_state_set. Signed-off-by: Egil Hjelmeland Signed-off-by: David S. Miller --- drivers/net/dsa/lan9303-core.c | 82 ++++++++++++++++++++++++++++++++++ drivers/net/dsa/lan9303.h | 2 + 2 files changed, 84 insertions(+) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 2215ec1fbe1e9..fecfe1fe67ea0 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "lan9303.h" @@ -146,6 +147,7 @@ # define LAN9303_SWE_PORT_STATE_FORWARDING_PORT0 (0) # define LAN9303_SWE_PORT_STATE_LEARNING_PORT0 BIT(1) # define LAN9303_SWE_PORT_STATE_BLOCKING_PORT0 BIT(0) +# define LAN9303_SWE_PORT_STATE_DISABLED_PORT0 (3) #define LAN9303_SWE_PORT_MIRROR 0x1846 # define LAN9303_SWE_PORT_MIRROR_SNIFF_ALL BIT(8) # define LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT2 BIT(7) @@ -156,6 +158,7 @@ # define LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT0 BIT(2) # define LAN9303_SWE_PORT_MIRROR_ENABLE_RX_MIRRORING BIT(1) # define LAN9303_SWE_PORT_MIRROR_ENABLE_TX_MIRRORING BIT(0) +# define LAN9303_SWE_PORT_MIRROR_DISABLED 0 #define LAN9303_SWE_INGRESS_PORT_TYPE 0x1847 #define LAN9303_SWE_INGRESS_PORT_TYPE_VLAN 3 #define LAN9303_BM_CFG 0x1c00 @@ -556,6 +559,16 @@ static int lan9303_separate_ports(struct lan9303 *chip) LAN9303_SWE_PORT_STATE_BLOCKING_PORT2); } +static void lan9303_bridge_ports(struct lan9303 *chip) +{ + /* ports bridged: remove mirroring */ + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR, + LAN9303_SWE_PORT_MIRROR_DISABLED); + + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, + chip->swe_port_state); +} + static int lan9303_handle_reset(struct lan9303 *chip) { if (!chip->reset_gpio) @@ -844,6 +857,72 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port, } } +static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); + if (ds->ports[1].bridge_dev == ds->ports[2].bridge_dev) { + lan9303_bridge_ports(chip); + chip->is_bridged = true; /* unleash stp_state_set() */ + } + + return 0; +} + +static void lan9303_port_bridge_leave(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); + if (chip->is_bridged) { + lan9303_separate_ports(chip); + chip->is_bridged = false; + } +} + +static void lan9303_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + int portmask, portstate; + struct lan9303 *chip = ds->priv; + + dev_dbg(chip->dev, "%s(port %d, state %d)\n", + __func__, port, state); + + switch (state) { + case BR_STATE_DISABLED: + portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + portstate = LAN9303_SWE_PORT_STATE_BLOCKING_PORT0; + break; + case BR_STATE_LEARNING: + portstate = LAN9303_SWE_PORT_STATE_LEARNING_PORT0; + break; + case BR_STATE_FORWARDING: + portstate = LAN9303_SWE_PORT_STATE_FORWARDING_PORT0; + break; + default: + portstate = LAN9303_SWE_PORT_STATE_DISABLED_PORT0; + dev_err(chip->dev, "unknown stp state: port %d, state %d\n", + port, state); + } + + portmask = 0x3 << (port * 2); + portstate <<= (port * 2); + + chip->swe_port_state = (chip->swe_port_state & ~portmask) | portstate; + + if (chip->is_bridged) + lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE, + chip->swe_port_state); + /* else: touching SWE_PORT_STATE would break port separation */ +} + static const struct dsa_switch_ops lan9303_switch_ops = { .get_tag_protocol = lan9303_get_tag_protocol, .setup = lan9303_setup, @@ -855,6 +934,9 @@ static const struct dsa_switch_ops lan9303_switch_ops = { .get_sset_count = lan9303_get_sset_count, .port_enable = lan9303_port_enable, .port_disable = lan9303_port_disable, + .port_bridge_join = lan9303_port_bridge_join, + .port_bridge_leave = lan9303_port_bridge_leave, + .port_stp_state_set = lan9303_port_stp_state_set, }; static int lan9303_register_switch(struct lan9303 *chip) diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h index 4d8be555ff4df..68ecd544b6587 100644 --- a/drivers/net/dsa/lan9303.h +++ b/drivers/net/dsa/lan9303.h @@ -21,6 +21,8 @@ struct lan9303 { struct dsa_switch *ds; struct mutex indirect_mutex; /* protect indexed register access */ const struct lan9303_phy_ops *ops; + bool is_bridged; /* true if port 1 and 2 are bridged */ + u32 swe_port_state; /* remember SWE_PORT_STATE while not bridged */ }; extern const struct regmap_access_table lan9303_register_set; -- GitLab From 87461f7a58ab694e638ac52afa543b427751a9d0 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Tue, 10 Oct 2017 12:42:55 -0500 Subject: [PATCH 1253/1507] net: phy: DP83822 initial driver submission Add support for the TI DP83822 10/100Mbit ethernet phy. The DP83822 provides flexibility to connect to a MAC through a standard MII, RMII or RGMII interface. In addition the DP83822 needs to be removed from the DP83848 driver as the WoL support is added here for this device. Datasheet: http://www.ti.com/product/DP83822I/datasheet Signed-off-by: Dan Murphy Acked-by: Andrew F. Davis Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/Kconfig | 5 + drivers/net/phy/Makefile | 1 + drivers/net/phy/dp83822.c | 344 ++++++++++++++++++++++++++++++++++++++ drivers/net/phy/dp83848.c | 3 - 4 files changed, 350 insertions(+), 3 deletions(-) create mode 100644 drivers/net/phy/dp83822.c diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index e2cf8ffc5c6f2..8125412c88142 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -277,6 +277,11 @@ config DAVICOM_PHY ---help--- Currently supports dm9161e and dm9131 +config DP83822_PHY + tristate "Texas Instruments DP83822 PHY" + ---help--- + Supports the DP83822 PHY. + config DP83848_PHY tristate "Texas Instruments DP83848 PHY" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 1404ad3b77c79..4b983be835666 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -55,6 +55,7 @@ obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_CORTINA_PHY) += cortina.o obj-$(CONFIG_DAVICOM_PHY) += davicom.o obj-$(CONFIG_DP83640_PHY) += dp83640.o +obj-$(CONFIG_DP83822_PHY) += dp83822.o obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_FIXED_PHY) += fixed_phy.o diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c new file mode 100644 index 0000000000000..14335d14e9e41 --- /dev/null +++ b/drivers/net/phy/dp83822.c @@ -0,0 +1,344 @@ +/* + * Driver for the Texas Instruments DP83822 PHY + * + * Copyright (C) 2017 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define DP83822_PHY_ID 0x2000a240 +#define DP83822_DEVADDR 0x1f + +#define MII_DP83822_PHYSCR 0x11 +#define MII_DP83822_MISR1 0x12 +#define MII_DP83822_MISR2 0x13 +#define MII_DP83822_RESET_CTRL 0x1f + +#define DP83822_HW_RESET BIT(15) +#define DP83822_SW_RESET BIT(14) + +/* PHYSCR Register Fields */ +#define DP83822_PHYSCR_INT_OE BIT(0) /* Interrupt Output Enable */ +#define DP83822_PHYSCR_INTEN BIT(1) /* Interrupt Enable */ + +/* MISR1 bits */ +#define DP83822_RX_ERR_HF_INT_EN BIT(0) +#define DP83822_FALSE_CARRIER_HF_INT_EN BIT(1) +#define DP83822_ANEG_COMPLETE_INT_EN BIT(2) +#define DP83822_DUP_MODE_CHANGE_INT_EN BIT(3) +#define DP83822_SPEED_CHANGED_INT_EN BIT(4) +#define DP83822_LINK_STAT_INT_EN BIT(5) +#define DP83822_ENERGY_DET_INT_EN BIT(6) +#define DP83822_LINK_QUAL_INT_EN BIT(7) + +/* MISR2 bits */ +#define DP83822_JABBER_DET_INT_EN BIT(0) +#define DP83822_WOL_PKT_INT_EN BIT(1) +#define DP83822_SLEEP_MODE_INT_EN BIT(2) +#define DP83822_MDI_XOVER_INT_EN BIT(3) +#define DP83822_LB_FIFO_INT_EN BIT(4) +#define DP83822_PAGE_RX_INT_EN BIT(5) +#define DP83822_ANEG_ERR_INT_EN BIT(6) +#define DP83822_EEE_ERROR_CHANGE_INT_EN BIT(7) + +/* INT_STAT1 bits */ +#define DP83822_WOL_INT_EN BIT(4) +#define DP83822_WOL_INT_STAT BIT(12) + +#define MII_DP83822_RXSOP1 0x04a5 +#define MII_DP83822_RXSOP2 0x04a6 +#define MII_DP83822_RXSOP3 0x04a7 + +/* WoL Registers */ +#define MII_DP83822_WOL_CFG 0x04a0 +#define MII_DP83822_WOL_STAT 0x04a1 +#define MII_DP83822_WOL_DA1 0x04a2 +#define MII_DP83822_WOL_DA2 0x04a3 +#define MII_DP83822_WOL_DA3 0x04a4 + +/* WoL bits */ +#define DP83822_WOL_MAGIC_EN BIT(0) +#define DP83822_WOL_SECURE_ON BIT(5) +#define DP83822_WOL_EN BIT(7) +#define DP83822_WOL_INDICATION_SEL BIT(8) +#define DP83822_WOL_CLR_INDICATION BIT(11) + +static int dp83822_ack_interrupt(struct phy_device *phydev) +{ + int err; + + err = phy_read(phydev, MII_DP83822_MISR1); + if (err < 0) + return err; + + err = phy_read(phydev, MII_DP83822_MISR2); + if (err < 0) + return err; + + return 0; +} + +static int dp83822_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + u16 value; + const u8 *mac; + + if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { + mac = (const u8 *)ndev->dev_addr; + + if (!is_valid_ether_addr(mac)) + return -EINVAL; + + /* MAC addresses start with byte 5, but stored in mac[0]. + * 822 PHYs store bytes 4|5, 2|3, 0|1 + */ + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA1, + (mac[1] << 8) | mac[0]); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA2, + (mac[3] << 8) | mac[2]); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_DA3, + (mac[5] << 8) | mac[4]); + + value = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG); + if (wol->wolopts & WAKE_MAGIC) + value |= DP83822_WOL_MAGIC_EN; + else + value &= ~DP83822_WOL_MAGIC_EN; + + if (wol->wolopts & WAKE_MAGICSECURE) { + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP1, + (wol->sopass[1] << 8) | wol->sopass[0]); + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP2, + (wol->sopass[3] << 8) | wol->sopass[2]); + phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP3, + (wol->sopass[5] << 8) | wol->sopass[4]); + value |= DP83822_WOL_SECURE_ON; + } else { + value &= ~DP83822_WOL_SECURE_ON; + } + + value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | + DP83822_WOL_CLR_INDICATION); + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); + } else { + value = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG); + value &= ~DP83822_WOL_EN; + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); + } + + return 0; +} + +static void dp83822_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + int value; + u16 sopass_val; + + wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE); + wol->wolopts = 0; + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + if (value & DP83822_WOL_MAGIC_EN) + wol->wolopts |= WAKE_MAGIC; + + if (value & DP83822_WOL_SECURE_ON) { + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP1); + wol->sopass[0] = (sopass_val & 0xff); + wol->sopass[1] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP2); + wol->sopass[2] = (sopass_val & 0xff); + wol->sopass[3] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_RXSOP3); + wol->sopass[4] = (sopass_val & 0xff); + wol->sopass[5] = (sopass_val >> 8); + + wol->wolopts |= WAKE_MAGICSECURE; + } + + /* WoL is not enabled so set wolopts to 0 */ + if (!(value & DP83822_WOL_EN)) + wol->wolopts = 0; +} + +static int dp83822_config_intr(struct phy_device *phydev) +{ + int misr_status; + int physcr_status; + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + misr_status = phy_read(phydev, MII_DP83822_MISR1); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83822_RX_ERR_HF_INT_EN | + DP83822_FALSE_CARRIER_HF_INT_EN | + DP83822_ANEG_COMPLETE_INT_EN | + DP83822_DUP_MODE_CHANGE_INT_EN | + DP83822_SPEED_CHANGED_INT_EN | + DP83822_LINK_STAT_INT_EN | + DP83822_ENERGY_DET_INT_EN | + DP83822_LINK_QUAL_INT_EN); + + err = phy_write(phydev, MII_DP83822_MISR1, misr_status); + if (err < 0) + return err; + + misr_status = phy_read(phydev, MII_DP83822_MISR2); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83822_JABBER_DET_INT_EN | + DP83822_WOL_PKT_INT_EN | + DP83822_SLEEP_MODE_INT_EN | + DP83822_MDI_XOVER_INT_EN | + DP83822_LB_FIFO_INT_EN | + DP83822_PAGE_RX_INT_EN | + DP83822_ANEG_ERR_INT_EN | + DP83822_EEE_ERROR_CHANGE_INT_EN); + + err = phy_write(phydev, MII_DP83822_MISR2, misr_status); + if (err < 0) + return err; + + physcr_status = phy_read(phydev, MII_DP83822_PHYSCR); + if (physcr_status < 0) + return physcr_status; + + physcr_status |= DP83822_PHYSCR_INT_OE | DP83822_PHYSCR_INTEN; + + } else { + err = phy_write(phydev, MII_DP83822_MISR1, 0); + if (err < 0) + return err; + + err = phy_write(phydev, MII_DP83822_MISR1, 0); + if (err < 0) + return err; + + physcr_status = phy_read(phydev, MII_DP83822_PHYSCR); + if (physcr_status < 0) + return physcr_status; + + physcr_status &= ~DP83822_PHYSCR_INTEN; + } + + return phy_write(phydev, MII_DP83822_PHYSCR, physcr_status); +} + +static int dp83822_config_init(struct phy_device *phydev) +{ + int err; + int value; + + err = genphy_config_init(phydev); + if (err < 0) + return err; + + value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; + + return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, + value); +} + +static int dp83822_phy_reset(struct phy_device *phydev) +{ + int err; + + err = phy_write(phydev, MII_DP83822_RESET_CTRL, DP83822_HW_RESET); + if (err < 0) + return err; + + dp83822_config_init(phydev); + + return 0; +} + +static int dp83822_suspend(struct phy_device *phydev) +{ + int value; + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + if (!(value & DP83822_WOL_EN)) + genphy_suspend(phydev); + + return 0; +} + +static int dp83822_resume(struct phy_device *phydev) +{ + int value; + + genphy_resume(phydev); + + value = phy_read_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG); + + phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, value | + DP83822_WOL_CLR_INDICATION); + + return 0; +} + +static struct phy_driver dp83822_driver[] = { + { + .phy_id = DP83822_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83822", + .features = PHY_BASIC_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = dp83822_config_init, + .soft_reset = dp83822_phy_reset, + .get_wol = dp83822_get_wol, + .set_wol = dp83822_set_wol, + .ack_interrupt = dp83822_ack_interrupt, + .config_intr = dp83822_config_intr, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = dp83822_suspend, + .resume = dp83822_resume, + }, +}; +module_phy_driver(dp83822_driver); + +static struct mdio_device_id __maybe_unused dp83822_tbl[] = { + { DP83822_PHY_ID, 0xfffffff0 }, + { }, +}; +MODULE_DEVICE_TABLE(mdio, dp83822_tbl); + +MODULE_DESCRIPTION("Texas Instruments DP83822 PHY driver"); +MODULE_AUTHOR("Dan Murphy Date: Tue, 10 Oct 2017 12:42:56 -0500 Subject: [PATCH 1254/1507] net: phy: at803x: Change error to EINVAL for invalid MAC Change the return error code to EINVAL if the MAC address is not valid in the set_wol function. Signed-off-by: Dan Murphy Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1e52b9dc58d3..5f93e6add5639 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -167,7 +167,7 @@ static int at803x_set_wol(struct phy_device *phydev, mac = (const u8 *) ndev->dev_addr; if (!is_valid_ether_addr(mac)) - return -EFAULT; + return -EINVAL; for (i = 0; i < 3; i++) { phy_write(phydev, AT803X_MMD_ACCESS_CONTROL, -- GitLab From b784ecba51da465bc15fdd1d6715479f3adc560e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 Oct 2017 12:25:48 -0700 Subject: [PATCH 1255/1507] atm: idt77105: Drop needless setup_timer() Calling setup_timer() is redundant when DEFINE_TIMER() has been used. Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/atm/idt77105.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c index 082aa02abc574..d781b3f876938 100644 --- a/drivers/atm/idt77105.c +++ b/drivers/atm/idt77105.c @@ -306,11 +306,9 @@ static int idt77105_start(struct atm_dev *dev) if (start_timer) { start_timer = 0; - setup_timer(&stats_timer, idt77105_stats_timer_func, 0UL); stats_timer.expires = jiffies+IDT77105_STATS_TIMER_PERIOD; add_timer(&stats_timer); - setup_timer(&restart_timer, idt77105_restart_timer_func, 0UL); restart_timer.expires = jiffies+IDT77105_RESTART_TIMER_PERIOD; add_timer(&restart_timer); } -- GitLab From 7822b0836d2121d7de3d0f9ec636338d7496e5dc Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 11 Oct 2017 02:35:23 +0000 Subject: [PATCH 1256/1507] net: hns3: make local functions static Fixes the following sparse warnings: drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c:464:5: warning: symbol 'hns3_change_all_ring_bd_num' was not declared. Should it be static? drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c:477:5: warning: symbol 'hns3_set_ringparam' was not declared. Should it be static? Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c index 9b36ce081f620..ddbd7f30c6a4e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -461,7 +461,8 @@ static int hns3_get_rxnfc(struct net_device *netdev, return 0; } -int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, u32 new_desc_num) +static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, + u32 new_desc_num) { struct hnae3_handle *h = priv->ae_handle; int i; @@ -474,7 +475,8 @@ int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, u32 new_desc_num) return hns3_init_all_ring(priv); } -int hns3_set_ringparam(struct net_device *ndev, struct ethtool_ringparam *param) +static int hns3_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) { struct hns3_nic_priv *priv = netdev_priv(ndev); struct hnae3_handle *h = priv->ae_handle; -- GitLab From ae85bfa87821b9fa60bf846c09a6a0056d87cdb2 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:17 -0700 Subject: [PATCH 1257/1507] net: qrtr: Invoke sk_error_report() after setting sk_err Rather than manually waking up any context sleeping on the sock to signal an error we should call sk_error_report(). This has the added benefit that in-kernel consumers can override this notification with its own callback. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c2f5c13550c05..7e4b49a8349e0 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -541,7 +541,7 @@ static void qrtr_reset_ports(void) sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - wake_up_interruptible(sk_sleep(&ipc->sk)); + ipc->sk.sk_error_report(&ipc->sk); sock_put(&ipc->sk); } mutex_unlock(&qrtr_port_lock); -- GitLab From 28978713c51b0a70acf748f76f9d6d2d20dcf980 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:18 -0700 Subject: [PATCH 1258/1507] net: qrtr: Move constants to header file The constants are used by both the name server and clients, so clarify their value and move them to the uapi header. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- include/uapi/linux/qrtr.h | 3 +++ net/qrtr/qrtr.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 9d76c566f66e8..63e8803e4d90e 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -4,6 +4,9 @@ #include #include +#define QRTR_NODE_BCAST 0xffffffffu +#define QRTR_PORT_CTRL 0xfffffffeu + struct sockaddr_qrtr { __kernel_sa_family_t sq_family; __u32 sq_node; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 7e4b49a8349e0..15981abc042cb 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -61,8 +61,6 @@ struct qrtr_hdr { } __packed; #define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) -#define QRTR_NODE_BCAST ((unsigned int)-1) -#define QRTR_PORT_CTRL ((unsigned int)-2) struct qrtr_sock { /* WARNING: sk must be the first member */ -- GitLab From da7653f0faabbe45eb2d3fd6e4b400fe003e81ae Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:19 -0700 Subject: [PATCH 1259/1507] net: qrtr: Add control packet definition to uapi The QMUX protocol specification defines structure of the special control packet messages being sent between handlers of the control port. Add these to the uapi header, as this structure and the associated types are shared between the kernel and all userspace handlers of control messages. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- include/uapi/linux/qrtr.h | 32 ++++++++++++++++++++++++++++++++ net/qrtr/qrtr.c | 12 ------------ 2 files changed, 32 insertions(+), 12 deletions(-) diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 63e8803e4d90e..179af64846e09 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -13,4 +13,36 @@ struct sockaddr_qrtr { __u32 sq_port; }; +enum qrtr_pkt_type { + QRTR_TYPE_DATA = 1, + QRTR_TYPE_HELLO = 2, + QRTR_TYPE_BYE = 3, + QRTR_TYPE_NEW_SERVER = 4, + QRTR_TYPE_DEL_SERVER = 5, + QRTR_TYPE_DEL_CLIENT = 6, + QRTR_TYPE_RESUME_TX = 7, + QRTR_TYPE_EXIT = 8, + QRTR_TYPE_PING = 9, + QRTR_TYPE_NEW_LOOKUP = 10, + QRTR_TYPE_DEL_LOOKUP = 11, +}; + +struct qrtr_ctrl_pkt { + __le32 cmd; + + union { + struct { + __le32 service; + __le32 instance; + __le32 node; + __le32 port; + } server; + + struct { + __le32 node; + __le32 port; + } client; + }; +} __packed; + #endif /* _LINUX_QRTR_H */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 15981abc042cb..d85ca7170b8f7 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -26,18 +26,6 @@ #define QRTR_MIN_EPH_SOCKET 0x4000 #define QRTR_MAX_EPH_SOCKET 0x7fff -enum qrtr_pkt_type { - QRTR_TYPE_DATA = 1, - QRTR_TYPE_HELLO = 2, - QRTR_TYPE_BYE = 3, - QRTR_TYPE_NEW_SERVER = 4, - QRTR_TYPE_DEL_SERVER = 5, - QRTR_TYPE_DEL_CLIENT = 6, - QRTR_TYPE_RESUME_TX = 7, - QRTR_TYPE_EXIT = 8, - QRTR_TYPE_PING = 9, -}; - /** * struct qrtr_hdr - (I|R)PCrouter packet header * @version: protocol version -- GitLab From e7044482c8ac5081f4775063995647787d5082a4 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:20 -0700 Subject: [PATCH 1260/1507] net: qrtr: Pass source and destination to enqueue functions Defer writing the message header to the skb until its time to enqueue the packet. As the receive path is reworked to decode the message header as it's received from the transport and only pass around the payload in the skb this change means that we do not have to fill out the full message header just to decode it immediately in qrtr_local_enqueue(). In the future this change also makes it possible to prepend message headers based on the version of each link. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 120 ++++++++++++++++++++++++++++-------------------- 1 file changed, 69 insertions(+), 51 deletions(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index d85ca7170b8f7..82dc83789310f 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -97,8 +97,12 @@ struct qrtr_node { struct list_head item; }; -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb); -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb); +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to); /* Release node resources and free the node. * @@ -136,10 +140,27 @@ static void qrtr_node_release(struct qrtr_node *node) } /* Pass an outgoing packet socket buffer to the endpoint driver. */ -static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { + struct qrtr_hdr *hdr; + size_t len = skb->len; int rc = -ENODEV; + hdr = skb_push(skb, QRTR_HDR_SIZE); + hdr->version = cpu_to_le32(QRTR_PROTO_VER); + hdr->type = cpu_to_le32(type); + hdr->src_node_id = cpu_to_le32(from->sq_node); + hdr->src_port_id = cpu_to_le32(from->sq_port); + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + + hdr->size = cpu_to_le32(len); + hdr->confirm_rx = 0; + + skb_put_padto(skb, ALIGN(len, 4)); + mutex_lock(&node->ep_lock); if (node->ep) rc = node->ep->xmit(node->ep, skb); @@ -237,23 +258,13 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_post); static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, u32 src_node, u32 dst_node) { - struct qrtr_hdr *hdr; struct sk_buff *skb; skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); if (!skb) return NULL; - skb_reset_transport_header(skb); - hdr = skb_put(skb, QRTR_HDR_SIZE); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->type = cpu_to_le32(type); - hdr->src_node_id = cpu_to_le32(src_node); - hdr->src_port_id = cpu_to_le32(QRTR_PORT_CTRL); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(pkt_len); - hdr->dst_node_id = cpu_to_le32(dst_node); - hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); + skb_reserve(skb, QRTR_HDR_SIZE); return skb; } @@ -326,6 +337,8 @@ static void qrtr_port_put(struct qrtr_sock *ipc); static void qrtr_node_rx_work(struct work_struct *work) { struct qrtr_node *node = container_of(work, struct qrtr_node, work); + struct sockaddr_qrtr dst; + struct sockaddr_qrtr src; struct sk_buff *skb; while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { @@ -341,6 +354,11 @@ static void qrtr_node_rx_work(struct work_struct *work) dst_port = le32_to_cpu(phdr->dst_port_id); confirm = !!phdr->confirm_rx; + src.sq_node = src_node; + src.sq_port = le32_to_cpu(phdr->src_port_id); + dst.sq_node = dst_node; + dst.sq_port = dst_port; + qrtr_node_assign(node, src_node); ipc = qrtr_port_lookup(dst_port); @@ -357,7 +375,9 @@ static void qrtr_node_rx_work(struct work_struct *work) skb = qrtr_alloc_resume_tx(dst_node, node->nid, dst_port); if (!skb) break; - if (qrtr_node_enqueue(node, skb)) + + if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, + &dst, &src)) break; } } @@ -407,6 +427,8 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_register); void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) { struct qrtr_node *node = ep->node; + struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; + struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; struct sk_buff *skb; mutex_lock(&node->ep_lock); @@ -416,7 +438,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) /* Notify the local controller about the event */ skb = qrtr_alloc_local_bye(node->nid); if (skb) - qrtr_local_enqueue(NULL, skb); + qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); qrtr_node_release(node); ep->node = NULL; @@ -454,11 +476,17 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) { struct sk_buff *skb; int port = ipc->us.sq_port; + struct sockaddr_qrtr to; + + to.sq_family = AF_QIPCRTR; + to.sq_node = QRTR_NODE_BCAST; + to.sq_port = QRTR_PORT_CTRL; skb = qrtr_alloc_del_client(&ipc->us); if (skb) { skb_set_owner_w(skb, &ipc->sk); - qrtr_bcast_enqueue(NULL, skb); + qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us, + &to); } if (port == QRTR_PORT_CTRL) @@ -606,19 +634,25 @@ static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len) } /* Queue packet to local peer socket. */ -static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { - const struct qrtr_hdr *phdr; struct qrtr_sock *ipc; + struct qrtr_hdr *phdr; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - - ipc = qrtr_port_lookup(le32_to_cpu(phdr->dst_port_id)); + ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ kfree_skb(skb); return -ENODEV; } + phdr = skb_push(skb, QRTR_HDR_SIZE); + skb_reset_transport_header(skb); + + phdr->src_node_id = cpu_to_le32(from->sq_node); + phdr->src_port_id = cpu_to_le32(from->sq_port); + if (sock_queue_rcv_skb(&ipc->sk, skb)) { qrtr_port_put(ipc); kfree_skb(skb); @@ -631,7 +665,9 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb) } /* Queue packet for broadcast. */ -static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) +static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, + int type, struct sockaddr_qrtr *from, + struct sockaddr_qrtr *to) { struct sk_buff *skbn; @@ -641,11 +677,11 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) if (!skbn) break; skb_set_owner_w(skbn, skb->sk); - qrtr_node_enqueue(node, skbn); + qrtr_node_enqueue(node, skbn, type, from, to); } mutex_unlock(&qrtr_node_lock); - qrtr_local_enqueue(node, skb); + qrtr_local_enqueue(node, skb, type, from, to); return 0; } @@ -653,13 +689,14 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb) static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *); + int (*enqueue_fn)(struct qrtr_node *, struct sk_buff *, int, + struct sockaddr_qrtr *, struct sockaddr_qrtr *); struct qrtr_sock *ipc = qrtr_sk(sock->sk); struct sock *sk = sock->sk; struct qrtr_node *node; - struct qrtr_hdr *hdr; struct sk_buff *skb; size_t plen; + u32 type = QRTR_TYPE_DATA; int rc; if (msg->msg_flags & ~(MSG_DONTWAIT)) @@ -713,32 +750,14 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (!skb) goto out_node; - skb_reset_transport_header(skb); - skb_put(skb, len + QRTR_HDR_SIZE); - - hdr = (struct qrtr_hdr *)skb_transport_header(skb); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); - hdr->src_node_id = cpu_to_le32(ipc->us.sq_node); - hdr->src_port_id = cpu_to_le32(ipc->us.sq_port); - hdr->confirm_rx = cpu_to_le32(0); - hdr->size = cpu_to_le32(len); - hdr->dst_node_id = cpu_to_le32(addr->sq_node); - hdr->dst_port_id = cpu_to_le32(addr->sq_port); + skb_reserve(skb, QRTR_HDR_SIZE); - rc = skb_copy_datagram_from_iter(skb, QRTR_HDR_SIZE, - &msg->msg_iter, len); + rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc) { kfree_skb(skb); goto out_node; } - if (plen != len) { - rc = skb_pad(skb, plen - len); - if (rc) - goto out_node; - skb_put(skb, plen - len); - } - if (ipc->us.sq_port == QRTR_PORT_CTRL) { if (len < 4) { rc = -EINVAL; @@ -747,12 +766,11 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } /* control messages already require the type as 'command' */ - skb_copy_bits(skb, QRTR_HDR_SIZE, &hdr->type, 4); - } else { - hdr->type = cpu_to_le32(QRTR_TYPE_DATA); + skb_copy_bits(skb, 0, &type, 4); + type = le32_to_cpu(type); } - rc = enqueue_fn(node, skb); + rc = enqueue_fn(node, skb, type, &ipc->us, addr); if (rc >= 0) rc = len; -- GitLab From 1a7959c76641674991ba3a49f25432f1e105391e Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:21 -0700 Subject: [PATCH 1261/1507] net: qrtr: Clean up control packet handling As the message header generation is deferred the internal functions for generating control packets can be simplified. This patch modifies qrtr_alloc_ctrl_packet() to, in addition to the sk_buff, return a reference to a struct qrtr_ctrl_pkt, which clarifies and simplifies the helpers to the point that these functions can be folded back into the callers. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 93 +++++++++++++++---------------------------------- 1 file changed, 29 insertions(+), 64 deletions(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 82dc83789310f..a84edba7b1ef7 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -255,9 +255,18 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) } EXPORT_SYMBOL_GPL(qrtr_endpoint_post); -static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, - u32 src_node, u32 dst_node) +/** + * qrtr_alloc_ctrl_packet() - allocate control packet skb + * @pkt: reference to qrtr_ctrl_pkt pointer + * + * Returns newly allocated sk_buff, or NULL on failure + * + * This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and + * on success returns a reference to the control packet in @pkt. + */ +static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) { + const int pkt_len = sizeof(struct qrtr_ctrl_pkt); struct sk_buff *skb; skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); @@ -265,64 +274,7 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(u32 type, size_t pkt_len, return NULL; skb_reserve(skb, QRTR_HDR_SIZE); - - return skb; -} - -/* Allocate and construct a resume-tx packet. */ -static struct sk_buff *qrtr_alloc_resume_tx(u32 src_node, - u32 dst_node, u32 port) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; - - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_RESUME_TX, pkt_len, - src_node, dst_node); - if (!skb) - return NULL; - - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_RESUME_TX); - buf[1] = cpu_to_le32(src_node); - buf[2] = cpu_to_le32(port); - - return skb; -} - -/* Allocate and construct a BYE message to signal remote termination */ -static struct sk_buff *qrtr_alloc_local_bye(u32 src_node) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; - - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_BYE, pkt_len, - src_node, qrtr_local_nid); - if (!skb) - return NULL; - - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_BYE); - - return skb; -} - -static struct sk_buff *qrtr_alloc_del_client(struct sockaddr_qrtr *sq) -{ - const int pkt_len = 20; - struct sk_buff *skb; - __le32 *buf; - - skb = qrtr_alloc_ctrl_packet(QRTR_TYPE_DEL_CLIENT, pkt_len, - sq->sq_node, QRTR_NODE_BCAST); - if (!skb) - return NULL; - - buf = skb_put_zero(skb, pkt_len); - buf[0] = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); - buf[1] = cpu_to_le32(sq->sq_node); - buf[2] = cpu_to_le32(sq->sq_port); + *pkt = skb_put_zero(skb, pkt_len); return skb; } @@ -337,6 +289,7 @@ static void qrtr_port_put(struct qrtr_sock *ipc); static void qrtr_node_rx_work(struct work_struct *work) { struct qrtr_node *node = container_of(work, struct qrtr_node, work); + struct qrtr_ctrl_pkt *pkt; struct sockaddr_qrtr dst; struct sockaddr_qrtr src; struct sk_buff *skb; @@ -372,10 +325,14 @@ static void qrtr_node_rx_work(struct work_struct *work) } if (confirm) { - skb = qrtr_alloc_resume_tx(dst_node, node->nid, dst_port); + skb = qrtr_alloc_ctrl_packet(&pkt); if (!skb) break; + pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); + pkt->client.node = cpu_to_le32(dst.sq_node); + pkt->client.port = cpu_to_le32(dst.sq_port); + if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, &dst, &src)) break; @@ -429,6 +386,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) struct qrtr_node *node = ep->node; struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; mutex_lock(&node->ep_lock); @@ -436,9 +394,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) mutex_unlock(&node->ep_lock); /* Notify the local controller about the event */ - skb = qrtr_alloc_local_bye(node->nid); - if (skb) + skb = qrtr_alloc_ctrl_packet(&pkt); + if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE); qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); + } qrtr_node_release(node); ep->node = NULL; @@ -474,6 +434,7 @@ static void qrtr_port_put(struct qrtr_sock *ipc) /* Remove port assignment. */ static void qrtr_port_remove(struct qrtr_sock *ipc) { + struct qrtr_ctrl_pkt *pkt; struct sk_buff *skb; int port = ipc->us.sq_port; struct sockaddr_qrtr to; @@ -482,8 +443,12 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) to.sq_node = QRTR_NODE_BCAST; to.sq_port = QRTR_PORT_CTRL; - skb = qrtr_alloc_del_client(&ipc->us); + skb = qrtr_alloc_ctrl_packet(&pkt); if (skb) { + pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + pkt->client.node = cpu_to_le32(ipc->us.sq_node); + pkt->client.port = cpu_to_le32(ipc->us.sq_port); + skb_set_owner_w(skb, &ipc->sk); qrtr_bcast_enqueue(NULL, skb, QRTR_TYPE_DEL_CLIENT, &ipc->us, &to); -- GitLab From f507a9b6e63b9f41b61d199c36ae046d17b5fe4b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:22 -0700 Subject: [PATCH 1262/1507] net: qrtr: Use sk_buff->cb in receive path Rather than parsing the header of incoming messages throughout the implementation do it once when we retrieve the message and store the relevant information in the "cb" member of the sk_buff. This allows us to, in a later commit, decode version 2 messages into this same structure. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 70 ++++++++++++++++++++++++++++--------------------- 1 file changed, 40 insertions(+), 30 deletions(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index a84edba7b1ef7..7bca6ec892a55 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -48,6 +48,16 @@ struct qrtr_hdr { __le32 dst_port_id; } __packed; +struct qrtr_cb { + u32 src_node; + u32 src_port; + u32 dst_node; + u32 dst_port; + + u8 type; + u8 confirm_rx; +}; + #define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) struct qrtr_sock { @@ -216,6 +226,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_node *node = ep->node; const struct qrtr_hdr *phdr = data; struct sk_buff *skb; + struct qrtr_cb *cb; unsigned int psize; unsigned int size; unsigned int type; @@ -245,8 +256,15 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!skb) return -ENOMEM; - skb_reset_transport_header(skb); - skb_put_data(skb, data, len); + cb = (struct qrtr_cb *)skb->cb; + cb->src_node = le32_to_cpu(phdr->src_node_id); + cb->src_port = le32_to_cpu(phdr->src_port_id); + cb->dst_node = le32_to_cpu(phdr->dst_node_id); + cb->dst_port = le32_to_cpu(phdr->dst_port_id); + cb->type = type; + cb->confirm_rx = !!phdr->confirm_rx; + + skb_put_data(skb, data + QRTR_HDR_SIZE, size); skb_queue_tail(&node->rx_queue, skb); schedule_work(&node->work); @@ -295,26 +313,20 @@ static void qrtr_node_rx_work(struct work_struct *work) struct sk_buff *skb; while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { - const struct qrtr_hdr *phdr; - u32 dst_node, dst_port; struct qrtr_sock *ipc; - u32 src_node; + struct qrtr_cb *cb; int confirm; - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - src_node = le32_to_cpu(phdr->src_node_id); - dst_node = le32_to_cpu(phdr->dst_node_id); - dst_port = le32_to_cpu(phdr->dst_port_id); - confirm = !!phdr->confirm_rx; + cb = (struct qrtr_cb *)skb->cb; + src.sq_node = cb->src_node; + src.sq_port = cb->src_port; + dst.sq_node = cb->dst_node; + dst.sq_port = cb->dst_port; + confirm = !!cb->confirm_rx; - src.sq_node = src_node; - src.sq_port = le32_to_cpu(phdr->src_port_id); - dst.sq_node = dst_node; - dst.sq_port = dst_port; + qrtr_node_assign(node, cb->src_node); - qrtr_node_assign(node, src_node); - - ipc = qrtr_port_lookup(dst_port); + ipc = qrtr_port_lookup(cb->dst_port); if (!ipc) { kfree_skb(skb); } else { @@ -604,7 +616,7 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, struct sockaddr_qrtr *to) { struct qrtr_sock *ipc; - struct qrtr_hdr *phdr; + struct qrtr_cb *cb; ipc = qrtr_port_lookup(to->sq_port); if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */ @@ -612,11 +624,9 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, return -ENODEV; } - phdr = skb_push(skb, QRTR_HDR_SIZE); - skb_reset_transport_header(skb); - - phdr->src_node_id = cpu_to_le32(from->sq_node); - phdr->src_port_id = cpu_to_le32(from->sq_port); + cb = (struct qrtr_cb *)skb->cb; + cb->src_node = from->sq_node; + cb->src_port = from->sq_port; if (sock_queue_rcv_skb(&ipc->sk, skb)) { qrtr_port_put(ipc); @@ -750,9 +760,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, msg->msg_name); - const struct qrtr_hdr *phdr; struct sock *sk = sock->sk; struct sk_buff *skb; + struct qrtr_cb *cb; int copied, rc; lock_sock(sk); @@ -769,22 +779,22 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, return rc; } - phdr = (const struct qrtr_hdr *)skb_transport_header(skb); - copied = le32_to_cpu(phdr->size); + copied = skb->len; if (copied > size) { copied = size; msg->msg_flags |= MSG_TRUNC; } - rc = skb_copy_datagram_msg(skb, QRTR_HDR_SIZE, msg, copied); + rc = skb_copy_datagram_msg(skb, 0, msg, copied); if (rc < 0) goto out; rc = copied; if (addr) { + cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; - addr->sq_node = le32_to_cpu(phdr->src_node_id); - addr->sq_port = le32_to_cpu(phdr->src_port_id); + addr->sq_node = cb->src_node; + addr->sq_port = cb->src_port; msg->msg_namelen = sizeof(*addr); } @@ -877,7 +887,7 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: skb = skb_peek(&sk->sk_receive_queue); if (skb) - len = skb->len - QRTR_HDR_SIZE; + len = skb->len; rc = put_user(len, (int __user *)argp); break; case SIOCGIFADDR: -- GitLab From 194ccc88297ae78d0803adad83c6dcc369787c9e Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:23 -0700 Subject: [PATCH 1263/1507] net: qrtr: Support decoding incoming v2 packets Add the necessary logic for decoding incoming messages of version 2 as well. Also make sure there's room for the bigger of version 1 and 2 headers in the code allocating skbs for outgoing messages. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 132 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 94 insertions(+), 38 deletions(-) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 7bca6ec892a55..e458ece96d3d3 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -20,14 +20,15 @@ #include "qrtr.h" -#define QRTR_PROTO_VER 1 +#define QRTR_PROTO_VER_1 1 +#define QRTR_PROTO_VER_2 3 /* auto-bind range */ #define QRTR_MIN_EPH_SOCKET 0x4000 #define QRTR_MAX_EPH_SOCKET 0x7fff /** - * struct qrtr_hdr - (I|R)PCrouter packet header + * struct qrtr_hdr_v1 - (I|R)PCrouter packet header version 1 * @version: protocol version * @type: packet type; one of QRTR_TYPE_* * @src_node_id: source node @@ -37,7 +38,7 @@ * @dst_node_id: destination node * @dst_port_id: destination port */ -struct qrtr_hdr { +struct qrtr_hdr_v1 { __le32 version; __le32 type; __le32 src_node_id; @@ -48,6 +49,32 @@ struct qrtr_hdr { __le32 dst_port_id; } __packed; +/** + * struct qrtr_hdr_v2 - (I|R)PCrouter packet header later versions + * @version: protocol version + * @type: packet type; one of QRTR_TYPE_* + * @flags: bitmask of QRTR_FLAGS_* + * @optlen: length of optional header data + * @size: length of packet, excluding this header and optlen + * @src_node_id: source node + * @src_port_id: source port + * @dst_node_id: destination node + * @dst_port_id: destination port + */ +struct qrtr_hdr_v2 { + u8 version; + u8 type; + u8 flags; + u8 optlen; + __le32 size; + __le16 src_node_id; + __le16 src_port_id; + __le16 dst_node_id; + __le16 dst_port_id; +}; + +#define QRTR_FLAGS_CONFIRM_RX BIT(0) + struct qrtr_cb { u32 src_node; u32 src_port; @@ -58,7 +85,8 @@ struct qrtr_cb { u8 confirm_rx; }; -#define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) +#define QRTR_HDR_MAX_SIZE max_t(size_t, sizeof(struct qrtr_hdr_v1), \ + sizeof(struct qrtr_hdr_v2)) struct qrtr_sock { /* WARNING: sk must be the first member */ @@ -154,12 +182,12 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, struct sockaddr_qrtr *to) { - struct qrtr_hdr *hdr; + struct qrtr_hdr_v1 *hdr; size_t len = skb->len; int rc = -ENODEV; - hdr = skb_push(skb, QRTR_HDR_SIZE); - hdr->version = cpu_to_le32(QRTR_PROTO_VER); + hdr = skb_push(skb, sizeof(*hdr)); + hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); hdr->type = cpu_to_le32(type); hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); @@ -224,52 +252,80 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) { struct qrtr_node *node = ep->node; - const struct qrtr_hdr *phdr = data; + const struct qrtr_hdr_v1 *v1; + const struct qrtr_hdr_v2 *v2; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int psize; unsigned int size; - unsigned int type; unsigned int ver; - unsigned int dst; + size_t hdrlen; - if (len < QRTR_HDR_SIZE || len & 3) + if (len & 3) return -EINVAL; - ver = le32_to_cpu(phdr->version); - size = le32_to_cpu(phdr->size); - type = le32_to_cpu(phdr->type); - dst = le32_to_cpu(phdr->dst_port_id); + skb = netdev_alloc_skb(NULL, len); + if (!skb) + return -ENOMEM; - psize = (size + 3) & ~3; + cb = (struct qrtr_cb *)skb->cb; - if (ver != QRTR_PROTO_VER) - return -EINVAL; + /* Version field in v1 is little endian, so this works for both cases */ + ver = *(u8*)data; - if (len != psize + QRTR_HDR_SIZE) - return -EINVAL; + switch (ver) { + case QRTR_PROTO_VER_1: + v1 = data; + hdrlen = sizeof(*v1); - if (dst != QRTR_PORT_CTRL && type != QRTR_TYPE_DATA) - return -EINVAL; + cb->type = le32_to_cpu(v1->type); + cb->src_node = le32_to_cpu(v1->src_node_id); + cb->src_port = le32_to_cpu(v1->src_port_id); + cb->confirm_rx = !!v1->confirm_rx; + cb->dst_node = le32_to_cpu(v1->dst_node_id); + cb->dst_port = le32_to_cpu(v1->dst_port_id); - skb = netdev_alloc_skb(NULL, len); - if (!skb) - return -ENOMEM; + size = le32_to_cpu(v1->size); + break; + case QRTR_PROTO_VER_2: + v2 = data; + hdrlen = sizeof(*v2) + v2->optlen; + + cb->type = v2->type; + cb->confirm_rx = !!(v2->flags & QRTR_FLAGS_CONFIRM_RX); + cb->src_node = le16_to_cpu(v2->src_node_id); + cb->src_port = le16_to_cpu(v2->src_port_id); + cb->dst_node = le16_to_cpu(v2->dst_node_id); + cb->dst_port = le16_to_cpu(v2->dst_port_id); + + if (cb->src_port == (u16)QRTR_PORT_CTRL) + cb->src_port = QRTR_PORT_CTRL; + if (cb->dst_port == (u16)QRTR_PORT_CTRL) + cb->dst_port = QRTR_PORT_CTRL; + + size = le32_to_cpu(v2->size); + break; + default: + pr_err("qrtr: Invalid version %d\n", ver); + goto err; + } - cb = (struct qrtr_cb *)skb->cb; - cb->src_node = le32_to_cpu(phdr->src_node_id); - cb->src_port = le32_to_cpu(phdr->src_port_id); - cb->dst_node = le32_to_cpu(phdr->dst_node_id); - cb->dst_port = le32_to_cpu(phdr->dst_port_id); - cb->type = type; - cb->confirm_rx = !!phdr->confirm_rx; + if (len != ALIGN(size, 4) + hdrlen) + goto err; - skb_put_data(skb, data + QRTR_HDR_SIZE, size); + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) + goto err; + + skb_put_data(skb, data + hdrlen, size); skb_queue_tail(&node->rx_queue, skb); schedule_work(&node->work); return 0; + +err: + kfree_skb(skb); + return -EINVAL; + } EXPORT_SYMBOL_GPL(qrtr_endpoint_post); @@ -287,11 +343,11 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) const int pkt_len = sizeof(struct qrtr_ctrl_pkt); struct sk_buff *skb; - skb = alloc_skb(QRTR_HDR_SIZE + pkt_len, GFP_KERNEL); + skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL); if (!skb) return NULL; - skb_reserve(skb, QRTR_HDR_SIZE); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); *pkt = skb_put_zero(skb, pkt_len); return skb; @@ -720,12 +776,12 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } plen = (len + 3) & ~3; - skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_SIZE, + skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) goto out_node; - skb_reserve(skb, QRTR_HDR_SIZE); + skb_reserve(skb, QRTR_HDR_MAX_SIZE); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc) { -- GitLab From d7e6b347560d1824d7bccfa307ad34bd3f133706 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 11 Oct 2017 14:52:23 -0500 Subject: [PATCH 1264/1507] net: qcom/emac: specify the correct DMA mask The 64/32-bit DMA mask hackery in the EMAC driver is not actually necessary, and is technically not accurate. The EMAC hardware is limted to a 45-bit DMA address. Although no EMAC-enabled system can have that much DDR, an IOMMU could possible provide a larger address. Rather than play games with the DMA mappings, the driver should provide a correct value and trust the DMA/IOMMU layers to do the right thing. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index f477ba29c569f..ee6f2d27502c6 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -615,20 +615,11 @@ static int emac_probe(struct platform_device *pdev) u32 reg; int ret; - /* The EMAC itself is capable of 64-bit DMA, so try that first. */ - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + /* The TPD buffer address is limited to 45 bits. */ + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(45)); if (ret) { - /* Some platforms may restrict the EMAC's address bus to less - * then the size of DDR. In this case, we need to try a - * smaller mask. We could try every possible smaller mask, - * but that's overkill. Instead, just fall to 32-bit, which - * should always work. - */ - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (ret) { - dev_err(&pdev->dev, "could not set DMA mask\n"); - return ret; - } + dev_err(&pdev->dev, "could not set DMA mask\n"); + return ret; } netdev = alloc_etherdev(sizeof(struct emac_adapter)); -- GitLab From 3958ffcd85060967a9c70bb92b21741073578d66 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 11 Oct 2017 14:52:24 -0500 Subject: [PATCH 1265/1507] net: qcom/emac: remove unused address arrays The EMAC is capable of multiple TX and RX rings, but the driver only supports one ring for each. One function had some left-over unused code that supports multiple rings, but all it did was make the code harder to read. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-mac.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 3ed9033e56dbe..9cbb27263742b 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -309,22 +309,12 @@ void emac_mac_mode_config(struct emac_adapter *adpt) /* Config descriptor rings */ static void emac_mac_dma_rings_config(struct emac_adapter *adpt) { - static const unsigned short tpd_q_offset[] = { - EMAC_DESC_CTRL_8, EMAC_H1TPD_BASE_ADDR_LO, - EMAC_H2TPD_BASE_ADDR_LO, EMAC_H3TPD_BASE_ADDR_LO}; - static const unsigned short rfd_q_offset[] = { - EMAC_DESC_CTRL_2, EMAC_DESC_CTRL_10, - EMAC_DESC_CTRL_12, EMAC_DESC_CTRL_13}; - static const unsigned short rrd_q_offset[] = { - EMAC_DESC_CTRL_5, EMAC_DESC_CTRL_14, - EMAC_DESC_CTRL_15, EMAC_DESC_CTRL_16}; - /* TPD (Transmit Packet Descriptor) */ writel(upper_32_bits(adpt->tx_q.tpd.dma_addr), adpt->base + EMAC_DESC_CTRL_1); writel(lower_32_bits(adpt->tx_q.tpd.dma_addr), - adpt->base + tpd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_8); writel(adpt->tx_q.tpd.count & TPD_RING_SIZE_BMSK, adpt->base + EMAC_DESC_CTRL_9); @@ -334,9 +324,9 @@ static void emac_mac_dma_rings_config(struct emac_adapter *adpt) adpt->base + EMAC_DESC_CTRL_0); writel(lower_32_bits(adpt->rx_q.rfd.dma_addr), - adpt->base + rfd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_2); writel(lower_32_bits(adpt->rx_q.rrd.dma_addr), - adpt->base + rrd_q_offset[0]); + adpt->base + EMAC_DESC_CTRL_5); writel(adpt->rx_q.rfd.count & RFD_RING_SIZE_BMSK, adpt->base + EMAC_DESC_CTRL_3); -- GitLab From df1ec1b9d0df57e96011f175418dc95b1af46821 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 11 Oct 2017 14:52:25 -0500 Subject: [PATCH 1266/1507] net: qcom/emac: enforce DMA address restrictions The EMAC has a restriction that the upper 32 bits of the base addresses for the RFD and RRD rings must be the same. The ensure that restriction, we allocate twice the space for the RRD and locate it at an appropriate address. We also re-arrange the allocations so that invalid addresses are even less likely. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-mac.c | 39 ++++++++++++------- 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 9cbb27263742b..0f5ece5d9507f 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -734,6 +734,11 @@ static int emac_rx_descs_alloc(struct emac_adapter *adpt) rx_q->rrd.size = rx_q->rrd.count * (adpt->rrd_size * 4); rx_q->rfd.size = rx_q->rfd.count * (adpt->rfd_size * 4); + /* Check if the RRD and RFD are aligned properly, and if not, adjust. */ + if (upper_32_bits(ring_header->dma_addr) != + upper_32_bits(ring_header->dma_addr + ALIGN(rx_q->rrd.size, 8))) + ring_header->used = ALIGN(rx_q->rrd.size, 8); + rx_q->rrd.dma_addr = ring_header->dma_addr + ring_header->used; rx_q->rrd.v_addr = ring_header->v_addr + ring_header->used; ring_header->used += ALIGN(rx_q->rrd.size, 8); @@ -767,11 +772,18 @@ int emac_mac_rx_tx_rings_alloc_all(struct emac_adapter *adpt) /* Ring DMA buffer. Each ring may need up to 8 bytes for alignment, * hence the additional padding bytes are allocated. + * + * Also double the memory allocated for the RRD so that we can + * re-align it if necessary. The EMAC has a restriction that the + * upper 32 bits of the base addresses for the RFD and RRD rings + * must be the same. It is extremely unlikely that this is not the + * case, since the rings are only a few KB in size. However, we + * need to check for this anyway, and if the two rings are not + * compliant, then we re-align. */ - ring_header->size = num_tx_descs * (adpt->tpd_size * 4) + - num_rx_descs * (adpt->rfd_size * 4) + - num_rx_descs * (adpt->rrd_size * 4) + - 8 + 2 * 8; /* 8 byte per one Tx and two Rx rings */ + ring_header->size = ALIGN(num_tx_descs * (adpt->tpd_size * 4), 8) + + ALIGN(num_rx_descs * (adpt->rfd_size * 4), 8) + + ALIGN(num_rx_descs * (adpt->rrd_size * 4), 8) * 2; ring_header->used = 0; ring_header->v_addr = dma_zalloc_coherent(dev, ring_header->size, @@ -780,26 +792,23 @@ int emac_mac_rx_tx_rings_alloc_all(struct emac_adapter *adpt) if (!ring_header->v_addr) return -ENOMEM; - ring_header->used = ALIGN(ring_header->dma_addr, 8) - - ring_header->dma_addr; - - ret = emac_tx_q_desc_alloc(adpt, &adpt->tx_q); - if (ret) { - netdev_err(adpt->netdev, "error: Tx Queue alloc failed\n"); - goto err_alloc_tx; - } - ret = emac_rx_descs_alloc(adpt); if (ret) { netdev_err(adpt->netdev, "error: Rx Queue alloc failed\n"); goto err_alloc_rx; } + ret = emac_tx_q_desc_alloc(adpt, &adpt->tx_q); + if (ret) { + netdev_err(adpt->netdev, "transmit queue allocation failed\n"); + goto err_alloc_tx; + } + return 0; -err_alloc_rx: - emac_tx_q_bufs_free(adpt); err_alloc_tx: + emac_rx_q_bufs_free(adpt); +err_alloc_rx: dma_free_coherent(dev, ring_header->size, ring_header->v_addr, ring_header->dma_addr); -- GitLab From 740d6f188fb71ae13e3e9f7208b6b3094517509d Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Wed, 11 Oct 2017 14:52:26 -0500 Subject: [PATCH 1267/1507] net: qcom/emac: clean up some TX/RX error messages Some of the error messages that are printed by the interrupt handlers are poorly written. For example, many don't include a device prefix, so there's no indication that they are EMAC errors. Also use rate limiting for all messages that could be printed from interrupt context. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-sgmii.c | 15 ++++++--------- drivers/net/ethernet/qualcomm/emac/emac.c | 8 ++++---- 2 files changed, 10 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c index 29ba37a083722..e8ab512ee7e34 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c @@ -68,10 +68,10 @@ static void emac_sgmii_link_init(struct emac_adapter *adpt) writel(val, phy->base + EMAC_SGMII_PHY_AUTONEG_CFG2); } -static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits) +static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u8 irq_bits) { struct emac_sgmii *phy = &adpt->phy; - u32 status; + u8 status; writel_relaxed(irq_bits, phy->base + EMAC_SGMII_PHY_INTERRUPT_CLEAR); writel_relaxed(IRQ_GLOBAL_CLEAR, phy->base + EMAC_SGMII_PHY_IRQ_CMD); @@ -86,9 +86,8 @@ static int emac_sgmii_irq_clear(struct emac_adapter *adpt, u32 irq_bits) EMAC_SGMII_PHY_INTERRUPT_STATUS, status, !(status & irq_bits), 1, SGMII_PHY_IRQ_CLR_WAIT_TIME)) { - netdev_err(adpt->netdev, - "error: failed clear SGMII irq: status:0x%x bits:0x%x\n", - status, irq_bits); + net_err_ratelimited("%s: failed to clear SGMII irq: status:0x%x bits:0x%x\n", + adpt->netdev->name, status, irq_bits); return -EIO; } @@ -109,7 +108,7 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data) { struct emac_adapter *adpt = data; struct emac_sgmii *phy = &adpt->phy; - u32 status; + u8 status; status = readl(phy->base + EMAC_SGMII_PHY_INTERRUPT_STATUS); status &= SGMII_ISR_MASK; @@ -139,10 +138,8 @@ static irqreturn_t emac_sgmii_interrupt(int irq, void *data) atomic_set(&phy->decode_error_count, 0); } - if (emac_sgmii_irq_clear(adpt, status)) { - netdev_warn(adpt->netdev, "failed to clear SGMII interrupt\n"); + if (emac_sgmii_irq_clear(adpt, status)) schedule_work(&adpt->work_thread); - } return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index ee6f2d27502c6..70c92b649b299 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -148,9 +148,8 @@ static irqreturn_t emac_isr(int _irq, void *data) goto exit; if (status & ISR_ERROR) { - netif_warn(adpt, intr, adpt->netdev, - "warning: error irq status 0x%lx\n", - status & ISR_ERROR); + net_err_ratelimited("%s: error interrupt 0x%lx\n", + adpt->netdev->name, status & ISR_ERROR); /* reset MAC */ schedule_work(&adpt->work_thread); } @@ -169,7 +168,8 @@ static irqreturn_t emac_isr(int _irq, void *data) emac_mac_tx_process(adpt, &adpt->tx_q); if (status & ISR_OVER) - net_warn_ratelimited("warning: TX/RX overflow\n"); + net_warn_ratelimited("%s: TX/RX overflow interrupt\n", + adpt->netdev->name); exit: /* enable the interrupt */ -- GitLab From d8bbb07adbfab5a8e03c361c7dd67fe0003d3757 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:52 -0600 Subject: [PATCH 1268/1507] net: qualcomm: rmnet: Remove existing logic for bridge mode This will be rewritten in the following patches. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- .../ethernet/qualcomm/rmnet/rmnet_config.h | 1 - .../ethernet/qualcomm/rmnet/rmnet_handlers.c | 77 +++---------------- 2 files changed, 9 insertions(+), 69 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index dde4e9f14f4ab..0b0c5a79c1dc3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -34,7 +34,6 @@ struct rmnet_endpoint { */ struct rmnet_port { struct net_device *dev; - struct rmnet_endpoint local_ep; struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP]; u32 ingress_data_format; u32 egress_data_format; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 540c7622dcb17..b50f401816619 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -44,56 +44,18 @@ static void rmnet_set_skb_proto(struct sk_buff *skb) /* Generic handler */ static rx_handler_result_t -rmnet_bridge_handler(struct sk_buff *skb, struct rmnet_endpoint *ep) +rmnet_deliver_skb(struct sk_buff *skb) { - if (!ep->egress_dev) - kfree_skb(skb); - else - rmnet_egress_handler(skb, ep); + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + rmnet_vnd_rx_fixup(skb, skb->dev); + skb->pkt_type = PACKET_HOST; + skb_set_mac_header(skb, 0); + netif_receive_skb(skb); return RX_HANDLER_CONSUMED; } -static rx_handler_result_t -rmnet_deliver_skb(struct sk_buff *skb, struct rmnet_endpoint *ep) -{ - switch (ep->rmnet_mode) { - case RMNET_EPMODE_NONE: - return RX_HANDLER_PASS; - - case RMNET_EPMODE_BRIDGE: - return rmnet_bridge_handler(skb, ep); - - case RMNET_EPMODE_VND: - skb_reset_transport_header(skb); - skb_reset_network_header(skb); - rmnet_vnd_rx_fixup(skb, skb->dev); - - skb->pkt_type = PACKET_HOST; - skb_set_mac_header(skb, 0); - netif_receive_skb(skb); - return RX_HANDLER_CONSUMED; - - default: - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } -} - -static rx_handler_result_t -rmnet_ingress_deliver_packet(struct sk_buff *skb, - struct rmnet_port *port) -{ - if (!port) { - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } - - skb->dev = port->local_ep.egress_dev; - - return rmnet_deliver_skb(skb, &port->local_ep); -} - /* MAP handler */ static rx_handler_result_t @@ -130,7 +92,7 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, skb_pull(skb, sizeof(struct rmnet_map_header)); skb_trim(skb, len); rmnet_set_skb_proto(skb); - return rmnet_deliver_skb(skb, ep); + return rmnet_deliver_skb(skb); } static rx_handler_result_t @@ -204,29 +166,8 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port(dev); - if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) { + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) rc = rmnet_map_ingress_handler(skb, port); - } else { - switch (ntohs(skb->protocol)) { - case ETH_P_MAP: - if (port->local_ep.rmnet_mode == - RMNET_EPMODE_BRIDGE) { - rc = rmnet_ingress_deliver_packet(skb, port); - } else { - kfree_skb(skb); - rc = RX_HANDLER_CONSUMED; - } - break; - - case ETH_P_IP: - case ETH_P_IPV6: - rc = rmnet_ingress_deliver_packet(skb, port); - break; - - default: - rc = RX_HANDLER_PASS; - } - } return rc; } -- GitLab From 1281726ec341702b16c3e67ea37ba485cf72ee66 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:53 -0600 Subject: [PATCH 1269/1507] net: qualcomm: rmnet: Remove some unused defines Most of these constants were used in the initial patchset where custom netlink configuration was used and hence are no longer relevant. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h index 7967198fdd90f..49102f922b311 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h @@ -19,23 +19,15 @@ #define RMNET_TX_QUEUE_LEN 1000 /* Constants */ -#define RMNET_EGRESS_FORMAT__RESERVED__ BIT(0) #define RMNET_EGRESS_FORMAT_MAP BIT(1) #define RMNET_EGRESS_FORMAT_AGGREGATION BIT(2) #define RMNET_EGRESS_FORMAT_MUXING BIT(3) -#define RMNET_EGRESS_FORMAT_MAP_CKSUMV3 BIT(4) -#define RMNET_EGRESS_FORMAT_MAP_CKSUMV4 BIT(5) -#define RMNET_INGRESS_FIX_ETHERNET BIT(0) #define RMNET_INGRESS_FORMAT_MAP BIT(1) #define RMNET_INGRESS_FORMAT_DEAGGREGATION BIT(2) #define RMNET_INGRESS_FORMAT_DEMUXING BIT(3) #define RMNET_INGRESS_FORMAT_MAP_COMMANDS BIT(4) -#define RMNET_INGRESS_FORMAT_MAP_CKSUMV3 BIT(5) -#define RMNET_INGRESS_FORMAT_MAP_CKSUMV4 BIT(6) -/* Pass the frame up the stack with no modifications to skb->dev */ -#define RMNET_EPMODE_NONE (0) /* Replace skb->dev to a virtual rmnet device and pass up the stack */ #define RMNET_EPMODE_VND (1) /* Pass the frame directly to another device with dev_queue_xmit() */ -- GitLab From 9148963201a4627a632d2c769805c9278f6d22d7 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:54 -0600 Subject: [PATCH 1270/1507] net: qualcomm: rmnet: Move rmnet_mode to rmnet_port Mode information on the real device makes it easier to route packets to rmnet device or bridged device based on the configuration. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 12 +++++------- drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h | 2 +- drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c | 3 +-- 3 files changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 8403eea08d0e3..85fce9c4d2349 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -124,20 +124,17 @@ static int rmnet_register_real_device(struct net_device *real_dev) } static void rmnet_set_endpoint_config(struct net_device *dev, - u8 mux_id, u8 rmnet_mode, - struct net_device *egress_dev) + u8 mux_id, struct net_device *egress_dev) { struct rmnet_endpoint *ep; - netdev_dbg(dev, "id %d mode %d dev %s\n", - mux_id, rmnet_mode, egress_dev->name); + netdev_dbg(dev, "id %d dev %s\n", mux_id, egress_dev->name); ep = rmnet_get_endpoint(dev, mux_id); /* This config is cleared on every set, so its ok to not * clear it on a device delete. */ memset(ep, 0, sizeof(struct rmnet_endpoint)); - ep->rmnet_mode = rmnet_mode; ep->egress_dev = egress_dev; ep->mux_id = mux_id; } @@ -183,9 +180,10 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, ingress_format, egress_format); port->egress_data_format = egress_format; port->ingress_data_format = ingress_format; + port->rmnet_mode = mode; - rmnet_set_endpoint_config(real_dev, mux_id, mode, dev); - rmnet_set_endpoint_config(dev, mux_id, mode, real_dev); + rmnet_set_endpoint_config(real_dev, mux_id, dev); + rmnet_set_endpoint_config(dev, mux_id, real_dev); return 0; err2: diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 0b0c5a79c1dc3..03d473f394766 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -24,7 +24,6 @@ * Exact usage of this parameter depends on the rmnet_mode. */ struct rmnet_endpoint { - u8 rmnet_mode; u8 mux_id; struct net_device *egress_dev; }; @@ -39,6 +38,7 @@ struct rmnet_port { u32 egress_data_format; struct net_device *rmnet_devices[RMNET_MAX_LOGICAL_EP]; u8 nr_rmnet_devs; + u8 rmnet_mode; }; extern struct rtnl_link_ops rmnet_link_ops; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index b50f401816619..86e37cc3b52c1 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -205,8 +205,7 @@ void rmnet_egress_handler(struct sk_buff *skb, } } - if (ep->rmnet_mode == RMNET_EPMODE_VND) - rmnet_vnd_tx_fixup(skb, orig_dev); + rmnet_vnd_tx_fixup(skb, orig_dev); dev_queue_xmit(skb); } -- GitLab From 56470c927f1ba1e101b5e5a93e02d23a14fd99b7 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:55 -0600 Subject: [PATCH 1271/1507] net: qualcomm: rmnet: Remove duplicate setting of rmnet private info The end point is set twice in the local_ep as well as the mux_id and the real_dev in the rmnet private structure. Remove the local_ep. While these elements are equivalent, rmnet_endpoint will be used only as part of the rmnet_port for muxed scenarios in VND mode. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- .../ethernet/qualcomm/rmnet/rmnet_config.c | 10 ++-------- .../ethernet/qualcomm/rmnet/rmnet_config.h | 4 ---- .../ethernet/qualcomm/rmnet/rmnet_handlers.c | 18 ++++++++++-------- .../ethernet/qualcomm/rmnet/rmnet_handlers.h | 3 +-- .../net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 19 ++----------------- .../net/ethernet/qualcomm/rmnet/rmnet_vnd.h | 1 - 6 files changed, 15 insertions(+), 40 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 85fce9c4d2349..96058bbccf716 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -67,13 +67,8 @@ rmnet_get_endpoint(struct net_device *dev, int config_id) struct rmnet_endpoint *ep; struct rmnet_port *port; - if (!rmnet_is_real_dev_registered(dev)) { - ep = rmnet_vnd_get_endpoint(dev); - } else { - port = rmnet_get_port_rtnl(dev); - - ep = &port->muxed_ep[config_id]; - } + port = rmnet_get_port_rtnl(dev); + ep = &port->muxed_ep[config_id]; return ep; } @@ -183,7 +178,6 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, port->rmnet_mode = mode; rmnet_set_endpoint_config(real_dev, mux_id, dev); - rmnet_set_endpoint_config(dev, mux_id, real_dev); return 0; err2: diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 03d473f394766..c5f5c6d957c01 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -20,9 +20,6 @@ #define RMNET_MAX_LOGICAL_EP 255 -/* Information about the next device to deliver the packet to. - * Exact usage of this parameter depends on the rmnet_mode. - */ struct rmnet_endpoint { u8 mux_id; struct net_device *egress_dev; @@ -44,7 +41,6 @@ struct rmnet_port { extern struct rtnl_link_ops rmnet_link_ops; struct rmnet_priv { - struct rmnet_endpoint local_ep; u8 mux_id; struct net_device *real_dev; }; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 86e37cc3b52c1..e0802d32d6a50 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -116,8 +116,7 @@ rmnet_map_ingress_handler(struct sk_buff *skb, } static int rmnet_map_egress_handler(struct sk_buff *skb, - struct rmnet_port *port, - struct rmnet_endpoint *ep, + struct rmnet_port *port, u8 mux_id, struct net_device *orig_dev) { int required_headroom, additional_header_len; @@ -136,10 +135,10 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, return RMNET_MAP_CONSUMED; if (port->egress_data_format & RMNET_EGRESS_FORMAT_MUXING) { - if (ep->mux_id == 0xff) + if (mux_id == 0xff) map_header->mux_id = 0; else - map_header->mux_id = ep->mux_id; + map_header->mux_id = mux_id; } skb->protocol = htons(ETH_P_MAP); @@ -176,14 +175,17 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) * for egress device configured in logical endpoint. Packet is then transmitted * on the egress device. */ -void rmnet_egress_handler(struct sk_buff *skb, - struct rmnet_endpoint *ep) +void rmnet_egress_handler(struct sk_buff *skb) { struct net_device *orig_dev; struct rmnet_port *port; + struct rmnet_priv *priv; + u8 mux_id; orig_dev = skb->dev; - skb->dev = ep->egress_dev; + priv = netdev_priv(orig_dev); + skb->dev = priv->real_dev; + mux_id = priv->mux_id; port = rmnet_get_port(skb->dev); if (!port) { @@ -192,7 +194,7 @@ void rmnet_egress_handler(struct sk_buff *skb, } if (port->egress_data_format & RMNET_EGRESS_FORMAT_MAP) { - switch (rmnet_map_egress_handler(skb, port, ep, orig_dev)) { + switch (rmnet_map_egress_handler(skb, port, mux_id, orig_dev)) { case RMNET_MAP_CONSUMED: return; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h index f2638cf5693c5..3537e4ceedb37 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h @@ -18,8 +18,7 @@ #include "rmnet_config.h" -void rmnet_egress_handler(struct sk_buff *skb, - struct rmnet_endpoint *ep); +void rmnet_egress_handler(struct sk_buff *skb); rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 7f90d5587653b..4ca59a4389b8b 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -45,8 +45,8 @@ static netdev_tx_t rmnet_vnd_start_xmit(struct sk_buff *skb, struct rmnet_priv *priv; priv = netdev_priv(dev); - if (priv->local_ep.egress_dev) { - rmnet_egress_handler(skb, &priv->local_ep); + if (priv->real_dev) { + rmnet_egress_handler(skb); } else { dev->stats.tx_dropped++; kfree_skb(skb); @@ -143,21 +143,6 @@ u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) return priv->mux_id; } -/* Gets the logical endpoint configuration for a RmNet virtual network device - * node. Caller should confirm that devices is a RmNet VND before calling. - */ -struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *rmnet_dev) -{ - struct rmnet_priv *priv; - - if (!rmnet_dev) - return NULL; - - priv = netdev_priv(rmnet_dev); - - return &priv->local_ep; -} - int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) { netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index 8a4042f0f6bfa..cae134d357748 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -17,7 +17,6 @@ #define _RMNET_VND_H_ int rmnet_vnd_do_flow_control(struct net_device *dev, int enable); -struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *dev); int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_port *port, struct net_device *real_dev); -- GitLab From 5451237ff7a77ded1d81538e3daa76dc3ee60538 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:56 -0600 Subject: [PATCH 1272/1507] net: qualcomm: rmnet: Remove duplicate setting of rmnet_devices The rmnet_devices information is already stored in muxed_ep, so storing this in rmnet_devices[] again is redundant. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h | 1 - drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 8 ++++---- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index c5f5c6d957c01..123ccf41fc952 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -33,7 +33,6 @@ struct rmnet_port { struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP]; u32 ingress_data_format; u32 egress_data_format; - struct net_device *rmnet_devices[RMNET_MAX_LOGICAL_EP]; u8 nr_rmnet_devs; u8 rmnet_mode; }; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 4ca59a4389b8b..8b8497b17f52b 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -105,12 +105,12 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_priv *priv; int rc; - if (port->rmnet_devices[id]) + if (port->muxed_ep[id].egress_dev) return -EINVAL; rc = register_netdevice(rmnet_dev); if (!rc) { - port->rmnet_devices[id] = rmnet_dev; + port->muxed_ep[id].egress_dev = rmnet_dev; port->nr_rmnet_devs++; rmnet_dev->rtnl_link_ops = &rmnet_link_ops; @@ -127,10 +127,10 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, int rmnet_vnd_dellink(u8 id, struct rmnet_port *port) { - if (id >= RMNET_MAX_LOGICAL_EP || !port->rmnet_devices[id]) + if (id >= RMNET_MAX_LOGICAL_EP || !port->muxed_ep[id].egress_dev) return -EINVAL; - port->rmnet_devices[id] = NULL; + port->muxed_ep[id].egress_dev = NULL; port->nr_rmnet_devs--; return 0; } -- GitLab From 3352e6c45760fd6675468a35ef699ab94617cab4 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:57 -0600 Subject: [PATCH 1273/1507] net: qualcomm: rmnet: Convert the muxed endpoint to hlist Rather than using a static array, use a hlist to store the muxed endpoints and use the mux id to query the rmnet_device. This is useful as usually very few mux ids are used. Signed-off-by: Subash Abhinov Kasiviswanathan Cc: Dan Williams Signed-off-by: David S. Miller --- .../ethernet/qualcomm/rmnet/rmnet_config.c | 75 ++++++++++--------- .../ethernet/qualcomm/rmnet/rmnet_config.h | 4 +- .../ethernet/qualcomm/rmnet/rmnet_handlers.c | 17 +++-- .../qualcomm/rmnet/rmnet_map_command.c | 4 +- .../net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 15 ++-- .../net/ethernet/qualcomm/rmnet/rmnet_vnd.h | 6 +- 6 files changed, 68 insertions(+), 53 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 96058bbccf716..b5fe3f4d22a62 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -61,18 +61,6 @@ rmnet_get_port_rtnl(const struct net_device *real_dev) return rtnl_dereference(real_dev->rx_handler_data); } -static struct rmnet_endpoint* -rmnet_get_endpoint(struct net_device *dev, int config_id) -{ - struct rmnet_endpoint *ep; - struct rmnet_port *port; - - port = rmnet_get_port_rtnl(dev); - ep = &port->muxed_ep[config_id]; - - return ep; -} - static int rmnet_unregister_real_device(struct net_device *real_dev, struct rmnet_port *port) { @@ -93,7 +81,7 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, static int rmnet_register_real_device(struct net_device *real_dev) { struct rmnet_port *port; - int rc; + int rc, entry; ASSERT_RTNL(); @@ -114,26 +102,13 @@ static int rmnet_register_real_device(struct net_device *real_dev) /* hold on to real dev for MAP data */ dev_hold(real_dev); + for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) + INIT_HLIST_HEAD(&port->muxed_ep[entry]); + netdev_dbg(real_dev, "registered with rmnet\n"); return 0; } -static void rmnet_set_endpoint_config(struct net_device *dev, - u8 mux_id, struct net_device *egress_dev) -{ - struct rmnet_endpoint *ep; - - netdev_dbg(dev, "id %d dev %s\n", mux_id, egress_dev->name); - - ep = rmnet_get_endpoint(dev, mux_id); - /* This config is cleared on every set, so its ok to not - * clear it on a device delete. - */ - memset(ep, 0, sizeof(struct rmnet_endpoint)); - ep->egress_dev = egress_dev; - ep->mux_id = mux_id; -} - static int rmnet_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -145,6 +120,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, RMNET_EGRESS_FORMAT_MAP; struct net_device *real_dev; int mode = RMNET_EPMODE_VND; + struct rmnet_endpoint *ep; struct rmnet_port *port; int err = 0; u16 mux_id; @@ -156,6 +132,10 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (!data[IFLA_VLAN_ID]) return -EINVAL; + ep = kzalloc(sizeof(*ep), GFP_ATOMIC); + if (!ep) + return -ENOMEM; + mux_id = nla_get_u16(data[IFLA_VLAN_ID]); err = rmnet_register_real_device(real_dev); @@ -163,7 +143,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, goto err0; port = rmnet_get_port_rtnl(real_dev); - err = rmnet_vnd_newlink(mux_id, dev, port, real_dev); + err = rmnet_vnd_newlink(mux_id, dev, port, real_dev, ep); if (err) goto err1; @@ -177,11 +157,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, port->ingress_data_format = ingress_format; port->rmnet_mode = mode; - rmnet_set_endpoint_config(real_dev, mux_id, dev); + hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); return 0; err2: - rmnet_vnd_dellink(mux_id, port); + rmnet_vnd_dellink(mux_id, port, ep); err1: rmnet_unregister_real_device(real_dev, port); err0: @@ -191,6 +171,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, static void rmnet_dellink(struct net_device *dev, struct list_head *head) { struct net_device *real_dev; + struct rmnet_endpoint *ep; struct rmnet_port *port; u8 mux_id; @@ -204,8 +185,15 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) port = rmnet_get_port_rtnl(real_dev); mux_id = rmnet_vnd_get_mux(dev); - rmnet_vnd_dellink(mux_id, port); netdev_upper_dev_unlink(dev, real_dev); + + ep = rmnet_get_endpoint(port, mux_id); + if (ep) { + hlist_del_init_rcu(&ep->hlnode); + rmnet_vnd_dellink(mux_id, port, ep); + kfree(ep); + } + rmnet_unregister_real_device(real_dev, port); unregister_netdevice_queue(dev, head); @@ -214,11 +202,16 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) static int rmnet_dev_walk_unreg(struct net_device *rmnet_dev, void *data) { struct rmnet_walk_data *d = data; + struct rmnet_endpoint *ep; u8 mux_id; mux_id = rmnet_vnd_get_mux(rmnet_dev); - - rmnet_vnd_dellink(mux_id, d->port); + ep = rmnet_get_endpoint(d->port, mux_id); + if (ep) { + hlist_del_init_rcu(&ep->hlnode); + rmnet_vnd_dellink(mux_id, d->port, ep); + kfree(ep); + } netdev_upper_dev_unlink(rmnet_dev, d->real_dev); unregister_netdevice_queue(rmnet_dev, d->head); @@ -316,6 +309,18 @@ struct rmnet_port *rmnet_get_port(struct net_device *real_dev) return NULL; } +struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id) +{ + struct rmnet_endpoint *ep; + + hlist_for_each_entry_rcu(ep, &port->muxed_ep[mux_id], hlnode) { + if (ep->mux_id == mux_id) + return ep; + } + + return NULL; +} + /* Startup/Shutdown */ static int __init rmnet_init(void) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 123ccf41fc952..8849986980f80 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -23,6 +23,7 @@ struct rmnet_endpoint { u8 mux_id; struct net_device *egress_dev; + struct hlist_node hlnode; }; /* One instance of this structure is instantiated for each real_dev associated @@ -30,11 +31,11 @@ struct rmnet_endpoint { */ struct rmnet_port { struct net_device *dev; - struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP]; u32 ingress_data_format; u32 egress_data_format; u8 nr_rmnet_devs; u8 rmnet_mode; + struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; }; extern struct rtnl_link_ops rmnet_link_ops; @@ -45,5 +46,6 @@ struct rmnet_priv { }; struct rmnet_port *rmnet_get_port(struct net_device *real_dev); +struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); #endif /* _RMNET_CONFIG_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index e0802d32d6a50..fa24ffb69713c 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -71,19 +71,18 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, & RMNET_INGRESS_FORMAT_MAP_COMMANDS) return rmnet_map_command(skb, port); - kfree_skb(skb); - return RX_HANDLER_CONSUMED; + goto free_skb; } mux_id = RMNET_MAP_GET_MUX_ID(skb); len = RMNET_MAP_GET_LENGTH(skb) - RMNET_MAP_GET_PAD(skb); - if (mux_id >= RMNET_MAX_LOGICAL_EP) { - kfree_skb(skb); - return RX_HANDLER_CONSUMED; - } + if (mux_id >= RMNET_MAX_LOGICAL_EP) + goto free_skb; - ep = &port->muxed_ep[mux_id]; + ep = rmnet_get_endpoint(port, mux_id); + if (!ep) + goto free_skb; if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEMUXING) skb->dev = ep->egress_dev; @@ -93,6 +92,10 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, skb_trim(skb, len); rmnet_set_skb_proto(skb); return rmnet_deliver_skb(skb); + +free_skb: + kfree_skb(skb); + return RX_HANDLER_CONSUMED; } static rx_handler_result_t diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c index d1ea5e21b982e..74d362f71cce9 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c @@ -17,7 +17,7 @@ #include "rmnet_vnd.h" static u8 rmnet_map_do_flow_control(struct sk_buff *skb, - struct rmnet_port *rdinfo, + struct rmnet_port *port, int enable) { struct rmnet_map_control_command *cmd; @@ -37,7 +37,7 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb, return RX_HANDLER_CONSUMED; } - ep = &rdinfo->muxed_ep[mux_id]; + ep = rmnet_get_endpoint(port, mux_id); vnd = ep->egress_dev; ip_family = cmd->flow_control.ip_family; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 8b8497b17f52b..1b6747d7154fe 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -100,17 +100,19 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_port *port, - struct net_device *real_dev) + struct net_device *real_dev, + struct rmnet_endpoint *ep) { struct rmnet_priv *priv; int rc; - if (port->muxed_ep[id].egress_dev) + if (ep->egress_dev) return -EINVAL; rc = register_netdevice(rmnet_dev); if (!rc) { - port->muxed_ep[id].egress_dev = rmnet_dev; + ep->egress_dev = rmnet_dev; + ep->mux_id = id; port->nr_rmnet_devs++; rmnet_dev->rtnl_link_ops = &rmnet_link_ops; @@ -125,12 +127,13 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, return rc; } -int rmnet_vnd_dellink(u8 id, struct rmnet_port *port) +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, + struct rmnet_endpoint *ep) { - if (id >= RMNET_MAX_LOGICAL_EP || !port->muxed_ep[id].egress_dev) + if (id >= RMNET_MAX_LOGICAL_EP || !ep->egress_dev) return -EINVAL; - port->muxed_ep[id].egress_dev = NULL; + ep->egress_dev = NULL; port->nr_rmnet_devs--; return 0; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index cae134d357748..71e4c32869512 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -19,8 +19,10 @@ int rmnet_vnd_do_flow_control(struct net_device *dev, int enable); int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct rmnet_port *port, - struct net_device *real_dev); -int rmnet_vnd_dellink(u8 id, struct rmnet_port *port); + struct net_device *real_dev, + struct rmnet_endpoint *ep); +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, + struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); -- GitLab From 60d58f971c1077a0f2467b2d5bc38058df43a819 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Wed, 11 Oct 2017 18:43:58 -0600 Subject: [PATCH 1274/1507] net: qualcomm: rmnet: Implement bridge mode Add support to bridge two devices which can send multiplexing and aggregation (MAP) data. This is done only when the data itself is not going to be consumed in the stack but is being passed on to a different endpoint. This is mainly used for testing. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- .../ethernet/qualcomm/rmnet/rmnet_config.c | 93 ++++++++++++++++++- .../ethernet/qualcomm/rmnet/rmnet_config.h | 7 +- .../ethernet/qualcomm/rmnet/rmnet_handlers.c | 26 +++++- .../net/ethernet/qualcomm/rmnet/rmnet_vnd.c | 2 + 4 files changed, 122 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index b5fe3f4d22a62..71bee1af71eff 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -109,6 +109,36 @@ static int rmnet_register_real_device(struct net_device *real_dev) return 0; } +static void rmnet_unregister_bridge(struct net_device *dev, + struct rmnet_port *port) +{ + struct net_device *rmnet_dev, *bridge_dev; + struct rmnet_port *bridge_port; + + if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) + return; + + /* bridge slave handling */ + if (!port->nr_rmnet_devs) { + rmnet_dev = netdev_master_upper_dev_get_rcu(dev); + netdev_upper_dev_unlink(dev, rmnet_dev); + + bridge_dev = port->bridge_ep; + + bridge_port = rmnet_get_port_rtnl(bridge_dev); + bridge_port->bridge_ep = NULL; + bridge_port->rmnet_mode = RMNET_EPMODE_VND; + } else { + bridge_dev = port->bridge_ep; + + bridge_port = rmnet_get_port_rtnl(bridge_dev); + rmnet_dev = netdev_master_upper_dev_get_rcu(bridge_dev); + netdev_upper_dev_unlink(bridge_dev, rmnet_dev); + + rmnet_unregister_real_device(bridge_dev, bridge_port); + } +} + static int rmnet_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -190,10 +220,10 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) ep = rmnet_get_endpoint(port, mux_id); if (ep) { hlist_del_init_rcu(&ep->hlnode); + rmnet_unregister_bridge(dev, port); rmnet_vnd_dellink(mux_id, port, ep); kfree(ep); } - rmnet_unregister_real_device(real_dev, port); unregister_netdevice_queue(dev, head); @@ -237,6 +267,8 @@ static void rmnet_force_unassociate_device(struct net_device *dev) d.port = port; rcu_read_lock(); + rmnet_unregister_bridge(dev, port); + netdev_walk_all_lower_dev_rcu(real_dev, rmnet_dev_walk_unreg, &d); rcu_read_unlock(); unregister_netdevice_many(&list); @@ -321,6 +353,65 @@ struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id) return NULL; } +int rmnet_add_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev, + struct netlink_ext_ack *extack) +{ + struct rmnet_priv *priv = netdev_priv(rmnet_dev); + struct net_device *real_dev = priv->real_dev; + struct rmnet_port *port, *slave_port; + int err; + + port = rmnet_get_port(real_dev); + + /* If there is more than one rmnet dev attached, its probably being + * used for muxing. Skip the briding in that case + */ + if (port->nr_rmnet_devs > 1) + return -EINVAL; + + if (rmnet_is_real_dev_registered(slave_dev)) + return -EBUSY; + + err = rmnet_register_real_device(slave_dev); + if (err) + return -EBUSY; + + err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, + extack); + if (err) + return -EINVAL; + + slave_port = rmnet_get_port(slave_dev); + slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; + slave_port->bridge_ep = real_dev; + + port->rmnet_mode = RMNET_EPMODE_BRIDGE; + port->bridge_ep = slave_dev; + + netdev_dbg(slave_dev, "registered with rmnet as slave\n"); + return 0; +} + +int rmnet_del_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev) +{ + struct rmnet_priv *priv = netdev_priv(rmnet_dev); + struct net_device *real_dev = priv->real_dev; + struct rmnet_port *port, *slave_port; + + port = rmnet_get_port(real_dev); + port->rmnet_mode = RMNET_EPMODE_VND; + port->bridge_ep = NULL; + + netdev_upper_dev_unlink(slave_dev, rmnet_dev); + slave_port = rmnet_get_port(slave_dev); + rmnet_unregister_real_device(slave_dev, slave_port); + + netdev_dbg(slave_dev, "removed from rmnet as slave\n"); + return 0; +} + /* Startup/Shutdown */ static int __init rmnet_init(void) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 8849986980f80..60115e69e4158 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -36,6 +36,7 @@ struct rmnet_port { u8 nr_rmnet_devs; u8 rmnet_mode; struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; + struct net_device *bridge_ep; }; extern struct rtnl_link_ops rmnet_link_ops; @@ -47,5 +48,9 @@ struct rmnet_priv { struct rmnet_port *rmnet_get_port(struct net_device *real_dev); struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); - +int rmnet_add_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev, + struct netlink_ext_ack *extack); +int rmnet_del_bridge(struct net_device *rmnet_dev, + struct net_device *slave_dev); #endif /* _RMNET_CONFIG_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index fa24ffb69713c..df3d2d16ce550 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -149,6 +149,17 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, return RMNET_MAP_SUCCESS; } +static rx_handler_result_t +rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev) +{ + if (bridge_dev) { + skb->dev = bridge_dev; + dev_queue_xmit(skb); + } + + return RX_HANDLER_CONSUMED; +} + /* Ingress / Egress Entry Points */ /* Processes packet as per ingress data format for receiving device. Logical @@ -157,10 +168,10 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, */ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) { - struct rmnet_port *port; + int rc = RX_HANDLER_CONSUMED; struct sk_buff *skb = *pskb; + struct rmnet_port *port; struct net_device *dev; - int rc; if (!skb) return RX_HANDLER_CONSUMED; @@ -168,8 +179,15 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) dev = skb->dev; port = rmnet_get_port(dev); - if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) - rc = rmnet_map_ingress_handler(skb, port); + switch (port->rmnet_mode) { + case RMNET_EPMODE_VND: + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) + rc = rmnet_map_ingress_handler(skb, port); + break; + case RMNET_EPMODE_BRIDGE: + rc = rmnet_bridge_handler(skb, port->bridge_ep); + break; + } return rc; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 1b6747d7154fe..12bd0bbd5235d 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -74,6 +74,8 @@ static const struct net_device_ops rmnet_vnd_ops = { .ndo_start_xmit = rmnet_vnd_start_xmit, .ndo_change_mtu = rmnet_vnd_change_mtu, .ndo_get_iflink = rmnet_vnd_get_iflink, + .ndo_add_slave = rmnet_add_bridge, + .ndo_del_slave = rmnet_del_bridge, }; /* Called by kernel whenever a new rmnet device is created. Sets MTU, -- GitLab From 843e79d05addd8eb06992cd6dfafc7b9d53f2bc8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Oct 2017 09:41:07 +0200 Subject: [PATCH 1275/1507] net: sched: make tc_action_ops->get_dev return dev and avoid passing net Return dev directly, NULL if not possible. That is enough. Makes no sense to pass struct net * to get_dev op, as there is only one net possible, the one the action was created in. So just store it in mirred priv and use directly. Rename the mirred op callback function. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 3 +-- include/net/tc_act/tc_mirred.h | 1 + net/sched/act_mirred.c | 13 +++++-------- net/sched/cls_api.c | 6 ++---- 4 files changed, 9 insertions(+), 14 deletions(-) diff --git a/include/net/act_api.h b/include/net/act_api.h index b944e0eb93be3..900168a9901e0 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -93,8 +93,7 @@ struct tc_action_ops { int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *); void (*stats_update)(struct tc_action *, u64, u32, u64); - int (*get_dev)(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev); + struct net_device *(*get_dev)(const struct tc_action *a); }; struct tc_action_net { diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 604bc31e23ab1..21a656569840d 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -10,6 +10,7 @@ struct tcf_mirred { int tcfm_ifindex; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; + struct net *net; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 416627c66f081..8b3e593884803 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -140,6 +140,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; + m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@ -313,15 +314,11 @@ static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; -static int tcf_mirred_device(const struct tc_action *a, struct net *net, - struct net_device **mirred_dev) +static struct net_device *tcf_mirred_get_dev(const struct tc_action *a) { - int ifindex = tcf_mirred_ifindex(a); + struct tcf_mirred *m = to_mirred(a); - *mirred_dev = __dev_get_by_index(net, ifindex); - if (!*mirred_dev) - return -EINVAL; - return 0; + return __dev_get_by_index(m->net, m->tcfm_ifindex); } static struct tc_action_ops act_mirred_ops = { @@ -336,7 +333,7 @@ static struct tc_action_ops act_mirred_ops = { .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .size = sizeof(struct tcf_mirred), - .get_dev = tcf_mirred_device, + .get_dev = tcf_mirred_get_dev, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0b2219adf520b..450873b0c4b95 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1016,10 +1016,8 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) { - a->ops->get_dev(a, dev_net(dev), hw_dev); - break; - } + if (a->ops->get_dev) + *hw_dev = a->ops->get_dev(a); } if (*hw_dev) return 0; -- GitLab From b3f55bdda8df55a563005e00b1b71212d8546541 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Oct 2017 09:41:08 +0200 Subject: [PATCH 1276/1507] net: sched: introduce per-egress action device callbacks Introduce infrastructure that allows drivers to register callbacks that are called whenever tc would offload inserted rule and specified device acts as tc action egress device. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/act_api.h | 34 +++++++ include/net/pkt_cls.h | 2 + net/sched/act_api.c | 220 ++++++++++++++++++++++++++++++++++++++++++ net/sched/cls_api.c | 30 ++++++ 4 files changed, 286 insertions(+) diff --git a/include/net/act_api.h b/include/net/act_api.h index 900168a9901e0..f5e8c9048fb08 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -174,4 +174,38 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #endif } +typedef int tc_setup_cb_t(enum tc_setup_type type, + void *type_data, void *cb_priv); + +#ifdef CONFIG_NET_CLS_ACT +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv); +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv); +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop); +#else +static inline +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + return 0; +} + +static inline +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ +} + +static inline +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop) +{ + return 0; +} +#endif + #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e80edd8879efc..6f8149c82571d 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -206,6 +206,8 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, struct net_device **hw_dev); +int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop); /** * struct tcf_pkt_info - packet information diff --git a/net/sched/act_api.c b/net/sched/act_api.c index da6fa82c98a8b..ac97db92ab68c 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #include #include #include @@ -1249,8 +1251,226 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +struct tcf_action_net { + struct rhashtable egdev_ht; +}; + +static unsigned int tcf_action_net_id; + +struct tcf_action_egdev_cb { + struct list_head list; + tc_setup_cb_t *cb; + void *cb_priv; +}; + +struct tcf_action_egdev { + struct rhash_head ht_node; + const struct net_device *dev; + unsigned int refcnt; + struct list_head cb_list; +}; + +static const struct rhashtable_params tcf_action_egdev_ht_params = { + .key_offset = offsetof(struct tcf_action_egdev, dev), + .head_offset = offsetof(struct tcf_action_egdev, ht_node), + .key_len = sizeof(const struct net_device *), +}; + +static struct tcf_action_egdev * +tcf_action_egdev_lookup(const struct net_device *dev) +{ + struct net *net = dev_net(dev); + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_lookup_fast(&tan->egdev_ht, &dev, + tcf_action_egdev_ht_params); +} + +static struct tcf_action_egdev * +tcf_action_egdev_get(const struct net_device *dev) +{ + struct tcf_action_egdev *egdev; + struct tcf_action_net *tan; + + egdev = tcf_action_egdev_lookup(dev); + if (egdev) + goto inc_ref; + + egdev = kzalloc(sizeof(*egdev), GFP_KERNEL); + if (!egdev) + return NULL; + INIT_LIST_HEAD(&egdev->cb_list); + tan = net_generic(dev_net(dev), tcf_action_net_id); + rhashtable_insert_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + +inc_ref: + egdev->refcnt++; + return egdev; +} + +static void tcf_action_egdev_put(struct tcf_action_egdev *egdev) +{ + struct tcf_action_net *tan; + + if (--egdev->refcnt) + return; + tan = net_generic(dev_net(egdev->dev), tcf_action_net_id); + rhashtable_remove_fast(&tan->egdev_ht, &egdev->ht_node, + tcf_action_egdev_ht_params); + kfree(egdev); +} + +static struct tcf_action_egdev_cb * +tcf_action_egdev_cb_lookup(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) + if (egdev_cb->cb == cb && egdev_cb->cb_priv == cb_priv) + return egdev_cb; + return NULL; +} + +static int tcf_action_egdev_cb_call(struct tcf_action_egdev *egdev, + enum tc_setup_type type, + void *type_data, bool err_stop) +{ + struct tcf_action_egdev_cb *egdev_cb; + int ok_count = 0; + int err; + + list_for_each_entry(egdev_cb, &egdev->cb_list, list) { + err = egdev_cb->cb(type, type_data, egdev_cb->cb_priv); + if (err) { + if (err_stop) + return err; + } else { + ok_count++; + } + } + return ok_count; +} + +static int tcf_action_egdev_cb_add(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(egdev_cb)) + return -EEXIST; + egdev_cb = kzalloc(sizeof(*egdev_cb), GFP_KERNEL); + if (!egdev_cb) + return -ENOMEM; + egdev_cb->cb = cb; + egdev_cb->cb_priv = cb_priv; + list_add(&egdev_cb->list, &egdev->cb_list); + return 0; +} + +static void tcf_action_egdev_cb_del(struct tcf_action_egdev *egdev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev_cb *egdev_cb; + + egdev_cb = tcf_action_egdev_cb_lookup(egdev, cb, cb_priv); + if (WARN_ON(!egdev_cb)) + return; + list_del(&egdev_cb->list); + kfree(egdev_cb); +} + +static int __tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_get(dev); + int err; + + if (!egdev) + return -ENOMEM; + err = tcf_action_egdev_cb_add(egdev, cb, cb_priv); + if (err) + goto err_cb_add; + return 0; + +err_cb_add: + tcf_action_egdev_put(egdev); + return err; +} +int tc_setup_cb_egdev_register(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + int err; + + rtnl_lock(); + err = __tc_setup_cb_egdev_register(dev, cb, cb_priv); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_register); + +static void __tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (WARN_ON(!egdev)) + return; + tcf_action_egdev_cb_del(egdev, cb, cb_priv); + tcf_action_egdev_put(egdev); +} +void tc_setup_cb_egdev_unregister(const struct net_device *dev, + tc_setup_cb_t *cb, void *cb_priv) +{ + rtnl_lock(); + __tc_setup_cb_egdev_unregister(dev, cb, cb_priv); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_unregister); + +int tc_setup_cb_egdev_call(const struct net_device *dev, + enum tc_setup_type type, void *type_data, + bool err_stop) +{ + struct tcf_action_egdev *egdev = tcf_action_egdev_lookup(dev); + + if (!egdev) + return 0; + return tcf_action_egdev_cb_call(egdev, type, type_data, err_stop); +} +EXPORT_SYMBOL_GPL(tc_setup_cb_egdev_call); + +static __net_init int tcf_action_net_init(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + return rhashtable_init(&tan->egdev_ht, &tcf_action_egdev_ht_params); +} + +static void __net_exit tcf_action_net_exit(struct net *net) +{ + struct tcf_action_net *tan = net_generic(net, tcf_action_net_id); + + rhashtable_destroy(&tan->egdev_ht); +} + +static struct pernet_operations tcf_action_net_ops = { + .init = tcf_action_net_init, + .exit = tcf_action_net_exit, + .id = &tcf_action_net_id, + .size = sizeof(struct tcf_action_net), +}; + static int __init tc_action_init(void) { + int err; + + err = register_pernet_subsys(&tcf_action_net_ops); + if (err) + return err; + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 450873b0c4b95..99f9432f63cf1 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1026,6 +1026,36 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, } EXPORT_SYMBOL(tcf_exts_get_dev); +int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + int ok_count = 0; +#ifdef CONFIG_NET_CLS_ACT + const struct tc_action *a; + struct net_device *dev; + LIST_HEAD(actions); + int ret; + + if (!tcf_exts_has_actions(exts)) + return 0; + + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { + if (!a->ops->get_dev) + continue; + dev = a->ops->get_dev(a); + if (!dev || !tc_can_offload(dev)) + continue; + ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop); + if (ret < 0) + return ret; + ok_count += ret; + } +#endif + return ok_count; +} +EXPORT_SYMBOL(tcf_exts_egdev_cb_call); + static int __init tc_filter_init(void) { rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); -- GitLab From 717503b9cf57c0bb7ea4d3a9f5699c9a04adf988 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Oct 2017 09:41:09 +0200 Subject: [PATCH 1277/1507] net: sched: convert cls_flower->egress_dev users to tc_setup_cb_egdev infra The only user of cls_flower->egress_dev is mlx5. So do the conversion there alongside with the code originating the call in cls_flower function fl_hw_replace_filter to the newly introduced egress device callback infrastucture. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 31 ++++++--- include/net/pkt_cls.h | 5 +- net/sched/cls_api.c | 13 +++- net/sched/cls_flower.c | 63 ++++++++++--------- 6 files changed, 73 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index cc13d3dbd3666..5ec6d3e8dc89f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1081,6 +1081,9 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv, struct ethtool_flash *flash); +int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data); + /* mlx5e generic netdev management API */ struct net_device* mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cc11bbbd0309d..2a32102e76486 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3108,8 +3108,8 @@ static int mlx5e_setup_tc_cls_flower(struct net_device *dev, } #endif -static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) +int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { switch (type) { #ifdef CONFIG_MLX5_ESWITCH diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 45e03c427faf9..765fc74fbb1b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -667,14 +668,6 @@ mlx5e_rep_setup_tc_cls_flower(struct net_device *dev, cls_flower->common.chain_index) return -EOPNOTSUPP; - if (cls_flower->egress_dev) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - - dev = mlx5_eswitch_get_uplink_netdev(esw); - return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - cls_flower); - } - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return mlx5e_configure_flower(priv, cls_flower); @@ -698,6 +691,14 @@ static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct net_device *dev = cb_priv; + + return mlx5e_setup_tc(dev, type, type_data); +} + bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -1017,15 +1018,24 @@ mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) goto err_detach_netdev; } + err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); + if (err) + goto err_neigh_cleanup; + err = register_netdev(netdev); if (err) { pr_warn("Failed to register representor netdev for vport %d\n", rep->vport); - goto err_neigh_cleanup; + goto err_egdev_cleanup; } return 0; +err_egdev_cleanup: + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); + err_neigh_cleanup: mlx5e_rep_neigh_cleanup(rpriv); @@ -1047,7 +1057,8 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) void *ppriv = priv->ppriv; unregister_netdev(rep->netdev); - + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb, + mlx5_eswitch_get_uplink_netdev(esw)); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); mlx5e_destroy_netdev(priv); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6f8149c82571d..c0bdf5cad7272 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -206,8 +206,6 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, struct net_device **hw_dev); -int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type, - void *type_data, bool err_stop); /** * struct tcf_pkt_info - packet information @@ -407,6 +405,9 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop); + struct tc_cls_common_offload { u32 chain_index; __be16 protocol; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 99f9432f63cf1..51994a202585a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1026,8 +1026,9 @@ int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, } EXPORT_SYMBOL(tcf_exts_get_dev); -int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type, - void *type_data, bool err_stop) +static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, + enum tc_setup_type type, + void *type_data, bool err_stop) { int ok_count = 0; #ifdef CONFIG_NET_CLS_ACT @@ -1054,7 +1055,13 @@ int tcf_exts_egdev_cb_call(struct tcf_exts *exts, enum tc_setup_type type, #endif return ok_count; } -EXPORT_SYMBOL(tcf_exts_egdev_cb_call); + +int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type, + void *type_data, bool err_stop) +{ + return tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop); +} +EXPORT_SYMBOL(tc_setup_cb_call); static int __init tc_filter_init(void) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index db831ac708f60..5b7bb968d1d44 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -88,7 +88,6 @@ struct cls_fl_filter { u32 handle; u32 flags; struct rcu_head rcu; - struct net_device *hw_dev; }; static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) @@ -201,16 +200,17 @@ static void fl_destroy_filter(struct rcu_head *head) static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct net_device *dev = tp->q->dev_queue->dev; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long) f; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, &cls_flower); + if (tc_can_offload(dev)) + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static int fl_hw_replace_filter(struct tcf_proto *tp, @@ -220,20 +220,9 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, { struct net_device *dev = tp->q->dev_queue->dev; struct tc_cls_flower_offload cls_flower = {}; + bool skip_sw = tc_skip_sw(f->flags); int err; - if (!tc_can_offload(dev)) { - if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev) || - (f->hw_dev && !tc_can_offload(f->hw_dev))) { - f->hw_dev = dev; - return tc_skip_sw(f->flags) ? -EINVAL : 0; - } - dev = f->hw_dev; - cls_flower.egress_dev = true; - } else { - f->hw_dev = dev; - } - tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; @@ -242,31 +231,47 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); - if (!err) - f->flags |= TCA_CLS_FLAGS_IN_HW; + if (tc_can_offload(dev)) { + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + if (err) { + if (skip_sw) + return err; + } else { + f->flags |= TCA_CLS_FLAGS_IN_HW; + } + } - if (tc_skip_sw(f->flags)) + err = tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, skip_sw); + if (err < 0) { + fl_hw_destroy_filter(tp, f); return err; + } else if (err > 0) { + f->flags |= TCA_CLS_FLAGS_IN_HW; + } + + if (skip_sw && !(f->flags & TCA_CLS_FLAGS_IN_HW)) + return -EINVAL; + return 0; } static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) { struct tc_cls_flower_offload cls_flower = {}; - struct net_device *dev = f->hw_dev; - - if (!tc_can_offload(dev)) - return; + struct net_device *dev = tp->q->dev_queue->dev; tc_cls_common_offload_init(&cls_flower.common, tp); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; cls_flower.exts = &f->exts; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, - &cls_flower); + if (tc_can_offload(dev)) + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + &cls_flower); + tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER, + &cls_flower, false); } static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f) -- GitLab From 7578d7b45ed870b13a8ace57e32feaed623c2a94 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 11 Oct 2017 09:41:10 +0200 Subject: [PATCH 1278/1507] net: sched: remove unused tcf_exts_get_dev helper and cls_flower->egress_dev The helper and the struct field ares no longer used by any code, so remove them. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 --- net/sched/cls_api.c | 22 ---------------------- 2 files changed, 25 deletions(-) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c0bdf5cad7272..f5263743076b8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -204,8 +204,6 @@ void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev); /** * struct tcf_pkt_info - packet information @@ -517,7 +515,6 @@ struct tc_cls_flower_offload { struct fl_flow_key *mask; struct fl_flow_key *key; struct tcf_exts *exts; - bool egress_dev; }; enum tc_matchall_command { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 51994a202585a..2977b8a908514 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1004,28 +1004,6 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_dump_stats); -int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, - struct net_device **hw_dev) -{ -#ifdef CONFIG_NET_CLS_ACT - const struct tc_action *a; - LIST_HEAD(actions); - - if (!tcf_exts_has_actions(exts)) - return -EINVAL; - - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { - if (a->ops->get_dev) - *hw_dev = a->ops->get_dev(a); - } - if (*hw_dev) - return 0; -#endif - return -EOPNOTSUPP; -} -EXPORT_SYMBOL(tcf_exts_get_dev); - static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts, enum tc_setup_type type, void *type_data, bool err_stop) -- GitLab From 4ea2607f7871ca433ab0c5300289215974213f26 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Oct 2017 10:28:00 +0200 Subject: [PATCH 1279/1507] ipv6: addrconf: don't use rtnl mutex in RTM_GETNETCONF Instead of relying on rtnl mutex bump device reference count. After this change, values reported can change in parallel, but thats not much different from current state, as anyone can change the settings right after rtnl_unlock (and before userspace processed reply). While at it, switch to GFP_KERNEL allocation. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d9f6226694eba..5207f567ef28c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -616,23 +616,23 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; + struct inet6_dev *in6_dev = NULL; + struct net_device *dev = NULL; struct netconfmsg *ncm; struct sk_buff *skb; struct ipv6_devconf *devconf; - struct inet6_dev *in6_dev; - struct net_device *dev; int ifindex; int err; err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, devconf_ipv6_policy, extack); if (err < 0) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; + err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: @@ -642,10 +642,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv6.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); + dev = dev_get_by_index(net, ifindex); if (!dev) - goto errout; - in6_dev = __in6_dev_get(dev); + return -EINVAL; + in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; @@ -653,7 +653,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = -ENOBUFS; - skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_ATOMIC); + skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; @@ -669,6 +669,10 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in6_dev) + in6_dev_put(in6_dev); + if (dev) + dev_put(dev); return err; } @@ -6570,7 +6574,7 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, 0); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - inet6_netconf_dump_devconf, 0); + inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED); ipv6_addr_label_rtnl_register(); -- GitLab From c24675f871d3bca569532b3744962dd49938ddff Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Oct 2017 10:28:01 +0200 Subject: [PATCH 1280/1507] ipv6: addrconf: don't use rtnl mutex in RTM_GETADDR Similar to the previous patch, use the device lookup functions that bump device refcount and flag this as DOIT_UNLOCKED to avoid rtnl mutex. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5207f567ef28c..4603aa488f4f9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4890,17 +4890,15 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) - goto errout; + return err; addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) { - err = -EINVAL; - goto errout; - } + if (!addr) + return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = __dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(net, ifm->ifa_index); ifa = ipv6_get_ifaddr(net, addr, dev, 1); if (!ifa) { @@ -4926,6 +4924,8 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, errout_ifa: in6_ifa_put(ifa); errout: + if (dev) + dev_put(dev); return err; } @@ -6568,7 +6568,7 @@ int __init addrconf_init(void) __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, - inet6_dump_ifaddr, 0); + inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED); __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr, 0); __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, -- GitLab From 1a37b770cf78dca77c386f8a95e05403233e4d52 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 11 Oct 2017 11:17:57 +0100 Subject: [PATCH 1281/1507] sctp: make array sctp_sched_ops static The array sctp_sched_ops is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: symbol 'sctp_sched_ops' was not declared. Should it be static? Signed-off-by: Colin Ian King Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/stream_sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 03513a9fa110b..0b83ec51e43b0 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -124,7 +124,7 @@ static struct sctp_sched_ops sctp_sched_fcfs = { extern struct sctp_sched_ops sctp_sched_prio; extern struct sctp_sched_ops sctp_sched_rr; -struct sctp_sched_ops *sctp_sched_ops[] = { +static struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, &sctp_sched_prio, &sctp_sched_rr, -- GitLab From 14c68c43b7695cbcfe148bf3c513b598c2886e7d Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 11 Oct 2017 10:53:28 +0100 Subject: [PATCH 1282/1507] net: mpls: make function ipgre_mpls_encap_hlen static The function ipgre_mpls_encap_hlen is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: symbol 'ipgre_mpls_encap_hlen' was not declared. Should it be static? Fixes: bdc476413dcdb ("ip_tunnel: add mpls over gre support") Signed-off-by: Colin Ian King Acked-by: David Ahern Signed-off-by: David S. Miller --- net/mpls/af_mpls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 9745e8f698103..8ca9915befc8c 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -41,7 +41,7 @@ static int label_limit = (1 << 20) - 1; static int ttl_max = 255; #if IS_ENABLED(CONFIG_NET_IP_TUNNEL) -size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) +static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct mpls_shim_hdr); } -- GitLab From 5dad61b83840d7eceaba5bf316419be11bbb993a Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:25 +0300 Subject: [PATCH 1283/1507] net/mlx4_en: Replace netdev parameter with priv in XDP xmit function The struct net_device parameter was passed only to extract struct mlx4_en_priv out of it. Here we pass the priv parameter directly. Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 3 +-- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index a7866954d1063..92aec17f4b4d6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -778,7 +778,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud case XDP_PASS: break; case XDP_TX: - if (likely(!mlx4_en_xmit_frame(ring, frags, dev, + if (likely(!mlx4_en_xmit_frame(ring, frags, priv, length, cq_ring, &doorbell_pending))) { frags[0].page = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 2cc82dc073974..f16774c9c347b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1087,10 +1087,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, - struct net_device *dev, unsigned int length, + struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - struct mlx4_en_priv *priv = netdev_priv(dev); union mlx4_wqe_qpn_vlan qpn_vlan = {}; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 245e9ea09ab29..8cad9b4f1936e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -693,7 +693,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, - struct net_device *dev, unsigned int length, + struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending); void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring); bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, -- GitLab From f6f0aa97413a420606aabe8142f8a5c0f15b9246 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:26 +0300 Subject: [PATCH 1284/1507] net/mlx4_en: Obsolete call to generic write_desc in XDP xmit flow Function mlx4_en_tx_write_desc() is not optimized to use of XDP xmit. Use the relevant parts inline instead. Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index f16774c9c347b..ac7254e3f9095 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1090,7 +1090,9 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - union mlx4_wqe_qpn_vlan qpn_vlan = {}; + union mlx4_wqe_qpn_vlan qpn_vlan = { + .fence_size = MLX4_EN_XDP_TX_REAL_SZ, + }; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; struct mlx4_wqe_data_seg *data; @@ -1140,7 +1142,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, data->byte_count = cpu_to_be32(length); /* tx completion can avoid cache line miss for common cases */ - tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; op_own = cpu_to_be32(MLX4_OPCODE_SEND) | ((ring->prod & ring->size) ? @@ -1151,10 +1152,16 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, ring->prod += MLX4_EN_XDP_TX_NRTXBB; - qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + tx_desc->ctrl.qpn_vlan = qpn_vlan; + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + + /* Ensure new descriptor hits memory + * before setting ownership of this descriptor to HW + */ + dma_wmb(); + tx_desc->ctrl.owner_opcode = op_own; + ring->xmit_more++; - mlx4_en_tx_write_desc(ring, tx_desc, qpn_vlan, TXBB_SIZE, 0, - op_own, false, false); *doorbell_pending = true; return NETDEV_TX_OK; -- GitLab From f025fd6061e120713d6c11c92983804c6805d6cb Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 11 Oct 2017 13:17:27 +0300 Subject: [PATCH 1285/1507] net/mlx4_en: XDP_TX, assign constant values of TX descs on ring creaion In XDP_TX, some fields in tx_info and tx_desc are constants across all entries of the different XDP_TX rings. Assign values to these fields on ring creation time, rather than in data-path. Patchset performance tests: Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz Single queue no-RSS optimization ON. XDP_TX packet rate: ------------------------------ Before | After | Gain | 13.7 Mpps | 14.0 Mpps | %2.2 | ------------------------------ Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_tx.c | 38 ++++++++++++------- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 + 3 files changed, 27 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index e4c7a80ef5a81..d611df2f274d5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1752,6 +1752,7 @@ int mlx4_en_start_port(struct net_device *dev) mlx4_en_arm_cq(priv, cq); } else { + mlx4_en_init_tx_xdp_ring_descs(priv, tx_ring); mlx4_en_init_recycle_ring(priv, i); /* XDP TX CQ should never be armed */ } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index ac7254e3f9095..596445a4a2414 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1085,14 +1085,35 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) #define MLX4_EN_XDP_TX_REAL_SZ (((CTRL_SIZE + MLX4_EN_XDP_TX_NRTXBB * DS_SIZE) \ / 16) & 0x3f) +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring) +{ + int i; + + for (i = 0; i < ring->size; i++) { + struct mlx4_en_tx_info *tx_info = &ring->tx_info[i]; + struct mlx4_en_tx_desc *tx_desc = ring->buf + + (i << LOG_TXBB_SIZE); + + tx_info->map0_byte_count = PAGE_SIZE; + tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; + tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); + tx_info->ts_requested = 0; + tx_info->nr_maps = 1; + tx_info->linear = 1; + tx_info->inl = 0; + + tx_desc->data.lkey = ring->mr_key; + tx_desc->ctrl.qpn_vlan.fence_size = MLX4_EN_XDP_TX_REAL_SZ; + tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; + } +} + netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_rx_alloc *frame, struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending) { - union mlx4_wqe_qpn_vlan qpn_vlan = { - .fence_size = MLX4_EN_XDP_TX_REAL_SZ, - }; struct mlx4_en_tx_desc *tx_desc; struct mlx4_en_tx_info *tx_info; struct mlx4_wqe_data_seg *data; @@ -1124,20 +1145,12 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, tx_info->page = frame->page; frame->page = NULL; tx_info->map0_dma = dma; - tx_info->map0_byte_count = PAGE_SIZE; - tx_info->nr_txbb = MLX4_EN_XDP_TX_NRTXBB; tx_info->nr_bytes = max_t(unsigned int, length, ETH_ZLEN); - tx_info->data_offset = offsetof(struct mlx4_en_tx_desc, data); - tx_info->ts_requested = 0; - tx_info->nr_maps = 1; - tx_info->linear = 1; - tx_info->inl = 0; dma_sync_single_range_for_device(priv->ddev, dma, frame->page_offset, length, PCI_DMA_TODEVICE); data->addr = cpu_to_be64(dma + frame->page_offset); - data->lkey = ring->mr_key; dma_wmb(); data->byte_count = cpu_to_be32(length); @@ -1152,9 +1165,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, ring->prod += MLX4_EN_XDP_TX_NRTXBB; - tx_desc->ctrl.qpn_vlan = qpn_vlan; - tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; - /* Ensure new descriptor hits memory * before setting ownership of this descriptor to HW */ diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 8cad9b4f1936e..1856e279a7e0a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -705,6 +705,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, int node, int queue_index); void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring); +void mlx4_en_init_tx_xdp_ring_descs(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring); int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, int cq, int user_prio); -- GitLab From 952925dec0f276b407b2abce4aee82cba7c700c3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 11 Oct 2017 11:56:23 +0100 Subject: [PATCH 1286/1507] bpf: remove redundant variable old_flags Variable old_flags is being assigned but is never read; it is redundant and can be removed. Cleans up clang warning: Value stored to 'old_flags' is never read Signed-off-by: Colin Ian King Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/cgroup.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index e88abc0865d50..3db5a17fcfe8d 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -192,7 +192,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct cgroup_subsys_state *css; struct bpf_prog_list *pl; bool pl_was_allocated; - u32 old_flags; int err; if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) @@ -239,7 +238,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, pl->prog = prog; } - old_flags = cgrp->bpf.flags[type]; cgrp->bpf.flags[type] = flags; /* allocate and recompute effective prog arrays */ -- GitLab From a67a4893f37d5389c812d85ccf1e258b87ef4ead Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 12 Oct 2017 11:23:04 +0200 Subject: [PATCH 1287/1507] cfg80211: remove set but never used variable cf_offset Perhaps it had been intended to be used, but it clearly isn't. Signed-off-by: Johannes Berg --- net/wireless/chan.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/wireless/chan.c b/net/wireless/chan.c index b8aa5a7d5c77a..eb824270f6e30 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -464,7 +464,7 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, struct ieee80211_channel *chan) { int width; - u32 cf_offset, freq; + u32 freq; if (chandef->chan->center_freq == chan->center_freq) return true; @@ -473,8 +473,6 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, if (width <= 20) return false; - cf_offset = width / 2 - 10; - for (freq = chandef->center_freq1 - width / 2 + 10; freq <= chandef->center_freq1 + width / 2 - 10; freq += 20) { if (chan->center_freq == freq) -- GitLab From 437d2762ba07f0fc639d5a09acb323fe4106a61f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Oct 2017 20:45:40 -0700 Subject: [PATCH 1288/1507] tcp: remove obsolete helpers Remove three inline helpers that are no longer needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 15163454174ba..3b3b9b968e2d4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1629,18 +1629,6 @@ static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) return skb_peek_tail(&sk->sk_write_queue); } -static inline struct sk_buff *tcp_write_queue_next(const struct sock *sk, - const struct sk_buff *skb) -{ - return skb_queue_next(&sk->sk_write_queue, skb); -} - -static inline struct sk_buff *tcp_write_queue_prev(const struct sock *sk, - const struct sk_buff *skb) -{ - return skb_queue_prev(&sk->sk_write_queue, skb); -} - #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) @@ -1697,11 +1685,6 @@ static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb } } -static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb) -{ - __skb_queue_head(&sk->sk_write_queue, skb); -} - /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, -- GitLab From 3f7832c26cc0cad2245981f777f3ee684399ce93 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Thu, 12 Oct 2017 12:42:04 -0500 Subject: [PATCH 1289/1507] Revert "net: qcom/emac: enforce DMA address restrictions" This reverts commit df1ec1b9d0df57e96011f175418dc95b1af46821. It turns out that memory allocated via dma_alloc_coherent is always aligned to the size of the buffer, so there's no way the RRD and RFD can ever be in separate 32-bit regions. Signed-off-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-mac.c | 39 +++++++------------ 1 file changed, 15 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 0f5ece5d9507f..9cbb27263742b 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -734,11 +734,6 @@ static int emac_rx_descs_alloc(struct emac_adapter *adpt) rx_q->rrd.size = rx_q->rrd.count * (adpt->rrd_size * 4); rx_q->rfd.size = rx_q->rfd.count * (adpt->rfd_size * 4); - /* Check if the RRD and RFD are aligned properly, and if not, adjust. */ - if (upper_32_bits(ring_header->dma_addr) != - upper_32_bits(ring_header->dma_addr + ALIGN(rx_q->rrd.size, 8))) - ring_header->used = ALIGN(rx_q->rrd.size, 8); - rx_q->rrd.dma_addr = ring_header->dma_addr + ring_header->used; rx_q->rrd.v_addr = ring_header->v_addr + ring_header->used; ring_header->used += ALIGN(rx_q->rrd.size, 8); @@ -772,18 +767,11 @@ int emac_mac_rx_tx_rings_alloc_all(struct emac_adapter *adpt) /* Ring DMA buffer. Each ring may need up to 8 bytes for alignment, * hence the additional padding bytes are allocated. - * - * Also double the memory allocated for the RRD so that we can - * re-align it if necessary. The EMAC has a restriction that the - * upper 32 bits of the base addresses for the RFD and RRD rings - * must be the same. It is extremely unlikely that this is not the - * case, since the rings are only a few KB in size. However, we - * need to check for this anyway, and if the two rings are not - * compliant, then we re-align. */ - ring_header->size = ALIGN(num_tx_descs * (adpt->tpd_size * 4), 8) + - ALIGN(num_rx_descs * (adpt->rfd_size * 4), 8) + - ALIGN(num_rx_descs * (adpt->rrd_size * 4), 8) * 2; + ring_header->size = num_tx_descs * (adpt->tpd_size * 4) + + num_rx_descs * (adpt->rfd_size * 4) + + num_rx_descs * (adpt->rrd_size * 4) + + 8 + 2 * 8; /* 8 byte per one Tx and two Rx rings */ ring_header->used = 0; ring_header->v_addr = dma_zalloc_coherent(dev, ring_header->size, @@ -792,23 +780,26 @@ int emac_mac_rx_tx_rings_alloc_all(struct emac_adapter *adpt) if (!ring_header->v_addr) return -ENOMEM; - ret = emac_rx_descs_alloc(adpt); - if (ret) { - netdev_err(adpt->netdev, "error: Rx Queue alloc failed\n"); - goto err_alloc_rx; - } + ring_header->used = ALIGN(ring_header->dma_addr, 8) - + ring_header->dma_addr; ret = emac_tx_q_desc_alloc(adpt, &adpt->tx_q); if (ret) { - netdev_err(adpt->netdev, "transmit queue allocation failed\n"); + netdev_err(adpt->netdev, "error: Tx Queue alloc failed\n"); goto err_alloc_tx; } + ret = emac_rx_descs_alloc(adpt); + if (ret) { + netdev_err(adpt->netdev, "error: Rx Queue alloc failed\n"); + goto err_alloc_rx; + } + return 0; -err_alloc_tx: - emac_rx_q_bufs_free(adpt); err_alloc_rx: + emac_tx_q_bufs_free(adpt); +err_alloc_tx: dma_free_coherent(dev, ring_header->size, ring_header->v_addr, ring_header->dma_addr); -- GitLab From 60724d4bae14cd295b27b1610cad9a2720eb0860 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 10:57:48 -0700 Subject: [PATCH 1290/1507] net: dsa: Add support for DSA specific notifiers In preparation for communicating a given DSA network device's port number and switch index, create a specialized DSA notifier and two events: DSA_PORT_REGISTER and DSA_PORT_UNREGISTER that communicate: the slave network device (slave_dev), port number and switch number in the tree. This will be later used for network device drivers like bcmsysport which needs to cooperate with its DSA network devices to set-up queue mapping and scheduling. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ net/dsa/dsa.c | 23 +++++++++++++++++++++++ net/dsa/slave.c | 13 +++++++++++++ 3 files changed, 81 insertions(+) diff --git a/include/net/dsa.h b/include/net/dsa.h index 10dceccd9ce86..40a709a0754dc 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -471,4 +471,49 @@ static inline int dsa_switch_resume(struct dsa_switch *ds) } #endif /* CONFIG_PM_SLEEP */ +enum dsa_notifier_type { + DSA_PORT_REGISTER, + DSA_PORT_UNREGISTER, +}; + +struct dsa_notifier_info { + struct net_device *dev; +}; + +struct dsa_notifier_register_info { + struct dsa_notifier_info info; /* must be first */ + struct net_device *master; + unsigned int port_number; + unsigned int switch_number; +}; + +static inline struct net_device * +dsa_notifier_info_to_dev(const struct dsa_notifier_info *info) +{ + return info->dev; +} + +#if IS_ENABLED(CONFIG_NET_DSA) +int register_dsa_notifier(struct notifier_block *nb); +int unregister_dsa_notifier(struct notifier_block *nb); +int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info); +#else +static inline int register_dsa_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int unregister_dsa_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info) +{ + return NOTIFY_DONE; +} +#endif + #endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 51ca2a524a27b..832c659ff9936 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -261,6 +262,28 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); + +int register_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(register_dsa_notifier); + +int unregister_dsa_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_dsa_notifier); + +int call_dsa_notifiers(unsigned long val, struct net_device *dev, + struct dsa_notifier_info *info) +{ + info->dev = dev; + return atomic_notifier_call_chain(&dsa_notif_chain, val, info); +} +EXPORT_SYMBOL_GPL(call_dsa_notifiers); + static int __init dsa_init_module(void) { int rc; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index fb2954ff198cd..45f4ea845c077 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1116,6 +1116,7 @@ int dsa_slave_resume(struct net_device *slave_dev) int dsa_slave_create(struct dsa_port *port, const char *name) { + struct dsa_notifier_register_info rinfo = { }; struct dsa_switch *ds = port->ds; struct net_device *master; struct net_device *slave_dev; @@ -1177,6 +1178,12 @@ int dsa_slave_create(struct dsa_port *port, const char *name) goto out_free; } + rinfo.info.dev = slave_dev; + rinfo.master = master; + rinfo.port_number = p->dp->index; + rinfo.switch_number = p->dp->ds->index; + call_dsa_notifiers(DSA_PORT_REGISTER, slave_dev, &rinfo.info); + ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", @@ -1200,6 +1207,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_notifier_register_info rinfo = { }; struct device_node *port_dn; port_dn = p->dp->dn; @@ -1211,6 +1219,11 @@ void dsa_slave_destroy(struct net_device *slave_dev) if (of_phy_is_fixed_link(port_dn)) of_phy_deregister_fixed_link(port_dn); } + rinfo.info.dev = slave_dev; + rinfo.master = p->dp->cpu_dp->netdev; + rinfo.port_number = p->dp->index; + rinfo.switch_number = p->dp->ds->index; + call_dsa_notifiers(DSA_PORT_UNREGISTER, slave_dev, &rinfo.info); unregister_netdev(slave_dev); free_percpu(p->stats64); free_netdev(slave_dev); -- GitLab From 0a5f14ce67a6e093e651d3cd75e6ac281123d93a Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 10:57:49 -0700 Subject: [PATCH 1291/1507] net: dsa: tag_brcm: Indicate to master netdevice port + queue We need to tell the DSA master network device doing the actual transmission what the desired switch port and queue number is for it to resolve that to the internal transmit queue it is mapped to. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ net/dsa/tag_brcm.c | 6 ++++++ 2 files changed, 11 insertions(+) diff --git a/include/net/dsa.h b/include/net/dsa.h index 40a709a0754dc..ce1d622734d73 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -516,4 +516,9 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, } #endif +/* Broadcom tag specific helpers to insert and extract queue/port number */ +#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q) +#define BRCM_TAG_GET_PORT(v) ((v) >> 8) +#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) + #endif diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 8e4bdb9d9ae36..cc4f472fbd772 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -86,6 +86,12 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK; + /* Now tell the master network device about the desired output queue + * as well + */ + skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(p->dp->index, + queue)); + return skb; } -- GitLab From d156576362c07e954dc36e07b0d7b0733a010f7d Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 10:57:50 -0700 Subject: [PATCH 1292/1507] net: systemport: Establish lower/upper queue mapping Establish a queue mapping between the DSA slave network device queues created that correspond to switch port queues, and the transmit queue that SYSTEMPORT manages. We need to configure the SYSTEMPORT transmit queue with the switch port number and switch port queue number in order for the switch and SYSTEMPORT hardware to utilize the out of band congestion notification. This hardware mechanism works by looking at the switch port egress queue and determines whether there is enough buffers for this queue, with that class of service for a successful transmission and if not, backpressures the SYSTEMPORT queue that is being used. For this to work, we implement a notifier which looks at the DSA_PORT_REGISTER event. When DSA network devices are registered, the framework calls the DSA notifiers when that happens, extracts the number of queues for these devices and their associated port number, remembers that in the driver private structure and linearly maps those queues to TX rings/queues that we manage. This scheme works because DSA slave network deviecs always transmit through SYSTEMPORT so when DSA slave network devices are destroyed/brought down, the corresponding SYSTEMPORT queues are no longer used. Also, by design of the DSA framework, the master network device (SYSTEMPORT) is registered first. For faster lookups we use an array of up to DSA_MAX_PORTS * number of queues per port, and then map pointers to bcm_sysport_tx_ring such that our ndo_select_queue() implementation can just index into that array to locate the corresponding ring index. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 115 ++++++++++++++++++++- drivers/net/ethernet/broadcom/bcmsysport.h | 11 +- 2 files changed, 121 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 83eec9a8c2751..78bed9a84e817 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1416,7 +1416,14 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index)); tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index)); - tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index)); + + /* Configure QID and port mapping */ + reg = tdma_readl(priv, TDMA_DESC_RING_MAPPING(index)); + reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT); + reg |= ring->switch_queue & RING_QID_MASK; + reg |= ring->switch_port << RING_PORT_ID_SHIFT; + reg |= RING_IGNORE_STATUS; + tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index)); /* Do not use tdma_control_bit() here because TSB_SWAP1 collides @@ -1447,8 +1454,9 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, napi_enable(&ring->napi); netif_dbg(priv, hw, priv->netdev, - "TDMA cfg, size=%d, desc_cpu=%p\n", - ring->size, ring->desc_cpu); + "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n", + ring->size, ring->desc_cpu, ring->switch_queue, + ring->switch_port); return 0; } @@ -2011,6 +2019,92 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; +static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, + select_queue_fallback_t fallback) +{ + struct bcm_sysport_priv *priv = netdev_priv(dev); + u16 queue = skb_get_queue_mapping(skb); + struct bcm_sysport_tx_ring *tx_ring; + unsigned int q, port; + + if (!netdev_uses_dsa(dev)) + return fallback(dev, skb); + + /* DSA tagging layer will have configured the correct queue */ + q = BRCM_TAG_GET_QUEUE(queue); + port = BRCM_TAG_GET_PORT(queue); + tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues]; + + return tx_ring->index; +} + +static int bcm_sysport_map_queues(struct net_device *dev, + struct dsa_notifier_register_info *info) +{ + struct bcm_sysport_priv *priv = netdev_priv(dev); + struct bcm_sysport_tx_ring *ring; + struct net_device *slave_dev; + unsigned int num_tx_queues; + unsigned int q, start, port; + + /* We can't be setting up queue inspection for non directly attached + * switches + */ + if (info->switch_number) + return 0; + + port = info->port_number; + slave_dev = info->info.dev; + + /* On SYSTEMPORT Lite we have twice as less queues, so we cannot do a + * 1:1 mapping, we can only do a 2:1 mapping. By reducing the number of + * per-port (slave_dev) network devices queue, we achieve just that. + * This need to happen now before any slave network device is used such + * it accurately reflects the number of real TX queues. + */ + if (priv->is_lite) + netif_set_real_num_tx_queues(slave_dev, + slave_dev->num_tx_queues / 2); + num_tx_queues = slave_dev->real_num_tx_queues; + + if (priv->per_port_num_tx_queues && + priv->per_port_num_tx_queues != num_tx_queues) + netdev_warn(slave_dev, "asymetric number of per-port queues\n"); + + priv->per_port_num_tx_queues = num_tx_queues; + + start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues); + for (q = 0; q < num_tx_queues; q++) { + ring = &priv->tx_rings[q + start]; + + /* Just remember the mapping actual programming done + * during bcm_sysport_init_tx_ring + */ + ring->switch_queue = q; + ring->switch_port = port; + priv->ring_map[q + port * num_tx_queues] = ring; + + /* Set all queues as being used now */ + set_bit(q + start, &priv->queue_bitmap); + } + + return 0; +} + +static int bcm_sysport_dsa_notifier(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct dsa_notifier_register_info *info; + + if (event != DSA_PORT_REGISTER) + return NOTIFY_DONE; + + info = ptr; + + return notifier_from_errno(bcm_sysport_map_queues(info->master, info)); +} + static const struct net_device_ops bcm_sysport_netdev_ops = { .ndo_start_xmit = bcm_sysport_xmit, .ndo_tx_timeout = bcm_sysport_tx_timeout, @@ -2023,6 +2117,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = { .ndo_poll_controller = bcm_sysport_poll_controller, #endif .ndo_get_stats64 = bcm_sysport_get_stats64, + .ndo_select_queue = bcm_sysport_select_queue, }; #define REV_FMT "v%2x.%02x" @@ -2172,10 +2267,18 @@ static int bcm_sysport_probe(struct platform_device *pdev) u64_stats_init(&priv->syncp); + priv->dsa_notifier.notifier_call = bcm_sysport_dsa_notifier; + + ret = register_dsa_notifier(&priv->dsa_notifier); + if (ret) { + dev_err(&pdev->dev, "failed to register DSA notifier\n"); + goto err_deregister_fixed_link; + } + ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); - goto err_deregister_fixed_link; + goto err_deregister_notifier; } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; @@ -2188,6 +2291,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) return 0; +err_deregister_notifier: + unregister_dsa_notifier(&priv->dsa_notifier); err_deregister_fixed_link: if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); @@ -2199,11 +2304,13 @@ static int bcm_sysport_probe(struct platform_device *pdev) static int bcm_sysport_remove(struct platform_device *pdev) { struct net_device *dev = dev_get_drvdata(&pdev->dev); + struct bcm_sysport_priv *priv = netdev_priv(dev); struct device_node *dn = pdev->dev.of_node; /* Not much to do, ndo_close has been called * and we use managed allocations */ + unregister_dsa_notifier(&priv->dsa_notifier); unregister_netdev(dev); if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 82e401df199e4..82f70a6783cba 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -404,7 +404,7 @@ struct bcm_rsb { #define RING_CONS_INDEX_MASK 0xffff #define RING_MAPPING 0x14 -#define RING_QID_MASK 0x3 +#define RING_QID_MASK 0x7 #define RING_PORT_ID_SHIFT 3 #define RING_PORT_ID_MASK 0x7 #define RING_IGNORE_STATUS (1 << 6) @@ -712,6 +712,8 @@ struct bcm_sysport_tx_ring { struct bcm_sysport_priv *priv; /* private context backpointer */ unsigned long packets; /* packets statistics */ unsigned long bytes; /* bytes statistics */ + unsigned int switch_queue; /* switch port queue number */ + unsigned int switch_port; /* switch port queue number */ }; /* Driver private structure */ @@ -765,5 +767,12 @@ struct bcm_sysport_priv { /* For atomic update generic 64bit value on 32bit Machine */ struct u64_stats_sync syncp; + + /* map information between switch port queues and local queues */ + struct notifier_block dsa_notifier; + unsigned int per_port_num_tx_queues; + unsigned long queue_bitmap; + struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8]; + }; #endif /* __BCM_SYSPORT_H */ -- GitLab From 32e47ff0cd236d5fcab8ffcce85d1dcded663f61 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 10:57:51 -0700 Subject: [PATCH 1293/1507] net: dsa: bcm_sf2: Turn on ACB at the switch level Turn on the out of band Advanced Congestion Buffering (ACB) mechanism at the switch level now that we have properly established the queue mapping between the switch egress queues and the SYSTEMPORT egress queues. This allows the switch to correctly backpressure the host system when one of its queue drops below the configured thresholds. This is also helping achieve so called "lossless" behavior by adapting the TX interrupt pacing to the actual speed and capacity of the switch port. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 30 ++++++++++++++++++++++++++++++ drivers/net/dsa/bcm_sf2_regs.h | 23 +++++++++++++++++++++++ 2 files changed, 53 insertions(+) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 7aecc98d0a189..32025b990437c 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -205,6 +205,19 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, if (port == priv->moca_port) bcm_sf2_port_intr_enable(priv, port); + /* Set per-queue pause threshold to 32 */ + core_writel(priv, 32, CORE_TXQ_THD_PAUSE_QN_PORT(port)); + + /* Set ACB threshold to 24 */ + for (i = 0; i < SF2_NUM_EGRESS_QUEUES; i++) { + reg = acb_readl(priv, ACB_QUEUE_CFG(port * + SF2_NUM_EGRESS_QUEUES + i)); + reg &= ~XOFF_THRESHOLD_MASK; + reg |= 24; + acb_writel(priv, reg, ACB_QUEUE_CFG(port * + SF2_NUM_EGRESS_QUEUES + i)); + } + return b53_enable_port(ds, port, phy); } @@ -613,6 +626,20 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, status->pause = 1; } +static void bcm_sf2_enable_acb(struct dsa_switch *ds) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + u32 reg; + + /* Enable ACB globally */ + reg = acb_readl(priv, ACB_CONTROL); + reg |= (ACB_FLUSH_MASK << ACB_FLUSH_SHIFT); + acb_writel(priv, reg, ACB_CONTROL); + reg &= ~(ACB_FLUSH_MASK << ACB_FLUSH_SHIFT); + reg |= ACB_EN | ACB_ALGORITHM; + acb_writel(priv, reg, ACB_CONTROL); +} + static int bcm_sf2_sw_suspend(struct dsa_switch *ds) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); @@ -655,6 +682,8 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) bcm_sf2_imp_setup(ds, port); } + bcm_sf2_enable_acb(ds); + return 0; } @@ -766,6 +795,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds) } bcm_sf2_sw_configure_vlan(ds); + bcm_sf2_enable_acb(ds); return 0; } diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index d8b8074a47b97..d1596dfca3232 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -115,6 +115,24 @@ enum bcm_sf2_reg_offs { #define P7_IRQ_OFF 0 #define P_IRQ_OFF(x) ((6 - (x)) * P_NUM_IRQ) +/* Register set relative to 'ACB' */ +#define ACB_CONTROL 0x00 +#define ACB_EN (1 << 0) +#define ACB_ALGORITHM (1 << 1) +#define ACB_FLUSH_SHIFT 2 +#define ACB_FLUSH_MASK 0x3 + +#define ACB_QUEUE_0_CFG 0x08 +#define XOFF_THRESHOLD_MASK 0x7ff +#define XON_EN (1 << 11) +#define TOTAL_XOFF_THRESHOLD_SHIFT 12 +#define TOTAL_XOFF_THRESHOLD_MASK 0x7ff +#define TOTAL_XOFF_EN (1 << 23) +#define TOTAL_XON_EN (1 << 24) +#define PKTLEN_SHIFT 25 +#define PKTLEN_MASK 0x3f +#define ACB_QUEUE_CFG(x) (ACB_QUEUE_0_CFG + ((x) * 0x4)) + /* Register set relative to 'CORE' */ #define CORE_G_PCTL_PORT0 0x00000 #define CORE_G_PCTL_PORT(x) (CORE_G_PCTL_PORT0 + (x * 0x4)) @@ -237,6 +255,11 @@ enum bcm_sf2_reg_offs { #define CORE_PORT_VLAN_CTL_PORT(x) (0xc400 + ((x) * 0x8)) #define PORT_VLAN_CTRL_MASK 0x1ff +#define CORE_TXQ_THD_PAUSE_QN_PORT_0 0x2c80 +#define TXQ_PAUSE_THD_MASK 0x7ff +#define CORE_TXQ_THD_PAUSE_QN_PORT(x) (CORE_TXQ_THD_PAUSE_QN_PORT_0 + \ + (x) * 0x8) + #define CORE_DEFAULT_1Q_TAG_P(x) (0xd040 + ((x) * 8)) #define CFI_SHIFT 12 #define PRI_SHIFT 13 -- GitLab From 723934fb792f2dbc76ee3ac334fcde95136bf409 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 10:57:52 -0700 Subject: [PATCH 1294/1507] net: systemport: Turn on ACB at the SYSTEMPORT level Now that we have established the queue mapping between the switch port egress queues and the SYSTEMPORT egress queues, we can turn on Advanced Congestion Buffering (ACB) at the SYSTEMPORT level. This enables the Ethernet MAC controller to get out of band flow control information directly from the switch port and queue that it monitors such that its internal TDMA can be appropriately backpressured. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 78bed9a84e817..dafc266905552 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1422,10 +1422,14 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, reg &= ~(RING_QID_MASK | RING_PORT_ID_MASK << RING_PORT_ID_SHIFT); reg |= ring->switch_queue & RING_QID_MASK; reg |= ring->switch_port << RING_PORT_ID_SHIFT; - reg |= RING_IGNORE_STATUS; tdma_writel(priv, reg, TDMA_DESC_RING_MAPPING(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index)); + /* Enable ACB algorithm 2 */ + reg = tdma_readl(priv, TDMA_CONTROL); + reg |= tdma_control_bit(priv, ACB_ALGO); + tdma_writel(priv, reg, TDMA_CONTROL); + /* Do not use tdma_control_bit() here because TSB_SWAP1 collides * with the original definition of ACB_ALGO */ -- GitLab From d921c420d2efa5731011b922e5a2f2ad33203c0b Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Wed, 11 Oct 2017 13:47:22 +0200 Subject: [PATCH 1295/1507] net/smc: replace function pointer get_netdev() SMC should not open code the function pointer get_netdev of the IB device. Replacing ib_query_gid(..., NULL) with ib_query_gid(..., gid_attr) allows access to the netdev. Signed-off-by: Ursula Braun Suggested-by: Parav Pandit Reviewed-by: Parav Pandit Signed-off-by: David S. Miller --- net/smc/smc_ib.c | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 0b5852299158a..468e1d725d97c 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -369,26 +369,17 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev, static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport) { - struct net_device *ndev; + struct ib_gid_attr gattr; int rc; rc = ib_query_gid(smcibdev->ibdev, ibport, 0, - &smcibdev->gid[ibport - 1], NULL); - /* the SMC protocol requires specification of the roce MAC address; - * if net_device cannot be determined, it can be derived from gid 0 - */ - ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport); - if (ndev) { - memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN); - dev_put(ndev); - } else if (!rc) { - memcpy(&smcibdev->mac[ibport - 1][0], - &smcibdev->gid[ibport - 1].raw[8], 3); - memcpy(&smcibdev->mac[ibport - 1][3], - &smcibdev->gid[ibport - 1].raw[13], 3); - smcibdev->mac[ibport - 1][0] &= ~0x02; - } - return rc; + &smcibdev->gid[ibport - 1], &gattr); + if (rc || !gattr.ndev) + return -ENODEV; + + memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN); + dev_put(gattr.ndev); + return 0; } /* Create an identifier unique for this instance of SMC-R. @@ -419,6 +410,7 @@ int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) &smcibdev->pattr[ibport - 1]); if (rc) goto out; + /* the SMC protocol requires specification of the RoCE MAC address */ rc = smc_ib_fill_gid_and_mac(smcibdev, ibport); if (rc) goto out; -- GitLab From 43e2ada3e06aefe3596be75bd05b34ef14fd1f7c Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Wed, 11 Oct 2017 13:47:23 +0200 Subject: [PATCH 1296/1507] net/smc: dev_put for netdev after usage of ib_query_gid() For RoCEs ib_query_gid() takes a reference count on the net_device. This reference count must be decreased by the caller. Signed-off-by: Ursula Braun Reported-by: Parav Pandit Reviewed-by: Parav Pandit Fixes: 0cfdd8f92cac ("smc: connection and link group creation") Signed-off-by: David S. Miller --- net/smc/smc_core.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 20b66e79c5d63..5f6a20084157b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -380,10 +380,14 @@ static int smc_link_determine_gid(struct smc_link_group *lgr) if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid, &gattr)) continue; - if (gattr.ndev && - (vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id)) { - lnk->gid = gid; - return 0; + if (gattr.ndev) { + if (is_vlan_dev(gattr.ndev) && + vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) { + lnk->gid = gid; + dev_put(gattr.ndev); + return 0; + } + dev_put(gattr.ndev); } } return -ENODEV; -- GitLab From 0eb16f82ecd40d4ce344ec882d6fb5c330f8ef39 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Oct 2017 15:55:31 +0200 Subject: [PATCH 1297/1507] ip_tunnel: fix building with NET_IP_TUNNEL=m When af_mpls is built-in but the tunnel support is a module, we get a link failure: net/mpls/af_mpls.o: In function `mpls_init': af_mpls.c:(.init.text+0xdc): undefined reference to `ip_tunnel_encap_add_ops' This adds a Kconfig statement to prevent the broken configuration and force mpls to be a module as well in this case. Fixes: bdc476413dcd ("ip_tunnel: add mpls over gre support") Signed-off-by: Arnd Bergmann Acked-by: Amine Kherbouche Signed-off-by: David S. Miller --- net/mpls/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 5c467ef973114..801ea90983870 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,6 +24,7 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" + depends on NET_IP_TUNNEL || NET_IP_TUNNEL=n ---help--- Add support for forwarding of mpls packets. -- GitLab From ad2d116c5242875bba27522682ec5ba7f0df75f0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 11:14:49 -0700 Subject: [PATCH 1298/1507] sched: tc_mirred: Remove whitespaces This file contains unnecessary whitespaces as newlines, remove them, found by looking at what struct tc_mirred looks like. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_mirred.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 3d7a2b352a62c..69038c29e8a95 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -9,13 +9,13 @@ #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */ #define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/ #define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */ - + struct tc_mirred { tc_gen; int eaction; /* one of IN/EGRESS_MIRROR/REDIR */ __u32 ifindex; /* ifindex of egress port */ }; - + enum { TCA_MIRRED_UNSPEC, TCA_MIRRED_TM, @@ -24,5 +24,5 @@ enum { __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) - + #endif -- GitLab From 47f25464122bd7aebba35bfb0a26ee24d8026885 Mon Sep 17 00:00:00 2001 From: Christos Gkekas Date: Wed, 11 Oct 2017 20:26:58 +0100 Subject: [PATCH 1299/1507] vxge: Clean up unused variables in vxge-traffic Delete unused channel variables in vxge-traffic. Signed-off-by: Christos Gkekas Signed-off-by: David S. Miller --- .../net/ethernet/neterion/vxge/vxge-traffic.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c index 5f630a24e491e..0c3b5dea2858a 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c @@ -1209,9 +1209,6 @@ void vxge_hw_ring_rxd_pre_post(struct __vxge_hw_ring *ring, void *rxdh) void vxge_hw_ring_rxd_post_post(struct __vxge_hw_ring *ring, void *rxdh) { struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh; - struct __vxge_hw_channel *channel; - - channel = &ring->channel; rxdp->control_0 = VXGE_HW_RING_RXD_LIST_OWN_ADAPTER; @@ -1359,11 +1356,8 @@ enum vxge_hw_status vxge_hw_ring_rxd_next_completed( enum vxge_hw_status vxge_hw_ring_handle_tcode( struct __vxge_hw_ring *ring, void *rxdh, u8 t_code) { - struct __vxge_hw_channel *channel; enum vxge_hw_status status = VXGE_HW_OK; - channel = &ring->channel; - /* If the t_code is not supported and if the * t_code is other than 0x5 (unparseable packet * such as unknown UPV6 header), Drop it !!! @@ -1399,10 +1393,6 @@ enum vxge_hw_status vxge_hw_ring_handle_tcode( static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo, u64 txdl_ptr, u32 num_txds, u32 no_snoop) { - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; - writeq(VXGE_HW_NODBW_TYPE(VXGE_HW_NODBW_TYPE_NODBW) | VXGE_HW_NODBW_LAST_TXD_NUMBER(num_txds) | VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop), @@ -1506,9 +1496,6 @@ void vxge_hw_fifo_txdl_buffer_set(struct __vxge_hw_fifo *fifo, { struct __vxge_hw_fifo_txdl_priv *txdl_priv; struct vxge_hw_fifo_txd *txdp, *txdp_last; - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh); txdp = (struct vxge_hw_fifo_txd *)txdlh + txdl_priv->frags; @@ -1554,9 +1541,6 @@ void vxge_hw_fifo_txdl_post(struct __vxge_hw_fifo *fifo, void *txdlh) struct __vxge_hw_fifo_txdl_priv *txdl_priv; struct vxge_hw_fifo_txd *txdp_last; struct vxge_hw_fifo_txd *txdp_first; - struct __vxge_hw_channel *channel; - - channel = &fifo->channel; txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh); txdp_first = txdlh; @@ -1672,10 +1656,7 @@ enum vxge_hw_status vxge_hw_fifo_handle_tcode(struct __vxge_hw_fifo *fifo, void *txdlh, enum vxge_hw_fifo_tcode t_code) { - struct __vxge_hw_channel *channel; - enum vxge_hw_status status = VXGE_HW_OK; - channel = &fifo->channel; if (((t_code & 0x7) < 0) || ((t_code & 0x7) > 0x4)) { status = VXGE_HW_ERR_INVALID_TCODE; -- GitLab From 8f04748016f3b583e675e0f649d42cfc10812a8b Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Wed, 11 Oct 2017 10:50:29 -0400 Subject: [PATCH 1300/1507] net sched actions: change IFE modules alias names Make style of module alias name consistent with other subsystems in kernel, for example net devices. Fixes: 084e2f6566d2 ("Support to encoding decoding skb mark on IFE action") Fixes: 200e10f46936 ("Support to encoding decoding skb prio on IFE action") Fixes: 408fbc22ef1e ("net sched ife action: Introduce skb tcindex metadata encap decap") Signed-off-by: Roman Mashak Signed-off-by: David S. Miller --- include/net/tc_act/tc_ife.h | 2 +- net/sched/act_ife.c | 2 +- net/sched/act_meta_mark.c | 2 +- net/sched/act_meta_skbprio.c | 2 +- net/sched/act_meta_skbtcindex.c | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 30ba459ddd34c..104578f160623 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -40,7 +40,7 @@ struct tcf_meta_ops { struct module *owner; }; -#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan)) +#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ife-meta-" metan) int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8ccd35825b6b9..791aeee11c7e9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -263,7 +263,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (exists) spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); - request_module("ifemeta%u", metaid); + request_module("ife-meta-%u", metaid); rtnl_lock(); if (exists) spin_lock_bh(&ife->tcf_lock); diff --git a/net/sched/act_meta_mark.c b/net/sched/act_meta_mark.c index 82892170ce4fc..1e3f10e5da996 100644 --- a/net/sched/act_meta_mark.c +++ b/net/sched/act_meta_mark.c @@ -76,4 +76,4 @@ module_exit(ifemark_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb mark metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBMARK); +MODULE_ALIAS_IFE_META("skbmark"); diff --git a/net/sched/act_meta_skbprio.c b/net/sched/act_meta_skbprio.c index 26bf4d86030b9..4033f9fc4d4a5 100644 --- a/net/sched/act_meta_skbprio.c +++ b/net/sched/act_meta_skbprio.c @@ -73,4 +73,4 @@ module_exit(ifeprio_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE skb prio metadata action"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_PRIO); +MODULE_ALIAS_IFE_META("skbprio"); diff --git a/net/sched/act_meta_skbtcindex.c b/net/sched/act_meta_skbtcindex.c index 3b35774ce890c..2ea1f26c9e966 100644 --- a/net/sched/act_meta_skbtcindex.c +++ b/net/sched/act_meta_skbtcindex.c @@ -76,4 +76,4 @@ module_exit(ifetc_index_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2016)"); MODULE_DESCRIPTION("Inter-FE skb tc_index metadata module"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_IFE_META(IFE_META_SKBTCINDEX); +MODULE_ALIAS_IFE_META("tcindex"); -- GitLab From d3f24ba895f0bbbc8ab0ecb03de7daa6eccc7ceb Mon Sep 17 00:00:00 2001 From: Roman Mashak Date: Wed, 11 Oct 2017 10:50:30 -0400 Subject: [PATCH 1301/1507] net sched actions: fix module auto-loading Macro __stringify_1() can stringify a macro argument, however IFE_META_* are enums, so they never expand, however request_module expects an integer in IFE module name, so as a result it always fails to auto-load. Fixes: ef6980b6becb ("introduce IFE action") Signed-off-by: Roman Mashak Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/act_ife.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 791aeee11c7e9..e0bc228c1218e 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -248,6 +248,20 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +static const char *ife_meta_id2name(u32 metaid) +{ + switch (metaid) { + case IFE_META_SKBMARK: + return "skbmark"; + case IFE_META_PRIO: + return "skbprio"; + case IFE_META_TCINDEX: + return "tcindex"; + default: + return "unknown"; + } +} + /* called when adding new meta information * under ife->tcf_lock for existing action */ @@ -263,7 +277,7 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (exists) spin_unlock_bh(&ife->tcf_lock); rtnl_unlock(); - request_module("ife-meta-%u", metaid); + request_module("ife-meta-%s", ife_meta_id2name(metaid)); rtnl_lock(); if (exists) spin_lock_bh(&ife->tcf_lock); -- GitLab From 734534e9a8e537d33d3598fa03b98eb089819961 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Oct 2017 17:16:06 -0400 Subject: [PATCH 1302/1507] sched: act: ife: move encode/decode check to init This patch adds the check of the two possible ife handlings encode and decode to the init callback. The decode value is for usability aspect and used in userspace code only. The current code offers encode else decode only. This patch avoids any other option than this. Signed-off-by: Alexander Aring Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_ife.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index e0bc228c1218e..21c10f5d12476 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -464,6 +464,13 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_IFE_PARMS]); + /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because + * they cannot run as the same time. Check on all other values which + * are not supported right now. + */ + if (parm->flags & ~IFE_ENCODE) + return -EINVAL; + exists = tcf_idr_check(tn, parm->index, a, bind); if (exists && bind) return 0; @@ -786,17 +793,7 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, if (ife->flags & IFE_ENCODE) return tcf_ife_encode(skb, a, res); - if (!(ife->flags & IFE_ENCODE)) - return tcf_ife_decode(skb, a, res); - - pr_info_ratelimited("unknown failure(policy neither de/encode\n"); - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); - tcf_lastuse_update(&ife->tcf_tm); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); - - return TC_ACT_SHOT; + return tcf_ife_decode(skb, a, res); } static int tcf_ife_walker(struct net *net, struct sk_buff *skb, -- GitLab From ced273eacfe1876e2c3c4ea1244a2e386e20eadb Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Oct 2017 17:16:07 -0400 Subject: [PATCH 1303/1507] sched: act: ife: migrate to use per-cpu counters This patch migrates the current counter handling which is protected by a spinlock to a per-cpu counter handling. This reduce the time where the spinlock is being held. Signed-off-by: Alexander Aring Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/act_ife.c | 29 +++++++++++------------------ 1 file changed, 11 insertions(+), 18 deletions(-) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 21c10f5d12476..f59d78918cf93 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -477,7 +477,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, - bind, false); + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -638,19 +638,15 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); - spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -668,14 +664,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); - ife->tcf_qstats.overlimits++; + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { - spin_lock(&ife->tcf_lock); - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -727,23 +721,20 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - spin_lock(&ife->tcf_lock); - bstats_update(&ife->tcf_bstats, skb); + bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ - ife->tcf_qstats.overlimits++; - spin_unlock(&ife->tcf_lock); + qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { - ife->tcf_qstats.drops++; - spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } @@ -752,6 +743,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, ife_meta = ife_encode(skb, metalen); + spin_lock(&ife->tcf_lock); + /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... @@ -763,8 +756,8 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } if (err < 0) { /* too corrupt to keep around if overwritten */ - ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; -- GitLab From aa9fd9a325d51fa0b11153b03b8fefff569fa955 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 11 Oct 2017 17:16:08 -0400 Subject: [PATCH 1304/1507] sched: act: ife: update parameters via rcu handling This patch changes the parameter updating via RCU and not protected by a spinlock anymore. This reduce the time that the spinlock is being held. Signed-off-by: Alexander Aring Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/tc_act/tc_ife.h | 10 ++++- net/sched/act_ife.c | 87 +++++++++++++++++++++++++------------ 2 files changed, 67 insertions(+), 30 deletions(-) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 104578f160623..c7fb99c3f76c0 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -6,12 +6,18 @@ #include #include -struct tcf_ife_info { - struct tc_action common; +struct tcf_ife_params { u8 eth_dst[ETH_ALEN]; u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; + + struct rcu_head rcu; +}; + +struct tcf_ife_info { + struct tc_action common; + struct tcf_ife_params __rcu *params; /* list of metaids allowed */ struct list_head metalist; }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index f59d78918cf93..252ee7d8c731d 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -406,10 +406,14 @@ static void _tcf_ife_cleanup(struct tc_action *a, int bind) static void tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a, bind); spin_unlock_bh(&ife->tcf_lock); + + p = rcu_dereference_protected(ife->params, 1); + kfree_rcu(p, rcu); } /* under ife->tcf_lock for existing action */ @@ -446,6 +450,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_ife_params *p, *p_old; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; @@ -471,24 +476,34 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (parm->flags & ~IFE_ENCODE) return -EINVAL; + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + exists = tcf_idr_check(tn, parm->index, a, bind); - if (exists && bind) + if (exists && bind) { + kfree(p); return 0; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, bind, true); - if (ret) + if (ret) { + kfree(p); return ret; + } ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); - if (!ovr) + if (!ovr) { + kfree(p); return -EEXIST; + } } ife = to_ife(*a); - ife->flags = parm->flags; + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) @@ -499,24 +514,25 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, saddr = nla_data(tb[TCA_IFE_SMAC]); } - if (exists) - spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (parm->flags & IFE_ENCODE) { if (daddr) - ether_addr_copy(ife->eth_dst, daddr); + ether_addr_copy(p->eth_dst, daddr); else - eth_zero_addr(ife->eth_dst); + eth_zero_addr(p->eth_dst); if (saddr) - ether_addr_copy(ife->eth_src, saddr); + ether_addr_copy(p->eth_src, saddr); else - eth_zero_addr(ife->eth_src); + eth_zero_addr(p->eth_src); - ife->eth_type = ife_type; + p->eth_type = ife_type; } + if (exists) + spin_lock_bh(&ife->tcf_lock); + if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -532,6 +548,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } @@ -552,6 +569,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (exists) spin_unlock_bh(&ife->tcf_lock); + kfree(p); return err; } } @@ -559,6 +577,11 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (exists) spin_unlock_bh(&ife->tcf_lock); + p_old = rtnl_dereference(ife->params); + rcu_assign_pointer(ife->params, p); + if (p_old) + kfree_rcu(p_old, rcu); + if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -570,12 +593,13 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); + struct tcf_ife_params *p = rtnl_dereference(ife->params); struct tc_ife opt = { .index = ife->tcf_index, .refcnt = ife->tcf_refcnt - ref, .bindcnt = ife->tcf_bindcnt - bind, .action = ife->tcf_action, - .flags = ife->flags, + .flags = p->flags, }; struct tcf_t t; @@ -586,17 +610,17 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; - if (!is_zero_ether_addr(ife->eth_dst)) { - if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) + if (!is_zero_ether_addr(p->eth_dst)) { + if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } - if (!is_zero_ether_addr(ife->eth_src)) { - if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) + if (!is_zero_ether_addr(p->eth_src)) { + if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } - if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) + if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { @@ -698,7 +722,7 @@ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, - struct tcf_result *res) + struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; @@ -762,19 +786,18 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, } skboff += err; } + spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; - if (!is_zero_ether_addr(ife->eth_src)) - ether_addr_copy(oethh->h_source, ife->eth_src); - if (!is_zero_ether_addr(ife->eth_dst)) - ether_addr_copy(oethh->h_dest, ife->eth_dst); - oethh->h_proto = htons(ife->eth_type); + if (!is_zero_ether_addr(p->eth_src)) + ether_addr_copy(oethh->h_source, p->eth_src); + if (!is_zero_ether_addr(p->eth_dst)) + ether_addr_copy(oethh->h_dest, p->eth_dst); + oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); - spin_unlock(&ife->tcf_lock); - return action; } @@ -782,9 +805,17 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); - - if (ife->flags & IFE_ENCODE) - return tcf_ife_encode(skb, a, res); + struct tcf_ife_params *p; + int ret; + + rcu_read_lock(); + p = rcu_dereference(ife->params); + if (p->flags & IFE_ENCODE) { + ret = tcf_ife_encode(skb, a, res, p); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); return tcf_ife_decode(skb, a, res); } -- GitLab From 32c10bbfe914c76d8802be33c97b59be9582df1b Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 11 Oct 2017 17:16:26 -0700 Subject: [PATCH 1305/1507] ipvlan: always use the current L2 addr of the master If the underlying master ever changes its L2 (e.g. bonding device), then make sure that the IPvlan slaves always emit packets with the current L2 of the master instead of the stale mac addr which was copied during the device creation. The problem can be seen with following script - #!/bin/bash # Create a vEth pair ip link add dev veth0 type veth peer name veth1 ip link set veth0 up ip link set veth1 up ip link show veth0 ip link show veth1 # Create an IPvlan device on one end of this vEth pair. ip link add link veth0 dev ipvl0 type ipvlan mode l2 ip link show ipvl0 # Change the mac-address of the vEth master. ip link set veth0 address 02:11:22:33:44:55 Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 57c3856bab055..3cf67db513e20 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -407,7 +407,7 @@ static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, - saddr ? : dev->dev_addr, len); + saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { @@ -730,6 +730,11 @@ static int ipvlan_device_event(struct notifier_block *unused, ipvlan_adjust_mtu(ipvlan, dev); break; + case NETDEV_CHANGEADDR: + list_for_each_entry(ipvlan, &port->ipvlans, pnode) + ether_addr_copy(ipvlan->dev->dev_addr, dev->dev_addr); + break; + case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; -- GitLab From 2355a6546a053b1c16ebefd6ce1f0cccc00e1da5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 12 Oct 2017 10:21:25 +0200 Subject: [PATCH 1306/1507] net: phy: broadcom: support new device flag for setting master mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some of Broadcom's PHYs run by default in slave mode with Automatic Slave/Master configuration disabled. It stops them from working properly with some devices. So far it has been verified for BCM54210E and BCM50212E which don't work well with Intel's I217-LM and I218-LM: http://ark.intel.com/products/60019/Intel-Ethernet-Connection-I217-LM http://ark.intel.com/products/71307/Intel-Ethernet-Connection-I218-LM I was told there is massive ping loss. This commit adds support for a new flag which can be set by an ethernet driver to fixup PHY setup. Signed-off-by: Rafał Miłecki Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 6 ++++++ include/linux/brcmphy.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 1e9ad30a35c8e..d7ed69deabfbf 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -43,6 +43,12 @@ static int bcm54210e_config_init(struct phy_device *phydev) val &= ~BCM54810_SHD_CLK_CTL_GTXCLK_EN; bcm_phy_write_shadow(phydev, BCM54810_SHD_CLK_CTL, val); + if (phydev->dev_flags & PHY_BRCM_EN_MASTER_MODE) { + val = phy_read(phydev, MII_CTRL1000); + val |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER; + phy_write(phydev, MII_CTRL1000, val); + } + return 0; } diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index abcda9b458ab6..9ac9e3e3d1e59 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -63,6 +63,7 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +#define PHY_BRCM_EN_MASTER_MODE 0x00010000 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- GitLab From 12acd136913ccdf394eeb2bc8686ff5505368119 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 12 Oct 2017 10:21:26 +0200 Subject: [PATCH 1307/1507] net: bgmac: enable master mode for BCM54210E and B50212E PHYs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are 4 very similar PHYs: 0x600d84a1: BCM54210E (rev B0) 0x600d84a2: BCM54210E (rev B1) 0x600d84a5: B50212E (rev B0) 0x600d84a6: B50212E (rev B1) that need setting master mode manually. It's because they run in slave mode by default with Automatic Slave/Master configuration disabled which can lead to unreliable connection with massive ping loss. So far it was reported for a board with BCM47189 SoC and B50212E B1 PHY connected to the bgmac supported ethernet device. Telling PHY driver to setup PHY properly solves this issue. Signed-off-by: Rafał Miłecki Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bgmac-bcma.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 6322594ab2600..6fe074c1588bb 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -184,13 +184,19 @@ static int bgmac_probe(struct bcma_device *core) if (!bgmac_is_bcm4707_family(core) && !(ci->id == BCMA_CHIP_ID_BCM53573 && core->core_unit == 1)) { + struct phy_device *phydev; + mii_bus = bcma_mdio_mii_register(bgmac); if (IS_ERR(mii_bus)) { err = PTR_ERR(mii_bus); goto err; } - bgmac->mii_bus = mii_bus; + + phydev = mdiobus_get_phy(bgmac->mii_bus, bgmac->phyaddr); + if (ci->id == BCMA_CHIP_ID_BCM53573 && phydev && + (phydev->drv->phy_id & phydev->drv->phy_id_mask) == PHY_ID_BCM54210E) + phydev->dev_flags |= PHY_BRCM_EN_MASTER_MODE; } if (core->bus->hosttype == BCMA_HOSTTYPE_PCI) { -- GitLab From ab104615e01c2c4cbe9ea4073a430d51f6547dd2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 12 Oct 2017 10:24:53 +0200 Subject: [PATCH 1308/1507] ravb: Consolidate clock handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The module clock is used for two purposes: - Wake-on-LAN (WoL), which is optional, - gPTP Timer Increment (GTI) configuration, which is mandatory. As the clock is needed for GTI configuration anyway, WoL is always available. Hence remove duplication and repeated obtaining of the clock by making GTI use the stored clock for WoL use. Signed-off-by: Geert Uytterhoeven Reviewed-by: Niklas Söderlund Reviewed-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 35 +++++++----------------- 1 file changed, 10 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index a8822a756e083..2b962d349f5f4 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1354,20 +1354,15 @@ static void ravb_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { struct ravb_private *priv = netdev_priv(ndev); - wol->supported = 0; - wol->wolopts = 0; - - if (priv->clk) { - wol->supported = WAKE_MAGIC; - wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0; - } + wol->supported = WAKE_MAGIC; + wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0; } static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) { struct ravb_private *priv = netdev_priv(ndev); - if (!priv->clk || wol->wolopts & ~WAKE_MAGIC) + if (wol->wolopts & ~WAKE_MAGIC) return -EOPNOTSUPP; priv->wol_enabled = !!(wol->wolopts & WAKE_MAGIC); @@ -1962,22 +1957,12 @@ MODULE_DEVICE_TABLE(of, ravb_match_table); static int ravb_set_gti(struct net_device *ndev) { - + struct ravb_private *priv = netdev_priv(ndev); struct device *dev = ndev->dev.parent; - struct device_node *np = dev->of_node; unsigned long rate; - struct clk *clk; uint64_t inc; - clk = of_clk_get(np, 0); - if (IS_ERR(clk)) { - dev_err(dev, "could not get clock\n"); - return PTR_ERR(clk); - } - - rate = clk_get_rate(clk); - clk_put(clk); - + rate = clk_get_rate(priv->clk); if (!rate) return -EINVAL; @@ -2126,10 +2111,11 @@ static int ravb_probe(struct platform_device *pdev) priv->chip_id = chip_id; - /* Get clock, if not found that's OK but Wake-On-Lan is unavailable */ priv->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(priv->clk)) - priv->clk = NULL; + if (IS_ERR(priv->clk)) { + error = PTR_ERR(priv->clk); + goto out_release; + } /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; @@ -2197,8 +2183,7 @@ static int ravb_probe(struct platform_device *pdev) if (error) goto out_napi_del; - if (priv->clk) - device_set_wakeup_capable(&pdev->dev, 1); + device_set_wakeup_capable(&pdev->dev, 1); /* Print device information */ netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n", -- GitLab From 2d0d21c12dfa3851620f1fa9fe2d444538f1fad4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 12 Oct 2017 11:11:22 +0200 Subject: [PATCH 1309/1507] selftests: rtnetlink: add a small macsec test case Signed-off-by: Florian Westphal Reviewed-by: Sabrina Dubroca Signed-off-by: David S. Miller --- tools/testing/selftests/net/rtnetlink.sh | 42 ++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a8a8cdf726b20..5215493166c98 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -461,6 +461,47 @@ kci_test_encap() ip netns del "$testns" } +kci_test_macsec() +{ + msname="test_macsec0" + ret=0 + + ip macsec help 2>&1 | grep -q "^Usage: ip macsec" + if [ $? -ne 0 ]; then + echo "SKIP: macsec: iproute2 too old" + return 0 + fi + + ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on + check_err $? + if [ $ret -ne 0 ];then + echo "FAIL: can't add macsec interface, skipping test" + return 1 + fi + + ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012 + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" + check_err $? + + ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on key 00 0123456789abcdef0123456789abcdef + check_err $? + + ip macsec show > /dev/null + check_err $? + + ip link del dev "$msname" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: macsec" + return 1 + fi + + echo "PASS: macsec" +} + kci_test_rtnl() { kci_add_dummy @@ -478,6 +519,7 @@ kci_test_rtnl() kci_test_ifalias kci_test_vrf kci_test_encap + kci_test_macsec kci_del_dummy } -- GitLab From 1188e2a9ef223f5c670301d54a6f65d223a87582 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Oct 2017 14:04:30 +0200 Subject: [PATCH 1310/1507] cfg80211: don't print log output for building shipped-certs Building an allmodconfig kernel with 'make -s' now prints a single line: GEN net/wireless/shipped-certs.c Using '$(kecho)' here will skip the output with 'make -s' but otherwise keeps printing it, which is consistent with how we handle all the other output. Fixes: 90a53e4432b1 ("cfg80211: implement regdb signature checking") Signed-off-by: Arnd Bergmann Signed-off-by: Johannes Berg --- net/wireless/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 219baea57e4e0..e585f3f71f778 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -23,7 +23,7 @@ cfg80211-y += extra-certs.o endif $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) - @echo " GEN $@" + @$(kecho) " GEN $@" @echo '#include "reg.h"' > $@ @echo 'const u8 shipped_regdb_certs[] = {' >> $@ @for f in $^ ; do hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ ; done @@ -32,7 +32,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) - @echo " GEN $@" + @$(kecho) " GEN $@" @echo '#include "reg.h"' > $@ @echo 'const u8 extra_regdb_certs[] = {' >> $@ @for f in $^ ; do test -f $$f && hexdump -v -e '1/1 "0x%.2x," "\n"' < $$f >> $@ || true ; done -- GitLab From 88230ef1f31bf2d8fcf42c20e5743ff4b3618a29 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Oct 2017 14:04:31 +0200 Subject: [PATCH 1311/1507] cfg80211: fix CFG80211_EXTRA_REGDB_KEYDIR typo The missing CONFIG_ prefix means this macro is never defined, leading to a possible Kbuild warning: net/wireless/reg.c:666:20: error: 'load_keys_from_buffer' defined but not used [-Werror=unused-function] static void __init load_keys_from_buffer(const u8 *p, unsigned int buflen) When we use the correct symbol, the warning also goes away. Fixes: 90a53e4432b1 ("cfg80211: implement regdb signature checking") Signed-off-by: Arnd Bergmann Signed-off-by: Johannes Berg --- net/wireless/reg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 58319c82ecb34..3871998059de7 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -723,7 +723,7 @@ static int __init load_builtin_regdb_keys(void) #ifdef CONFIG_CFG80211_USE_KERNEL_REGDB_KEYS load_keys_from_buffer(shipped_regdb_certs, shipped_regdb_certs_len); #endif -#ifdef CFG80211_EXTRA_REGDB_KEYDIR +#ifdef CONFIG_CFG80211_EXTRA_REGDB_KEYDIR if (CONFIG_CFG80211_EXTRA_REGDB_KEYDIR[0] != '\0') load_keys_from_buffer(extra_regdb_certs, extra_regdb_certs_len); #endif -- GitLab From b1b1ae2c1c150f8db5d3523c74e81eaf8cae5cbb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 13 Oct 2017 15:26:01 +0300 Subject: [PATCH 1312/1507] mac80211: don't track HT capability changes The code here (more or less accidentally) tracks the HT capability of the AP when connected, and we found at least one AP that erroneously toggles its 20/40 capability bit when changing between 20/40 MHz. The connection to the AP is then broken because we set the 40 MHz disable flag based on this, as soon as it switches to 20 MHz, but because the flag then changed, we disconnect. I'd be inclined to just ignore this issue, since we then reconnect while the AP is in 20 MHz mode and never use 40 MHz with it again, but this code is a bit strange anyway - we don't use the capabilities for anything else. Change the code to simply not track the HT capabilities at all, which assumes that the AP at least sets 20/40 capability when operating in 40 MHz (or higher). If not, rate scaling might end up using only the narrower bandwidth. The new behaviour also mirrors what VHT does, where we only check the VHT operation. Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ee5ca1bc5a20f..e4ededa1909d8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -145,7 +145,6 @@ static u32 ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, - const struct ieee80211_ht_cap *ht_cap, const struct ieee80211_ht_operation *ht_oper, const struct ieee80211_vht_operation *vht_oper, struct cfg80211_chan_def *chandef, bool tracking) @@ -163,20 +162,13 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, chandef->center_freq1 = channel->center_freq; chandef->center_freq2 = 0; - if (!ht_cap || !ht_oper || !sta_ht_cap.ht_supported) { + if (!ht_oper || !sta_ht_cap.ht_supported) { ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; goto out; } chandef->width = NL80211_CHAN_WIDTH_20; - if (!(ht_cap->cap_info & - cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40))) { - ret = IEEE80211_STA_DISABLE_40MHZ; - vht_chandef = *chandef; - goto out; - } - ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, channel->band); /* check that channel matches the right operating channel */ @@ -344,7 +336,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* calculate new channel (type) based on HT/VHT operation IEs */ flags = ieee80211_determine_chantype(sdata, sband, chan, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, true); /* @@ -4312,7 +4304,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= ieee80211_determine_chantype(sdata, sband, cbss->channel, - ht_cap, ht_oper, vht_oper, + ht_oper, vht_oper, &chandef, false); sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), -- GitLab From 14c04493cb77bc38404dbcb39d5ccbb667831ad7 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:17 +0200 Subject: [PATCH 1313/1507] tipc: add ability to order and receive topology events in driver As preparation for introducing communication groups, we add the ability to issue topology subscriptions and receive topology events from kernel space. This will make it possible for group member sockets to keep track of other group members. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/core.h | 5 ++ net/tipc/msg.h | 1 + net/tipc/server.c | 121 +++++++++++++++++++++++++++++++++++----------- net/tipc/server.h | 5 +- net/tipc/socket.c | 32 +++++++----- 5 files changed, 124 insertions(+), 40 deletions(-) diff --git a/net/tipc/core.h b/net/tipc/core.h index 5cc5398be7225..964342689f2c4 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -132,6 +132,11 @@ static inline struct list_head *tipc_nodes(struct net *net) return &tipc_net(net)->node_list; } +static inline struct tipc_server *tipc_topsrv(struct net *net) +{ + return tipc_net(net)->topsrv; +} + static inline unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index c843fd2bc48d2..d058b1c464e99 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -78,6 +78,7 @@ struct plist; #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 #define SOCK_WAKEUP 14 /* pseudo user */ +#define TOP_SRV 15 /* pseudo user */ /* * Message header sizes diff --git a/net/tipc/server.c b/net/tipc/server.c index 3cd6402e812cb..713077536d0ce 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -36,6 +36,8 @@ #include "server.h" #include "core.h" #include "socket.h" +#include "addr.h" +#include "msg.h" #include #include @@ -105,13 +107,11 @@ static void tipc_conn_kref_release(struct kref *kref) kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr)); sock_release(sock); con->sock = NULL; - - spin_lock_bh(&s->idr_lock); - idr_remove(&s->conn_idr, con->conid); - s->idr_in_use--; - spin_unlock_bh(&s->idr_lock); } - + spin_lock_bh(&s->idr_lock); + idr_remove(&s->conn_idr, con->conid); + s->idr_in_use--; + spin_unlock_bh(&s->idr_lock); tipc_clean_outqueues(con); kfree(con); } @@ -197,7 +197,8 @@ static void tipc_close_conn(struct tipc_conn *con) struct tipc_server *s = con->server; if (test_and_clear_bit(CF_CONNECTED, &con->flags)) { - tipc_unregister_callbacks(con); + if (con->sock) + tipc_unregister_callbacks(con); if (con->conid) s->tipc_conn_release(con->conid, con->usr_data); @@ -207,8 +208,8 @@ static void tipc_close_conn(struct tipc_conn *con) * are harmless for us here as we have already deleted this * connection from server connection list. */ - kernel_sock_shutdown(con->sock, SHUT_RDWR); - + if (con->sock) + kernel_sock_shutdown(con->sock, SHUT_RDWR); conn_put(con); } } @@ -487,38 +488,104 @@ void tipc_conn_terminate(struct tipc_server *s, int conid) } } +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid) +{ + struct tipc_subscriber *scbr; + struct tipc_subscr sub; + struct tipc_server *s; + struct tipc_conn *con; + + sub.seq.type = type; + sub.seq.lower = lower; + sub.seq.upper = upper; + sub.timeout = TIPC_WAIT_FOREVER; + sub.filter = TIPC_SUB_PORTS; + *(u32 *)&sub.usr_handle = port; + + con = tipc_alloc_conn(tipc_topsrv(net)); + if (!con) + return false; + + *conid = con->conid; + s = con->server; + scbr = s->tipc_conn_new(*conid); + if (!scbr) { + tipc_close_conn(con); + return false; + } + + con->usr_data = scbr; + con->sock = NULL; + s->tipc_conn_recvmsg(net, *conid, NULL, scbr, &sub, sizeof(sub)); + return true; +} + +void tipc_topsrv_kern_unsubscr(struct net *net, int conid) +{ + struct tipc_conn *con; + + con = tipc_conn_lookup(tipc_topsrv(net), conid); + if (!con) + return; + tipc_close_conn(con); + conn_put(con); +} + +static void tipc_send_kern_top_evt(struct net *net, struct tipc_event *evt) +{ + u32 port = *(u32 *)&evt->s.usr_handle; + u32 self = tipc_own_addr(net); + struct sk_buff_head evtq; + struct sk_buff *skb; + + skb = tipc_msg_create(TOP_SRV, 0, INT_H_SIZE, sizeof(*evt), + self, self, port, port, 0); + if (!skb) + return; + msg_set_dest_droppable(buf_msg(skb), true); + memcpy(msg_data(buf_msg(skb)), evt, sizeof(*evt)); + skb_queue_head_init(&evtq); + __skb_queue_tail(&evtq, skb); + tipc_sk_rcv(net, &evtq); +} + static void tipc_send_to_sock(struct tipc_conn *con) { - int count = 0; struct tipc_server *s = con->server; struct outqueue_entry *e; + struct tipc_event *evt; struct msghdr msg; + int count = 0; int ret; spin_lock_bh(&con->outqueue_lock); while (test_bit(CF_CONNECTED, &con->flags)) { - e = list_entry(con->outqueue.next, struct outqueue_entry, - list); + e = list_entry(con->outqueue.next, struct outqueue_entry, list); if ((struct list_head *) e == &con->outqueue) break; - spin_unlock_bh(&con->outqueue_lock); - memset(&msg, 0, sizeof(msg)); - msg.msg_flags = MSG_DONTWAIT; + spin_unlock_bh(&con->outqueue_lock); - if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { - msg.msg_name = &e->dest; - msg.msg_namelen = sizeof(struct sockaddr_tipc); - } - ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, - e->iov.iov_len); - if (ret == -EWOULDBLOCK || ret == 0) { - cond_resched(); - goto out; - } else if (ret < 0) { - goto send_err; + if (con->sock) { + memset(&msg, 0, sizeof(msg)); + msg.msg_flags = MSG_DONTWAIT; + if (s->type == SOCK_DGRAM || s->type == SOCK_RDM) { + msg.msg_name = &e->dest; + msg.msg_namelen = sizeof(struct sockaddr_tipc); + } + ret = kernel_sendmsg(con->sock, &msg, &e->iov, 1, + e->iov.iov_len); + if (ret == -EWOULDBLOCK || ret == 0) { + cond_resched(); + goto out; + } else if (ret < 0) { + goto send_err; + } + } else { + evt = e->iov.iov_base; + tipc_send_kern_top_evt(s->net, evt); } - /* Don't starve users filling buffers */ if (++count >= MAX_SEND_MSG_COUNT) { cond_resched(); diff --git a/net/tipc/server.h b/net/tipc/server.h index 34f8055afa3b7..2113c9192633a 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -83,13 +83,16 @@ struct tipc_server { int tipc_conn_sendmsg(struct tipc_server *s, int conid, struct sockaddr_tipc *addr, void *data, size_t len); +bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, + u32 lower, u32 upper, int *conid); +void tipc_topsrv_kern_unsubscr(struct net *net, int conid); + /** * tipc_conn_terminate - terminate connection with server * * Note: Must call it in process context since it might sleep */ void tipc_conn_terminate(struct tipc_server *s, int conid); - int tipc_server_start(struct tipc_server *s); void tipc_server_stop(struct tipc_server *s); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index d50edd6e00196..9a7e7b5cf23f5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -896,6 +896,10 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, kfree_skb(skb); } +static void tipc_sk_top_evt(struct tipc_sock *tsk, struct tipc_event *evt) +{ +} + /** * tipc_sendmsg - send message in connectionless manner * @sock: socket structure @@ -1671,20 +1675,24 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); unsigned int limit = rcvbuf_limit(sk, skb); int err = TIPC_OK; - int usr = msg_user(hdr); - u32 onode; - - if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb, xmitq); - return false; - } - if (unlikely(usr == SOCK_WAKEUP)) { - onode = msg_orignode(hdr); + if (unlikely(!msg_isdata(hdr))) { + switch (msg_user(hdr)) { + case CONN_MANAGER: + tipc_sk_proto_rcv(tsk, skb, xmitq); + return false; + case SOCK_WAKEUP: + u32_del(&tsk->cong_links, msg_orignode(hdr)); + tsk->cong_link_cnt--; + sk->sk_write_space(sk); + break; + case TOP_SRV: + tipc_sk_top_evt(tsk, (void *)msg_data(hdr)); + break; + default: + break; + } kfree_skb(skb); - u32_del(&tsk->cong_links, onode); - tsk->cong_link_cnt--; - sk->sk_write_space(sk); return false; } -- GitLab From 23998835be98a6842e5698fa1824f404c7de850d Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:18 +0200 Subject: [PATCH 1314/1507] tipc: improve address sanity check in tipc_connect() The address given to tipc_connect() is not completely sanity checked, under the assumption that this will be done later in the function __tipc_sendmsg() when the address is used there. However, the latter functon will in the next commits serve as caller to several other send functions, so we want to move the corresponding sanity check there to the beginning of that function, before we possibly need to grab the address stored by tipc_connect(). We must therefore be able to trust that this address already has been thoroughly checked. We do this in this commit. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/socket.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 9a7e7b5cf23f5..7659e792ecdbb 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1911,28 +1911,27 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, int previous; int res = 0; + if (destlen != sizeof(struct sockaddr_tipc)) + return -EINVAL; + lock_sock(sk); - /* DGRAM/RDM connect(), just save the destaddr */ - if (tipc_sk_type_connectionless(sk)) { - if (dst->family == AF_UNSPEC) { - memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); - } else if (destlen != sizeof(struct sockaddr_tipc)) { + if (dst->family == AF_UNSPEC) { + memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); + if (!tipc_sk_type_connectionless(sk)) res = -EINVAL; - } else { - memcpy(&tsk->peer, dest, destlen); - } goto exit; + } else if (dst->family != AF_TIPC) { + res = -EINVAL; } - - /* - * Reject connection attempt using multicast address - * - * Note: send_msg() validates the rest of the address fields, - * so there's no need to do it here - */ - if (dst->addrtype == TIPC_ADDR_MCAST) { + if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME) res = -EINVAL; + if (res) + goto exit; + + /* DGRAM/RDM connect(), just save the destaddr */ + if (tipc_sk_type_connectionless(sk)) { + memcpy(&tsk->peer, dest, destlen); goto exit; } -- GitLab From 38077b8ef831daba55913f7e24732b062d0bdebb Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:19 +0200 Subject: [PATCH 1315/1507] tipc: add ability to obtain node availability status from other files In the coming commits, functions at the socket level will need the ability to read the availability status of a given node. We therefore introduce a new function for this purpose, while renaming the existing static function currently having the wanted name. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/node.c | 26 +++++++++++++++++++++----- net/tipc/node.h | 1 + 2 files changed, 22 insertions(+), 5 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index 198dbc7adbe12..6cc1ae6008200 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -157,7 +157,7 @@ static void tipc_node_timeout(unsigned long data); static void tipc_node_fsm_evt(struct tipc_node *n, int evt); static struct tipc_node *tipc_node_find(struct net *net, u32 addr); static void tipc_node_put(struct tipc_node *node); -static bool tipc_node_is_up(struct tipc_node *n); +static bool node_is_up(struct tipc_node *n); struct tipc_sock_conn { u32 port; @@ -657,7 +657,7 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, *slot1 = i; } - if (!tipc_node_is_up(n)) { + if (!node_is_up(n)) { if (tipc_link_peer_is_down(l)) tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT); @@ -717,11 +717,27 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_sk_rcv(n->net, &le->inputq); } -static bool tipc_node_is_up(struct tipc_node *n) +static bool node_is_up(struct tipc_node *n) { return n->active_links[0] != INVALID_BEARER_ID; } +bool tipc_node_is_up(struct net *net, u32 addr) +{ + struct tipc_node *n; + bool retval = false; + + if (in_own_node(net, addr)) + return true; + + n = tipc_node_find(net, addr); + if (!n) + return false; + retval = node_is_up(n); + tipc_node_put(n); + return retval; +} + void tipc_node_check_dest(struct net *net, u32 onode, struct tipc_bearer *b, u16 capabilities, u32 signature, @@ -1149,7 +1165,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node) if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr)) goto attr_msg_full; - if (tipc_node_is_up(node)) + if (node_is_up(node)) if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP)) goto attr_msg_full; @@ -1249,7 +1265,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb) dst = n->addr; if (in_own_node(net, dst)) continue; - if (!tipc_node_is_up(n)) + if (!node_is_up(n)) continue; txskb = pskb_copy(skb, GFP_ATOMIC); if (!txskb) diff --git a/net/tipc/node.h b/net/tipc/node.h index 898c229169841..8db59feb122f8 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -76,6 +76,7 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel); +bool tipc_node_is_up(struct net *net, u32 addr); u16 tipc_node_get_capabilities(struct net *net, u32 addr); int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_node_dump_link(struct sk_buff *skb, struct netlink_callback *cb); -- GitLab From 64ac5f5977df5b276374fb2f051082129f5cdb22 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:20 +0200 Subject: [PATCH 1316/1507] tipc: refactor function filter_rcv() In the following commits we will need to handle multiple incoming and rejected/returned buffers in the function socket.c::filter_rcv(). As a preparation for this, we generalize the function by handling buffer queues instead of individual buffers. We also introduce a help function tipc_skb_reject(), and rename filter_rcv() to tipc_sk_filter_rcv() in line with other functions in socket.c. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/msg.c | 7 ++ net/tipc/msg.h | 2 + net/tipc/socket.c | 161 +++++++++++++++++++++++----------------------- 3 files changed, 89 insertions(+), 81 deletions(-) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 17146c16ee2df..1649d456e22d1 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -666,3 +666,10 @@ void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, } kfree_skb(skb); } + +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) + __skb_queue_tail(xmitq, skb); +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h index d058b1c464e99..be3e38aa9dd25 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -819,6 +819,8 @@ static inline bool msg_is_reset(struct tipc_msg *hdr) struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); +void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, + struct sk_buff_head *xmitq); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 7659e792ecdbb..bc226f5a1be32 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -111,7 +111,7 @@ struct tipc_sock { struct rcu_head rcu; }; -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb); +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); @@ -453,7 +453,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, msg_set_origport(msg, tsk->portid); setup_timer(&sk->sk_timer, tipc_sk_timeout, (unsigned long)tsk); sk->sk_shutdown = 0; - sk->sk_backlog_rcv = tipc_backlog_rcv; + sk->sk_backlog_rcv = tipc_sk_backlog_rcv; sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; @@ -850,16 +850,16 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, } /** - * tipc_sk_proto_rcv - receive a connection mng protocol message + * tipc_sk_conn_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - struct sock *sk = &tsk->sk; - u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); + u32 onode = tsk_own_node(tsk); + struct sock *sk = &tsk->sk; int mtyp = msg_type(hdr); bool conn_cong; @@ -1536,14 +1536,41 @@ static void tipc_sock_destruct(struct sock *sk) __skb_queue_purge(&sk->sk_receive_queue); } +static void tipc_sk_proto_rcv(struct sock *sk, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_msg *hdr = buf_msg(skb); + + switch (msg_user(hdr)) { + case CONN_MANAGER: + tipc_sk_conn_proto_rcv(tsk, skb, xmitq); + return; + case SOCK_WAKEUP: + u32_del(&tsk->cong_links, msg_orignode(hdr)); + tsk->cong_link_cnt--; + sk->sk_write_space(sk); + break; + case TOP_SRV: + tipc_sk_top_evt(tsk, (void *)msg_data(hdr)); + break; + default: + break; + } + + kfree_skb(skb); +} + /** - * filter_connect - Handle all incoming messages for a connection-based socket + * tipc_filter_connect - Handle incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. Set to NULL if buffer is consumed * * Returns true if everything ok, false otherwise */ -static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -1657,7 +1684,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) } /** - * filter_rcv - validate incoming message + * tipc_sk_filter_rcv - validate incoming message * @sk: socket * @skb: pointer to message. * @@ -1666,75 +1693,49 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) * * Called with socket lock already taken * - * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *xmitq) +static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { + bool sk_conn = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); - unsigned int limit = rcvbuf_limit(sk, skb); - int err = TIPC_OK; + struct net *net = sock_net(sk); + struct sk_buff_head inputq; + int limit, err = TIPC_OK; - if (unlikely(!msg_isdata(hdr))) { - switch (msg_user(hdr)) { - case CONN_MANAGER: - tipc_sk_proto_rcv(tsk, skb, xmitq); - return false; - case SOCK_WAKEUP: - u32_del(&tsk->cong_links, msg_orignode(hdr)); - tsk->cong_link_cnt--; - sk->sk_write_space(sk); - break; - case TOP_SRV: - tipc_sk_top_evt(tsk, (void *)msg_data(hdr)); - break; - default: - break; - } - kfree_skb(skb); - return false; - } + TIPC_SKB_CB(skb)->bytes_read = 0; + __skb_queue_head_init(&inputq); + __skb_queue_tail(&inputq, skb); - /* Drop if illegal message type */ - if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) { - kfree_skb(skb); - return false; - } + if (unlikely(!msg_isdata(hdr))) + tipc_sk_proto_rcv(sk, &inputq, xmitq); + else if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) + return kfree_skb(skb); - /* Reject if wrong message type for current socket state */ - if (tipc_sk_type_connectionless(sk)) { - if (msg_connected(hdr)) { + /* Validate and add to receive buffer if there is space */ + while ((skb = __skb_dequeue(&inputq))) { + hdr = buf_msg(skb); + limit = rcvbuf_limit(sk, skb); + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + (!sk_conn && msg_connected(hdr))) err = TIPC_ERR_NO_PORT; - goto reject; - } - } else if (unlikely(!filter_connect(tsk, skb))) { - err = TIPC_ERR_NO_PORT; - goto reject; - } + else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) + err = TIPC_ERR_OVERLOAD; - /* Reject message if there isn't room to queue it */ - if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) { - err = TIPC_ERR_OVERLOAD; - goto reject; + if (unlikely(err)) { + tipc_skb_reject(net, err, skb, xmitq); + err = TIPC_OK; + continue; + } + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); + sk->sk_data_ready(sk); } - - /* Enqueue message */ - TIPC_SKB_CB(skb)->bytes_read = 0; - __skb_queue_tail(&sk->sk_receive_queue, skb); - skb_set_owner_r(skb, sk); - - sk->sk_data_ready(sk); - return true; - -reject: - if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) - __skb_queue_tail(xmitq, skb); - return false; } /** - * tipc_backlog_rcv - handle incoming message from backlog queue + * tipc_sk_backlog_rcv - handle incoming message from backlog queue * @sk: socket * @skb: message * @@ -1742,27 +1743,25 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb, * * Returns 0 */ -static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) +static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - unsigned int truesize = skb->truesize; + unsigned int before = sk_rmem_alloc_get(sk); struct sk_buff_head xmitq; u32 dnode, selector; + unsigned int added; __skb_queue_head_init(&xmitq); - if (likely(filter_rcv(sk, skb, &xmitq))) { - atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); - return 0; - } - - if (skb_queue_empty(&xmitq)) - return 0; + tipc_sk_filter_rcv(sk, skb, &xmitq); + added = sk_rmem_alloc_get(sk) - before; + atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt); - /* Send response/rejected message */ - skb = __skb_dequeue(&xmitq); - dnode = msg_destnode(buf_msg(skb)); - selector = msg_origport(buf_msg(skb)); - tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); + /* Send pending response/rejected messages, if any */ + while ((skb = __skb_dequeue(&xmitq))) { + selector = msg_origport(buf_msg(skb)); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); + } return 0; } @@ -1794,7 +1793,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb, xmitq); + tipc_sk_filter_rcv(sk, skb, xmitq); continue; } -- GitLab From f70d37b796241f617107d5585ee96a7e1b660b63 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:21 +0200 Subject: [PATCH 1317/1507] tipc: add new function for sending multiple small messages We see an increasing need to send multiple single-buffer messages of TIPC_SYSTEM_IMPORTANCE to different individual destination nodes. Instead of looping over the send queue and sending each buffer individually, as we do now, we add a new help function tipc_node_distr_xmit() to do this. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/node.c | 16 ++++++++++++++++ net/tipc/node.h | 1 + net/tipc/socket.c | 14 ++------------ 3 files changed, 19 insertions(+), 12 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6cc1ae6008200..89f8ac73bf65c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1254,6 +1254,22 @@ int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, return 0; } +/* tipc_node_distr_xmit(): send single buffer msgs to individual destinations + * Note: this is only for SYSTEM_IMPORTANCE messages, which cannot be rejected + */ +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + u32 selector, dnode; + + while ((skb = __skb_dequeue(xmitq))) { + selector = msg_origport(buf_msg(skb)); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, selector); + } + return 0; +} + void tipc_node_broadcast(struct net *net, struct sk_buff *skb) { struct sk_buff *txskb; diff --git a/net/tipc/node.h b/net/tipc/node.h index 8db59feb122f8..df2f2197c4ad1 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -68,6 +68,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, int selector); +int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *list); int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, u32 selector); void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index bc226f5a1be32..c7c6749344747 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1740,14 +1740,11 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, * @skb: message * * Caller must hold socket lock - * - * Returns 0 */ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { unsigned int before = sk_rmem_alloc_get(sk); struct sk_buff_head xmitq; - u32 dnode, selector; unsigned int added; __skb_queue_head_init(&xmitq); @@ -1757,11 +1754,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) atomic_add(added, &tipc_sk(sk)->dupl_rcvcnt); /* Send pending response/rejected messages, if any */ - while ((skb = __skb_dequeue(&xmitq))) { - selector = msg_origport(buf_msg(skb)); - dnode = msg_destnode(buf_msg(skb)); - tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); - } + tipc_node_distr_xmit(sock_net(sk), &xmitq); return 0; } @@ -1840,10 +1833,7 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) spin_unlock_bh(&sk->sk_lock.slock); } /* Send pending response/rejected messages, if any */ - while ((skb = __skb_dequeue(&xmitq))) { - dnode = msg_destnode(buf_msg(skb)); - tipc_node_xmit_skb(net, skb, dnode, dport); - } + tipc_node_distr_xmit(sock_net(sk), &xmitq); sock_put(sk); continue; } -- GitLab From a80ae5306a7346d4e52f59462878beb8362f4bbd Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:22 +0200 Subject: [PATCH 1318/1507] tipc: improve destination linked list We often see a need for a linked list of destination identities, sometimes containing a port number, sometimes a node identity, and sometimes both. The currently defined struct u32_list is not generic enough to cover all cases, so we extend it to contain two u32 integers and rename it to struct tipc_dest_list. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/bcast.c | 18 ++++----- net/tipc/name_table.c | 89 ++++++++++++++++++++++--------------------- net/tipc/name_table.h | 22 +++++++---- net/tipc/socket.c | 12 +++--- 4 files changed, 74 insertions(+), 67 deletions(-) diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a140dd4a84afc..329325bd553e4 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -258,20 +258,20 @@ static int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_nlist *dests, u16 *cong_link_cnt) { + struct tipc_dest *dst, *tmp; struct sk_buff_head _pkts; - struct u32_item *n, *tmp; - u32 dst, selector; + u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); skb_queue_head_init(&_pkts); - list_for_each_entry_safe(n, tmp, &dests->list, list) { - dst = n->value; - if (!tipc_msg_pskb_copy(dst, pkts, &_pkts)) + list_for_each_entry_safe(dst, tmp, &dests->list, list) { + dnode = dst->node; + if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts)) return -ENOMEM; /* Any other return value than -ELINKCONG is ignored */ - if (tipc_node_xmit(net, &_pkts, dst, selector) == -ELINKCONG) + if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG) (*cong_link_cnt)++; } return 0; @@ -554,7 +554,7 @@ void tipc_nlist_add(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = true; - else if (u32_push(&nl->list, node)) + else if (tipc_dest_push(&nl->list, node, 0)) nl->remote++; } @@ -562,13 +562,13 @@ void tipc_nlist_del(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = false; - else if (u32_del(&nl->list, node)) + else if (tipc_dest_del(&nl->list, node, 0)) nl->remote--; } void tipc_nlist_purge(struct tipc_nlist *nl) { - u32_list_purge(&nl->list); + tipc_dest_list_purge(&nl->list); nl->remote = 0; nl->local = 0; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bd0aac87b41ac..76bd2777baafa 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -634,7 +634,7 @@ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, info = sseq->info; list_for_each_entry(publ, &info->node_list, node_list) { if (publ->scope <= limit) - u32_push(dports, publ->ref); + tipc_dest_push(dports, 0, publ->ref); } if (info->cluster_list_size != info->node_list_size) @@ -1057,78 +1057,79 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -bool u32_find(struct list_head *l, u32 value) +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return true; + list_for_each_entry(dst, l, list) { + if (dst->value != value) + continue; + return dst; } - return false; + return NULL; } -bool u32_push(struct list_head *l, u32 value) +bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - struct u32_item *item; + u64 value = (u64)node << 32 | port; + struct tipc_dest *dst; - list_for_each_entry(item, l, list) { - if (item->value == value) - return false; - } - item = kmalloc(sizeof(*item), GFP_ATOMIC); - if (unlikely(!item)) + if (tipc_dest_find(l, node, port)) return false; - item->value = value; - list_add(&item->list, l); + dst = kmalloc(sizeof(*dst), GFP_ATOMIC); + if (unlikely(!dst)) + return false; + dst->value = value; + list_add(&dst->list, l); return true; } -u32 u32_pop(struct list_head *l) +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port) { - struct u32_item *item; - u32 value = 0; + struct tipc_dest *dst; if (list_empty(l)) - return 0; - item = list_first_entry(l, typeof(*item), list); - value = item->value; - list_del(&item->list); - kfree(item); - return value; + return false; + dst = list_first_entry(l, typeof(*dst), list); + if (port) + *port = dst->port; + if (node) + *node = dst->node; + list_del(&dst->list); + kfree(dst); + return true; } -bool u32_del(struct list_head *l, u32 value) +bool tipc_dest_del(struct list_head *l, u32 node, u32 port) { - struct u32_item *item, *tmp; + struct tipc_dest *dst; - list_for_each_entry_safe(item, tmp, l, list) { - if (item->value != value) - continue; - list_del(&item->list); - kfree(item); - return true; - } - return false; + dst = tipc_dest_find(l, node, port); + if (!dst) + return false; + list_del(&dst->list); + kfree(dst); + return true; } -void u32_list_purge(struct list_head *l) +void tipc_dest_list_purge(struct list_head *l) { - struct u32_item *item, *tmp; + struct tipc_dest *dst, *tmp; - list_for_each_entry_safe(item, tmp, l, list) { - list_del(&item->list); - kfree(item); + list_for_each_entry_safe(dst, tmp, l, list) { + list_del(&dst->list); + kfree(dst); } } -int u32_list_len(struct list_head *l) +int tipc_dest_list_len(struct list_head *l) { - struct u32_item *item; + struct tipc_dest *dst; int i = 0; - list_for_each_entry(item, l, list) { + list_for_each_entry(dst, l, list) { i++; } return i; diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 6ebdeb1d84a55..d121175a92b51 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -120,16 +120,22 @@ void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); -struct u32_item { +struct tipc_dest { struct list_head list; - u32 value; + union { + struct { + u32 port; + u32 node; + }; + u64 value; + }; }; -bool u32_push(struct list_head *l, u32 value); -u32 u32_pop(struct list_head *l); -bool u32_find(struct list_head *l, u32 value); -bool u32_del(struct list_head *l, u32 value); -void u32_list_purge(struct list_head *l); -int u32_list_len(struct list_head *l); +struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); +bool tipc_dest_push(struct list_head *l, u32 node, u32 port); +bool tipc_dest_pop(struct list_head *l, u32 *node, u32 *port); +bool tipc_dest_del(struct list_head *l, u32 node, u32 port); +void tipc_dest_list_purge(struct list_head *l); +int tipc_dest_list_len(struct list_head *l); #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c7c6749344747..daf7c4df4531d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -565,7 +565,7 @@ static int tipc_release(struct socket *sock) /* Reject any messages that accumulated in backlog queue */ release_sock(sk); - u32_list_purge(&tsk->cong_links); + tipc_dest_list_purge(&tsk->cong_links); tsk->cong_link_cnt = 0; call_rcu(&tsk->rcu, tipc_sk_callback); sock->sk = NULL; @@ -826,8 +826,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, tipc_nametbl_mc_translate(net, msg_nametype(msg), msg_namelower(msg), msg_nameupper(msg), scope, &dports); - portid = u32_pop(&dports); - for (; portid; portid = u32_pop(&dports)) { + while (tipc_dest_pop(&dports, NULL, &portid)) { _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); if (_skb) { msg_set_destport(buf_msg(_skb), portid); @@ -1000,7 +999,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) } /* Block or return if destination link is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !u32_find(clinks, dnode)); + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(clinks, dnode, 0)); if (unlikely(rc)) return rc; @@ -1012,7 +1012,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); if (unlikely(rc == -ELINKCONG)) { - u32_push(clinks, dnode); + tipc_dest_push(clinks, dnode, 0); tsk->cong_link_cnt++; rc = 0; } @@ -1549,7 +1549,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, tipc_sk_conn_proto_rcv(tsk, skb, xmitq); return; case SOCK_WAKEUP: - u32_del(&tsk->cong_links, msg_orignode(hdr)); + tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); tsk->cong_link_cnt--; sk->sk_write_space(sk); break; -- GitLab From 75da2163dbb6af9f2dce1d80056d11d290dd19a5 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:23 +0200 Subject: [PATCH 1319/1507] tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is closed, i.e., sockets which have not joined a group will not be able to send messages to or receive messages from members of the group, and vice versa. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 14 ++ net/tipc/Makefile | 2 +- net/tipc/group.c | 404 ++++++++++++++++++++++++++++++++++++++ net/tipc/group.h | 64 ++++++ net/tipc/link.c | 3 +- net/tipc/msg.h | 50 ++++- net/tipc/name_table.c | 44 +++-- net/tipc/name_table.h | 3 + net/tipc/node.h | 3 +- net/tipc/socket.c | 209 +++++++++++++++++--- 10 files changed, 748 insertions(+), 48 deletions(-) create mode 100644 net/tipc/group.c create mode 100644 net/tipc/group.h diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5351b08c897a2..5f7b2c4a09ab8 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -231,6 +231,20 @@ struct sockaddr_tipc { #define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */ #define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */ #define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */ +#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */ +#define TIPC_GROUP_LEAVE 136 /* No argument */ + +/* + * Flag values + */ +#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */ + +struct tipc_group_req { + __u32 type; /* group id */ + __u32 instance; /* member id */ + __u32 scope; /* zone/cluster/node */ + __u32 flags; +}; /* * Maximum sizes of TIPC bearer-related names (including terminating NULL) diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 31b9f9c529742..a3af73ec0b78a 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -8,7 +8,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o + server.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/group.c b/net/tipc/group.c new file mode 100644 index 0000000000000..3f0e1ce1e3b9a --- /dev/null +++ b/net/tipc/group.c @@ -0,0 +1,404 @@ +/* + * net/tipc/group.c: TIPC group messaging code + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "addr.h" +#include "group.h" +#include "bcast.h" +#include "server.h" +#include "msg.h" +#include "socket.h" +#include "node.h" +#include "name_table.h" +#include "subscr.h" + +#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) +#define ADV_IDLE ADV_UNIT + +enum mbr_state { + MBR_QUARANTINED, + MBR_DISCOVERED, + MBR_JOINING, + MBR_PUBLISHED, + MBR_JOINED, + MBR_LEAVING +}; + +struct tipc_member { + struct rb_node tree_node; + struct list_head list; + u32 node; + u32 port; + enum mbr_state state; + u16 bc_rcv_nxt; +}; + +struct tipc_group { + struct rb_root members; + struct tipc_nlist dests; + struct net *net; + int subid; + u32 type; + u32 instance; + u32 domain; + u32 scope; + u32 portid; + u16 member_cnt; + u16 bc_snd_nxt; + bool loopback; +}; + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq); + +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) +{ + return grp->bc_snd_nxt; +} + +static bool tipc_group_is_receiver(struct tipc_member *m) +{ + return m && m->state >= MBR_JOINED; +} + +int tipc_group_size(struct tipc_group *grp) +{ + return grp->member_cnt; +} + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq) +{ + struct tipc_group *grp; + u32 type = mreq->type; + + grp = kzalloc(sizeof(*grp), GFP_ATOMIC); + if (!grp) + return NULL; + tipc_nlist_init(&grp->dests, tipc_own_addr(net)); + grp->members = RB_ROOT; + grp->net = net; + grp->portid = portid; + grp->domain = addr_domain(net, mreq->scope); + grp->type = type; + grp->instance = mreq->instance; + grp->scope = mreq->scope; + grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) + return grp; + kfree(grp); + return NULL; +} + +void tipc_group_delete(struct net *net, struct tipc_group *grp) +{ + struct rb_root *tree = &grp->members; + struct tipc_member *m, *tmp; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { + tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); + list_del(&m->list); + kfree(m); + } + tipc_node_distr_xmit(net, &xmitq); + tipc_nlist_purge(&grp->dests); + tipc_topsrv_kern_unsubscr(net, grp->subid); + kfree(grp); +} + +struct tipc_member *tipc_group_find_member(struct tipc_group *grp, + u32 node, u32 port) +{ + struct rb_node *n = grp->members.rb_node; + u64 nkey, key = (u64)node << 32 | port; + struct tipc_member *m; + + while (n) { + m = container_of(n, struct tipc_member, tree_node); + nkey = (u64)m->node << 32 | m->port; + if (key < nkey) + n = n->rb_left; + else if (key > nkey) + n = n->rb_right; + else + return m; + } + return NULL; +} + +static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, + u32 node) +{ + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (m->node == node) + return m; + } + return NULL; +} + +static void tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) +{ + u64 nkey, key = (u64)m->node << 32 | m->port; + struct rb_node **n, *parent = NULL; + struct tipc_member *tmp; + + n = &grp->members.rb_node; + while (*n) { + tmp = container_of(*n, struct tipc_member, tree_node); + parent = *n; + tmp = container_of(parent, struct tipc_member, tree_node); + nkey = (u64)tmp->node << 32 | tmp->port; + if (key < nkey) + n = &(*n)->rb_left; + else if (key > nkey) + n = &(*n)->rb_right; + else + return; + } + rb_link_node(&m->tree_node, parent, n); + rb_insert_color(&m->tree_node, &grp->members); +} + +static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, + u32 node, u32 port, + int state) +{ + struct tipc_member *m; + + m = kzalloc(sizeof(*m), GFP_ATOMIC); + if (!m) + return NULL; + INIT_LIST_HEAD(&m->list); + m->node = node; + m->port = port; + grp->member_cnt++; + tipc_group_add_to_tree(grp, m); + tipc_nlist_add(&grp->dests, m->node); + m->state = state; + return m; +} + +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port) +{ + tipc_group_create_member(grp, node, port, MBR_DISCOVERED); +} + +static void tipc_group_delete_member(struct tipc_group *grp, + struct tipc_member *m) +{ + rb_erase(&m->tree_node, &grp->members); + grp->member_cnt--; + list_del_init(&m->list); + + /* If last member on a node, remove node from dest list */ + if (!tipc_group_find_node(grp, m->node)) + tipc_nlist_del(&grp->dests, m->node); + + kfree(m); +} + +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) +{ + return &grp->dests; +} + +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope) +{ + seq->type = grp->type; + seq->lower = grp->instance; + seq->upper = grp->instance; + *scope = grp->scope; +} + +void tipc_group_update_bc_members(struct tipc_group *grp) +{ + grp->bc_snd_nxt++; +} + +/* tipc_group_filter_msg() - determine if we should accept arriving message + */ +void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + struct tipc_member *m; + struct tipc_msg *hdr; + u32 node, port; + int mtyp; + + if (!skb) + return; + + hdr = buf_msg(skb); + mtyp = msg_type(hdr); + node = msg_orignode(hdr); + port = msg_origport(hdr); + + if (!msg_in_group(hdr)) + goto drop; + + m = tipc_group_find_member(grp, node, port); + if (!tipc_group_is_receiver(m)) + goto drop; + + __skb_queue_tail(inputq, skb); + + m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; + return; +drop: + kfree_skb(skb); +} + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr; + struct sk_buff *skb; + + skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, + m->node, tipc_own_addr(grp->net), + m->port, grp->portid, 0); + if (!skb) + return; + + hdr = buf_msg(skb); + if (mtyp == GRP_JOIN_MSG) + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + __skb_queue_tail(xmitq, skb); +} + +void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *xmitq) +{ + u32 node = msg_orignode(hdr); + u32 port = msg_origport(hdr); + struct tipc_member *m; + + if (!grp) + return; + + m = tipc_group_find_member(grp, node, port); + + switch (msg_type(hdr)) { + case GRP_JOIN_MSG: + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_QUARANTINED); + if (!m) + return; + m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); + + /* Wait until PUBLISH event is received */ + if (m->state == MBR_DISCOVERED) + m->state = MBR_JOINING; + else if (m->state == MBR_PUBLISHED) + m->state = MBR_JOINED; + return; + case GRP_LEAVE_MSG: + if (!m) + return; + + /* Wait until WITHDRAW event is received */ + if (m->state != MBR_LEAVING) { + m->state = MBR_LEAVING; + return; + } + /* Otherwise deliver already received WITHDRAW event */ + tipc_group_delete_member(grp, m); + return; + default: + pr_warn("Received unknown GROUP_PROTO message\n"); + } +} + +/* tipc_group_member_evt() - receive and handle a member up/down event + */ +void tipc_group_member_evt(struct tipc_group *grp, + struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_event *evt = (void *)msg_data(hdr); + u32 node = evt->port.node; + u32 port = evt->port.ref; + struct tipc_member *m; + struct net *net; + u32 self; + + if (!grp) + goto drop; + + net = grp->net; + self = tipc_own_addr(net); + if (!grp->loopback && node == self && port == grp->portid) + goto drop; + + m = tipc_group_find_member(grp, node, port); + + if (evt->event == TIPC_PUBLISHED) { + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_DISCOVERED); + if (!m) + goto drop; + + /* Wait if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) + m->state = MBR_PUBLISHED; + else + m->state = MBR_JOINED; + tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); + } else if (evt->event == TIPC_WITHDRAWN) { + if (!m) + goto drop; + + /* Keep back event if more messages might be expected */ + if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) + m->state = MBR_LEAVING; + else + tipc_group_delete_member(grp, m); + } +drop: + kfree_skb(skb); +} diff --git a/net/tipc/group.h b/net/tipc/group.h new file mode 100644 index 0000000000000..9bdf4479fc035 --- /dev/null +++ b/net/tipc/group.h @@ -0,0 +1,64 @@ +/* + * net/tipc/group.h: Include file for TIPC group unicast/multicast functions + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_GROUP_H +#define _TIPC_GROUP_H + +#include "core.h" + +struct tipc_group; +struct tipc_member; +struct tipc_msg; + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq); +void tipc_group_delete(struct net *net, struct tipc_group *grp); +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port); +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp); +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope); +void tipc_group_filter_msg(struct tipc_group *grp, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_member_evt(struct tipc_group *grp, + struct sk_buff *skb, + struct sk_buff_head *xmitq); +void tipc_group_proto_rcv(struct tipc_group *grp, + struct tipc_msg *hdr, + struct sk_buff_head *xmitq); +void tipc_group_update_bc_members(struct tipc_group *grp); +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); +int tipc_group_size(struct tipc_group *grp); +#endif diff --git a/net/tipc/link.c b/net/tipc/link.c index ac0144f532aa6..bd25bff63925d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1046,11 +1046,12 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: - if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) { + if (unlikely(msg_mcast(hdr))) { skb_queue_tail(l->bc_rcvlink->inputq, skb); return true; } case CONN_MANAGER: + case GROUP_PROTOCOL: skb_queue_tail(inputq, skb); return true; case NAME_DISTRIBUTOR: diff --git a/net/tipc/msg.h b/net/tipc/msg.h index be3e38aa9dd25..dad400935405b 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -1,7 +1,7 @@ /* * net/tipc/msg.h: Include file for TIPC message header routines * - * Copyright (c) 2000-2007, 2014-2015 Ericsson AB + * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * @@ -61,10 +61,11 @@ struct plist; /* * Payload message types */ -#define TIPC_CONN_MSG 0 -#define TIPC_MCAST_MSG 1 -#define TIPC_NAMED_MSG 2 -#define TIPC_DIRECT_MSG 3 +#define TIPC_CONN_MSG 0 +#define TIPC_MCAST_MSG 1 +#define TIPC_NAMED_MSG 2 +#define TIPC_DIRECT_MSG 3 +#define TIPC_GRP_BCAST_MSG 4 /* * Internal message users @@ -73,6 +74,7 @@ struct plist; #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 +#define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 @@ -87,6 +89,7 @@ struct plist; #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ +#define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ @@ -252,6 +255,11 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 29, 0x7, n); } +static inline int msg_in_group(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_GRP_BCAST_MSG); +} + static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; @@ -259,7 +267,9 @@ static inline u32 msg_named(struct tipc_msg *m) static inline u32 msg_mcast(struct tipc_msg *m) { - return msg_type(m) == TIPC_MCAST_MSG; + int mtyp = msg_type(m); + + return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) @@ -514,6 +524,12 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 +/* + * Group protocol message types + */ +#define GRP_JOIN_MSG 0 +#define GRP_LEAVE_MSG 1 + /* * Word 1 */ @@ -795,6 +811,28 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +/* Word 10 + */ +static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) +{ + return msg_bits(m, 10, 16, 0xffff); +} + +static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 10, 16, 0xffff, n); +} + static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 76bd2777baafa..114d72bab8272 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -43,6 +43,7 @@ #include "bcast.h" #include "addr.h" #include "node.h" +#include "group.h" #include #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ @@ -596,18 +597,6 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, return ref; } -/** - * tipc_nametbl_mc_translate - find multicast destinations - * - * Creates list of all local ports that overlap the given multicast address; - * also determines if any off-node ports overlap. - * - * Note: Publications with a scope narrower than 'limit' are ignored. - * (i.e. local node-scope publications mustn't receive messages arriving - * from another node, even if the multcast link brought it here) - * - * Returns non-zero if any off-node ports overlap - */ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports) { @@ -679,6 +668,37 @@ void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, rcu_read_unlock(); } +/* tipc_nametbl_build_group - build list of communication group members + */ +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain) +{ + struct sub_seq *sseq, *stop; + struct name_info *info; + struct publication *p; + struct name_seq *seq; + + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (!seq) + goto exit; + + spin_lock_bh(&seq->lock); + sseq = seq->sseqs; + stop = seq->sseqs + seq->first_free; + for (; sseq != stop; sseq++) { + info = sseq->info; + list_for_each_entry(p, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, p->node)) + continue; + tipc_group_add_member(grp, p->node, p->ref); + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); +} + /* * tipc_nametbl_publish - add name publication to network name tables */ diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index d121175a92b51..97646b17a4a25 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -40,6 +40,7 @@ struct tipc_subscription; struct tipc_plist; struct tipc_nlist; +struct tipc_group; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -101,6 +102,8 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports); +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain); void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, u32 upper, u32 domain, struct tipc_nlist *nodes); diff --git a/net/tipc/node.h b/net/tipc/node.h index df2f2197c4ad1..acd58d23a70e3 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -48,7 +48,8 @@ enum { TIPC_BCAST_SYNCH = (1 << 1), TIPC_BCAST_STATE_NACK = (1 << 2), TIPC_BLOCK_FLOWCTL = (1 << 3), - TIPC_BCAST_RCAST = (1 << 4) + TIPC_BCAST_RCAST = (1 << 4), + TIPC_MCAST_GROUPS = (1 << 5) }; #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ diff --git a/net/tipc/socket.c b/net/tipc/socket.c index daf7c4df4531d..64bbf9d036290 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2016, Ericsson AB + * Copyright (c) 2001-2007, 2012-2017, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -45,6 +45,7 @@ #include "socket.h" #include "bcast.h" #include "netlink.h" +#include "group.h" #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */ @@ -78,7 +79,7 @@ enum { * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue * @cong_link_cnt: number of congested links - * @sent_unacked: # messages sent by socket, and not yet acked by peer + * @snt_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer * @peer: 'connected' peer for dgram/rdm * @node: hash table node @@ -109,6 +110,7 @@ struct tipc_sock { struct rhash_head node; struct tipc_mc_method mc_method; struct rcu_head rcu; + struct tipc_group *group; }; static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -123,6 +125,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); +static int tipc_sk_leave(struct tipc_sock *tsk); static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); static int tipc_sk_insert(struct tipc_sock *tsk); static void tipc_sk_remove(struct tipc_sock *tsk); @@ -559,6 +562,7 @@ static int tipc_release(struct socket *sock) __tipc_shutdown(sock, TIPC_ERR_NO_PORT); sk->sk_shutdown = SHUTDOWN_MASK; + tipc_sk_leave(tsk); tipc_sk_withdraw(tsk, 0, NULL); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); @@ -601,7 +605,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, res = tipc_sk_withdraw(tsk, 0, NULL); goto exit; } - + if (tsk->group) { + res = -EACCES; + goto exit; + } if (uaddr_len < sizeof(struct sockaddr_tipc)) { res = -EINVAL; goto exit; @@ -698,6 +705,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; u32 mask = 0; sock_poll_wait(file, sk_sleep(sk), wait); @@ -718,8 +726,9 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, mask |= (POLLIN | POLLRDNORM); break; case TIPC_OPEN: - if (!tsk->cong_link_cnt) - mask |= POLLOUT; + if (!grp || tipc_group_size(grp)) + if (!tsk->cong_link_cnt) + mask |= POLLOUT; if (tipc_sk_type_connectionless(sk) && (!skb_queue_empty(&sk->sk_receive_queue))) mask |= (POLLIN | POLLRDNORM); @@ -757,6 +766,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_nlist dsts; int rc; + if (tsk->group) + return -EACCES; + /* Block or return if any destination link is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); if (unlikely(rc)) @@ -793,6 +805,64 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, return rc ? rc : dlen; } +/** + * tipc_send_group_bcast - send message to all members in communication group + * @sk: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_mc_method *method = &tsk->mc_method; + struct tipc_msg *hdr = &tsk->phdr; + int mtu = tipc_bcast_get_mtu(net); + struct sk_buff_head pkts; + int rc = -EHOSTUNREACH; + + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + + /* Block or return if any destination link is congested */ + rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Complete message header */ + msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + msg_set_hdr_sz(hdr, MCAST_H_SIZE); + msg_set_destport(hdr, 0); + msg_set_destnode(hdr, 0); + msg_set_nameinst(hdr, 0); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_mcast_xmit(net, &pkts, method, dsts, + &tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Update broadcast sequence number */ + tipc_group_update_bc_members(tsk->group); + + return dlen; +} + /** * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets * @arrvq: queue with arriving messages, to be cloned after destination lookup @@ -803,13 +873,15 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq) { - struct tipc_msg *msg; - struct list_head dports; - u32 portid; u32 scope = TIPC_CLUSTER_SCOPE; - struct sk_buff_head tmpq; - uint hsz; + u32 self = tipc_own_addr(net); struct sk_buff *skb, *_skb; + u32 lower = 0, upper = ~0; + struct sk_buff_head tmpq; + u32 portid, oport, onode; + struct list_head dports; + struct tipc_msg *msg; + int hsz; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); @@ -818,14 +890,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { msg = buf_msg(skb); hsz = skb_headroom(skb) + msg_hdr_sz(msg); - - if (in_own_node(net, msg_orignode(msg))) + oport = msg_origport(msg); + onode = msg_orignode(msg); + if (onode == self) scope = TIPC_NODE_SCOPE; /* Create destination port list and message clones: */ - tipc_nametbl_mc_translate(net, - msg_nametype(msg), msg_namelower(msg), - msg_nameupper(msg), scope, &dports); + if (!msg_in_group(msg)) { + lower = msg_namelower(msg); + upper = msg_nameupper(msg); + } + tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper, + scope, &dports); while (tipc_dest_pop(&dports, NULL, &portid)) { _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); if (_skb) { @@ -895,10 +971,6 @@ static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, kfree_skb(skb); } -static void tipc_sk_top_evt(struct tipc_sock *tsk, struct tipc_event *evt) -{ -} - /** * tipc_sendmsg - send message in connectionless manner * @sock: socket structure @@ -934,6 +1006,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); struct list_head *clinks = &tsk->cong_links; bool syn = !tipc_sk_type_connectionless(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; @@ -944,6 +1017,9 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; + if (unlikely(grp)) + return tipc_send_group_bcast(sock, m, dlen, timeout); + if (unlikely(!dest)) { dest = &tsk->peer; if (!syn || dest->family != AF_TIPC) @@ -1543,6 +1619,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, struct sk_buff *skb = __skb_dequeue(inputq); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); + struct tipc_group *grp = tsk->group; switch (msg_user(hdr)) { case CONN_MANAGER: @@ -1553,8 +1630,12 @@ static void tipc_sk_proto_rcv(struct sock *sk, tsk->cong_link_cnt--; sk->sk_write_space(sk); break; + case GROUP_PROTOCOL: + tipc_group_proto_rcv(grp, hdr, xmitq); + break; case TOP_SRV: - tipc_sk_top_evt(tsk, (void *)msg_data(hdr)); + tipc_group_member_evt(tsk->group, skb, xmitq); + skb = NULL; break; default: break; @@ -1699,6 +1780,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, { bool sk_conn = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = buf_msg(skb); struct net *net = sock_net(sk); struct sk_buff_head inputq; @@ -1710,15 +1792,19 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, if (unlikely(!msg_isdata(hdr))) tipc_sk_proto_rcv(sk, &inputq, xmitq); - else if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) + else if (unlikely(msg_type(hdr) > TIPC_GRP_BCAST_MSG)) return kfree_skb(skb); + if (unlikely(grp)) + tipc_group_filter_msg(grp, &inputq, xmitq); + /* Validate and add to receive buffer if there is space */ while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); limit = rcvbuf_limit(sk, skb); if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || - (!sk_conn && msg_connected(hdr))) + (!sk_conn && msg_connected(hdr)) || + (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) err = TIPC_ERR_OVERLOAD; @@ -1837,7 +1923,6 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) sock_put(sk); continue; } - /* No destination socket => dequeue skb if still there */ skb = tipc_skb_dequeue(inputq, dport); if (!skb) @@ -1905,6 +1990,11 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, lock_sock(sk); + if (tsk->group) { + res = -EINVAL; + goto exit; + } + if (dst->family == AF_UNSPEC) { memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); if (!tipc_sk_type_connectionless(sk)) @@ -2341,6 +2431,52 @@ void tipc_sk_rht_destroy(struct net *net) rhashtable_destroy(&tn->sk_rht); } +static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) +{ + struct net *net = sock_net(&tsk->sk); + u32 domain = addr_domain(net, mreq->scope); + struct tipc_group *grp = tsk->group; + struct tipc_msg *hdr = &tsk->phdr; + struct tipc_name_seq seq; + int rc; + + if (mreq->type < TIPC_RESERVED_TYPES) + return -EACCES; + if (grp) + return -EACCES; + grp = tipc_group_create(net, tsk->portid, mreq); + if (!grp) + return -ENOMEM; + tsk->group = grp; + msg_set_lookup_scope(hdr, mreq->scope); + msg_set_nametype(hdr, mreq->type); + msg_set_dest_droppable(hdr, true); + seq.type = mreq->type; + seq.lower = mreq->instance; + seq.upper = seq.lower; + tipc_nametbl_build_group(net, grp, mreq->type, domain); + rc = tipc_sk_publish(tsk, mreq->scope, &seq); + if (rc) + tipc_group_delete(net, grp); + return rc; +} + +static int tipc_sk_leave(struct tipc_sock *tsk) +{ + struct net *net = sock_net(&tsk->sk); + struct tipc_group *grp = tsk->group; + struct tipc_name_seq seq; + int scope; + + if (!grp) + return -EINVAL; + tipc_group_self(grp, &seq, &scope); + tipc_group_delete(net, grp); + tsk->group = NULL; + tipc_sk_withdraw(tsk, scope, &seq); + return 0; +} + /** * tipc_setsockopt - set socket option * @sock: socket structure @@ -2359,6 +2495,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group_req mreq; u32 value = 0; int res = 0; @@ -2374,9 +2511,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_CONN_TIMEOUT: if (ol < sizeof(value)) return -EINVAL; - res = get_user(value, (u32 __user *)ov); - if (res) - return res; + if (get_user(value, (u32 __user *)ov)) + return -EFAULT; + break; + case TIPC_GROUP_JOIN: + if (ol < sizeof(mreq)) + return -EINVAL; + if (copy_from_user(&mreq, ov, sizeof(mreq))) + return -EFAULT; break; default: if (ov || ol) @@ -2409,6 +2551,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, tsk->mc_method.rcast = true; tsk->mc_method.mandatory = true; break; + case TIPC_GROUP_JOIN: + res = tipc_sk_join(tsk, &mreq); + break; + case TIPC_GROUP_LEAVE: + res = tipc_sk_leave(tsk); + break; default: res = -EINVAL; } @@ -2436,7 +2584,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - int len; + struct tipc_name_seq seq; + int len, scope; u32 value; int res; @@ -2470,6 +2619,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; + case TIPC_GROUP_JOIN: + seq.type = 0; + if (tsk->group) + tipc_group_self(tsk->group, &seq, &scope); + value = seq.type; + break; default: res = -EINVAL; } -- GitLab From 31c82a2d9d51fccbb85cbd2be983eb115225301c Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:24 +0200 Subject: [PATCH 1320/1507] tipc: add second source address to recvmsg()/recvfrom() With group communication, it becomes important for a message receiver to identify not only from which socket (identfied by a node:port tuple) the message was sent, but also the logical identity (type:instance) of the sending member. We fix this by adding a second instance of struct sockaddr_tipc to the source address area when a message is read. The extra address struct is filled in with data found in the received message header (type,) and in the local member representation struct (instance.) Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 3 +++ net/tipc/msg.h | 1 + net/tipc/socket.c | 53 +++++++++++++++++++++++++++++++---------------- 3 files changed, 39 insertions(+), 18 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 3f0e1ce1e3b9a..beb214a3420c1 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -61,6 +61,7 @@ struct tipc_member { struct list_head list; u32 node; u32 port; + u32 instance; enum mbr_state state; u16 bc_rcv_nxt; }; @@ -282,6 +283,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!tipc_group_is_receiver(m)) goto drop; + TIPC_SKB_CB(skb)->orig_member = m->instance; __skb_queue_tail(inputq, skb); m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; @@ -388,6 +390,7 @@ void tipc_group_member_evt(struct tipc_group *grp, m->state = MBR_PUBLISHED; else m->state = MBR_JOINED; + m->instance = evt->found_lower; tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); } else if (evt->event == TIPC_WITHDRAWN) { if (!m) diff --git a/net/tipc/msg.h b/net/tipc/msg.h index dad400935405b..e438716d23726 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -100,6 +100,7 @@ struct plist; struct tipc_skb_cb { u32 bytes_read; + u32 orig_member; struct sk_buff *tail; bool validated; u16 chain_imp; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 64bbf9d036290..25ecf1201527e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -62,6 +62,11 @@ enum { TIPC_CONNECTING = TCP_SYN_SENT, }; +struct sockaddr_pair { + struct sockaddr_tipc sock; + struct sockaddr_tipc member; +}; + /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API @@ -1222,26 +1227,38 @@ static void tipc_sk_finish_conn(struct tipc_sock *tsk, u32 peer_port, } /** - * set_orig_addr - capture sender's address for received message + * tipc_sk_set_orig_addr - capture sender's address for received message * @m: descriptor for message info - * @msg: received message header + * @hdr: received message header * * Note: Address is not captured if not requested by receiver. */ -static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) -{ - DECLARE_SOCKADDR(struct sockaddr_tipc *, addr, m->msg_name); - - if (addr) { - addr->family = AF_TIPC; - addr->addrtype = TIPC_ADDR_ID; - memset(&addr->addr, 0, sizeof(addr->addr)); - addr->addr.id.ref = msg_origport(msg); - addr->addr.id.node = msg_orignode(msg); - addr->addr.name.domain = 0; /* could leave uninitialized */ - addr->scope = 0; /* could leave uninitialized */ - m->msg_namelen = sizeof(struct sockaddr_tipc); - } +static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) +{ + DECLARE_SOCKADDR(struct sockaddr_pair *, srcaddr, m->msg_name); + struct tipc_msg *hdr = buf_msg(skb); + + if (!srcaddr) + return; + + srcaddr->sock.family = AF_TIPC; + srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.addr.id.ref = msg_origport(hdr); + srcaddr->sock.addr.id.node = msg_orignode(hdr); + srcaddr->sock.addr.name.domain = 0; + srcaddr->sock.scope = 0; + m->msg_namelen = sizeof(struct sockaddr_tipc); + + if (!msg_in_group(hdr)) + return; + + /* Group message users may also want to know sending member's id */ + srcaddr->member.family = AF_TIPC; + srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.addr.name.name.type = msg_nametype(hdr); + srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; + srcaddr->member.addr.name.domain = 0; + m->msg_namelen = sizeof(*srcaddr); } /** @@ -1432,7 +1449,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, } while (1); /* Collect msg meta data, including error code and rejected data */ - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (unlikely(rc)) goto exit; @@ -1526,7 +1543,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Collect msg meta data, incl. error code and rejected data */ if (!copied) { - set_orig_addr(m, hdr); + tipc_sk_set_orig_addr(m, skb); rc = tipc_sk_anc_data_recv(m, hdr, tsk); if (rc) break; -- GitLab From ae236fb208a6fbbd2e7a6913385e8fb78ac807f8 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:25 +0200 Subject: [PATCH 1321/1507] tipc: receive group membership events via member socket Like with any other service, group members' availability can be subscribed for by connecting to be topology server. However, because the events arrive via a different socket than the member socket, there is a real risk that membership events my arrive out of synch with the actual JOIN/LEAVE action. I.e., it is possible to receive the first messages from a new member before the corresponding JOIN event arrives, just as it is possible to receive the last messages from a leaving member after the LEAVE event has already been received. Since each member socket is internally also subscribing for membership events, we now fix this problem by passing those events on to the user via the member socket. We leverage the already present member synch- ronization protocol to guarantee correct message/event order. An event is delivered to the user as an empty message where the two source addresses identify the new/lost member. Furthermore, we set the MSG_OOB bit in the message flags to mark it as an event. If the event is an indication about a member loss we also set the MSG_EOR bit, so it can be distinguished from a member addition event. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 1 + net/tipc/group.c | 60 ++++++++++++++++++++++++++++++--------- net/tipc/group.h | 2 ++ net/tipc/msg.h | 22 ++++++++++++-- net/tipc/socket.c | 49 ++++++++++++++++++++------------ 5 files changed, 101 insertions(+), 33 deletions(-) diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5f7b2c4a09ab8..ef41c11a7f38c 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -238,6 +238,7 @@ struct sockaddr_tipc { * Flag values */ #define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */ +#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */ struct tipc_group_req { __u32 type; /* group id */ diff --git a/net/tipc/group.c b/net/tipc/group.c index beb214a3420c1..1bfa9348b26d3 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -59,6 +59,7 @@ enum mbr_state { struct tipc_member { struct rb_node tree_node; struct list_head list; + struct sk_buff *event_msg; u32 node; u32 port; u32 instance; @@ -79,6 +80,7 @@ struct tipc_group { u16 member_cnt; u16 bc_snd_nxt; bool loopback; + bool events; }; static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, @@ -117,6 +119,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->instance = mreq->instance; grp->scope = mreq->scope; grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) return grp; kfree(grp); @@ -279,6 +282,13 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!msg_in_group(hdr)) goto drop; + if (mtyp == TIPC_GRP_MEMBER_EVT) { + if (!grp->events) + goto drop; + __skb_queue_tail(inputq, skb); + return; + } + m = tipc_group_find_member(grp, node, port); if (!tipc_group_is_receiver(m)) goto drop; @@ -311,6 +321,7 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, } void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { u32 node = msg_orignode(hdr); @@ -332,10 +343,12 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); /* Wait until PUBLISH event is received */ - if (m->state == MBR_DISCOVERED) + if (m->state == MBR_DISCOVERED) { m->state = MBR_JOINING; - else if (m->state == MBR_PUBLISHED) + } else if (m->state == MBR_PUBLISHED) { m->state = MBR_JOINED; + __skb_queue_tail(inputq, m->event_msg); + } return; case GRP_LEAVE_MSG: if (!m) @@ -347,6 +360,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, return; } /* Otherwise deliver already received WITHDRAW event */ + __skb_queue_tail(inputq, m->event_msg); tipc_group_delete_member(grp, m); return; default: @@ -354,16 +368,17 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, } } -/* tipc_group_member_evt() - receive and handle a member up/down event - */ void tipc_group_member_evt(struct tipc_group *grp, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_event *evt = (void *)msg_data(hdr); + u32 instance = evt->found_lower; u32 node = evt->port.node; u32 port = evt->port.ref; + int event = evt->event; struct tipc_member *m; struct net *net; u32 self; @@ -376,32 +391,51 @@ void tipc_group_member_evt(struct tipc_group *grp, if (!grp->loopback && node == self && port == grp->portid) goto drop; + /* Convert message before delivery to user */ + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_GRP_MEMBER_EVT); + msg_set_origport(hdr, port); + msg_set_orignode(hdr, node); + msg_set_nametype(hdr, grp->type); + msg_set_grp_evt(hdr, event); + m = tipc_group_find_member(grp, node, port); - if (evt->event == TIPC_PUBLISHED) { + if (event == TIPC_PUBLISHED) { if (!m) m = tipc_group_create_member(grp, node, port, MBR_DISCOVERED); if (!m) goto drop; - /* Wait if JOIN message not yet received */ - if (m->state == MBR_DISCOVERED) + /* Hold back event if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) { + m->event_msg = skb; m->state = MBR_PUBLISHED; - else + } else { + __skb_queue_tail(inputq, skb); m->state = MBR_JOINED; - m->instance = evt->found_lower; + } + m->instance = instance; + TIPC_SKB_CB(skb)->orig_member = m->instance; tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); - } else if (evt->event == TIPC_WITHDRAWN) { + } else if (event == TIPC_WITHDRAWN) { if (!m) goto drop; - /* Keep back event if more messages might be expected */ - if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) + TIPC_SKB_CB(skb)->orig_member = m->instance; + + /* Hold back event if more messages might be expected */ + if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) { + m->event_msg = skb; m->state = MBR_LEAVING; - else + } else { + __skb_queue_tail(inputq, skb); tipc_group_delete_member(grp, m); + } } + return; drop: kfree_skb(skb); } diff --git a/net/tipc/group.h b/net/tipc/group.h index 9bdf4479fc035..5d3f10d289678 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -54,9 +54,11 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *xmitq); void tipc_group_member_evt(struct tipc_group *grp, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq); void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq); void tipc_group_update_bc_members(struct tipc_group *grp); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index e438716d23726..1b527b154e465 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -65,7 +65,8 @@ struct plist; #define TIPC_MCAST_MSG 1 #define TIPC_NAMED_MSG 2 #define TIPC_DIRECT_MSG 3 -#define TIPC_GRP_BCAST_MSG 4 +#define TIPC_GRP_MEMBER_EVT 4 +#define TIPC_GRP_BCAST_MSG 5 /* * Internal message users @@ -258,7 +259,14 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) static inline int msg_in_group(struct tipc_msg *m) { - return (msg_type(m) == TIPC_GRP_BCAST_MSG); + int mtyp = msg_type(m); + + return (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MEMBER_EVT); +} + +static inline bool msg_is_grp_evt(struct tipc_msg *m) +{ + return msg_type(m) == TIPC_GRP_MEMBER_EVT; } static inline u32 msg_named(struct tipc_msg *m) @@ -824,6 +832,16 @@ static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) /* Word 10 */ +static inline u16 msg_grp_evt(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x3); +} + +static inline void msg_set_grp_evt(struct tipc_msg *m, int n) +{ + msg_set_bits(m, 10, 0, 0x3, n); +} + static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) { return msg_bits(m, 10, 16, 0xffff); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 25ecf1201527e..0a2eac3091779 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -709,41 +709,43 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_group *grp = tsk->group; - u32 mask = 0; + u32 revents = 0; sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + revents |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + revents |= POLLHUP; switch (sk->sk_state) { case TIPC_ESTABLISHED: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) - mask |= POLLOUT; + revents |= POLLOUT; /* fall thru' */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= (POLLIN | POLLRDNORM); + if (skb) + revents |= POLLIN | POLLRDNORM; break; case TIPC_OPEN: if (!grp || tipc_group_size(grp)) if (!tsk->cong_link_cnt) - mask |= POLLOUT; - if (tipc_sk_type_connectionless(sk) && - (!skb_queue_empty(&sk->sk_receive_queue))) - mask |= (POLLIN | POLLRDNORM); + revents |= POLLOUT; + if (!tipc_sk_type_connectionless(sk)) + break; + if (!skb) + break; + revents |= POLLIN | POLLRDNORM; break; case TIPC_DISCONNECTING: - mask = (POLLIN | POLLRDNORM | POLLHUP); + revents = POLLIN | POLLRDNORM | POLLHUP; break; } - - return mask; + return revents; } /** @@ -1415,11 +1417,12 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buflen, int flags) { struct sock *sk = sock->sk; - struct tipc_sock *tsk = tipc_sk(sk); - struct sk_buff *skb; - struct tipc_msg *hdr; bool connected = !tipc_sk_type_connectionless(sk); + struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct tipc_msg *hdr; + struct sk_buff *skb; + bool grp_evt; long timeout; /* Catch invalid receive requests */ @@ -1443,6 +1446,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); err = msg_errcode(hdr); + grp_evt = msg_is_grp_evt(hdr); if (likely(dlen || err)) break; tsk_advance_rx_queue(sk); @@ -1469,11 +1473,20 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; + /* Mark message as group event if applicable */ + if (unlikely(grp_evt)) { + if (msg_grp_evt(hdr) == TIPC_WITHDRAWN) + m->msg_flags |= MSG_EOR; + m->msg_flags |= MSG_OOB; + copy = 0; + } + /* Caption of data or error code/rejected data was successful */ if (unlikely(flags & MSG_PEEK)) goto exit; tsk_advance_rx_queue(sk); + if (likely(!connected)) goto exit; @@ -1648,10 +1661,10 @@ static void tipc_sk_proto_rcv(struct sock *sk, sk->sk_write_space(sk); break; case GROUP_PROTOCOL: - tipc_group_proto_rcv(grp, hdr, xmitq); + tipc_group_proto_rcv(grp, hdr, inputq, xmitq); break; case TOP_SRV: - tipc_group_member_evt(tsk->group, skb, xmitq); + tipc_group_member_evt(tsk->group, skb, inputq, xmitq); skb = NULL; break; default: -- GitLab From b7d42635517fde2b095deddd0fba37be2302a285 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:26 +0200 Subject: [PATCH 1322/1507] tipc: introduce flow control for group broadcast messages We introduce an end-to-end flow control mechanism for group broadcast messages. This ensures that no messages are ever lost because of destination receive buffer overflow, with minimal impact on performance. For now, the algorithm is based on the assumption that there is only one active transmitter at any moment in time. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 148 ++++++++++++++++++++++++++++++++++++++++++++-- net/tipc/group.h | 11 ++-- net/tipc/msg.h | 5 +- net/tipc/socket.c | 48 +++++++++++---- 4 files changed, 190 insertions(+), 22 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 1bfa9348b26d3..b8ed70abba014 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -46,6 +46,7 @@ #define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) #define ADV_IDLE ADV_UNIT +#define ADV_ACTIVE (ADV_UNIT * 12) enum mbr_state { MBR_QUARANTINED, @@ -59,16 +60,22 @@ enum mbr_state { struct tipc_member { struct rb_node tree_node; struct list_head list; + struct list_head congested; struct sk_buff *event_msg; + struct tipc_group *group; u32 node; u32 port; u32 instance; enum mbr_state state; + u16 advertised; + u16 window; u16 bc_rcv_nxt; + bool usr_pending; }; struct tipc_group { struct rb_root members; + struct list_head congested; struct tipc_nlist dests; struct net *net; int subid; @@ -86,11 +93,24 @@ struct tipc_group { static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq); +static int tipc_group_rcvbuf_limit(struct tipc_group *grp) +{ + int mcnt = grp->member_cnt + 1; + + /* Scale to bytes, considering worst-case truesize/msgsize ratio */ + return mcnt * ADV_ACTIVE * FLOWCTL_BLK_SZ * 4; +} + u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) { return grp->bc_snd_nxt; } +static bool tipc_group_is_enabled(struct tipc_member *m) +{ + return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING; +} + static bool tipc_group_is_receiver(struct tipc_member *m) { return m && m->state >= MBR_JOINED; @@ -111,6 +131,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, if (!grp) return NULL; tipc_nlist_init(&grp->dests, tipc_own_addr(net)); + INIT_LIST_HEAD(&grp->congested); grp->members = RB_ROOT; grp->net = net; grp->portid = portid; @@ -213,6 +234,8 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, if (!m) return NULL; INIT_LIST_HEAD(&m->list); + INIT_LIST_HEAD(&m->congested); + m->group = grp; m->node = node; m->port = port; grp->member_cnt++; @@ -233,6 +256,7 @@ static void tipc_group_delete_member(struct tipc_group *grp, rb_erase(&m->tree_node, &grp->members); grp->member_cnt--; list_del_init(&m->list); + list_del_init(&m->congested); /* If last member on a node, remove node from dest list */ if (!tipc_group_find_node(grp, m->node)) @@ -255,11 +279,59 @@ void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, *scope = grp->scope; } -void tipc_group_update_bc_members(struct tipc_group *grp) +void tipc_group_update_member(struct tipc_member *m, int len) +{ + struct tipc_group *grp = m->group; + struct tipc_member *_m, *tmp; + + if (!tipc_group_is_enabled(m)) + return; + + m->window -= len; + + if (m->window >= ADV_IDLE) + return; + + if (!list_empty(&m->congested)) + return; + + /* Sort member into congested members' list */ + list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { + if (m->window > _m->window) + continue; + list_add_tail(&m->congested, &_m->congested); + return; + } + list_add_tail(&m->congested, &grp->congested); +} + +void tipc_group_update_bc_members(struct tipc_group *grp, int len) { + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (tipc_group_is_enabled(m)) + tipc_group_update_member(m, len); + } grp->bc_snd_nxt++; } +bool tipc_group_bc_cong(struct tipc_group *grp, int len) +{ + struct tipc_member *m; + + if (list_empty(&grp->congested)) + return false; + + m = list_first_entry(&grp->congested, struct tipc_member, congested); + if (m->window >= len) + return false; + + return true; +} + /* tipc_group_filter_msg() - determine if we should accept arriving message */ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, @@ -302,11 +374,36 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, kfree_skb(skb); } +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq) +{ + struct tipc_member *m; + + m = tipc_group_find_member(grp, node, port); + if (!m) + return; + + m->advertised -= blks; + + switch (m->state) { + case MBR_JOINED: + if (m->advertised <= (ADV_ACTIVE - ADV_UNIT)) + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + break; + case MBR_DISCOVERED: + case MBR_JOINING: + case MBR_LEAVING: + default: + break; + } +} + static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq) { struct tipc_msg *hdr; struct sk_buff *skb; + int adv = 0; skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, m->node, tipc_own_addr(grp->net), @@ -314,14 +411,24 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, if (!skb) return; + if (m->state == MBR_JOINED) + adv = ADV_ACTIVE - m->advertised; + hdr = buf_msg(skb); - if (mtyp == GRP_JOIN_MSG) + + if (mtyp == GRP_JOIN_MSG) { msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } else if (mtyp == GRP_ADV_MSG) { + msg_set_adv_win(hdr, adv); + m->advertised += adv; + } __skb_queue_tail(xmitq, skb); } -void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, - struct sk_buff_head *inputq, +void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, + struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { u32 node = msg_orignode(hdr); @@ -341,14 +448,22 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, if (!m) return; m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); + m->window += msg_adv_win(hdr); /* Wait until PUBLISH event is received */ if (m->state == MBR_DISCOVERED) { m->state = MBR_JOINING; } else if (m->state == MBR_PUBLISHED) { m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); __skb_queue_tail(inputq, m->event_msg); } + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); return; case GRP_LEAVE_MSG: if (!m) @@ -361,14 +476,28 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, } /* Otherwise deliver already received WITHDRAW event */ __skb_queue_tail(inputq, m->event_msg); + *usr_wakeup = m->usr_pending; tipc_group_delete_member(grp, m); + list_del_init(&m->congested); + return; + case GRP_ADV_MSG: + if (!m) + return; + m->window += msg_adv_win(hdr); + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + list_del_init(&m->congested); return; default: pr_warn("Received unknown GROUP_PROTO message\n"); } } +/* tipc_group_member_evt() - receive and handle a member up/down event + */ void tipc_group_member_evt(struct tipc_group *grp, + bool *usr_wakeup, + int *sk_rcvbuf, struct sk_buff *skb, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) @@ -416,16 +545,25 @@ void tipc_group_member_evt(struct tipc_group *grp, } else { __skb_queue_tail(inputq, skb); m->state = MBR_JOINED; + *usr_wakeup = true; + m->usr_pending = false; } m->instance = instance; TIPC_SKB_CB(skb)->orig_member = m->instance; tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); + if (m->window < ADV_IDLE) + tipc_group_update_member(m, 0); + else + list_del_init(&m->congested); } else if (event == TIPC_WITHDRAWN) { if (!m) goto drop; TIPC_SKB_CB(skb)->orig_member = m->instance; + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + /* Hold back event if more messages might be expected */ if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) { m->event_msg = skb; @@ -434,7 +572,9 @@ void tipc_group_member_evt(struct tipc_group *grp, __skb_queue_tail(inputq, skb); tipc_group_delete_member(grp, m); } + list_del_init(&m->congested); } + *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); return; drop: kfree_skb(skb); diff --git a/net/tipc/group.h b/net/tipc/group.h index 5d3f10d289678..0e2740e1da901 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -52,15 +52,18 @@ void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); -void tipc_group_member_evt(struct tipc_group *grp, - struct sk_buff *skb, +void tipc_group_member_evt(struct tipc_group *grp, bool *wakeup, + int *sk_rcvbuf, struct sk_buff *skb, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); -void tipc_group_proto_rcv(struct tipc_group *grp, +void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); -void tipc_group_update_bc_members(struct tipc_group *grp); +void tipc_group_update_bc_members(struct tipc_group *grp, int len); +bool tipc_group_bc_cong(struct tipc_group *grp, int len); +void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, + u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); int tipc_group_size(struct tipc_group *grp); #endif diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 1b527b154e465..237d007499f9f 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -538,6 +538,7 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) */ #define GRP_JOIN_MSG 0 #define GRP_LEAVE_MSG 1 +#define GRP_ADV_MSG 2 /* * Word 1 @@ -790,12 +791,12 @@ static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 16, 0xffff, n); } -static inline u32 msg_adv_win(struct tipc_msg *m) +static inline u16 msg_adv_win(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } -static inline void msg_set_adv_win(struct tipc_msg *m, u32 n) +static inline void msg_set_adv_win(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 0, 0xffff, n); } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 0a2eac3091779..50145c95ac966 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -201,6 +201,11 @@ static bool tsk_conn_cong(struct tipc_sock *tsk) return tsk->snt_unacked > tsk->snd_win; } +static u16 tsk_blocks(int len) +{ + return ((len / FLOWCTL_BLK_SZ) + 1); +} + /* tsk_blocks(): translate a buffer size in bytes to number of * advertisable blocks, taking into account the ratio truesize(len)/len * We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ @@ -831,6 +836,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct tipc_group *grp = tsk->group; struct tipc_nlist *dsts = tipc_group_dests(grp); struct tipc_mc_method *method = &tsk->mc_method; + int blks = tsk_blocks(MCAST_H_SIZE + dlen); struct tipc_msg *hdr = &tsk->phdr; int mtu = tipc_bcast_get_mtu(net); struct sk_buff_head pkts; @@ -839,14 +845,15 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, if (!dsts->local && !dsts->remote) return -EHOSTUNREACH; - /* Block or return if any destination link is congested */ - rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); + /* Block or return if any destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && + !tipc_group_bc_cong(grp, blks)); if (unlikely(rc)) return rc; /* Complete message header */ msg_set_type(hdr, TIPC_GRP_BCAST_MSG); - msg_set_hdr_sz(hdr, MCAST_H_SIZE); + msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); msg_set_nameinst(hdr, 0); @@ -864,9 +871,8 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, if (unlikely(rc)) return rc; - /* Update broadcast sequence number */ - tipc_group_update_bc_members(tsk->group); - + /* Update broadcast sequence number and send windows */ + tipc_group_update_bc_members(tsk->group, blks); return dlen; } @@ -1024,7 +1030,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; - if (unlikely(grp)) + if (unlikely(grp && !dest)) return tipc_send_group_bcast(sock, m, dlen, timeout); if (unlikely(!dest)) { @@ -1420,6 +1426,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, bool connected = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct sk_buff_head xmitq; struct tipc_msg *hdr; struct sk_buff *skb; bool grp_evt; @@ -1436,8 +1443,8 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + /* Step rcv queue to first msg with data or error; wait if necessary */ do { - /* Look at first msg in receive queue; wait if necessary */ rc = tipc_wait_for_rcvmsg(sock, &timeout); if (unlikely(rc)) goto exit; @@ -1485,12 +1492,21 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(flags & MSG_PEEK)) goto exit; + /* Send group flow control advertisement when applicable */ + if (tsk->group && msg_in_group(hdr) && !grp_evt) { + skb_queue_head_init(&xmitq); + tipc_group_update_rcv_win(tsk->group, tsk_blocks(hlen + dlen), + msg_orignode(hdr), msg_origport(hdr), + &xmitq); + tipc_node_distr_xmit(sock_net(sk), &xmitq); + } + tsk_advance_rx_queue(sk); if (likely(!connected)) goto exit; - /* Send connection flow control ack when applicable */ + /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); @@ -1650,6 +1666,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); struct tipc_group *grp = tsk->group; + bool wakeup = false; switch (msg_user(hdr)) { case CONN_MANAGER: @@ -1658,19 +1675,23 @@ static void tipc_sk_proto_rcv(struct sock *sk, case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); tsk->cong_link_cnt--; - sk->sk_write_space(sk); + wakeup = true; break; case GROUP_PROTOCOL: - tipc_group_proto_rcv(grp, hdr, inputq, xmitq); + tipc_group_proto_rcv(grp, &wakeup, hdr, inputq, xmitq); break; case TOP_SRV: - tipc_group_member_evt(tsk->group, skb, inputq, xmitq); + tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf, + skb, inputq, xmitq); skb = NULL; break; default: break; } + if (wakeup) + sk->sk_write_space(sk); + kfree_skb(skb); } @@ -1785,6 +1806,9 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); + if (unlikely(msg_in_group(hdr))) + return sk->sk_rcvbuf; + if (unlikely(!msg_connected(hdr))) return sk->sk_rcvbuf << msg_importance(hdr); -- GitLab From 27bd9ec027f396457d1a147043c92ff22fc4c71e Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:27 +0200 Subject: [PATCH 1323/1507] tipc: introduce group unicast messaging We now make it possible to send connectionless unicast messages within a communication group. To send a message, the sender can use either a direct port address, aka port identity, or an indirect port name to be looked up. This type of messages are subject to the same start synchronization and flow control mechanism as group broadcast messages. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 45 ++++++++++++++++++- net/tipc/group.h | 3 ++ net/tipc/msg.h | 3 +- net/tipc/socket.c | 112 +++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 150 insertions(+), 13 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index b8ed70abba014..18440be5b5fc6 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -186,6 +186,17 @@ struct tipc_member *tipc_group_find_member(struct tipc_group *grp, return NULL; } +static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp, + u32 node, u32 port) +{ + struct tipc_member *m; + + m = tipc_group_find_member(grp, node, port); + if (m && tipc_group_is_enabled(m)) + return m; + return NULL; +} + static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, u32 node) { @@ -318,9 +329,39 @@ void tipc_group_update_bc_members(struct tipc_group *grp, int len) grp->bc_snd_nxt++; } -bool tipc_group_bc_cong(struct tipc_group *grp, int len) +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **mbr) { + struct sk_buff_head xmitq; struct tipc_member *m; + int adv, state; + + m = tipc_group_find_dest(grp, dnode, dport); + *mbr = m; + if (!m) + return false; + if (m->usr_pending) + return true; + if (m->window >= len) + return false; + m->usr_pending = true; + + /* If not fully advertised, do it now to prevent mutual blocking */ + adv = m->advertised; + state = m->state; + if (state < MBR_JOINED) + return true; + if (state == MBR_JOINED && adv == ADV_IDLE) + return true; + skb_queue_head_init(&xmitq); + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); + tipc_node_distr_xmit(grp->net, &xmitq); + return true; +} + +bool tipc_group_bc_cong(struct tipc_group *grp, int len) +{ + struct tipc_member *m = NULL; if (list_empty(&grp->congested)) return false; @@ -329,7 +370,7 @@ bool tipc_group_bc_cong(struct tipc_group *grp, int len) if (m->window >= len) return false; - return true; + return tipc_group_cong(grp, m->node, m->port, len, &m); } /* tipc_group_filter_msg() - determine if we should accept arriving message diff --git a/net/tipc/group.h b/net/tipc/group.h index 0e2740e1da901..8f77290bb4158 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -61,9 +61,12 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); void tipc_group_update_bc_members(struct tipc_group *grp, int len); +bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, + int len, struct tipc_member **m); bool tipc_group_bc_cong(struct tipc_group *grp, int len); void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); +void tipc_group_update_member(struct tipc_member *m, int len); int tipc_group_size(struct tipc_group *grp); #endif diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 237d007499f9f..f5033f4a7951e 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -67,6 +67,7 @@ struct plist; #define TIPC_DIRECT_MSG 3 #define TIPC_GRP_MEMBER_EVT 4 #define TIPC_GRP_BCAST_MSG 5 +#define TIPC_GRP_UCAST_MSG 6 /* * Internal message users @@ -261,7 +262,7 @@ static inline int msg_in_group(struct tipc_msg *m) { int mtyp = msg_type(m); - return (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MEMBER_EVT); + return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG; } static inline bool msg_is_grp_evt(struct tipc_msg *m) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 50145c95ac966..e71c8d23acb9f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -817,6 +817,93 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, return rc ? rc : dlen; } +/** + * tipc_send_group_msg - send a message to a member in the group + * @net: network namespace + * @m: message to send + * @mb: group member + * @dnode: destination node + * @dport: destination port + * @dlen: total length of message data + */ +static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, + struct msghdr *m, struct tipc_member *mb, + u32 dnode, u32 dport, int dlen) +{ + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_msg *hdr = &tsk->phdr; + struct sk_buff_head pkts; + int mtu, rc; + + /* Complete message header */ + msg_set_type(hdr, TIPC_GRP_UCAST_MSG); + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_destport(hdr, dport); + msg_set_destnode(hdr, dnode); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + mtu = tipc_node_get_mtu(net, dnode, tsk->portid); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); + if (unlikely(rc == -ELINKCONG)) { + tipc_dest_push(&tsk->cong_links, dnode, 0); + tsk->cong_link_cnt++; + } + + /* Update send window and sequence number */ + tipc_group_update_member(mb, blks); + + return dlen; +} + +/** + * tipc_send_group_unicast - send message to a member in the group + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + struct tipc_member *mb = NULL; + u32 node, port; + int rc; + + node = dest->addr.id.node; + port = dest->addr.id.ref; + if (!port && !node) + return -EHOSTUNREACH; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(&tsk->cong_links, node, 0) && + !tipc_group_cong(grp, node, port, blks, &mb)); + if (unlikely(rc)) + return rc; + + if (unlikely(!mb)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen); + + return rc ? rc : dlen; +} + /** * tipc_send_group_bcast - send message to all members in communication group * @sk: socket structure @@ -1030,8 +1117,20 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; - if (unlikely(grp && !dest)) - return tipc_send_group_bcast(sock, m, dlen, timeout); + if (likely(dest)) { + if (unlikely(m->msg_namelen < sizeof(*dest))) + return -EINVAL; + if (unlikely(dest->family != AF_TIPC)) + return -EINVAL; + } + + if (grp) { + if (!dest) + return tipc_send_group_bcast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_ID) + return tipc_send_group_unicast(sock, m, dlen, timeout); + return -EINVAL; + } if (unlikely(!dest)) { dest = &tsk->peer; @@ -1039,12 +1138,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return -EDESTADDRREQ; } - if (unlikely(m->msg_namelen < sizeof(*dest))) - return -EINVAL; - - if (unlikely(dest->family != AF_TIPC)) - return -EINVAL; - if (unlikely(syn)) { if (sk->sk_state == TIPC_LISTEN) return -EPIPE; @@ -1077,7 +1170,6 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; - } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; msg_set_type(hdr, TIPC_DIRECT_MSG); @@ -1846,7 +1938,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, if (unlikely(!msg_isdata(hdr))) tipc_sk_proto_rcv(sk, &inputq, xmitq); - else if (unlikely(msg_type(hdr) > TIPC_GRP_BCAST_MSG)) + else if (unlikely(msg_type(hdr) > TIPC_GRP_UCAST_MSG)) return kfree_skb(skb); if (unlikely(grp)) -- GitLab From ee106d7f942dabce1352e01c6fe9ca4a720c2331 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:28 +0200 Subject: [PATCH 1324/1507] tipc: introduce group anycast messaging In this commit, we make it possible to send connectionless unicast messages to any member corresponding to the given member identity, when there is more than one such member. The sender must use a TIPC_ADDR_NAME address to achieve this effect. We also perform load balancing between the destinations, i.e., we primarily select one which has advertised sufficient send window to not cause a block/EAGAIN delay, if any. This mechanism is overlayed on the always present round-robin selection. Anycast messages are subject to the same start synchronization and flow control mechanism as group broadcast messages. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 7 ++++ net/tipc/group.h | 3 ++ net/tipc/name_table.c | 41 +++++++++++++++++++++ net/tipc/name_table.h | 3 ++ net/tipc/socket.c | 84 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 138 insertions(+) diff --git a/net/tipc/group.c b/net/tipc/group.c index 18440be5b5fc6..16aaaa97a005c 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -116,6 +116,13 @@ static bool tipc_group_is_receiver(struct tipc_member *m) return m && m->state >= MBR_JOINED; } +u32 tipc_group_exclude(struct tipc_group *grp) +{ + if (!grp->loopback) + return grp->portid; + return 0; +} + int tipc_group_size(struct tipc_group *grp) { return grp->member_cnt; diff --git a/net/tipc/group.h b/net/tipc/group.h index 8f77290bb4158..e432066a211e8 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -49,6 +49,7 @@ void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port); struct tipc_nlist *tipc_group_dests(struct tipc_group *grp); void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, int *scope); +u32 tipc_group_exclude(struct tipc_group *grp); void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); @@ -68,5 +69,7 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); void tipc_group_update_member(struct tipc_member *m, int len); +struct tipc_member *tipc_group_find_sender(struct tipc_group *grp, + u32 node, u32 port); int tipc_group_size(struct tipc_group *grp); #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 114d72bab8272..2856e19e036e7 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -597,6 +597,47 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, return ref; } +bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, + struct list_head *dsts, int *dstcnt, u32 exclude, + bool all) +{ + u32 self = tipc_own_addr(net); + struct publication *publ; + struct name_info *info; + struct name_seq *seq; + struct sub_seq *sseq; + + if (!tipc_in_scope(domain, self)) + return false; + + *dstcnt = 0; + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (unlikely(!seq)) + goto exit; + spin_lock_bh(&seq->lock); + sseq = nameseq_find_subseq(seq, instance); + if (likely(sseq)) { + info = sseq->info; + list_for_each_entry(publ, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, publ->node)) + continue; + if (publ->ref == exclude && publ->node == self) + continue; + tipc_dest_push(dsts, publ->node, publ->ref); + (*dstcnt)++; + if (all) + continue; + list_move_tail(&publ->zone_list, &info->zone_list); + break; + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); + return !list_empty(dsts); +} + int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports) { diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 97646b17a4a25..71926e4294463 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -107,6 +107,9 @@ void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, u32 upper, u32 domain, struct tipc_nlist *nodes); +bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 domain, + struct list_head *dsts, int *dstcnt, u32 exclude, + bool all); struct publication *tipc_nametbl_publish(struct net *net, u32 type, u32 lower, u32 upper, u32 scope, u32 port_ref, u32 key); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e71c8d23acb9f..66165e12d2f47 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -904,6 +904,88 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m, return rc ? rc : dlen; } +/** + * tipc_send_group_anycast - send message to any member with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); + struct list_head *cong_links = &tsk->cong_links; + int blks = tsk_blocks(GROUP_H_SIZE + dlen); + struct tipc_group *grp = tsk->group; + struct tipc_member *first = NULL; + struct tipc_member *mbr = NULL; + struct net *net = sock_net(sk); + u32 node, port, exclude; + u32 type, inst, domain; + struct list_head dsts; + int lookups = 0; + int dstcnt, rc; + bool cong; + + INIT_LIST_HEAD(&dsts); + + type = dest->addr.name.name.type; + inst = dest->addr.name.name.instance; + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + + while (++lookups < 4) { + first = NULL; + + /* Look for a non-congested destination member, if any */ + while (1) { + if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts, + &dstcnt, exclude, false)) + return -EHOSTUNREACH; + tipc_dest_pop(&dsts, &node, &port); + cong = tipc_group_cong(grp, node, port, blks, &mbr); + if (!cong) + break; + if (mbr == first) + break; + if (!first) + first = mbr; + } + + /* Start over if destination was not in member list */ + if (unlikely(!mbr)) + continue; + + if (likely(!cong && !tipc_dest_find(cong_links, node, 0))) + break; + + /* Block or return if destination link or member is congested */ + rc = tipc_wait_for_cond(sock, &timeout, + !tipc_dest_find(cong_links, node, 0) && + !tipc_group_cong(grp, node, port, + blks, &mbr)); + if (unlikely(rc)) + return rc; + + /* Send, unless destination disappeared while waiting */ + if (likely(mbr)) + break; + } + + if (unlikely(lookups >= 4)) + return -EHOSTUNREACH; + + rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen); + + return rc ? rc : dlen; +} + /** * tipc_send_group_bcast - send message to all members in communication group * @sk: socket structure @@ -1127,6 +1209,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (grp) { if (!dest) return tipc_send_group_bcast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_NAME) + return tipc_send_group_anycast(sock, m, dlen, timeout); if (dest->addrtype == TIPC_ADDR_ID) return tipc_send_group_unicast(sock, m, dlen, timeout); return -EINVAL; -- GitLab From 5b8dddb63769587badc50725ec9857caaeba4de0 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:29 +0200 Subject: [PATCH 1325/1507] tipc: introduce group multicast messaging The previously introduced message transport to all group members is based on the tipc multicast service, but is logically a broadcast service within the group, and that is what we call it. We now add functionality for sending messages to all group members having a certain identity. Correspondingly, we call this feature 'group multicast'. The service is using unicast when only one destination is found, otherwise it will use the bearer broadcast service to transfer the messages. In the latter case, the receiving members filter arriving messages by looking at the intended destination instance. If there is no match, the message will be dropped, while still being considered received and read as seen by the flow control mechanism. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 14 +++++++++++- net/tipc/msg.h | 11 ++++++++-- net/tipc/socket.c | 56 +++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 74 insertions(+), 7 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 16aaaa97a005c..ffac2f33fce2b 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -413,10 +413,22 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!tipc_group_is_receiver(m)) goto drop; + m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; + + /* Drop multicast here if not for this member */ + if (mtyp == TIPC_GRP_MCAST_MSG) { + if (msg_nameinst(hdr) != grp->instance) { + m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; + tipc_group_update_rcv_win(grp, msg_blocks(hdr), + node, port, xmitq); + kfree_skb(skb); + return; + } + } + TIPC_SKB_CB(skb)->orig_member = m->instance; __skb_queue_tail(inputq, skb); - m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; return; drop: kfree_skb(skb); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index f5033f4a7951e..d6f98215267ee 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -67,7 +67,8 @@ struct plist; #define TIPC_DIRECT_MSG 3 #define TIPC_GRP_MEMBER_EVT 4 #define TIPC_GRP_BCAST_MSG 5 -#define TIPC_GRP_UCAST_MSG 6 +#define TIPC_GRP_MCAST_MSG 6 +#define TIPC_GRP_UCAST_MSG 7 /* * Internal message users @@ -195,6 +196,11 @@ static inline u32 msg_size(struct tipc_msg *m) return msg_bits(m, 0, 0, 0x1ffff); } +static inline u32 msg_blocks(struct tipc_msg *m) +{ + return (msg_size(m) / 1024) + 1; +} + static inline u32 msg_data_sz(struct tipc_msg *m) { return msg_size(m) - msg_hdr_sz(m); @@ -279,7 +285,8 @@ static inline u32 msg_mcast(struct tipc_msg *m) { int mtyp = msg_type(m); - return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG)); + return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) || + (mtyp == TIPC_GRP_MCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 66165e12d2f47..8fdd969e12bd2 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -999,6 +999,7 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, int dlen, long timeout) { + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); @@ -1021,11 +1022,16 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, return rc; /* Complete message header */ - msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + if (dest) { + msg_set_type(hdr, TIPC_GRP_MCAST_MSG); + msg_set_nameinst(hdr, dest->addr.name.name.instance); + } else { + msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + msg_set_nameinst(hdr, 0); + } msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, 0); msg_set_destnode(hdr, 0); - msg_set_nameinst(hdr, 0); msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); /* Build message as chain of buffers */ @@ -1045,6 +1051,48 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, return dlen; } +/** + * tipc_send_group_mcast - send message to all members with given identity + * @sock: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); + struct tipc_name_seq *seq = &dest->addr.nameseq; + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct net *net = sock_net(sk); + u32 domain, exclude, dstcnt; + struct list_head dsts; + + INIT_LIST_HEAD(&dsts); + + if (seq->lower != seq->upper) + return -ENOTSUPP; + + domain = addr_domain(net, dest->scope); + exclude = tipc_group_exclude(grp); + if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain, + &dsts, &dstcnt, exclude, true)) + return -EHOSTUNREACH; + + if (dstcnt == 1) { + tipc_dest_pop(&dsts, &dest->addr.id.node, &dest->addr.id.ref); + return tipc_send_group_unicast(sock, m, dlen, timeout); + } + + tipc_dest_list_purge(&dsts); + return tipc_send_group_bcast(sock, m, dlen, timeout); +} + /** * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets * @arrvq: queue with arriving messages, to be cloned after destination lookup @@ -1213,6 +1261,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return tipc_send_group_anycast(sock, m, dlen, timeout); if (dest->addrtype == TIPC_ADDR_ID) return tipc_send_group_unicast(sock, m, dlen, timeout); + if (dest->addrtype == TIPC_ADDR_MCAST) + return tipc_send_group_mcast(sock, m, dlen, timeout); return -EINVAL; } @@ -2022,8 +2072,6 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, if (unlikely(!msg_isdata(hdr))) tipc_sk_proto_rcv(sk, &inputq, xmitq); - else if (unlikely(msg_type(hdr) > TIPC_GRP_UCAST_MSG)) - return kfree_skb(skb); if (unlikely(grp)) tipc_group_filter_msg(grp, &inputq, xmitq); -- GitLab From b87a5ea31c935a7f7e11ca85df2ec7917921e96d Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:30 +0200 Subject: [PATCH 1326/1507] tipc: guarantee group unicast doesn't bypass group broadcast Group unicast messages don't follow the same path as broadcast messages, and there is a high risk that unicasts sent from a socket might bypass previously sent broadcasts from the same socket. We fix this by letting all unicast messages carry the sequence number of the next sent broadcast from the same node, but without updating this number at the receiver. This way, a receiver can check and if necessary re-order such messages before they are added to the socket receive buffer. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 87 +++++++++++++++++++++++++++++++++++++++-------- net/tipc/socket.c | 2 ++ 2 files changed, 74 insertions(+), 15 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index ffac2f33fce2b..985e0ce32e8e0 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -62,6 +62,7 @@ struct tipc_member { struct list_head list; struct list_head congested; struct sk_buff *event_msg; + struct sk_buff_head deferredq; struct tipc_group *group; u32 node; u32 port; @@ -253,6 +254,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, return NULL; INIT_LIST_HEAD(&m->list); INIT_LIST_HEAD(&m->congested); + __skb_queue_head_init(&m->deferredq); m->group = grp; m->node = node; m->port = port; @@ -380,29 +382,54 @@ bool tipc_group_bc_cong(struct tipc_group *grp, int len) return tipc_group_cong(grp, m->node, m->port, len, &m); } +/* tipc_group_sort_msg() - sort msg into queue by bcast sequence number + */ +static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) +{ + struct tipc_msg *_hdr, *hdr = buf_msg(skb); + u16 bc_seqno = msg_grp_bc_seqno(hdr); + struct sk_buff *_skb, *tmp; + int mtyp = msg_type(hdr); + + /* Bcast may be bypassed by unicast, - sort it in */ + if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { + skb_queue_walk_safe(defq, _skb, tmp) { + _hdr = buf_msg(_skb); + if (!less(bc_seqno, msg_grp_bc_seqno(_hdr))) + continue; + __skb_queue_before(defq, _skb, skb); + return; + } + /* Bcast was not bypassed, - add to tail */ + } + /* Unicasts are never bypassed, - always add to tail */ + __skb_queue_tail(defq, skb); +} + /* tipc_group_filter_msg() - determine if we should accept arriving message */ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct sk_buff *skb = __skb_dequeue(inputq); + struct sk_buff_head *defq; struct tipc_member *m; struct tipc_msg *hdr; + bool deliver, update; u32 node, port; - int mtyp; + int mtyp, blks; if (!skb) return; hdr = buf_msg(skb); - mtyp = msg_type(hdr); node = msg_orignode(hdr); port = msg_origport(hdr); if (!msg_in_group(hdr)) goto drop; - if (mtyp == TIPC_GRP_MEMBER_EVT) { + if (msg_is_grp_evt(hdr)) { if (!grp->events) goto drop; __skb_queue_tail(inputq, skb); @@ -413,22 +440,52 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!tipc_group_is_receiver(m)) goto drop; - m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; + if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + goto drop; - /* Drop multicast here if not for this member */ - if (mtyp == TIPC_GRP_MCAST_MSG) { - if (msg_nameinst(hdr) != grp->instance) { - m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; - tipc_group_update_rcv_win(grp, msg_blocks(hdr), - node, port, xmitq); - kfree_skb(skb); - return; + TIPC_SKB_CB(skb)->orig_member = m->instance; + defq = &m->deferredq; + tipc_group_sort_msg(skb, defq); + + while ((skb = skb_peek(defq))) { + hdr = buf_msg(skb); + mtyp = msg_type(hdr); + deliver = true; + update = false; + + if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) + break; + + /* Decide what to do with message */ + switch (mtyp) { + case TIPC_GRP_MCAST_MSG: + if (msg_nameinst(hdr) != grp->instance) { + update = true; + deliver = false; + } + /* Fall thru */ + case TIPC_GRP_BCAST_MSG: + m->bc_rcv_nxt++; + break; + case TIPC_GRP_UCAST_MSG: + break; + default: + break; } - } - TIPC_SKB_CB(skb)->orig_member = m->instance; - __skb_queue_tail(inputq, skb); + /* Execute decisions */ + __skb_dequeue(defq); + if (deliver) + __skb_queue_tail(inputq, skb); + else + kfree_skb(skb); + + if (!update) + continue; + blks = msg_blocks(hdr); + tipc_group_update_rcv_win(grp, blks, node, port, xmitq); + } return; drop: kfree_skb(skb); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 8fdd969e12bd2..3276b7a0d4457 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -830,6 +830,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, struct msghdr *m, struct tipc_member *mb, u32 dnode, u32 dport, int dlen) { + u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group); int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_msg *hdr = &tsk->phdr; struct sk_buff_head pkts; @@ -840,6 +841,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, msg_set_hdr_sz(hdr, GROUP_H_SIZE); msg_set_destport(hdr, dport); msg_set_destnode(hdr, dnode); + msg_set_grp_bc_seqno(hdr, bc_snd_nxt); /* Build message as chain of buffers */ skb_queue_head_init(&pkts); -- GitLab From 2f487712b89376fce267223bbb0db93d393d4b09 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:31 +0200 Subject: [PATCH 1327/1507] tipc: guarantee that group broadcast doesn't bypass group unicast We need a mechanism guaranteeing that group unicasts sent out from a socket are not bypassed by later sent broadcasts from the same socket. We do this as follows: - Each time a unicast is sent, we set a the broadcast method for the socket to "replicast" and "mandatory". This forces the first subsequent broadcast message to follow the same network and data path as the preceding unicast to a destination, hence preventing it from overtaking the latter. - In order to make the 'same data path' statement above true, we let group unicasts pass through the multicast link input queue, instead of as previously through the unicast link input queue. - In the first broadcast following a unicast, we set a new header flag, requiring all recipients to immediately acknowledge its reception. - During the period before all the expected acknowledges are received, the socket refuses to accept any more broadcast attempts, i.e., by blocking or returning EAGAIN. This period should typically not be longer than a few microseconds. - When all acknowledges have been received, the sending socket will open up for subsequent broadcasts, this time giving the link layer freedom to itself select the best transmission method. - The forced and/or abrupt transmission method changes described above may lead to broadcasts arriving out of order to the recipients. We remedy this by introducing code that checks and if necessary re-orders such messages at the receiving end. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 47 +++++++++++++++++++++++++++++++++++++++++------ net/tipc/group.h | 4 +--- net/tipc/link.c | 5 ++--- net/tipc/msg.h | 21 +++++++++++++++++++++ net/tipc/socket.c | 34 +++++++++++++++++++++++++++++----- 5 files changed, 94 insertions(+), 17 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 985e0ce32e8e0..eab862e047dc2 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -71,6 +71,7 @@ struct tipc_member { u16 advertised; u16 window; u16 bc_rcv_nxt; + u16 bc_acked; bool usr_pending; }; @@ -87,6 +88,7 @@ struct tipc_group { u32 portid; u16 member_cnt; u16 bc_snd_nxt; + u16 bc_ackers; bool loopback; bool events; }; @@ -258,6 +260,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, m->group = grp; m->node = node; m->port = port; + m->bc_acked = grp->bc_snd_nxt - 1; grp->member_cnt++; tipc_group_add_to_tree(grp, m); tipc_nlist_add(&grp->dests, m->node); @@ -275,6 +278,11 @@ static void tipc_group_delete_member(struct tipc_group *grp, { rb_erase(&m->tree_node, &grp->members); grp->member_cnt--; + + /* Check if we were waiting for replicast ack from this member */ + if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1)) + grp->bc_ackers--; + list_del_init(&m->list); list_del_init(&m->congested); @@ -325,16 +333,23 @@ void tipc_group_update_member(struct tipc_member *m, int len) list_add_tail(&m->congested, &grp->congested); } -void tipc_group_update_bc_members(struct tipc_group *grp, int len) +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) { + u16 prev = grp->bc_snd_nxt - 1; struct tipc_member *m; struct rb_node *n; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); - if (tipc_group_is_enabled(m)) + if (tipc_group_is_enabled(m)) { tipc_group_update_member(m, len); + m->bc_acked = prev; + } } + + /* Mark number of acknowledges to expect, if any */ + if (ack) + grp->bc_ackers = grp->member_cnt; grp->bc_snd_nxt++; } @@ -372,6 +387,10 @@ bool tipc_group_bc_cong(struct tipc_group *grp, int len) { struct tipc_member *m = NULL; + /* If prev bcast was replicast, reject until all receivers have acked */ + if (grp->bc_ackers) + return true; + if (list_empty(&grp->congested)) return false; @@ -391,7 +410,7 @@ static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) struct sk_buff *_skb, *tmp; int mtyp = msg_type(hdr); - /* Bcast may be bypassed by unicast, - sort it in */ + /* Bcast may be bypassed by unicast or other bcast, - sort it in */ if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); @@ -412,10 +431,10 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct sk_buff *skb = __skb_dequeue(inputq); + bool ack, deliver, update; struct sk_buff_head *defq; struct tipc_member *m; struct tipc_msg *hdr; - bool deliver, update; u32 node, port; int mtyp, blks; @@ -451,6 +470,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, hdr = buf_msg(skb); mtyp = msg_type(hdr); deliver = true; + ack = false; update = false; if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) @@ -466,6 +486,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, /* Fall thru */ case TIPC_GRP_BCAST_MSG: m->bc_rcv_nxt++; + ack = msg_grp_bc_ack_req(hdr); break; case TIPC_GRP_UCAST_MSG: break; @@ -480,6 +501,9 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, else kfree_skb(skb); + if (ack) + tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); + if (!update) continue; @@ -540,6 +564,8 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, } else if (mtyp == GRP_ADV_MSG) { msg_set_adv_win(hdr, adv); m->advertised += adv; + } else if (mtyp == GRP_ACK_MSG) { + msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); } __skb_queue_tail(xmitq, skb); } @@ -593,7 +619,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, } /* Otherwise deliver already received WITHDRAW event */ __skb_queue_tail(inputq, m->event_msg); - *usr_wakeup = m->usr_pending; + *usr_wakeup = true; tipc_group_delete_member(grp, m); list_del_init(&m->congested); return; @@ -605,6 +631,15 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, m->usr_pending = false; list_del_init(&m->congested); return; + case GRP_ACK_MSG: + if (!m) + return; + m->bc_acked = msg_grp_bc_acked(hdr); + if (--grp->bc_ackers) + break; + *usr_wakeup = true; + m->usr_pending = false; + return; default: pr_warn("Received unknown GROUP_PROTO message\n"); } @@ -678,7 +713,7 @@ void tipc_group_member_evt(struct tipc_group *grp, TIPC_SKB_CB(skb)->orig_member = m->instance; - *usr_wakeup = m->usr_pending; + *usr_wakeup = true; m->usr_pending = false; /* Hold back event if more messages might be expected */ diff --git a/net/tipc/group.h b/net/tipc/group.h index e432066a211e8..d525e1cd7de5d 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -61,7 +61,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *wakeup, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq); -void tipc_group_update_bc_members(struct tipc_group *grp, int len); +void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack); bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, int len, struct tipc_member **m); bool tipc_group_bc_cong(struct tipc_group *grp, int len); @@ -69,7 +69,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); void tipc_group_update_member(struct tipc_member *m, int len); -struct tipc_member *tipc_group_find_sender(struct tipc_group *grp, - u32 node, u32 port); int tipc_group_size(struct tipc_group *grp); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index bd25bff63925d..70a21499804d0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1046,13 +1046,12 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: - if (unlikely(msg_mcast(hdr))) { + if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { skb_queue_tail(l->bc_rcvlink->inputq, skb); return true; } - case CONN_MANAGER: case GROUP_PROTOCOL: - skb_queue_tail(inputq, skb); + case CONN_MANAGER: return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index d6f98215267ee..52c6a2e01995c 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -547,6 +547,7 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define GRP_JOIN_MSG 0 #define GRP_LEAVE_MSG 1 #define GRP_ADV_MSG 2 +#define GRP_ACK_MSG 3 /* * Word 1 @@ -839,6 +840,16 @@ static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) msg_set_bits(m, 9, 16, 0xffff, n); } +static inline u16 msg_grp_bc_acked(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + /* Word 10 */ static inline u16 msg_grp_evt(struct tipc_msg *m) @@ -851,6 +862,16 @@ static inline void msg_set_grp_evt(struct tipc_msg *m, int n) msg_set_bits(m, 10, 0, 0x3, n); } +static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x1); +} + +static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n) +{ + msg_set_bits(m, 10, 0, 0x1, n); +} + static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) { return msg_bits(m, 10, 16, 0xffff); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3276b7a0d4457..b1f1c3c2b1e2a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -831,6 +831,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, u32 dnode, u32 dport, int dlen) { u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group); + struct tipc_mc_method *method = &tsk->mc_method; int blks = tsk_blocks(GROUP_H_SIZE + dlen); struct tipc_msg *hdr = &tsk->phdr; struct sk_buff_head pkts; @@ -857,9 +858,12 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk, tsk->cong_link_cnt++; } - /* Update send window and sequence number */ + /* Update send window */ tipc_group_update_member(mb, blks); + /* A broadcast sent within next EXPIRE period must follow same path */ + method->rcast = true; + method->mandatory = true; return dlen; } @@ -1008,6 +1012,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct tipc_group *grp = tsk->group; struct tipc_nlist *dsts = tipc_group_dests(grp); struct tipc_mc_method *method = &tsk->mc_method; + bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); struct tipc_msg *hdr = &tsk->phdr; int mtu = tipc_bcast_get_mtu(net); @@ -1036,6 +1041,9 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, msg_set_destnode(hdr, 0); msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + /* Avoid getting stuck with repeated forced replicasts */ + msg_set_grp_bc_ack_req(hdr, ack); + /* Build message as chain of buffers */ skb_queue_head_init(&pkts); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); @@ -1043,13 +1051,17 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, return rc; /* Send message */ - rc = tipc_mcast_xmit(net, &pkts, method, dsts, - &tsk->cong_link_cnt); + rc = tipc_mcast_xmit(net, &pkts, method, dsts, &tsk->cong_link_cnt); if (unlikely(rc)) return rc; /* Update broadcast sequence number and send windows */ - tipc_group_update_bc_members(tsk->group, blks); + tipc_group_update_bc_members(tsk->group, blks, ack); + + /* Broadcast link is now free to choose method for next broadcast */ + method->mandatory = false; + method->expires = jiffies; + return dlen; } @@ -1113,7 +1125,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, u32 portid, oport, onode; struct list_head dports; struct tipc_msg *msg; - int hsz; + int user, mtyp, hsz; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); @@ -1121,6 +1133,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { msg = buf_msg(skb); + user = msg_user(msg); + mtyp = msg_type(msg); + if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { + spin_lock_bh(&inputq->lock); + if (skb_peek(arrvq) == skb) { + __skb_dequeue(arrvq); + __skb_queue_tail(inputq, skb); + } + refcount_dec(&skb->users); + spin_unlock_bh(&inputq->lock); + continue; + } hsz = skb_headroom(skb) + msg_hdr_sz(msg); oport = msg_origport(msg); onode = msg_orignode(msg); -- GitLab From 399574d41963285e72ba28dd46783c96316a81d1 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:32 +0200 Subject: [PATCH 1328/1507] tipc: guarantee delivery of UP event before first broadcast The following scenario is possible: - A user joins a group, and immediately sends out a broadcast message to its members. - The broadcast message, following a different data path than the initial JOIN message sent out during the joining procedure, arrives to a receiver before the latter.. - The receiver drops the message, since it is not ready to accept any messages until the JOIN has arrived. We avoid this by treating group protocol JOIN messages like unicast messages. - We let them pass through the recipient's multicast input queue, just like ordinary unicasts. - We force the first following broadacst to be sent as replicated unicast and being acknowledged by the recipient before accepting any more broadcast transmissions. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/link.c | 7 +++++-- net/tipc/socket.c | 4 ++++ 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index 70a21499804d0..723dd6998684d 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1039,6 +1039,7 @@ int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker, static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *inputq) { + struct sk_buff_head *mc_inputq = l->bc_rcvlink->inputq; struct tipc_msg *hdr = buf_msg(skb); switch (msg_user(hdr)) { @@ -1047,12 +1048,14 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: if (unlikely(msg_in_group(hdr) || msg_mcast(hdr))) { - skb_queue_tail(l->bc_rcvlink->inputq, skb); + skb_queue_tail(mc_inputq, skb); return true; } - case GROUP_PROTOCOL: case CONN_MANAGER: return true; + case GROUP_PROTOCOL: + skb_queue_tail(mc_inputq, skb); + return true; case NAME_DISTRIBUTOR: l->bc_rcvlink->state = LINK_ESTABLISHED; skb_queue_tail(l->namedq, skb); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b1f1c3c2b1e2a..2bbab4fe2f533 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2762,6 +2762,10 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) rc = tipc_sk_publish(tsk, mreq->scope, &seq); if (rc) tipc_group_delete(net, grp); + + /* Eliminate any risk that a broadcast overtakes the sent JOIN */ + tsk->mc_method.rcast = true; + tsk->mc_method.mandatory = true; return rc; } -- GitLab From a3bada70660fb020430135ec8a774ae1ea6bc9a9 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:33 +0200 Subject: [PATCH 1329/1507] tipc: guarantee delivery of last broadcast before DOWN event The following scenario is possible: - A user sends a broadcast message, and thereafter immediately leaves the group. - The LEAVE message, following a different path than the broadcast, arrives ahead of the broadcast, and the sending member is removed from the receiver's list. - The broadcast message arrives, but is dropped because the sender now is unknown to the receipient. We fix this by sequence numbering membership events, just like ordinary unicast messages. Currently, when a JOIN is sent to a peer, it contains a synchronization point, - the sequence number of the next sent broadcast, in order to give the receiver a start synchronization point. We now let even LEAVE messages contain such an "end synchronization" point, so that the recipient can delay the removal of the sending member until it knows that all messages have been received. The received synchronization points are added as sequence numbers to the generated membership events, making it possible to handle them almost the same way as regular unicasts in the receiving filter function. In particular, a DOWN event with a too high sequence number will be kept in the reordering queue until the missing broadcast(s) arrive and have been delivered. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 45 ++++++++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 13 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index eab862e047dc2..8f0eb5d22e8f9 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -71,6 +71,7 @@ struct tipc_member { u16 advertised; u16 window; u16 bc_rcv_nxt; + u16 bc_syncpt; u16 bc_acked; bool usr_pending; }; @@ -410,7 +411,7 @@ static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) struct sk_buff *_skb, *tmp; int mtyp = msg_type(hdr); - /* Bcast may be bypassed by unicast or other bcast, - sort it in */ + /* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */ if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); @@ -431,7 +432,7 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct sk_buff *skb = __skb_dequeue(inputq); - bool ack, deliver, update; + bool ack, deliver, update, leave = false; struct sk_buff_head *defq; struct tipc_member *m; struct tipc_msg *hdr; @@ -448,13 +449,6 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!msg_in_group(hdr)) goto drop; - if (msg_is_grp_evt(hdr)) { - if (!grp->events) - goto drop; - __skb_queue_tail(inputq, skb); - return; - } - m = tipc_group_find_member(grp, node, port); if (!tipc_group_is_receiver(m)) goto drop; @@ -490,6 +484,12 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, break; case TIPC_GRP_UCAST_MSG: break; + case TIPC_GRP_MEMBER_EVT: + if (m->state == MBR_LEAVING) + leave = true; + if (!grp->events) + deliver = false; + break; default: break; } @@ -504,6 +504,11 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (ack) tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); + if (leave) { + tipc_group_delete_member(grp, m); + __skb_queue_purge(defq); + break; + } if (!update) continue; @@ -561,6 +566,8 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); msg_set_adv_win(hdr, adv); m->advertised += adv; + } else if (mtyp == GRP_LEAVE_MSG) { + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); } else if (mtyp == GRP_ADV_MSG) { msg_set_adv_win(hdr, adv); m->advertised += adv; @@ -577,6 +584,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, u32 node = msg_orignode(hdr); u32 port = msg_origport(hdr); struct tipc_member *m; + struct tipc_msg *ehdr; if (!grp) return; @@ -590,7 +598,8 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, MBR_QUARANTINED); if (!m) return; - m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); + m->bc_syncpt = msg_grp_bc_syncpt(hdr); + m->bc_rcv_nxt = m->bc_syncpt; m->window += msg_adv_win(hdr); /* Wait until PUBLISH event is received */ @@ -601,6 +610,8 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, *usr_wakeup = true; m->usr_pending = false; tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); } if (m->window < ADV_IDLE) @@ -611,6 +622,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, case GRP_LEAVE_MSG: if (!m) return; + m->bc_syncpt = msg_grp_bc_syncpt(hdr); /* Wait until WITHDRAW event is received */ if (m->state != MBR_LEAVING) { @@ -618,9 +630,10 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, return; } /* Otherwise deliver already received WITHDRAW event */ + ehdr = buf_msg(m->event_msg); + msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); *usr_wakeup = true; - tipc_group_delete_member(grp, m); list_del_init(&m->congested); return; case GRP_ADV_MSG: @@ -662,6 +675,7 @@ void tipc_group_member_evt(struct tipc_group *grp, int event = evt->event; struct tipc_member *m; struct net *net; + bool node_up; u32 self; if (!grp) @@ -695,6 +709,7 @@ void tipc_group_member_evt(struct tipc_group *grp, m->event_msg = skb; m->state = MBR_PUBLISHED; } else { + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); __skb_queue_tail(inputq, skb); m->state = MBR_JOINED; *usr_wakeup = true; @@ -715,14 +730,18 @@ void tipc_group_member_evt(struct tipc_group *grp, *usr_wakeup = true; m->usr_pending = false; + node_up = tipc_node_is_up(net, node); /* Hold back event if more messages might be expected */ - if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) { + if (m->state != MBR_LEAVING && node_up) { m->event_msg = skb; m->state = MBR_LEAVING; } else { + if (node_up) + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + else + msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt); __skb_queue_tail(inputq, skb); - tipc_group_delete_member(grp, m); } list_del_init(&m->congested); } -- GitLab From 04d7b574b245c66001a33cb9da2c0311063af73f Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:34 +0200 Subject: [PATCH 1330/1507] tipc: add multipoint-to-point flow control We already have point-to-multipoint flow control within a group. But we even need the opposite; -a scheme which can handle that potentially hundreds of sources may try to send messages to the same destination simultaneously without causing buffer overflow at the recipient. This commit adds such a mechanism. The algorithm works as follows: - When a member detects a new, joining member, it initially set its state to JOINED and advertises a minimum window to the new member. This window is chosen so that the new member can send exactly one maximum sized message, or several smaller ones, to the recipient before it must stop and wait for an additional advertisement. This minimum window ADV_IDLE is set to 65 1kB blocks. - When a member receives the first data message from a JOINED member, it changes the state of the latter to ACTIVE, and advertises a larger window ADV_ACTIVE = 12 x ADV_IDLE blocks to the sender, so it can continue sending with minimal disturbances to the data flow. - The active members are kept in a dedicated linked list. Each time a message is received from an active member, it will be moved to the tail of that list. This way, we keep a record of which members have been most (tail) and least (head) recently active. - There is a maximum number (16) of permitted simultaneous active senders per receiver. When this limit is reached, the receiver will not advertise anything immediately to a new sender, but instead put it in a PENDING state, and add it to a corresponding queue. At the same time, it will pick the least recently active member, send it an advertisement RECLAIM message, and set this member to state RECLAIMING. - The reclaimee member has to respond with a REMIT message, meaning that it goes back to a send window of ADV_IDLE, and returns its unused advertised blocks beyond that value to the reclaiming member. - When the reclaiming member receives the REMIT message, it unlinks the reclaimee from its active list, resets its state to JOINED, and notes that it is now back at ADV_IDLE advertised blocks to that member. If there are still unread data messages sent out by reclaimee before the REMIT, the member goes into an intermediate state REMITTED, where it stays until the said messages have been consumed. - The returned advertised blocks can now be re-advertised to the pending member, which is now set to state ACTIVE and added to the active member list. - To be proactive, i.e., to minimize the risk that any member will end up in the pending queue, we start reclaiming resources already when the number of active members exceeds 3/4 of the permitted maximum. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/group.c | 129 +++++++++++++++++++++++++++++++++++++++++++++-- net/tipc/msg.h | 12 +++++ 2 files changed, 136 insertions(+), 5 deletions(-) diff --git a/net/tipc/group.c b/net/tipc/group.c index 8f0eb5d22e8f9..7821085a7dd87 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -54,6 +54,10 @@ enum mbr_state { MBR_JOINING, MBR_PUBLISHED, MBR_JOINED, + MBR_PENDING, + MBR_ACTIVE, + MBR_RECLAIMING, + MBR_REMITTED, MBR_LEAVING }; @@ -79,6 +83,9 @@ struct tipc_member { struct tipc_group { struct rb_root members; struct list_head congested; + struct list_head pending; + struct list_head active; + struct list_head reclaiming; struct tipc_nlist dests; struct net *net; int subid; @@ -88,6 +95,8 @@ struct tipc_group { u32 scope; u32 portid; u16 member_cnt; + u16 active_cnt; + u16 max_active; u16 bc_snd_nxt; u16 bc_ackers; bool loopback; @@ -97,12 +106,29 @@ struct tipc_group { static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq); +static void tipc_group_decr_active(struct tipc_group *grp, + struct tipc_member *m) +{ + if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING) + grp->active_cnt--; +} + static int tipc_group_rcvbuf_limit(struct tipc_group *grp) { + int max_active, active_pool, idle_pool; int mcnt = grp->member_cnt + 1; + /* Limit simultaneous reception from other members */ + max_active = min(mcnt / 8, 64); + max_active = max(max_active, 16); + grp->max_active = max_active; + + /* Reserve blocks for active and idle members */ + active_pool = max_active * ADV_ACTIVE; + idle_pool = (mcnt - max_active) * ADV_IDLE; + /* Scale to bytes, considering worst-case truesize/msgsize ratio */ - return mcnt * ADV_ACTIVE * FLOWCTL_BLK_SZ * 4; + return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4; } u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) @@ -143,6 +169,9 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, return NULL; tipc_nlist_init(&grp->dests, tipc_own_addr(net)); INIT_LIST_HEAD(&grp->congested); + INIT_LIST_HEAD(&grp->active); + INIT_LIST_HEAD(&grp->pending); + INIT_LIST_HEAD(&grp->reclaiming); grp->members = RB_ROOT; grp->net = net; grp->portid = portid; @@ -286,6 +315,7 @@ static void tipc_group_delete_member(struct tipc_group *grp, list_del_init(&m->list); list_del_init(&m->congested); + tipc_group_decr_active(grp, m); /* If last member on a node, remove node from dest list */ if (!tipc_group_find_node(grp, m->node)) @@ -378,6 +408,10 @@ bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, return true; if (state == MBR_JOINED && adv == ADV_IDLE) return true; + if (state == MBR_ACTIVE && adv == ADV_ACTIVE) + return true; + if (state == MBR_PENDING && adv == ADV_IDLE) + return true; skb_queue_head_init(&xmitq); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); tipc_node_distr_xmit(grp->net, &xmitq); @@ -523,7 +557,11 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq) { - struct tipc_member *m; + struct list_head *active = &grp->active; + int max_active = grp->max_active; + int reclaim_limit = max_active * 3 / 4; + int active_cnt = grp->active_cnt; + struct tipc_member *m, *rm; m = tipc_group_find_member(grp, node, port); if (!m) @@ -533,9 +571,41 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, switch (m->state) { case MBR_JOINED: - if (m->advertised <= (ADV_ACTIVE - ADV_UNIT)) + /* Reclaim advertised space from least active member */ + if (!list_empty(active) && active_cnt >= reclaim_limit) { + rm = list_first_entry(active, struct tipc_member, list); + rm->state = MBR_RECLAIMING; + list_move_tail(&rm->list, &grp->reclaiming); + tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq); + } + /* If max active, become pending and wait for reclaimed space */ + if (active_cnt >= max_active) { + m->state = MBR_PENDING; + list_add_tail(&m->list, &grp->pending); + break; + } + /* Otherwise become active */ + m->state = MBR_ACTIVE; + list_add_tail(&m->list, &grp->active); + grp->active_cnt++; + /* Fall through */ + case MBR_ACTIVE: + if (!list_is_last(&m->list, &grp->active)) + list_move_tail(&m->list, &grp->active); + if (m->advertised > (ADV_ACTIVE * 3 / 4)) + break; + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + break; + case MBR_REMITTED: + if (m->advertised > ADV_IDLE) + break; + m->state = MBR_JOINED; + if (m->advertised < ADV_IDLE) { + pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + } break; + case MBR_RECLAIMING: case MBR_DISCOVERED: case MBR_JOINING: case MBR_LEAVING: @@ -557,8 +627,10 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, if (!skb) return; - if (m->state == MBR_JOINED) + if (m->state == MBR_ACTIVE) adv = ADV_ACTIVE - m->advertised; + else if (m->state == MBR_JOINED || m->state == MBR_PENDING) + adv = ADV_IDLE - m->advertised; hdr = buf_msg(skb); @@ -573,6 +645,8 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, m->advertised += adv; } else if (mtyp == GRP_ACK_MSG) { msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); + } else if (mtyp == GRP_REMIT_MSG) { + msg_set_grp_remitted(hdr, m->window); } __skb_queue_tail(xmitq, skb); } @@ -583,8 +657,9 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, { u32 node = msg_orignode(hdr); u32 port = msg_origport(hdr); - struct tipc_member *m; + struct tipc_member *m, *pm; struct tipc_msg *ehdr; + u16 remitted, in_flight; if (!grp) return; @@ -626,6 +701,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, /* Wait until WITHDRAW event is received */ if (m->state != MBR_LEAVING) { + tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; return; } @@ -653,6 +729,48 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, *usr_wakeup = true; m->usr_pending = false; return; + case GRP_RECLAIM_MSG: + if (!m) + return; + *usr_wakeup = m->usr_pending; + m->usr_pending = false; + tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq); + m->window = ADV_IDLE; + return; + case GRP_REMIT_MSG: + if (!m || m->state != MBR_RECLAIMING) + return; + + list_del_init(&m->list); + grp->active_cnt--; + remitted = msg_grp_remitted(hdr); + + /* Messages preceding the REMIT still in receive queue */ + if (m->advertised > remitted) { + m->state = MBR_REMITTED; + in_flight = m->advertised - remitted; + } + /* All messages preceding the REMIT have been read */ + if (m->advertised <= remitted) { + m->state = MBR_JOINED; + in_flight = 0; + } + /* ..and the REMIT overtaken by more messages => re-advertise */ + if (m->advertised < remitted) + tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); + + m->advertised = ADV_IDLE + in_flight; + + /* Set oldest pending member to active and advertise */ + if (list_empty(&grp->pending)) + return; + pm = list_first_entry(&grp->pending, struct tipc_member, list); + pm->state = MBR_ACTIVE; + list_move_tail(&pm->list, &grp->active); + grp->active_cnt++; + if (pm->advertised <= (ADV_ACTIVE * 3 / 4)) + tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); + return; default: pr_warn("Received unknown GROUP_PROTO message\n"); } @@ -735,6 +853,7 @@ void tipc_group_member_evt(struct tipc_group *grp, /* Hold back event if more messages might be expected */ if (m->state != MBR_LEAVING && node_up) { m->event_msg = skb; + tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; } else { if (node_up) diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 52c6a2e01995c..cedf811317fb9 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -548,6 +548,8 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define GRP_LEAVE_MSG 1 #define GRP_ADV_MSG 2 #define GRP_ACK_MSG 3 +#define GRP_RECLAIM_MSG 4 +#define GRP_REMIT_MSG 5 /* * Word 1 @@ -850,6 +852,16 @@ static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) msg_set_bits(m, 9, 16, 0xffff, n); } +static inline u16 msg_grp_remitted(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + /* Word 10 */ static inline u16 msg_grp_evt(struct tipc_msg *m) -- GitLab From 4e8b86c062695454df0b76f3fee4fab8dc4bb716 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:06 -0700 Subject: [PATCH 1331/1507] mqprio: Introduce new hardware offload mode and shaper in mqprio The offload types currently supported in mqprio are 0 (no offload) and 1 (offload only TCs) by setting these values for the 'hw' option. If offloads are supported by setting the 'hw' option to 1, the default offload mode is 'dcb' where only the TC values are offloaded to the device. This patch introduces a new hardware offload mode called 'channel' with 'hw' set to 1 in mqprio which makes full use of the mqprio options, the TCs, the queue configurations and the QoS parameters for the TCs. This is achieved through a new netlink attribute for the 'mode' option which takes values such as 'dcb' (default) and 'channel'. The 'channel' mode also supports QoS attributes for traffic class such as minimum and maximum values for bandwidth rate limits. This patch enables configuring additional HW shaper attributes associated with a traffic class. Currently the shaper for bandwidth rate limiting is supported which takes options such as minimum and maximum bandwidth rates and are offloaded to the hardware in the 'channel' mode. The min and max limits for bandwidth rates are provided by the user along with the TCs and the queue configurations when creating the mqprio qdisc. The interface can be extended to support new HW shapers in future through the 'shaper' attribute. Introduces a new data structure 'tc_mqprio_qopt_offload' for offloading mqprio queue options and use this to be shared between the kernel and device driver. This contains a copy of the existing data structure for mqprio queue options. This new data structure can be extended when adding new attributes for traffic class such as mode, shaper, shaper parameters (bandwidth rate limits). The existing data structure for mqprio queue options will be shared between the kernel and userspace. Example: queues 4@0 4@4 hw 1 mode channel shaper bw_rlimit\ min_rate 1Gbit 2Gbit max_rate 4Gbit 5Gbit To dump the bandwidth rates: qdisc mqprio 804a: root tc 2 map 0 0 0 0 1 1 1 1 0 0 0 0 0 0 0 0 queues:(0:3) (4:7) mode:channel shaper:bw_rlimit min_rate:1Gbit 2Gbit max_rate:4Gbit 5Gbit Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/net/pkt_cls.h | 9 ++ include/uapi/linux/pkt_sched.h | 32 ++++++ net/sched/sch_mqprio.c | 183 +++++++++++++++++++++++++++++++-- 3 files changed, 215 insertions(+), 9 deletions(-) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index f5263743076b8..60d39789e4f07 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -546,6 +546,15 @@ struct tc_cls_bpf_offload { u32 gen_flags; }; +struct tc_mqprio_qopt_offload { + /* struct tc_mqprio_qopt must always be the first element */ + struct tc_mqprio_qopt qopt; + u16 mode; + u16 shaper; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; +}; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 099bf5528fed3..e95b5c9b9fad9 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -625,6 +625,22 @@ enum { #define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; @@ -633,6 +649,22 @@ struct tc_mqprio_qopt { __u16 offset[TC_QOPT_MAX_QUEUE]; }; +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + /* SFB */ enum { diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6bcdfe6e7b63a..f1ae9be839346 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -18,10 +18,16 @@ #include #include #include +#include struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,9 +45,17 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt mqprio = {}; + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + &mqprio); + break; + default: + return; + } } else { netdev_set_num_tc(dev, 0); } @@ -97,6 +111,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return 0; } +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, +}; + +static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, + const struct nla_policy *policy, int len) +{ + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); @@ -105,6 +139,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int rem; + int len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -122,6 +160,58 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (mqprio_parse_opt(dev, qopt)) return -EINVAL; + if (len > 0) { + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -146,14 +236,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt mqprio = *qopt; + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + err = dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_MQPRIO, &mqprio); if (err) return err; - priv->hw_offload = mqprio.hw; + priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -223,11 +335,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; unsigned int i; @@ -258,12 +410,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) goto nla_put_failure; - return skb->len; + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } -- GitLab From ff4241881232265dbc237591901116fe272967d6 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:11 -0700 Subject: [PATCH 1332/1507] i40e: Add macro for PF reset bit Introduce a macro for the bit setting the PF reset flag and update its usages. This makes it easier to use this flag in functions to be introduced in future without encountering checkpatch issues related to alignment and line over 80 characters. Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 2 ++ drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 3 +-- drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++----- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 5 ++--- 4 files changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 8139b4ee1dc32..e7c7a853cf7fe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -157,6 +157,8 @@ enum i40e_state_t { __I40E_STATE_SIZE__, }; +#define I40E_PF_RESET_FLAG BIT_ULL(__I40E_PF_RESET_REQUESTED) + /* VSI state flags */ enum i40e_vsi_state_t { __I40E_VSI_DOWN, diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 6f2725fc50a18..2b8bbc84e34f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -798,8 +798,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, */ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 4de52001a2b9d..6190257eecfec 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5747,7 +5747,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi) err_setup_tx: i40e_vsi_free_tx_resources(vsi); if (vsi == pf->vsi[pf->lan_vsi]) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return err; } @@ -5875,7 +5875,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) wr32(&pf->hw, I40E_GLGEN_RTRIG, val); i40e_flush(&pf->hw); - } else if (reset_flags & BIT_ULL(__I40E_PF_RESET_REQUESTED)) { + } else if (reset_flags & I40E_PF_RESET_FLAG) { /* Request a PF Reset * @@ -9223,7 +9223,7 @@ static int i40e_set_features(struct net_device *netdev, need_reset = i40e_set_ntuple(pf, features); if (need_reset) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); return 0; } @@ -9475,8 +9475,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; else pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), - true); + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); break; } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 0c4fa225c7bee..e7f98e3065545 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1425,8 +1425,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (num_vfs) { if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, - BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } return i40e_pci_sriov_enable(pdev, num_vfs); } @@ -1434,7 +1433,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!pci_vfs_assigned(pf->pdev)) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } else { dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n"); return -EINVAL; -- GitLab From 8f88b3034db3be2eb600b9f57012bc63f1ea197f Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:17 -0700 Subject: [PATCH 1333/1507] i40e: Add infrastructure for queue channel support This patch sets up the infrastructure for offloading TCs and queue configurations to the hardware by creating HW channels(VSI). A new channel is created for each of the traffic class configuration offloaded via mqprio framework except for the first TC (TC0). TC0 for the main VSI is also reconfigured as per user provided queue parameters. Queue counts that are not power-of-2 are handled by reconfiguring RSS by reprogramming LUTs using the queue count value. This patch also handles configuring the TX rings for the channels, setting up the RX queue map for channel. Also, the channels so created are removed and all the queue configuration is set to default when the qdisc is detached from the root of the device. Signed-off-by: Amritha Nambiar Signed-off-by: Kiran Patil Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 32 + drivers/net/ethernet/intel/i40e/i40e_main.c | 718 +++++++++++++++++++- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 2 + 3 files changed, 743 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index e7c7a853cf7fe..bde982541772f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -87,6 +87,7 @@ #define I40E_AQ_LEN 256 #define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ #define I40E_MAX_USER_PRIORITY 8 +#define I40E_MAX_QUEUES_PER_CH 64 #define I40E_DEFAULT_TRAFFIC_CLASS BIT(0) #define I40E_DEFAULT_MSG_ENABLE 4 #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 @@ -340,6 +341,23 @@ struct i40e_flex_pit { u8 pit_index; }; +struct i40e_channel { + struct list_head list; + bool initialized; + u8 type; + u16 vsi_number; /* Assigned VSI number from AQ 'Add VSI' response */ + u16 stat_counter_idx; + u16 base_queue; + u16 num_queue_pairs; /* Requested by user */ + u16 seid; + + u8 enabled_tc; + struct i40e_aqc_vsi_properties_data info; + + /* track this channel belongs to which VSI */ + struct i40e_vsi *parent_vsi; +}; + /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; @@ -456,6 +474,7 @@ struct i40e_pf { #define I40E_FLAG_CLIENT_RESET BIT(26) #define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27) #define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28) +#define I40E_FLAG_TC_MQPRIO BIT(29) struct i40e_client_instance *cinst; bool stat_offsets_loaded; @@ -536,6 +555,8 @@ struct i40e_pf { u32 ioremap_len; u32 fd_inv; u16 phy_led_val; + + u16 override_q_count; }; /** @@ -700,6 +721,15 @@ struct i40e_vsi { bool current_isup; /* Sync 'link up' logging */ enum i40e_aq_link_speed current_speed; /* Sync link speed logging */ + /* channel specific fields */ + u16 cnt_q_avail; /* num of queues available for channel usage */ + u16 orig_rss_size; + u16 current_rss_size; + + u16 next_base_queue; /* next queue to be used for channel setup */ + + struct list_head ch_list; + void *priv; /* client driver data reference. */ /* VSI specific handlers */ @@ -1004,4 +1034,6 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) { return !!vsi->xdp_prog; } + +int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 6190257eecfec..e23105bee6d10 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2881,7 +2881,7 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { int cpu; - if (!ring->q_vector || !ring->netdev) + if (!ring->q_vector || !ring->netdev || ring->ch) return; /* We only initialize XPS once, so as not to overwrite user settings */ @@ -2944,7 +2944,14 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) * initialization. This has to be done regardless of * DCB as by default everything is mapped to TC0. */ - tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + + if (ring->ch) + tx_ctx.rdylist = + le16_to_cpu(ring->ch->info.qs_handle[ring->dcb_tc]); + + else + tx_ctx.rdylist = le16_to_cpu(vsi->info.qs_handle[ring->dcb_tc]); + tx_ctx.rdylist_act = 0; /* clear the context in the HMC */ @@ -2966,12 +2973,23 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /* Now associate this queue with this PCI function */ - if (vsi->type == I40E_VSI_VMDQ2) { - qtx_ctl = I40E_QTX_CTL_VM_QUEUE; - qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & - I40E_QTX_CTL_VFVM_INDX_MASK; + if (ring->ch) { + if (ring->ch->type == I40E_VSI_VMDQ2) + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + else + return -EINVAL; + + qtx_ctl |= (ring->ch->vsi_number << + I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; } else { - qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + if (vsi->type == I40E_VSI_VMDQ2) { + qtx_ctl = I40E_QTX_CTL_VM_QUEUE; + qtx_ctl |= ((vsi->id) << I40E_QTX_CTL_VFVM_INDX_SHIFT) & + I40E_QTX_CTL_VFVM_INDX_MASK; + } else { + qtx_ctl = I40E_QTX_CTL_PF_QUEUE; + } } qtx_ctl |= ((hw->pf_id << I40E_QTX_CTL_PF_INDX_SHIFT) & @@ -5161,6 +5179,643 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) return ret; } +/** + * i40e_remove_queue_channels - Remove queue channels for the TCs + * @vsi: VSI to be configured + * + * Remove queue channels for the TCs + **/ +static void i40e_remove_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int ret, i; + + /* Reset rss size that was stored when reconfiguring rss for + * channel VSIs with non-power-of-2 queue count. + */ + vsi->current_rss_size = 0; + + /* perform cleanup for channels if they exist */ + if (list_empty(&vsi->ch_list)) + return; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + struct i40e_vsi *p_vsi; + + list_del(&ch->list); + p_vsi = ch->parent_vsi; + if (!p_vsi || !ch->initialized) { + kfree(ch); + continue; + } + /* Reset queue contexts */ + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = NULL; + + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = NULL; + } + + /* delete VSI from FW */ + ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid, + NULL); + if (ret) + dev_err(&vsi->back->pdev->dev, + "unable to remove channel (%d) for parent VSI(%d)\n", + ch->seid, p_vsi->seid); + kfree(ch); + } + INIT_LIST_HEAD(&vsi->ch_list); +} + +/** + * i40e_is_any_channel - channel exist or not + * @vsi: ptr to VSI to which channels are associated with + * + * Returns true or false if channel(s) exist for associated VSI or not + **/ +static bool i40e_is_any_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (ch->initialized) + return true; + } + + return false; +} + +/** + * i40e_get_max_queues_for_channel + * @vsi: ptr to VSI to which channels are associated with + * + * Helper function which returns max value among the queue counts set on the + * channels/TCs created. + **/ +static int i40e_get_max_queues_for_channel(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + int max = 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + continue; + if (ch->num_queue_pairs > max) + max = ch->num_queue_pairs; + } + + return max; +} + +/** + * i40e_validate_num_queues - validate num_queues w.r.t channel + * @pf: ptr to PF device + * @num_queues: number of queues + * @vsi: the parent VSI + * @reconfig_rss: indicates should the RSS be reconfigured or not + * + * This function validates number of queues in the context of new channel + * which is being established and determines if RSS should be reconfigured + * or not for parent VSI. + **/ +static int i40e_validate_num_queues(struct i40e_pf *pf, int num_queues, + struct i40e_vsi *vsi, bool *reconfig_rss) +{ + int max_ch_queues; + + if (!reconfig_rss) + return -EINVAL; + + *reconfig_rss = false; + + if (num_queues > I40E_MAX_QUEUES_PER_CH) { + dev_err(&pf->pdev->dev, + "Failed to create VMDq VSI. User requested num_queues (%d) > I40E_MAX_QUEUES_PER_VSI (%u)\n", + num_queues, I40E_MAX_QUEUES_PER_CH); + return -EINVAL; + } + + if (vsi->current_rss_size) { + if (num_queues > vsi->current_rss_size) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) > vsi's current_size(%d)\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } else if ((num_queues < vsi->current_rss_size) && + (!is_power_of_2(num_queues))) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < vsi's current_size(%d), but not power of 2\n", + num_queues, vsi->current_rss_size); + return -EINVAL; + } + } + + if (!is_power_of_2(num_queues)) { + /* Find the max num_queues configured for channel if channel + * exist. + * if channel exist, then enforce 'num_queues' to be more than + * max ever queues configured for channel. + */ + max_ch_queues = i40e_get_max_queues_for_channel(vsi); + if (num_queues < max_ch_queues) { + dev_dbg(&pf->pdev->dev, + "Error: num_queues (%d) < max queues configured for channel(%d)\n", + num_queues, max_ch_queues); + return -EINVAL; + } + *reconfig_rss = true; + } + + return 0; +} + +/** + * i40e_vsi_reconfig_rss - reconfig RSS based on specified rss_size + * @vsi: the VSI being setup + * @rss_size: size of RSS, accordingly LUT gets reprogrammed + * + * This function reconfigures RSS by reprogramming LUTs using 'rss_size' + **/ +static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + struct i40e_hw *hw = &pf->hw; + int local_rss_size; + u8 *lut; + int ret; + + if (!vsi->rss_size) + return -EINVAL; + + if (rss_size > vsi->rss_size) + return -EINVAL; + + local_rss_size = min_t(int, vsi->rss_size, rss_size); + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Ignoring user configured lut if there is one */ + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, local_rss_size); + + /* Use user configured hash key if there is one, otherwise + * use default. + */ + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + + ret = i40e_config_rss(vsi, seed, lut, vsi->rss_table_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + kfree(lut); + return ret; + } + kfree(lut); + + /* Do the update w.r.t. storing rss_size */ + if (!vsi->orig_rss_size) + vsi->orig_rss_size = vsi->rss_size; + vsi->current_rss_size = local_rss_size; + + return ret; +} + +/** + * i40e_channel_setup_queue_map - Setup a channel queue map + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ctxt: VSI context structure + * @ch: ptr to channel structure + * + * Setup queue map for a specific channel + **/ +static void i40e_channel_setup_queue_map(struct i40e_pf *pf, + struct i40e_vsi_context *ctxt, + struct i40e_channel *ch) +{ + u16 qcount, qmap, sections = 0; + u8 offset = 0; + int pow; + + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + + qcount = min_t(int, ch->num_queue_pairs, pf->num_lan_msix); + ch->num_queue_pairs = qcount; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(qcount); + if (!is_power_of_2(qcount)) + pow++; + + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + + ctxt->info.up_enable_bits = 0x1; /* TC0 enabled */ + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(ch->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); +} + +/** + * i40e_add_channel - add a channel by adding VSI + * @pf: ptr to PF device + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Add a channel (VSI) using add_vsi and queue_map + **/ +static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, + struct i40e_channel *ch) +{ + struct i40e_hw *hw = &pf->hw; + struct i40e_vsi_context ctxt; + u8 enabled_tc = 0x1; /* TC0 enabled */ + int ret; + + if (ch->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "add new vsi failed, ch->type %d\n", ch->type); + return -EINVAL; + } + + memset(&ctxt, 0, sizeof(ctxt)); + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = 0; + ctxt.uplink_seid = uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + if (ch->type == I40E_VSI_VMDQ2) + ctxt.flags = I40E_AQ_VSI_TYPE_VMDQ2; + + if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) { + ctxt.info.valid_sections |= + cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID); + ctxt.info.switch_id = + cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB); + } + + /* Set queue map for a given VSI context */ + i40e_channel_setup_queue_map(pf, &ctxt, ch); + + /* Now time to create VSI */ + ret = i40e_aq_add_vsi(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "add new vsi failed, err %s aq_err %s\n", + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); + return -ENOENT; + } + + /* Success, update channel */ + ch->enabled_tc = enabled_tc; + ch->seid = ctxt.seid; + ch->vsi_number = ctxt.vsi_number; + ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx); + + /* copy just the sections touched not the entire info + * since not all sections are valid as returned by + * update vsi params + */ + ch->info.mapping_flags = ctxt.info.mapping_flags; + memcpy(&ch->info.queue_mapping, + &ctxt.info.queue_mapping, sizeof(ctxt.info.queue_mapping)); + memcpy(&ch->info.tc_mapping, ctxt.info.tc_mapping, + sizeof(ctxt.info.tc_mapping)); + + return 0; +} + +static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch, + u8 *bw_share) +{ + struct i40e_aqc_configure_vsi_tc_bw_data bw_data; + i40e_status ret; + int i; + + bw_data.tc_valid_bits = ch->enabled_tc; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + bw_data.tc_bw_credits[i] = bw_share[i]; + + ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, ch->seid, + &bw_data, NULL); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Config VSI BW allocation per TC failed, aq_err: %d for new_vsi->seid %u\n", + vsi->back->hw.aq.asq_last_status, ch->seid); + return -EINVAL; + } + + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) + ch->info.qs_handle[i] = bw_data.qs_handles[i]; + + return 0; +} + +/** + * i40e_channel_config_tx_ring - config TX ring associated with new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * + * Configure TX rings associated with channel (VSI) since queues are being + * from parent VSI. + **/ +static int i40e_channel_config_tx_ring(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + i40e_status ret; + int i; + u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0}; + + /* Enable ETS TCs with equal BW Share for now across all VSIs */ + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (ch->enabled_tc & BIT(i)) + bw_share[i] = 1; + } + + /* configure BW for new VSI */ + ret = i40e_channel_config_bw(vsi, ch, bw_share); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed configuring TC map %d for channel (seid %u)\n", + ch->enabled_tc, ch->seid); + return ret; + } + + for (i = 0; i < ch->num_queue_pairs; i++) { + struct i40e_ring *tx_ring, *rx_ring; + u16 pf_q; + + pf_q = ch->base_queue + i; + + /* Get to TX ring ptr of main VSI, for re-setup TX queue + * context + */ + tx_ring = vsi->tx_rings[pf_q]; + tx_ring->ch = ch; + + /* Get the RX ring ptr */ + rx_ring = vsi->rx_rings[pf_q]; + rx_ring->ch = ch; + } + + return 0; +} + +/** + * i40e_setup_hw_channel - setup new channel + * @pf: ptr to PF device + * @vsi: the VSI being setup + * @ch: ptr to channel structure + * @uplink_seid: underlying HW switching element (VEB) ID + * @type: type of channel to be created (VMDq2/VF) + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and configures TX rings accordingly + **/ +static inline int i40e_setup_hw_channel(struct i40e_pf *pf, + struct i40e_vsi *vsi, + struct i40e_channel *ch, + u16 uplink_seid, u8 type) +{ + int ret; + + ch->initialized = false; + ch->base_queue = vsi->next_base_queue; + ch->type = type; + + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(pf, uplink_seid, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to add_channel using uplink_seid %u\n", + uplink_seid); + return ret; + } + + /* Mark the successful creation of channel */ + ch->initialized = true; + + /* Reconfigure TX queues using QTX_CTL register */ + ret = i40e_channel_config_tx_ring(pf, vsi, ch); + if (ret) { + dev_info(&pf->pdev->dev, + "failed to configure TX rings for channel %u\n", + ch->seid); + return ret; + } + + /* update 'next_base_queue' */ + vsi->next_base_queue = vsi->next_base_queue + ch->num_queue_pairs; + dev_dbg(&pf->pdev->dev, + "Added channel: vsi_seid %u, vsi_number %u, stat_counter_idx %u, num_queue_pairs %u, pf->next_base_queue %d\n", + ch->seid, ch->vsi_number, ch->stat_counter_idx, + ch->num_queue_pairs, + vsi->next_base_queue); + return ret; +} + +/** + * i40e_setup_channel - setup new channel using uplink element + * @pf: ptr to PF device + * @type: type of channel to be created (VMDq2/VF) + * @uplink_seid: underlying HW switching element (VEB) ID + * @ch: ptr to channel structure + * + * Setup new channel (VSI) based on specified type (VMDq2/VF) + * and uplink switching element (uplink_seid) + **/ +static bool i40e_setup_channel(struct i40e_pf *pf, struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + u8 vsi_type; + u16 seid; + int ret; + + if (vsi->type == I40E_VSI_MAIN) { + vsi_type = I40E_VSI_VMDQ2; + } else { + dev_err(&pf->pdev->dev, "unsupported parent vsi type(%d)\n", + vsi->type); + return false; + } + + /* underlying switching element */ + seid = pf->vsi[pf->lan_vsi]->uplink_seid; + + /* create channel (VSI), configure TX rings */ + ret = i40e_setup_hw_channel(pf, vsi, ch, seid, vsi_type); + if (ret) { + dev_err(&pf->pdev->dev, "failed to setup hw_channel\n"); + return false; + } + + return ch->initialized ? true : false; +} + +/** + * i40e_create_queue_channel - function to create channel + * @vsi: VSI to be configured + * @ch: ptr to channel (it contains channel specific params) + * + * This function creates channel (VSI) using num_queues specified by user, + * reconfigs RSS if needed. + **/ +int i40e_create_queue_channel(struct i40e_vsi *vsi, + struct i40e_channel *ch) +{ + struct i40e_pf *pf = vsi->back; + bool reconfig_rss; + int err; + + if (!ch) + return -EINVAL; + + if (!ch->num_queue_pairs) { + dev_err(&pf->pdev->dev, "Invalid num_queues requested: %d\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* validate user requested num_queues for channel */ + err = i40e_validate_num_queues(pf, ch->num_queue_pairs, vsi, + &reconfig_rss); + if (err) { + dev_info(&pf->pdev->dev, "Failed to validate num_queues (%d)\n", + ch->num_queue_pairs); + return -EINVAL; + } + + /* By default we are in VEPA mode, if this is the first VF/VMDq + * VSI to be added switch to VEB mode. + */ + if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || + (!i40e_is_any_channel(vsi))) { + if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { + dev_dbg(&pf->pdev->dev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + return -EINVAL; + } + + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, + true); + else + i40e_do_reset_safe(pf, + I40E_PF_RESET_FLAG); + } + } + /* now onwards for main VSI, number of queues will be value + * of TC0's queue count + */ + } + + /* By this time, vsi->cnt_q_avail shall be set to non-zero and + * it should be more than num_queues + */ + if (!vsi->cnt_q_avail || vsi->cnt_q_avail < ch->num_queue_pairs) { + dev_dbg(&pf->pdev->dev, + "Error: cnt_q_avail (%u) less than num_queues %d\n", + vsi->cnt_q_avail, ch->num_queue_pairs); + return -EINVAL; + } + + /* reconfig_rss only if vsi type is MAIN_VSI */ + if (reconfig_rss && (vsi->type == I40E_VSI_MAIN)) { + err = i40e_vsi_reconfig_rss(vsi, ch->num_queue_pairs); + if (err) { + dev_info(&pf->pdev->dev, + "Error: unable to reconfig rss for num_queues (%u)\n", + ch->num_queue_pairs); + return -EINVAL; + } + } + + if (!i40e_setup_channel(pf, vsi, ch)) { + dev_info(&pf->pdev->dev, "Failed to setup channel\n"); + return -EINVAL; + } + + dev_info(&pf->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + ch->seid, ch->num_queue_pairs); + + /* in case of VF, this will be main SRIOV VSI */ + ch->parent_vsi = vsi; + + /* and update main_vsi's count for queue_available to use */ + vsi->cnt_q_avail -= ch->num_queue_pairs; + + return 0; +} + +/** + * i40e_configure_queue_channels - Add queue channel for the given TCs + * @vsi: VSI to be configured + * + * Configures queue channel mapping to the given TCs + **/ +static int i40e_configure_queue_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch; + int ret = 0, i; + + /* Create app vsi with the TCs. Main VSI with TC0 is already set up */ + for (i = 1; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (vsi->tc_config.enabled_tc & BIT(i)) { + ch = kzalloc(sizeof(*ch), GFP_KERNEL); + if (!ch) { + ret = -ENOMEM; + goto err_free; + } + + INIT_LIST_HEAD(&ch->list); + ch->num_queue_pairs = + vsi->tc_config.tc_info[i].qcount; + ch->base_queue = + vsi->tc_config.tc_info[i].qoffset; + + list_add_tail(&ch->list, &vsi->ch_list); + + ret = i40e_create_queue_channel(vsi, ch); + if (ret) { + dev_err(&vsi->back->pdev->dev, + "Failed creating queue channel with TC%d: queues %d\n", + i, ch->num_queue_pairs); + goto err_free; + } + } + } + return ret; + +err_free: + i40e_remove_queue_channels(vsi); + return ret; +} + /** * i40e_veb_config_tc - Configure TCs for given VEB * @veb: given VEB @@ -5612,10 +6267,18 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc) goto exit; } - /* Unquiesce VSI */ - i40e_unquiesce_vsi(vsi); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { + ret = i40e_configure_queue_channels(vsi); + if (ret) { + netdev_info(netdev, + "Failed configuring queue channels\n"); + goto exit; + } + } exit: + /* Unquiesce VSI */ + i40e_unquiesce_vsi(vsi); return ret; } @@ -7030,6 +7693,35 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) i40e_vsi_release(vsi); } +/** + * i40e_rebuild_channels - Rebuilds channel VSIs if they existed before reset + * @vsi: PF main vsi + * + * Rebuilds channel VSIs if they existed before reset + **/ +static int i40e_rebuild_channels(struct i40e_vsi *vsi) +{ + struct i40e_channel *ch, *ch_tmp; + i40e_status ret; + + if (list_empty(&vsi->ch_list)) + return 0; + + list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { + if (!ch->initialized) + break; + /* Proceed with creation of channel (VMDq2) VSI */ + ret = i40e_add_channel(vsi->back, vsi->uplink_seid, ch); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "failed to rebuild channels using uplink_seid %u\n", + vsi->uplink_seid); + return ret; + } + } + return 0; +} + /** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure @@ -7295,6 +7987,13 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } + /* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs + * for this main VSI if they exist + */ + ret = i40e_rebuild_channels(pf->vsi[pf->lan_vsi]); + if (ret) + goto end_unlock; + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. @@ -11608,6 +12307,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; } + INIT_LIST_HEAD(&pf->vsi[pf->lan_vsi]->ch_list); /* Make sure flow control is set according to current settings */ err = i40e_set_fc(hw, &set_fc_aq_fail, true); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index ff57ae451524f..fbae1182e2eab 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -426,6 +426,8 @@ struct i40e_ring { * i40e_clean_rx_ring_irq() is called * for this ring. */ + + struct i40e_channel *ch; } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) -- GitLab From a9ce82f744dc401ec27c787e2eacf3bbb33565ec Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:22 -0700 Subject: [PATCH 1334/1507] i40e: Enable 'channel' mode in mqprio for TC configs The i40e driver is modified to enable the new mqprio hardware offload mode and factor the TCs and queue configuration by creating channel VSIs. In this mode, the priority to traffic class mapping and the user specified queue ranges are used to configure the traffic classes by setting the mode option to 'channel'. Example: map 0 0 0 0 1 2 2 3 queues 2@0 2@2 1@4 1@5\ hw 1 mode channel qdisc mqprio 8038: root tc 4 map 0 0 0 0 1 2 2 3 0 0 0 0 0 0 0 0 queues:(0:1) (2:3) (4:4) (5:5) mode:channel shaper:dcb The HW channels created are removed and all the queue configuration is set to default when the qdisc is detached from the root of the device. This patch also disables setting up channels via ethtool (ethtool -L) when the TCs are configured using mqprio scheduler. The patch also limits setting ethtool Rx flow hash indirection (ethtool -X eth0 equal N) to max queues configured via mqprio. The Rx flow hash indirection input through ethtool should be validated so that it is within in the queue range configured via tc/mqprio. The bound checking is achieved by reporting the current rss size to the kernel when queues are configured via mqprio. Example: map 0 0 0 1 0 2 3 0 queues 2@0 4@2 8@6 11@14\ hw 1 mode channel Cannot set RX flow hash configuration: Invalid argument Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 3 + .../net/ethernet/intel/i40e/i40e_ethtool.c | 8 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 457 ++++++++++++++---- 3 files changed, 362 insertions(+), 106 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index bde982541772f..024c884749511 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -54,6 +54,7 @@ #include #include #include +#include #include "i40e_type.h" #include "i40e_prototype.h" #include "i40e_client.h" @@ -700,6 +701,7 @@ struct i40e_vsi { enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */ s16 vf_id; /* Virtual function ID for SRIOV VSIs */ + struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */ struct i40e_tc_configuration tc_config; struct i40e_aqc_vsi_properties_data info; @@ -725,6 +727,7 @@ struct i40e_vsi { u16 cnt_q_avail; /* num of queues available for channel usage */ u16 orig_rss_size; u16 current_rss_size; + bool reconfig_rss; u16 next_base_queue; /* next queue to be used for channel setup */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index afd3ca8d98511..72d5f2cdf419f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2652,7 +2652,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = vsi->num_queue_pairs; + cmd->data = vsi->rss_size; ret = 0; break; case ETHTOOL_GRXFH: @@ -3897,6 +3897,12 @@ static int i40e_set_channels(struct net_device *dev, if (vsi->type != I40E_VSI_MAIN) return -EINVAL; + /* We do not support setting channels via ethtool when TCs are + * configured through mqprio + */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return -EINVAL; + /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e23105bee6d10..e803aa1552c62 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1588,6 +1588,170 @@ static int i40e_set_mac(struct net_device *netdev, void *p) return 0; } +/** + * i40e_config_rss_aq - Prepare for RSS using AQ commands + * @vsi: vsi structure + * @seed: RSS hash seed + **/ +static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, + u8 *lut, u16 lut_size) +{ + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + int ret = 0; + + if (seed) { + struct i40e_aqc_get_set_rss_key_data *seed_dw = + (struct i40e_aqc_get_set_rss_key_data *)seed; + ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS key, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + if (lut) { + bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; + + ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); + if (ret) { + dev_info(&pf->pdev->dev, + "Cannot set RSS lut, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + } + return ret; +} + +/** + * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used + * @vsi: VSI structure + **/ +static int i40e_vsi_config_rss(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + u8 seed[I40E_HKEY_ARRAY_SIZE]; + u8 *lut; + int ret; + + if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) + return 0; + if (!vsi->rss_size) + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + if (!vsi->rss_size) + return -EINVAL; + lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + /* Use the user configured hash keys and lookup table if there is one, + * otherwise use default + */ + if (vsi->rss_lut_user) + memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); + else + i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); + if (vsi->rss_hkey_user) + memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); + else + netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); + ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); + kfree(lut); + return ret; +} + +/** + * i40e_vsi_setup_queue_map_mqprio - Prepares mqprio based tc_config + * @vsi: the VSI being configured, + * @ctxt: VSI context structure + * @enabled_tc: number of traffic classes to enable + * + * Prepares VSI tc_config to have queue configurations based on MQPRIO options. + **/ +static int i40e_vsi_setup_queue_map_mqprio(struct i40e_vsi *vsi, + struct i40e_vsi_context *ctxt, + u8 enabled_tc) +{ + u16 qcount = 0, max_qcount, qmap, sections = 0; + int i, override_q, pow, num_qps, ret; + u8 netdev_tc = 0, offset = 0; + + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; + sections |= I40E_AQ_VSI_PROP_SCHED_VALID; + vsi->tc_config.numtc = vsi->mqprio_qopt.qopt.num_tc; + vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1; + num_qps = vsi->mqprio_qopt.qopt.count[0]; + + /* find the next higher power-of-2 of num queue pairs */ + pow = ilog2(num_qps); + if (!is_power_of_2(num_qps)) + pow++; + qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) | + (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT); + + /* Setup queue offset/count for all TCs for given VSI */ + max_qcount = vsi->mqprio_qopt.qopt.count[0]; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* See if the given TC is enabled for the given VSI */ + if (vsi->tc_config.enabled_tc & BIT(i)) { + offset = vsi->mqprio_qopt.qopt.offset[i]; + qcount = vsi->mqprio_qopt.qopt.count[i]; + if (qcount > max_qcount) + max_qcount = qcount; + vsi->tc_config.tc_info[i].qoffset = offset; + vsi->tc_config.tc_info[i].qcount = qcount; + vsi->tc_config.tc_info[i].netdev_tc = netdev_tc++; + } else { + /* TC is not enabled so set the offset to + * default queue and allocate one queue + * for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } + } + + /* Set actual Tx/Rx queue pairs */ + vsi->num_queue_pairs = offset + qcount; + + /* Setup queue TC[0].qmap for given VSI context */ + ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); + ctxt->info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG); + ctxt->info.queue_mapping[0] = cpu_to_le16(vsi->base_queue); + ctxt->info.valid_sections |= cpu_to_le16(sections); + + /* Reconfigure RSS for main VSI with max queue count */ + vsi->rss_size = max_qcount; + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues (%u)\n", + max_qcount); + return ret; + } + vsi->reconfig_rss = true; + dev_dbg(&vsi->back->pdev->dev, + "Reconfigured rss with num_queues (%u)\n", max_qcount); + + /* Find queue count available for channel VSIs and starting offset + * for channel VSIs + */ + override_q = vsi->mqprio_qopt.qopt.count[0]; + if (override_q && override_q < vsi->num_queue_pairs) { + vsi->cnt_q_avail = vsi->num_queue_pairs - override_q; + vsi->next_base_queue = override_q; + } + return 0; +} + /** * i40e_vsi_setup_queue_map - Setup a VSI queue map based on enabled_tc * @vsi: the VSI being setup @@ -1626,7 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, numtc = 1; } } else { - /* At least TC0 is enabled in case of non-DCB case */ + /* At least TC0 is enabled in non-DCB, non-MQPRIO case */ numtc = 1; } @@ -3158,6 +3322,7 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi) rx_ring->dcb_tc = 0; tx_ring->dcb_tc = 0; } + return; } for (n = 0; n < I40E_MAX_TRAFFIC_CLASS; n++) { @@ -4873,6 +5038,24 @@ static u8 i40e_dcb_get_enabled_tc(struct i40e_dcbx_config *dcbcfg) return enabled_tc; } +/** + * i40e_mqprio_get_enabled_tc - Get enabled traffic classes + * @pf: PF being queried + * + * Query the current MQPRIO configuration and return the number of + * traffic classes enabled. + **/ +static u8 i40e_mqprio_get_enabled_tc(struct i40e_pf *pf) +{ + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + u8 num_tc = vsi->mqprio_qopt.qopt.num_tc; + u8 enabled_tc = 1, i; + + for (i = 1; i < num_tc; i++) + enabled_tc |= BIT(i); + return enabled_tc; +} + /** * i40e_pf_get_num_tc - Get enabled traffic classes for PF * @pf: PF being queried @@ -4886,7 +5069,10 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) u8 num_tc = 0; struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; - /* If DCB is not enabled then always in single TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc; + + /* If neither MQPRIO nor DCB is enabled, then always use single TC */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return 1; @@ -4915,7 +5101,12 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) **/ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) { - /* If DCB is not enabled for this PF then just return default TC */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return i40e_mqprio_get_enabled_tc(pf); + + /* If neither MQPRIO nor DCB is enabled for this PF then just return + * default TC + */ if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return I40E_DEFAULT_TRAFFIC_CLASS; @@ -5005,6 +5196,9 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, i40e_status ret; int i; + if ((vsi->back->flags & I40E_FLAG_TC_MQPRIO) || + !vsi->mqprio_qopt.qopt.hw) + return 0; bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -5067,6 +5261,9 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) vsi->tc_config.tc_info[i].qoffset); } + if (pf->flags & I40E_FLAG_TC_MQPRIO) + return; + /* Assign UP2TC map for the VSI */ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { /* Get the actual TC# for the UP */ @@ -5117,7 +5314,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) int i; /* Check if enabled_tc is same as existing or new TCs */ - if (vsi->tc_config.enabled_tc == enabled_tc) + if (vsi->tc_config.enabled_tc == enabled_tc && + vsi->mqprio_qopt.mode != TC_MQPRIO_MODE_CHANNEL) return ret; /* Enable ETS TCs with equal BW Share for now across all VSIs */ @@ -5140,15 +5338,37 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ctxt.vf_num = 0; ctxt.uplink_seid = vsi->uplink_seid; ctxt.info = vsi->info; - i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) { + ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc); + if (ret) + goto out; + } else { + i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, false); + } + /* On destroying the qdisc, reset vsi->rss_size, as number of enabled + * queues changed. + */ + if (!vsi->mqprio_qopt.qopt.hw && vsi->reconfig_rss) { + vsi->rss_size = min_t(int, vsi->back->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } if (vsi->back->flags & I40E_FLAG_IWARP_ENABLED) { ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID); ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA; } - /* Update the VSI after updating the VSI queue-mapping information */ + /* Update the VSI after updating the VSI queue-mapping + * information + */ ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, @@ -6216,54 +6436,157 @@ void i40e_down(struct i40e_vsi *vsi) } +/** + * i40e_validate_mqprio_qopt- validate queue mapping info + * @vsi: the VSI being configured + * @mqprio_qopt: queue parametrs + **/ +static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, + struct tc_mqprio_qopt_offload *mqprio_qopt) +{ + int i; + + if (mqprio_qopt->qopt.offset[0] != 0 || + mqprio_qopt->qopt.num_tc < 1 || + mqprio_qopt->qopt.num_tc > I40E_MAX_TRAFFIC_CLASS) + return -EINVAL; + for (i = 0; ; i++) { + if (!mqprio_qopt->qopt.count[i]) + return -EINVAL; + if (mqprio_qopt->min_rate[i] || mqprio_qopt->max_rate[i]) + return -EINVAL; + if (i >= mqprio_qopt->qopt.num_tc - 1) + break; + if (mqprio_qopt->qopt.offset[i + 1] != + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) + return -EINVAL; + } + if (vsi->num_queue_pairs < + (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { + return -EINVAL; + } + return 0; +} + +/** + * i40e_vsi_set_default_tc_config - set default values for tc configuration + * @vsi: the VSI being configured + **/ +static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) +{ + u16 qcount; + int i; + + /* Only TC0 is enabled */ + vsi->tc_config.numtc = 1; + vsi->tc_config.enabled_tc = 1; + qcount = min_t(int, vsi->alloc_queue_pairs, + i40e_pf_get_max_q_per_tc(vsi->back)); + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + /* For the TC that is not enabled set the offset to to default + * queue and allocate one queue for the given TC. + */ + vsi->tc_config.tc_info[i].qoffset = 0; + if (i == 0) + vsi->tc_config.tc_info[i].qcount = qcount; + else + vsi->tc_config.tc_info[i].qcount = 1; + vsi->tc_config.tc_info[i].netdev_tc = 0; + } +} + /** * i40e_setup_tc - configure multiple traffic classes * @netdev: net device to configure - * @tc: number of traffic classes to enable + * @type_data: tc offload data **/ -static int i40e_setup_tc(struct net_device *netdev, u8 tc) +static int i40e_setup_tc(struct net_device *netdev, void *type_data) { + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u8 enabled_tc = 0; + u8 enabled_tc = 0, num_tc, hw; + bool need_reset = false; int ret = -EINVAL; + u16 mode; int i; - /* Check if DCB enabled to continue */ - if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { - netdev_info(netdev, "DCB is not enabled for adapter\n"); - goto exit; + num_tc = mqprio_qopt->qopt.num_tc; + hw = mqprio_qopt->qopt.hw; + mode = mqprio_qopt->mode; + if (!hw) { + pf->flags &= ~I40E_FLAG_TC_MQPRIO; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt)); + goto config_tc; } /* Check if MFP enabled */ if (pf->flags & I40E_FLAG_MFP_ENABLED) { - netdev_info(netdev, "Configuring TC not supported in MFP mode\n"); - goto exit; + netdev_info(netdev, + "Configuring TC not supported in MFP mode\n"); + return ret; } + switch (mode) { + case TC_MQPRIO_MODE_DCB: + pf->flags &= ~I40E_FLAG_TC_MQPRIO; - /* Check whether tc count is within enabled limit */ - if (tc > i40e_pf_get_num_tc(pf)) { - netdev_info(netdev, "TC count greater than enabled on link for adapter\n"); - goto exit; + /* Check if DCB enabled to continue */ + if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) { + netdev_info(netdev, + "DCB is not enabled for adapter\n"); + return ret; + } + + /* Check whether tc count is within enabled limit */ + if (num_tc > i40e_pf_get_num_tc(pf)) { + netdev_info(netdev, + "TC count greater than enabled on link for adapter\n"); + return ret; + } + break; + case TC_MQPRIO_MODE_CHANNEL: + if (pf->flags & I40E_FLAG_DCB_ENABLED) { + netdev_info(netdev, + "Full offload of TC Mqprio options is not supported when DCB is enabled\n"); + return ret; + } + if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) + return ret; + ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt); + if (ret) + return ret; + memcpy(&vsi->mqprio_qopt, mqprio_qopt, + sizeof(*mqprio_qopt)); + pf->flags |= I40E_FLAG_TC_MQPRIO; + pf->flags &= ~I40E_FLAG_DCB_ENABLED; + break; + default: + return -EINVAL; } +config_tc: /* Generate TC map for number of tc requested */ - for (i = 0; i < tc; i++) + for (i = 0; i < num_tc; i++) enabled_tc |= BIT(i); /* Requesting same TC configuration as already enabled */ - if (enabled_tc == vsi->tc_config.enabled_tc) + if (enabled_tc == vsi->tc_config.enabled_tc && + mode != TC_MQPRIO_MODE_CHANNEL) return 0; /* Quiesce VSI queues */ i40e_quiesce_vsi(vsi); + if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO)) + i40e_remove_queue_channels(vsi); + /* Configure VSI for enabled TCs */ ret = i40e_vsi_config_tc(vsi, enabled_tc); if (ret) { netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n", vsi->seid); + need_reset = true; goto exit; } @@ -6272,11 +6595,18 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc) if (ret) { netdev_info(netdev, "Failed configuring queue channels\n"); + need_reset = true; goto exit; } } exit: + /* Reset the configuration data to defaults, only TC0 is enabled */ + if (need_reset) { + i40e_vsi_set_default_tc_config(vsi); + need_reset = false; + } + /* Unquiesce VSI */ i40e_unquiesce_vsi(vsi); return ret; @@ -6285,14 +6615,10 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc) static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { - struct tc_mqprio_qopt *mqprio = type_data; - if (type != TC_SETUP_MQPRIO) return -EOPNOTSUPP; - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - - return i40e_setup_tc(netdev, mqprio->num_tc); + return i40e_setup_tc(netdev, type_data); } /** @@ -9153,45 +9479,6 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) return err; } -/** - * i40e_config_rss_aq - Prepare for RSS using AQ commands - * @vsi: vsi structure - * @seed: RSS hash seed - **/ -static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, - u8 *lut, u16 lut_size) -{ - struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int ret = 0; - - if (seed) { - struct i40e_aqc_get_set_rss_key_data *seed_dw = - (struct i40e_aqc_get_set_rss_key_data *)seed; - ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS key, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - if (lut) { - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false; - - ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); - if (ret) { - dev_info(&pf->pdev->dev, - "Cannot set RSS lut, err %s aq_err %s\n", - i40e_stat_str(hw, ret), - i40e_aq_str(hw, hw->aq.asq_last_status)); - return ret; - } - } - return ret; -} - /** * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands * @vsi: Pointer to vsi structure @@ -9238,46 +9525,6 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, return ret; } -/** - * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used - * @vsi: VSI structure - **/ -static int i40e_vsi_config_rss(struct i40e_vsi *vsi) -{ - u8 seed[I40E_HKEY_ARRAY_SIZE]; - struct i40e_pf *pf = vsi->back; - u8 *lut; - int ret; - - if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) - return 0; - - if (!vsi->rss_size) - vsi->rss_size = min_t(int, pf->alloc_rss_size, - vsi->num_queue_pairs); - if (!vsi->rss_size) - return -EINVAL; - - lut = kzalloc(vsi->rss_table_size, GFP_KERNEL); - if (!lut) - return -ENOMEM; - /* Use the user configured hash keys and lookup table if there is one, - * otherwise use default - */ - if (vsi->rss_lut_user) - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size); - else - i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size); - if (vsi->rss_hkey_user) - memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE); - else - netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE); - ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size); - kfree(lut); - - return ret; -} - /** * i40e_config_rss_reg - Configure RSS keys and lut by writing registers * @vsi: Pointer to vsi structure -- GitLab From 5ecae4120a6b50fb8a31d2f335eab390bcf5ad66 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:27 -0700 Subject: [PATCH 1335/1507] i40e: Refactor VF BW rate limiting This patch refactors the BW rate limiting for Tx traffic on the VF to be reused in the next patch for rate limiting Tx traffic for the VSIs on the PF as well. Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 5 ++ drivers/net/ethernet/intel/i40e/i40e_main.c | 64 +++++++++++++++++++ .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 45 +------------ 3 files changed, 71 insertions(+), 43 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 024c884749511..524aa06a9e0ee 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -128,6 +128,10 @@ /* default to trying for four seconds */ #define I40E_TRY_LINK_TIMEOUT (4 * HZ) +/* BW rate limiting */ +#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ +#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* accumulate 4 credits max */ + /* driver state flags */ enum i40e_state_t { __I40E_TESTING, @@ -1039,4 +1043,5 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) } int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e803aa1552c62..fc6eaf44d87c1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5399,6 +5399,70 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) return ret; } +/** + * i40e_get_link_speed - Returns link speed for the interface + * @vsi: VSI to be configured + * + **/ +int i40e_get_link_speed(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + + switch (pf->hw.phy.link_info.link_speed) { + case I40E_LINK_SPEED_40GB: + return 40000; + case I40E_LINK_SPEED_25GB: + return 25000; + case I40E_LINK_SPEED_20GB: + return 20000; + case I40E_LINK_SPEED_10GB: + return 10000; + case I40E_LINK_SPEED_1GB: + return 1000; + default: + return -EINVAL; + } +} + +/** + * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate + * @vsi: VSI to be configured + * @seid: seid of the channel/VSI + * @max_tx_rate: max TX rate to be configured as BW limit + * + * Helper function to set BW limit for a given VSI + **/ +int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) +{ + struct i40e_pf *pf = vsi->back; + int speed = 0; + int ret = 0; + + speed = i40e_get_link_speed(vsi); + if (max_tx_rate > speed) { + dev_err(&pf->pdev->dev, + "Invalid max tx rate %llu specified for VSI seid %d.", + max_tx_rate, seid); + return -EINVAL; + } + if (max_tx_rate && max_tx_rate < 50) { + dev_warn(&pf->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = 50; + } + + /* Tx rate credits are in values of 50Mbps, 0 is disabled */ + ret = i40e_aq_config_vsi_bw_limit(&pf->hw, seid, + max_tx_rate / I40E_BW_CREDIT_DIVISOR, + I40E_MAX_BW_INACTIVE_ACCUM, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed set tx rate (%llu Mbps) for vsi->seid %u, err %s aq_err %s\n", + max_tx_rate, seid, i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + return ret; +} + /** * i40e_remove_queue_channels - Remove queue channels for the TCs * @vsi: VSI to be configured diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e7f98e3065545..ce0981e2f6055 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3117,8 +3117,6 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, return ret; } -#define I40E_BW_CREDIT_DIVISOR 50 /* 50Mbps per BW credit */ -#define I40E_MAX_BW_INACTIVE_ACCUM 4 /* device can accumulate 4 credits max */ /** * i40e_ndo_set_vf_bw * @netdev: network interface device structure @@ -3134,7 +3132,6 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi; struct i40e_vf *vf; - int speed = 0; int ret = 0; /* validate the request */ @@ -3159,48 +3156,10 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, goto error; } - switch (pf->hw.phy.link_info.link_speed) { - case I40E_LINK_SPEED_40GB: - speed = 40000; - break; - case I40E_LINK_SPEED_25GB: - speed = 25000; - break; - case I40E_LINK_SPEED_20GB: - speed = 20000; - break; - case I40E_LINK_SPEED_10GB: - speed = 10000; - break; - case I40E_LINK_SPEED_1GB: - speed = 1000; - break; - default: - break; - } - - if (max_tx_rate > speed) { - dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for VF %d.\n", - max_tx_rate, vf->vf_id); - ret = -EINVAL; + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (ret) goto error; - } - if ((max_tx_rate < 50) && (max_tx_rate > 0)) { - dev_warn(&pf->pdev->dev, "Setting max Tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; - } - - /* Tx rate credits are in values of 50Mbps, 0 is disabled*/ - ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, - max_tx_rate / I40E_BW_CREDIT_DIVISOR, - I40E_MAX_BW_INACTIVE_ACCUM, NULL); - if (ret) { - dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n", - ret); - ret = -EIO; - goto error; - } vf->tx_rate = max_tx_rate; error: return ret; -- GitLab From 2027d4deacb129579f022746830ea05b72fe114a Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:32 -0700 Subject: [PATCH 1336/1507] i40e: Add support setting TC max bandwidth rates This patch enables setting up maximum Tx rates for the traffic classes in i40e. The maximum rate is offloaded to the hardware through the mqprio framework by specifying the mode option as 'channel' and shaper option as 'bw_rlimit' and is configured for the VSI. Configuring minimum Tx rate limit is not supported in the device. The minimum usable value for Tx rate is 50Mbps. Example: # tc qdisc add dev eth0 root mqprio num_tc 2 map 0 0 0 0 1 1 1 1\ queues 4@0 4@4 hw 1 mode channel shaper bw_rlimit\ max_rate 4Gbit 5Gbit To dump the bandwidth rates: # tc qdisc show dev eth0 qdisc mqprio 804a: root tc 2 map 0 0 0 0 1 1 1 1 0 0 0 0 0 0 0 0 queues:(0:3) (4:7) mode:channel shaper:bw_rlimit max_rate:4Gbit 5Gbit Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e.h | 2 + drivers/net/ethernet/intel/i40e/i40e_main.c | 100 ++++++++++++++++++-- 2 files changed, 93 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 524aa06a9e0ee..266e1dc5e7865 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -359,6 +359,8 @@ struct i40e_channel { u8 enabled_tc; struct i40e_aqc_vsi_properties_data info; + u64 max_tx_rate; + /* track this channel belongs to which VSI */ struct i40e_vsi *parent_vsi; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index fc6eaf44d87c1..bb31d53c49234 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5196,9 +5196,16 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, i40e_status ret; int i; - if ((vsi->back->flags & I40E_FLAG_TC_MQPRIO) || - !vsi->mqprio_qopt.qopt.hw) + if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) return 0; + if (!vsi->mqprio_qopt.qopt.hw) { + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for vsi->seid %u\n", + vsi->seid); + return ret; + } bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; @@ -5505,6 +5512,13 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) rx_ring->ch = NULL; } + /* Reset BW configured for this VSI via mqprio */ + ret = i40e_set_bw_limit(vsi, ch->seid, 0); + if (ret) + dev_info(&vsi->back->pdev->dev, + "Failed to reset tx rate for ch->seid %u\n", + ch->seid); + /* delete VSI from FW */ ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid, NULL); @@ -6047,6 +6061,17 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, "Setup channel (id:%u) utilizing num_queues %d\n", ch->seid, ch->num_queue_pairs); + /* configure VSI for BW limit */ + if (ch->max_tx_rate) { + if (i40e_set_bw_limit(vsi, ch->seid, ch->max_tx_rate)) + return -EINVAL; + + dev_dbg(&pf->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + ch->max_tx_rate / I40E_BW_CREDIT_DIVISOR, ch->seid); + } + /* in case of VF, this will be main SRIOV VSI */ ch->parent_vsi = vsi; @@ -6082,6 +6107,12 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi) ch->base_queue = vsi->tc_config.tc_info[i].qoffset; + /* Bandwidth limit through tc interface is in bytes/s, + * change to Mbit/s + */ + ch->max_tx_rate = + vsi->mqprio_qopt.max_rate[i] / (1000000 / 8); + list_add_tail(&ch->list, &vsi->ch_list); ret = i40e_create_queue_channel(vsi, ch); @@ -6508,6 +6539,7 @@ void i40e_down(struct i40e_vsi *vsi) static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, struct tc_mqprio_qopt_offload *mqprio_qopt) { + u64 sum_max_rate = 0; int i; if (mqprio_qopt->qopt.offset[0] != 0 || @@ -6517,8 +6549,13 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, for (i = 0; ; i++) { if (!mqprio_qopt->qopt.count[i]) return -EINVAL; - if (mqprio_qopt->min_rate[i] || mqprio_qopt->max_rate[i]) + if (mqprio_qopt->min_rate[i]) { + dev_err(&vsi->back->pdev->dev, + "Invalid min tx rate (greater than 0) specified\n"); return -EINVAL; + } + sum_max_rate += (mqprio_qopt->max_rate[i] / (1000000 / 8)); + if (i >= mqprio_qopt->qopt.num_tc - 1) break; if (mqprio_qopt->qopt.offset[i + 1] != @@ -6529,6 +6566,11 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi, (mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) { return -EINVAL; } + if (sum_max_rate > i40e_get_link_speed(vsi)) { + dev_err(&vsi->back->pdev->dev, + "Invalid max tx rate specified\n"); + return -EINVAL; + } return 0; } @@ -6655,6 +6697,21 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data) } if (pf->flags & I40E_FLAG_TC_MQPRIO) { + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0] / + (1000000 / 8); + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (!ret) { + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + max_tx_rate / I40E_BW_CREDIT_DIVISOR, + vsi->seid); + } else { + need_reset = true; + goto exit; + } + } ret = i40e_configure_queue_channels(vsi); if (ret) { netdev_info(netdev, @@ -8108,6 +8165,17 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) vsi->uplink_seid); return ret; } + if (ch->max_tx_rate) { + if (i40e_set_bw_limit(vsi, ch->seid, + ch->max_tx_rate)) + return -EINVAL; + + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + ch->max_tx_rate, + ch->max_tx_rate / I40E_BW_CREDIT_DIVISOR, + ch->seid); + } } return 0; } @@ -8248,6 +8316,7 @@ static int i40e_reset(struct i40e_pf *pf) **/ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; u8 set_fc_aq_fail = 0; i40e_status ret; @@ -8330,7 +8399,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * If there were VEBs but the reconstitution failed, we'll try * try to recover minimal use by getting the basic PF VSI working. */ - if (pf->vsi[pf->lan_vsi]->uplink_seid != pf->mac_seid) { + if (vsi->uplink_seid != pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild switch\n"); /* find the one VEB connected to the MAC, and find orphans */ for (v = 0; v < I40E_MAX_VEB; v++) { @@ -8354,8 +8423,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) dev_info(&pf->pdev->dev, "rebuild of switch failed: %d, will try to set up simple PF connection\n", ret); - pf->vsi[pf->lan_vsi]->uplink_seid - = pf->mac_seid; + vsi->uplink_seid = pf->mac_seid; break; } else if (pf->veb[v]->uplink_seid == 0) { dev_info(&pf->pdev->dev, @@ -8366,10 +8434,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } - if (pf->vsi[pf->lan_vsi]->uplink_seid == pf->mac_seid) { + if (vsi->uplink_seid == pf->mac_seid) { dev_dbg(&pf->pdev->dev, "attempting to rebuild PF VSI\n"); /* no VEB, so rebuild only the Main VSI */ - ret = i40e_add_vsi(pf->vsi[pf->lan_vsi]); + ret = i40e_add_vsi(vsi); if (ret) { dev_info(&pf->pdev->dev, "rebuild of Main VSI failed: %d\n", ret); @@ -8377,10 +8445,24 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } } + if (vsi->mqprio_qopt.max_rate[0]) { + u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0] / (1000000 / 8); + + ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); + if (!ret) + dev_dbg(&vsi->back->pdev->dev, + "Set tx rate of %llu Mbps (count of 50Mbps %llu) for vsi->seid %u\n", + max_tx_rate, + max_tx_rate / I40E_BW_CREDIT_DIVISOR, + vsi->seid); + else + goto end_unlock; + } + /* PF Main VSI is rebuild by now, go ahead and rebuild channel VSIs * for this main VSI if they exist */ - ret = i40e_rebuild_channels(pf->vsi[pf->lan_vsi]); + ret = i40e_rebuild_channels(vsi); if (ret) goto end_unlock; -- GitLab From b06da8f939ff8dcf28eb9b86aae933850658742e Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 22 Sep 2017 15:11:38 +0100 Subject: [PATCH 1337/1507] i40e: make const array patterns static, reduces object code size Don't populate const array patterns on the stack, instead make it static. Makes the object code smaller by over 60 bytes: Before: text data bss dec hex filename 1953 496 0 2449 991 i40e_diag.o After: text data bss dec hex filename 1798 584 0 2382 94e i40e_diag.o (gcc 6.3.0, x86-64) Signed-off-by: Colin Ian King Acked-by: Jesse Brandeburg Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_diag.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index f141e78d409e5..76ed566418644 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -36,7 +36,9 @@ static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw, u32 reg, u32 mask) { - const u32 patterns[] = {0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + static const u32 patterns[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF + }; u32 pat, val, orig_val; int i; -- GitLab From 8fdb69dd383f1f937f7e2f1f24efe97c5268a84c Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Wed, 11 Oct 2017 14:49:42 -0700 Subject: [PATCH 1338/1507] i40e: fix link reporting When querying the NVM for supported phy_types, on some firmware versions, we were failing to actually fill out the phy_types which means ethtool wouldn't report any link types. Testing-hints: Check 'ethtool ' if you have the right (wrong?) firmware. Without this patch, no link modes will be reported. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_common.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 53aad378d49c1..aeb497258f204 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1611,8 +1611,13 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, if (report_init) { if (hw->mac.type == I40E_MAC_XL710 && hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && - hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) + hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) { status = i40e_aq_get_link_info(hw, true, NULL, NULL); + } else { + hw->phy.phy_types = le32_to_cpu(abilities->phy_type); + hw->phy.phy_types |= + ((u64)abilities->phy_type_ext << 32); + } } return status; -- GitLab From 17a9422de78c3a59b490b400f555635c477f1476 Mon Sep 17 00:00:00 2001 From: Alan Brady Date: Wed, 11 Oct 2017 14:49:43 -0700 Subject: [PATCH 1339/1507] i40e/i40evf: don't trust VF to reset itself When using 'ethtool -L' on a VF to change number of requested queues from PF, we shouldn't trust the VF to reset itself after making the request. Doing it that way opens the door for a potentially malicious VF to do nasty things to the PF which should never be the case. This makes it such that after VF makes a successful request, PF will then reset the VF to institute required changes. Only if the request fails will PF send a message back to VF letting it know the request was unsuccessful. Testing-hints: There should be no real functional changes. This is simply hardening against a potentially malicious VF. Signed-off-by: Alan Brady Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 9 +++++++-- drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c | 7 +++---- include/linux/avf/virtchnl.h | 4 ++-- 3 files changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index ce0981e2f6055..f8a794b724628 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2045,8 +2045,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) * @msglen: msg length * * VFs get a default number of queues but can use this message to request a - * different number. Will respond with either the number requested or the - * maximum we can support. + * different number. If the request is successful, PF will reset the VF and + * return 0. If unsuccessful, PF will send message informing VF of number of + * available queues and return result of sending VF a message. **/ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) { @@ -2077,7 +2078,11 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg, int msglen) pf->queues_left); vfres->num_queue_pairs = pf->queues_left + cur_pairs; } else { + /* successful request */ vf->num_req_queues = req_pairs; + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); + return 0; } return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES, 0, diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 2bb81c39d85fa..46c8b8a3907cc 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -407,6 +407,7 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) vfres.num_queue_pairs = num; adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; + adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, (u8 *)&vfres, sizeof(vfres)); } @@ -1098,15 +1099,13 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_REQUEST_QUEUES: { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; - if (vfres->num_queue_pairs == adapter->num_req_queues) { - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; - i40evf_schedule_reset(adapter); - } else { + if (vfres->num_queue_pairs != adapter->num_req_queues) { dev_info(&adapter->pdev->dev, "Requested %d queues, PF can support %d\n", adapter->num_req_queues, vfres->num_queue_pairs); adapter->num_req_queues = 0; + adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; } } break; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 60e5d90cb18ac..3ce61342fa311 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -333,8 +333,8 @@ struct virtchnl_vsi_queue_config_info { * additional queues must be negotiated. This is a best effort request as it * is possible the PF does not have enough queues left to support the request. * If the PF cannot support the number requested it will respond with the - * maximum number it is able to support; otherwise it will respond with the - * number requested. + * maximum number it is able to support. If the request is successful, PF will + * then reset the VF to institute required changes. */ /* VF resource request */ -- GitLab From 258bbb1b0e594ad5f5652cb526b3c63e6a7fad3d Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Thu, 12 Oct 2017 16:12:37 +0200 Subject: [PATCH 1340/1507] icmp: don't fail on fragment reassembly time exceeded The ICMP implementation currently replies to an ICMP time exceeded message (type 11) with an ICMP host unreachable message (type 3, code 1). However, time exceeded messages can either represent "time to live exceeded in transit" (code 0) or "fragment reassembly time exceeded" (code 1). Unconditionally replying to "fragment reassembly time exceeded" with host unreachable messages might cause unjustified connection resets which are now easily triggered as UFO has been removed, because, in turn, sending large buffers triggers IP fragmentation. The issue can be easily reproduced by running a lot of UDP streams which is likely to trigger IP fragmentation: # start netserver in the test namespace ip netns add test ip netns exec test netserver # create a VETH pair ip link add name veth0 type veth peer name veth0 netns test ip link set veth0 up ip -n test link set veth0 up for i in $(seq 20 29); do # assign addresses to both ends ip addr add dev veth0 192.168.$i.1/24 ip -n test addr add dev veth0 192.168.$i.2/24 # start the traffic netperf -L 192.168.$i.1 -H 192.168.$i.2 -t UDP_STREAM -l 0 & done # wait send_data: data send error: No route to host (errno 113) netperf: send_omni: send_data failed: No route to host We need to differentiate instead: if fragment reassembly time exceeded is reported, we need to silently drop the packet, if time to live exceeded is reported, maintain the current behaviour. In both cases increment the related error count "icmpInTimeExcds". While at it, fix a typo in a comment, and convert the if statement into a switch to mate it more readable. Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- net/ipv4/icmp.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 681e33998e03b..3c1570d3e22fa 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -782,7 +782,7 @@ static bool icmp_tag_validation(int proto) } /* - * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and + * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and * ICMP_PARAMETERPROB. */ @@ -810,7 +810,8 @@ static bool icmp_unreach(struct sk_buff *skb) if (iph->ihl < 5) /* Mangled header, drop. */ goto out_err; - if (icmph->type == ICMP_DEST_UNREACH) { + switch (icmph->type) { + case ICMP_DEST_UNREACH: switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: @@ -846,8 +847,16 @@ static bool icmp_unreach(struct sk_buff *skb) } if (icmph->code > NR_ICMP_UNREACH) goto out; - } else if (icmph->type == ICMP_PARAMETERPROB) + break; + case ICMP_PARAMETERPROB: info = ntohl(icmph->un.gateway) >> 24; + break; + case ICMP_TIME_EXCEEDED: + __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS); + if (icmph->code == ICMP_EXC_FRAGTIME) + goto out; + break; + } /* * Throw it at our lower layers -- GitLab From 52a76235d0c4dd259cd0df503afed4757c04ba1d Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Fri, 13 Oct 2017 10:58:36 +0100 Subject: [PATCH 1341/1507] net: stmmac: Use correct values in TQS/RQS fields Currently we are using all the available fifo size in RQS and TQS fields. This will not work correctly in multi-queues IP's because total fifo size must be splitted to the enabled queues. Correct this by computing the available fifo size per queue and setting the right value in TQS and RQS fields. Signed-off-by: Jose Abreu Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 ++- .../net/ethernet/stmicro/stmmac/dwmac4_dma.c | 15 ++++++++----- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 22 +++++++++++++++++-- 3 files changed, 31 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e82b4b70b7be3..c26c8a7f957f5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -443,7 +443,8 @@ struct stmmac_dma_ops { int rxfifosz); void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, int fifosz); - void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel); + void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz); /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index e84831e1b63b3..898849bbc7d44 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -271,9 +271,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, } static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, - u32 channel) + u32 channel, int fifosz) { u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); + unsigned int tqs = fifosz / 256 - 1; if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable TX store and forward mode\n"); @@ -306,12 +307,14 @@ static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, * For an IP with DWC_EQOS_NUM_TXQ > 1, the fields TXQEN and TQS are R/W * with reset values: TXQEN off, TQS 256 bytes. * - * Write the bits in both cases, since it will have no effect when RO. - * For DWC_EQOS_NUM_TXQ > 1, the top bits in MTL_OP_MODE_TQS_MASK might - * be RO, however, writing the whole TQS field will result in a value - * equal to DWC_EQOS_TXFIFO_SIZE, just like for DWC_EQOS_NUM_TXQ == 1. + * TXQEN must be written for multi-channel operation and TQS must + * reflect the available fifo size per queue (total fifo size / number + * of enabled queues). */ - mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK; + mtl_tx_op |= MTL_OP_MODE_TXQEN; + mtl_tx_op &= ~MTL_OP_MODE_TQS_MASK; + mtl_tx_op |= tqs << MTL_OP_MODE_TQS_SHIFT; + writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f41661a04f237..edf245b8bce32 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1750,12 +1750,19 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) u32 rx_channels_count = priv->plat->rx_queues_to_use; u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + int txfifosz = priv->plat->tx_fifo_size; u32 txmode = 0; u32 rxmode = 0; u32 chan = 0; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + /* Adjust for real per queue fifo size */ + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; if (priv->plat->force_thresh_dma_mode) { txmode = tc; @@ -1783,7 +1790,8 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) rxfifosz); for (chan = 0; chan < tx_channels_count; chan++) - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, + txfifosz); } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); @@ -1946,15 +1954,25 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan) { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; + int txfifosz = priv->plat->tx_fifo_size; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; + if (txfifosz == 0) + txfifosz = priv->dma_cap.tx_fifo_size; + + /* Adjust for real per queue fifo size */ + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; if (priv->synopsys_id >= DWMAC_CORE_4_00) { priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, rxfifosz); - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan); + priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, + txfifosz); } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); -- GitLab From a0daae13776994cf90e9a7bc81cd8e4ad3959093 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Fri, 13 Oct 2017 10:58:37 +0100 Subject: [PATCH 1342/1507] net: stmmac: Disable flow ctrl for RX AVB queues and really enable TX AVB queues Flow control must be disabled for AVB enabled queues and TX AVB queues must be enabled by setting BIT(2) of TXQEN. Correct this by passing the queue mode to DMA callbacks and by checking in these functions wether we are in AVB performing the necessary adjustments. Signed-off-by: Jose Abreu Cc: David S. Miller Cc: Joao Pinto Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 2 ++ .../net/ethernet/stmicro/stmmac/dwmac4_dma.c | 16 +++++++++----- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 21 +++++++++++++------ 4 files changed, 30 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index c26c8a7f957f5..e1e5ac0537606 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -442,9 +442,9 @@ struct stmmac_dma_ops { void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, int rxfifosz); void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, - int fifosz); + int fifosz, u8 qmode); void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel, - int fifosz); + int fifosz, u8 qmode); /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, void __iomem *ioaddr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index d74cedf2a3975..aeda3ab2d761c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -225,6 +225,8 @@ enum power_event { #define MTL_CHAN_RX_DEBUG(x) (MTL_CHANX_BASE_ADDR(x) + 0x38) #define MTL_OP_MODE_RSF BIT(5) +#define MTL_OP_MODE_TXQEN_MASK GENMASK(3, 2) +#define MTL_OP_MODE_TXQEN_AV BIT(2) #define MTL_OP_MODE_TXQEN BIT(3) #define MTL_OP_MODE_TSF BIT(1) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 898849bbc7d44..c110f6850ffa3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -191,7 +191,7 @@ static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan) } static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, - u32 channel, int fifosz) + u32 channel, int fifosz, u8 qmode) { unsigned int rqs = fifosz / 256 - 1; u32 mtl_rx_op, mtl_rx_int; @@ -218,8 +218,10 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK; mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT; - /* enable flow control only if each channel gets 4 KiB or more FIFO */ - if (fifosz >= 4096) { + /* Enable flow control only if each channel gets 4 KiB or more FIFO and + * only if channel is not an AVB channel. + */ + if ((fifosz >= 4096) && (qmode != MTL_QUEUE_AVB)) { unsigned int rfd, rfa; mtl_rx_op |= MTL_OP_MODE_EHFC; @@ -271,7 +273,7 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode, } static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, - u32 channel, int fifosz) + u32 channel, int fifosz, u8 qmode) { u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel)); unsigned int tqs = fifosz / 256 - 1; @@ -311,7 +313,11 @@ static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, * reflect the available fifo size per queue (total fifo size / number * of enabled queues). */ - mtl_tx_op |= MTL_OP_MODE_TXQEN; + mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK; + if (qmode != MTL_QUEUE_AVB) + mtl_tx_op |= MTL_OP_MODE_TXQEN; + else + mtl_tx_op |= MTL_OP_MODE_TXQEN_AV; mtl_tx_op &= ~MTL_OP_MODE_TQS_MASK; mtl_tx_op |= tqs << MTL_OP_MODE_TQS_SHIFT; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index edf245b8bce32..0e1b0a3d7b766 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1754,6 +1754,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) u32 txmode = 0; u32 rxmode = 0; u32 chan = 0; + u8 qmode = 0; if (rxfifosz == 0) rxfifosz = priv->dma_cap.rx_fifo_size; @@ -1785,13 +1786,19 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) /* configure all channels */ if (priv->synopsys_id >= DWMAC_CORE_4_00) { - for (chan = 0; chan < rx_channels_count; chan++) + for (chan = 0; chan < rx_channels_count; chan++) { + qmode = priv->plat->rx_queues_cfg[chan].mode_to_use; + priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz); + rxfifosz, qmode); + } + + for (chan = 0; chan < tx_channels_count; chan++) { + qmode = priv->plat->tx_queues_cfg[chan].mode_to_use; - for (chan = 0; chan < tx_channels_count; chan++) priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, - txfifosz); + txfifosz, qmode); + } } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); @@ -1954,6 +1961,8 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan) { + u8 rxqmode = priv->plat->rx_queues_cfg[chan].mode_to_use; + u8 txqmode = priv->plat->tx_queues_cfg[chan].mode_to_use; u32 rx_channels_count = priv->plat->rx_queues_to_use; u32 tx_channels_count = priv->plat->tx_queues_to_use; int rxfifosz = priv->plat->rx_fifo_size; @@ -1970,9 +1979,9 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, if (priv->synopsys_id >= DWMAC_CORE_4_00) { priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz); + rxfifosz, rxqmode); priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, - txfifosz); + txfifosz, txqmode); } else { priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, rxfifosz); -- GitLab From 1bdec44955edc22fb840f5965987d2972307dcc9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:07 -0700 Subject: [PATCH 1343/1507] bpf: verifier: set reg_type on context accesses in second pass Use a simplified is_valid_access() callback when verifier is used for program analysis by non-host JITs. This allows us to teach the verifier about packet start and packet end offsets for direct packet access. We can extend the callback as needed but for most packet processing needs there isn't much more the offloads may require. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 43 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 37 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2cdbcc4f8f6b2..9755279d94cb8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -813,6 +813,36 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, return err; } +static bool analyzer_is_valid_access(struct bpf_verifier_env *env, int off, + struct bpf_insn_access_aux *info) +{ + switch (env->prog->type) { + case BPF_PROG_TYPE_XDP: + switch (off) { + case offsetof(struct xdp_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct xdp_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; + case BPF_PROG_TYPE_SCHED_CLS: + switch (off) { + case offsetof(struct sk_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct sk_buff, cb) + + offsetof(struct bpf_skb_data_end, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; + default: + return false; + } +} + /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) @@ -821,12 +851,13 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, .reg_type = *reg_type, }; - /* for analyzer ctx accesses are already validated and converted */ - if (env->analyzer_ops) - return 0; - - if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + if (env->analyzer_ops) { + if (analyzer_is_valid_access(env, off, &info)) { + *reg_type = info.reg_type; + return 0; + } + } else if (env->prog->aux->ops->is_valid_access && + env->prog->aux->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower -- GitLab From bc8c80a8c978d24b2746dc7d9a8cef65ae82be3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:08 -0700 Subject: [PATCH 1344/1507] nfp: bpf: reorder arguments to emit_ld_field_any() ld_field instruction has the following format in NFP assembler: ld_field[dst, 1000, src, <<24] reoder parameters to emit_ld_field_any() to make it closer to the familiar assembler order. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 13148f30fc4c1..cf8a6eb3ec993 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -402,8 +402,8 @@ __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc, } static void -emit_ld_field_any(struct nfp_prog *nfp_prog, enum shf_sc sc, u8 shift, - swreg dst, u8 bmask, swreg src, bool zero) +emit_ld_field_any(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, + enum shf_sc sc, u8 shift, bool zero) { struct nfp_insn_re_regs reg; int err; @@ -424,7 +424,7 @@ static void emit_ld_field(struct nfp_prog *nfp_prog, swreg dst, u8 bmask, swreg src, enum shf_sc sc, u8 shift) { - emit_ld_field_any(nfp_prog, sc, shift, dst, bmask, src, false); + emit_ld_field_any(nfp_prog, dst, bmask, src, sc, shift, false); } static void emit_nop(struct nfp_prog *nfp_prog) -- GitLab From 8283737065b2dab480cd10e00e6f8abbcb62b5b0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:09 -0700 Subject: [PATCH 1345/1507] nfp: bpf: add missing return in jne_imm optimization We optimize comparisons to immediate 0 as if (reg.lo | reg.hi). The early return statement was missing, however, which means we would generate two comparisons - optimized one followed by a normal 2x 32 bit compare. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index cf8a6eb3ec993..5ac834e91aed5 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1191,6 +1191,7 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2), ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1)); emit_br(nfp_prog, BR_BNE, insn->off, 0); + return 0; } tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog)); -- GitLab From 26fa818dc07c649fcb37674580ebd5a3c7cae66c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:10 -0700 Subject: [PATCH 1346/1507] nfp: bpf: fix compare instructions Now that we have BPF assemebler support in LLVM 6 we can easily test all compare instructions (LLVM 4 didn't generate most of them from C). Fix the compare to immediates and refactor the order of compare to regs to make sure they both follow the same pattern. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 21 +++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 5ac834e91aed5..e970f284c8a40 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -720,7 +720,10 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, enum br_mask br_mask, bool swap) { const struct bpf_insn *insn = &meta->insn; - u8 areg = insn->src_reg * 2, breg = insn->dst_reg * 2; + u8 areg, breg; + + areg = insn->dst_reg * 2; + breg = insn->src_reg * 2; if (insn->off < 0) /* TODO */ return -EOPNOTSUPP; @@ -1129,22 +1132,22 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false); + return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); } static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); + return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); } static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); + return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false); } static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); + return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); } static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -1227,22 +1230,22 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false); + return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); } static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); + return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); } static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); + return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false); } static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); + return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); } static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -- GitLab From c000dfb5e29a2abaf303cf90502cb68227f29fae Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:11 -0700 Subject: [PATCH 1347/1507] nfp: bpf: add mov helper Register move operation is encoded as alu no op. This means that one has to specify number of unused/none parameters to the emit_alu(). Add a helper. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 31 ++++++++++---------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index e970f284c8a40..4f7cfa6adfc13 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -504,9 +504,14 @@ wrp_br_special(struct nfp_prog *nfp_prog, enum br_mask mask, FIELD_PREP(OP_BR_SPECIAL, special); } +static void wrp_mov(struct nfp_prog *nfp_prog, swreg dst, swreg src) +{ + emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, src); +} + static void wrp_reg_mov(struct nfp_prog *nfp_prog, u16 dst, u16 src) { - emit_alu(nfp_prog, reg_both(dst), reg_none(), ALU_OP_NONE, reg_b(src)); + wrp_mov(nfp_prog, reg_both(dst), reg_b(src)); } static int @@ -556,8 +561,7 @@ construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, reg_xfer(0), SHF_SC_R_SHF, shift * 8); else for (; i * 4 < size; i++) - emit_alu(nfp_prog, reg_both(i), - reg_none(), ALU_OP_NONE, reg_xfer(i)); + wrp_mov(nfp_prog, reg_both(i), reg_xfer(i)); if (i < 2) wrp_immed(nfp_prog, reg_both(1), 0); @@ -1032,8 +1036,8 @@ static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { if (meta->insn.off == offsetof(struct sk_buff, len)) - emit_alu(nfp_prog, reg_both(meta->insn.dst_reg * 2), - reg_none(), ALU_OP_NONE, plen_reg(nfp_prog)); + wrp_mov(nfp_prog, + reg_both(meta->insn.dst_reg * 2), plen_reg(nfp_prog)); else return -EOPNOTSUPP; @@ -1048,7 +1052,7 @@ static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) meta->insn.off != offsetof(struct xdp_md, data_end)) return -EOPNOTSUPP; - emit_alu(nfp_prog, dst, reg_none(), ALU_OP_NONE, pptr_reg(nfp_prog)); + wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); if (meta->insn.off == offsetof(struct xdp_md, data)) return 0; @@ -1438,8 +1442,7 @@ static void nfp_outro_tc_legacy(struct nfp_prog *nfp_prog) * ife + tx 0x24 -> redir, count as stat1 */ emit_br_byte_neq(nfp_prog, reg_b(0), 0xff, 0, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16); emit_br(nfp_prog, BR_UNC, nfp_prog->tgt_done, 1); @@ -1466,8 +1469,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x11), SHF_SC_L_SHF, 16); /* Target for normal exits */ @@ -1476,8 +1478,7 @@ static void nfp_outro_tc_da(struct nfp_prog *nfp_prog) /* if R0 > 7 jump to abort */ emit_alu(nfp_prog, reg_none(), reg_imm(7), ALU_OP_SUB, reg_b(0)); emit_br(nfp_prog, BR_BLO, nfp_prog->tgt_abort, 0); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); wrp_immed(nfp_prog, reg_b(2), 0x41221211); wrp_immed(nfp_prog, reg_b(3), 0x41001211); @@ -1514,8 +1515,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_imm(0x82), SHF_SC_L_SHF, 16); /* Target for normal exits */ @@ -1536,8 +1536,7 @@ static void nfp_outro_xdp(struct nfp_prog *nfp_prog) emit_br_def(nfp_prog, nfp_prog->tgt_done, 2); - emit_alu(nfp_prog, reg_a(0), - reg_none(), ALU_OP_NONE, NFP_BPF_ABI_FLAGS); + wrp_mov(nfp_prog, reg_a(0), NFP_BPF_ABI_FLAGS); emit_ld_field(nfp_prog, reg_a(0), 0xc, reg_b(2), SHF_SC_L_SHF, 16); } -- GitLab From 3119d1fd46464c61c80731c3a9f40eee4434fc1d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:12 -0700 Subject: [PATCH 1348/1507] nfp: bpf: implement byte swap instruction Implement byte swaps with rotations, shifts and byte loads. Remember to clear upper parts of the 64 bit registers. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 38 ++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 4f7cfa6adfc13..5e8a6b7667908 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -746,6 +746,14 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, return 0; } +static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out) +{ + emit_ld_field(nfp_prog, reg_both(gpr_out), 0xf, reg_in, + SHF_SC_R_ROT, 8); + emit_ld_field(nfp_prog, reg_both(gpr_out), 0x5, reg_a(gpr_out), + SHF_SC_R_ROT, 16); +} + /* --- Callbacks --- */ static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { @@ -982,6 +990,35 @@ static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return 0; } +static int end_reg32(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + const struct bpf_insn *insn = &meta->insn; + u8 gpr = insn->dst_reg * 2; + + switch (insn->imm) { + case 16: + emit_ld_field(nfp_prog, reg_both(gpr), 0x9, reg_b(gpr), + SHF_SC_R_ROT, 8); + emit_ld_field(nfp_prog, reg_both(gpr), 0xe, reg_a(gpr), + SHF_SC_R_SHF, 16); + + wrp_immed(nfp_prog, reg_both(gpr + 1), 0); + break; + case 32: + wrp_end32(nfp_prog, reg_a(gpr), gpr); + wrp_immed(nfp_prog, reg_both(gpr + 1), 0); + break; + case 64: + wrp_mov(nfp_prog, imm_a(nfp_prog), reg_b(gpr + 1)); + + wrp_end32(nfp_prog, reg_a(gpr), gpr + 1); + wrp_end32(nfp_prog, imm_a(nfp_prog), gpr); + break; + } + + return 0; +} + static int imm_ld8_part2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { wrp_immed(nfp_prog, reg_both(nfp_meta_prev(meta)->insn.dst_reg * 2 + 1), @@ -1297,6 +1334,7 @@ static const instr_cb_t instr_cb[256] = { [BPF_ALU | BPF_SUB | BPF_X] = sub_reg, [BPF_ALU | BPF_SUB | BPF_K] = sub_imm, [BPF_ALU | BPF_LSH | BPF_K] = shl_imm, + [BPF_ALU | BPF_END | BPF_X] = end_reg32, [BPF_LD | BPF_IMM | BPF_DW] = imm_ld8, [BPF_LD | BPF_ABS | BPF_B] = data_ld1, [BPF_LD | BPF_ABS | BPF_H] = data_ld2, -- GitLab From 0f6cf4ddf63fa4d645c36d96ed1092fe7a0a8d0f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:13 -0700 Subject: [PATCH 1349/1507] nfp: bpf: support BPF offload only on little endian eBPF is host-endian specific. Translating both BE and LE eBPF to the NFP is feasible, but would require quite a bit of indirection. The fact that I don't have access to any BE hosts that would fit a 25G/40G/100G NIC is also limiting my ability to test big endian. For now restrict the offload to little endian hosts only. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 074726980994d..6e74f8db1cc11 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -42,9 +42,11 @@ static bool nfp_net_ebpf_capable(struct nfp_net *nn) { +#ifdef __LITTLE_ENDIAN if (nn->cap & NFP_NET_CFG_CTRL_BPF && nn_readb(nn, NFP_NET_CFG_BPF_ABI) == NFP_NET_BPF_ABI) return true; +#endif return false; } -- GitLab From 943c57b97cde2ce0806e59b553c650c9889d8b69 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:14 -0700 Subject: [PATCH 1350/1507] nfp: bpf: fix context accesses Sizes of fields in struct xdp_md/xdp_buff and some in sk_buff depend on target architecture. Take that into account and use struct xdp_buff, not struct xdp_md. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 49 ++++++++++++-------- 1 file changed, 29 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 5e8a6b7667908..4b62f5497728d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1070,47 +1070,56 @@ static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) meta->insn.src_reg * 2, true, 4); } -static int mem_ldx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + u8 size) { - if (meta->insn.off == offsetof(struct sk_buff, len)) + switch (meta->insn.off) { + case offsetof(struct sk_buff, len): + if (size != FIELD_SIZEOF(struct sk_buff, len)) + return -EOPNOTSUPP; wrp_mov(nfp_prog, reg_both(meta->insn.dst_reg * 2), plen_reg(nfp_prog)); - else + break; + default: return -EOPNOTSUPP; + } + + wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); return 0; } -static int mem_ldx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + u8 size) { swreg dst = reg_both(meta->insn.dst_reg * 2); - if (meta->insn.off != offsetof(struct xdp_md, data) && - meta->insn.off != offsetof(struct xdp_md, data_end)) - return -EOPNOTSUPP; - - wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); + if (size != sizeof(void *)) + return -EINVAL; - if (meta->insn.off == offsetof(struct xdp_md, data)) - return 0; + switch (meta->insn.off) { + case offsetof(struct xdp_buff, data): + wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); + break; + case offsetof(struct xdp_buff, data_end): + emit_alu(nfp_prog, dst, + plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); + break; + default: + return -EOPNOTSUPP; + } - emit_alu(nfp_prog, dst, dst, ALU_OP_ADD, plen_reg(nfp_prog)); + wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); return 0; } static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - int ret; - if (nfp_prog->act == NN_ACT_XDP) - ret = mem_ldx4_xdp(nfp_prog, meta); + return mem_ldx_xdp(nfp_prog, meta, 4); else - ret = mem_ldx4_skb(nfp_prog, meta); - - wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0); - - return ret; + return mem_ldx_skb(nfp_prog, meta, 4); } static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -- GitLab From 0a7939775f8546268206c1e8efe78218f3c18aae Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:15 -0700 Subject: [PATCH 1351/1507] nfp: bpf: separate I/O from checks for legacy data load Move data load into a separate function and separate it from packet length checks of legacy I/O. This makes the code more readable and easier to reuse. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 77 ++++++++++---------- 1 file changed, 40 insertions(+), 37 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 4b62f5497728d..3e173da16428a 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -515,63 +515,66 @@ static void wrp_reg_mov(struct nfp_prog *nfp_prog, u16 dst, u16 src) } static int -construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, - u16 src, bool src_valid, u8 size) +data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size) { unsigned int i; u16 shift, sz; - swreg tmp_reg; /* We load the value from the address indicated in @offset and then * shift out the data we don't need. Note: this is big endian! */ - sz = size < 4 ? 4 : size; + sz = max(size, 4); shift = size < 4 ? 4 - size : 0; - if (src_valid) { - /* Calculate the true offset (src_reg + imm) */ - tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); - emit_alu(nfp_prog, imm_both(nfp_prog), - reg_a(src), ALU_OP_ADD, tmp_reg); - /* Check packet length (size guaranteed to fit b/c it's u8) */ - emit_alu(nfp_prog, imm_a(nfp_prog), - imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size)); - emit_alu(nfp_prog, reg_none(), - plen_reg(nfp_prog), ALU_OP_SUB, imm_a(nfp_prog)); - wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); - /* Load data */ - emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pptr_reg(nfp_prog), imm_b(nfp_prog), sz - 1, true); - } else { - /* Check packet length */ - tmp_reg = ur_load_imm_any(nfp_prog, offset + size, - imm_a(nfp_prog)); - emit_alu(nfp_prog, reg_none(), - plen_reg(nfp_prog), ALU_OP_SUB, tmp_reg); - wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); - /* Load data */ - tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); - emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, - pptr_reg(nfp_prog), tmp_reg, sz - 1, true); - } + emit_cmd(nfp_prog, CMD_TGT_READ8, CMD_MODE_32b, 0, + pptr_reg(nfp_prog), offset, sz - 1, true); i = 0; if (shift) - emit_shf(nfp_prog, reg_both(0), reg_none(), SHF_OP_NONE, + emit_shf(nfp_prog, reg_both(dst_gpr), reg_none(), SHF_OP_NONE, reg_xfer(0), SHF_SC_R_SHF, shift * 8); else for (; i * 4 < size; i++) - wrp_mov(nfp_prog, reg_both(i), reg_xfer(i)); + wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i)); if (i < 2) - wrp_immed(nfp_prog, reg_both(1), 0); + wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0); return 0; } +static int +construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size) +{ + swreg tmp_reg; + + /* Calculate the true offset (src_reg + imm) */ + tmp_reg = ur_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); + emit_alu(nfp_prog, imm_both(nfp_prog), reg_a(src), ALU_OP_ADD, tmp_reg); + + /* Check packet length (size guaranteed to fit b/c it's u8) */ + emit_alu(nfp_prog, imm_a(nfp_prog), + imm_a(nfp_prog), ALU_OP_ADD, reg_imm(size)); + emit_alu(nfp_prog, reg_none(), + plen_reg(nfp_prog), ALU_OP_SUB, imm_a(nfp_prog)); + wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); + + /* Load data */ + return data_ld(nfp_prog, imm_b(nfp_prog), 0, size); +} + static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size) { - return construct_data_ind_ld(nfp_prog, offset, 0, false, size); + swreg tmp_reg; + + /* Check packet length */ + tmp_reg = ur_load_imm_any(nfp_prog, offset + size, imm_a(nfp_prog)); + emit_alu(nfp_prog, reg_none(), plen_reg(nfp_prog), ALU_OP_SUB, tmp_reg); + wrp_br_special(nfp_prog, BR_BLO, OP_BR_GO_ABORT); + + /* Load data */ + tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog)); + return data_ld(nfp_prog, tmp_reg, 0, size); } static void @@ -1055,19 +1058,19 @@ static int data_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int data_ind_ld1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 1); + meta->insn.src_reg * 2, 1); } static int data_ind_ld2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 2); + meta->insn.src_reg * 2, 2); } static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return construct_data_ind_ld(nfp_prog, meta->insn.imm, - meta->insn.src_reg * 2, true, 4); + meta->insn.src_reg * 2, 4); } static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, -- GitLab From 2ca71441f524b0a0cc01d8e51c875b00fbe31275 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:16 -0700 Subject: [PATCH 1352/1507] nfp: bpf: add support for direct packet access - read In direct packet access bound checks are already done, we can simply dereference the packet pointer. Verifier/parser logic needs to record pointer type. Note that although verifier does protect us from CTX vs other pointer changes we will also want to differentiate between PACKET vs MAP_VALUE or STACK, so we can add the check already. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 85 ++++++++++++++++++- drivers/net/ethernet/netronome/nfp/bpf/main.h | 3 + .../net/ethernet/netronome/nfp/bpf/verifier.c | 21 +++-- drivers/net/ethernet/netronome/nfp/nfp_asm.c | 3 + drivers/net/ethernet/netronome/nfp/nfp_asm.h | 4 + 5 files changed, 105 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 3e173da16428a..975d63fbc1d53 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -543,6 +543,36 @@ data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size) return 0; } +static int +data_ld_host_order(struct nfp_prog *nfp_prog, u8 src_gpr, swreg offset, + u8 dst_gpr, int size) +{ + unsigned int i; + u8 mask, sz; + + /* We load the value from the address indicated in @offset and then + * mask out the data we don't need. Note: this is little endian! + */ + sz = max(size, 4); + mask = size < 4 ? GENMASK(size - 1, 0) : 0; + + emit_cmd(nfp_prog, CMD_TGT_READ32_SWAP, CMD_MODE_32b, 0, + reg_a(src_gpr), offset, sz / 4 - 1, true); + + i = 0; + if (mask) + emit_ld_field_any(nfp_prog, reg_both(dst_gpr), mask, + reg_xfer(0), SHF_SC_NONE, 0, true); + else + for (; i * 4 < size; i++) + wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i)); + + if (i < 2) + wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0); + + return 0; +} + static int construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size) { @@ -1117,12 +1147,53 @@ static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, return 0; } +static int +mem_ldx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + swreg tmp_reg; + + tmp_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_ld_host_order(nfp_prog, meta->insn.src_reg * 2, tmp_reg, + meta->insn.dst_reg * 2, size); +} + +static int +mem_ldx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + if (meta->ptr.type == PTR_TO_CTX) { + if (nfp_prog->act == NN_ACT_XDP) + return mem_ldx_xdp(nfp_prog, meta, size); + else + return mem_ldx_skb(nfp_prog, meta, size); + } + + if (meta->ptr.type == PTR_TO_PACKET) + return mem_ldx_data(nfp_prog, meta, size); + + return -EOPNOTSUPP; +} + +static int mem_ldx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 1); +} + +static int mem_ldx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 2); +} + static int mem_ldx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - if (nfp_prog->act == NN_ACT_XDP) - return mem_ldx_xdp(nfp_prog, meta, 4); - else - return mem_ldx_skb(nfp_prog, meta, 4); + return mem_ldx(nfp_prog, meta, 4); +} + +static int mem_ldx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_ldx(nfp_prog, meta, 8); } static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -1137,6 +1208,9 @@ static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { + if (meta->ptr.type == PTR_TO_PACKET) + return -EOPNOTSUPP; + if (nfp_prog->act == NN_ACT_XDP) return mem_stx4_xdp(nfp_prog, meta); return mem_stx4_skb(nfp_prog, meta); @@ -1354,7 +1428,10 @@ static const instr_cb_t instr_cb[256] = { [BPF_LD | BPF_IND | BPF_B] = data_ind_ld1, [BPF_LD | BPF_IND | BPF_H] = data_ind_ld2, [BPF_LD | BPF_IND | BPF_W] = data_ind_ld4, + [BPF_LDX | BPF_MEM | BPF_B] = mem_ldx1, + [BPF_LDX | BPF_MEM | BPF_H] = mem_ldx2, [BPF_LDX | BPF_MEM | BPF_W] = mem_ldx4, + [BPF_LDX | BPF_MEM | BPF_DW] = mem_ldx8, [BPF_STX | BPF_MEM | BPF_W] = mem_stx4, [BPF_JMP | BPF_JA | BPF_K] = jump, [BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index b7a112acbdb72..d77e88a454096 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -36,6 +36,7 @@ #include #include +#include #include #include @@ -96,6 +97,7 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *); /** * struct nfp_insn_meta - BPF instruction wrapper * @insn: BPF instruction + * @ptr: pointer type for memory operations * @off: index of first generated machine instruction (in nfp_prog.prog) * @n: eBPF instruction number * @skip: skip this instruction (optimized out) @@ -104,6 +106,7 @@ typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *); */ struct nfp_insn_meta { struct bpf_insn insn; + struct bpf_reg_state ptr; unsigned int off; unsigned short n; bool skip; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index 5b783a91b115e..e361c0e3b788d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -112,12 +112,19 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog, } static int -nfp_bpf_check_ctx_ptr(struct nfp_prog *nfp_prog, - const struct bpf_verifier_env *env, u8 reg) +nfp_bpf_check_ptr(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + const struct bpf_verifier_env *env, u8 reg) { - if (env->cur_state.regs[reg].type != PTR_TO_CTX) + if (env->cur_state.regs[reg].type != PTR_TO_CTX && + env->cur_state.regs[reg].type != PTR_TO_PACKET) return -EINVAL; + if (meta->ptr.type != NOT_INIT && + meta->ptr.type != env->cur_state.regs[reg].type) + return -EINVAL; + + meta->ptr = env->cur_state.regs[reg]; + return 0; } @@ -145,11 +152,11 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) return nfp_bpf_check_exit(priv->prog, env); if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM)) - return nfp_bpf_check_ctx_ptr(priv->prog, env, - meta->insn.src_reg); + return nfp_bpf_check_ptr(priv->prog, meta, env, + meta->insn.src_reg); if ((meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM)) - return nfp_bpf_check_ctx_ptr(priv->prog, env, - meta->insn.dst_reg); + return nfp_bpf_check_ptr(priv->prog, meta, env, + meta->insn.dst_reg); return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index de76e7444fc23..7cae99b3e00a5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -42,6 +42,9 @@ const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { [CMD_TGT_WRITE8] = { 0x00, 0x42 }, [CMD_TGT_READ8] = { 0x01, 0x43 }, + [CMD_TGT_READ32] = { 0x00, 0x5c }, + [CMD_TGT_READ32_LE] = { 0x01, 0x5c }, + [CMD_TGT_READ32_SWAP] = { 0x02, 0x5c }, [CMD_TGT_READ_LE] = { 0x01, 0x40 }, [CMD_TGT_READ_SWAP_LE] = { 0x03, 0x40 }, }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index c4c18dd5630a9..e3df7a26724fd 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -153,6 +153,7 @@ enum shf_op { enum shf_sc { SHF_SC_R_ROT = 0, + SHF_SC_NONE = SHF_SC_R_ROT, SHF_SC_R_SHF = 1, SHF_SC_L_SHF = 2, SHF_SC_R_DSHF = 3, @@ -217,6 +218,9 @@ struct cmd_tgt_act { enum cmd_tgt_map { CMD_TGT_READ8, CMD_TGT_WRITE8, + CMD_TGT_READ32, + CMD_TGT_READ32_LE, + CMD_TGT_READ32_SWAP, CMD_TGT_READ_LE, CMD_TGT_READ_SWAP_LE, __CMD_TGT_MAP_SIZE, -- GitLab From e663fe3863ad20c5e6a84a1a1d47aff8e71f583f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:17 -0700 Subject: [PATCH 1353/1507] nfp: bpf: direct packet access - write This patch adds ability to write packet contents using pre-validated packet pointers (direct packet access). Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 114 +++++++++++++++++-- drivers/net/ethernet/netronome/nfp/nfp_asm.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_asm.h | 2 +- 3 files changed, 109 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 975d63fbc1d53..139a4ebdc774b 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -607,6 +607,35 @@ static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size) return data_ld(nfp_prog, tmp_reg, 0, size); } +static int +data_stx_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset, + u8 src_gpr, u8 size) +{ + unsigned int i; + + for (i = 0; i * 4 < size; i++) + wrp_mov(nfp_prog, reg_xfer(i), reg_a(src_gpr + i)); + + emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0, + reg_a(dst_gpr), offset, size - 1, true); + + return 0; +} + +static int +data_st_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr, swreg offset, + u64 imm, u8 size) +{ + wrp_immed(nfp_prog, reg_xfer(0), imm); + if (size == 8) + wrp_immed(nfp_prog, reg_xfer(1), imm >> 32); + + emit_cmd(nfp_prog, CMD_TGT_WRITE8_SWAP, CMD_MODE_32b, 0, + reg_a(dst_gpr), offset, size - 1, true); + + return 0; +} + static void wrp_alu_imm(struct nfp_prog *nfp_prog, u8 dst, enum alu_op alu_op, u32 imm) { @@ -1196,24 +1225,88 @@ static int mem_ldx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return mem_ldx(nfp_prog, meta, 8); } -static int mem_stx4_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int +mem_st_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + u64 imm = meta->insn.imm; /* sign extend */ + swreg off_reg; + + off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_st_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg, + imm, size); +} + +static int mem_st(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) { + if (meta->ptr.type == PTR_TO_PACKET) + return mem_st_data(nfp_prog, meta, size); + return -EOPNOTSUPP; } -static int mem_stx4_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +static int mem_st1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 1); +} + +static int mem_st2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 2); +} + +static int mem_st4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_st(nfp_prog, meta, 4); +} + +static int mem_st8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { + return mem_st(nfp_prog, meta, 8); +} + +static int +mem_stx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + swreg off_reg; + + off_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog)); + + return data_stx_host_order(nfp_prog, meta->insn.dst_reg * 2, off_reg, + meta->insn.src_reg * 2, size); +} + +static int +mem_stx(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, + unsigned int size) +{ + if (meta->ptr.type == PTR_TO_PACKET) + return mem_stx_data(nfp_prog, meta, size); + return -EOPNOTSUPP; } +static int mem_stx1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 1); +} + +static int mem_stx2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 2); +} + static int mem_stx4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - if (meta->ptr.type == PTR_TO_PACKET) - return -EOPNOTSUPP; + return mem_stx(nfp_prog, meta, 4); +} - if (nfp_prog->act == NN_ACT_XDP) - return mem_stx4_xdp(nfp_prog, meta); - return mem_stx4_skb(nfp_prog, meta); +static int mem_stx8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return mem_stx(nfp_prog, meta, 8); } static int jump(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -1432,7 +1525,14 @@ static const instr_cb_t instr_cb[256] = { [BPF_LDX | BPF_MEM | BPF_H] = mem_ldx2, [BPF_LDX | BPF_MEM | BPF_W] = mem_ldx4, [BPF_LDX | BPF_MEM | BPF_DW] = mem_ldx8, + [BPF_STX | BPF_MEM | BPF_B] = mem_stx1, + [BPF_STX | BPF_MEM | BPF_H] = mem_stx2, [BPF_STX | BPF_MEM | BPF_W] = mem_stx4, + [BPF_STX | BPF_MEM | BPF_DW] = mem_stx8, + [BPF_ST | BPF_MEM | BPF_B] = mem_st1, + [BPF_ST | BPF_MEM | BPF_H] = mem_st2, + [BPF_ST | BPF_MEM | BPF_W] = mem_st4, + [BPF_ST | BPF_MEM | BPF_DW] = mem_st8, [BPF_JMP | BPF_JA | BPF_K] = jump, [BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm, [BPF_JMP | BPF_JGT | BPF_K] = jgt_imm, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 7cae99b3e00a5..830f6de25f475 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -40,7 +40,7 @@ #include "nfp_asm.h" const struct cmd_tgt_act cmd_tgt_act[__CMD_TGT_MAP_SIZE] = { - [CMD_TGT_WRITE8] = { 0x00, 0x42 }, + [CMD_TGT_WRITE8_SWAP] = { 0x02, 0x42 }, [CMD_TGT_READ8] = { 0x01, 0x43 }, [CMD_TGT_READ32] = { 0x00, 0x5c }, [CMD_TGT_READ32_LE] = { 0x01, 0x5c }, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index e3df7a26724fd..c26aa7e4a8396 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -217,7 +217,7 @@ struct cmd_tgt_act { enum cmd_tgt_map { CMD_TGT_READ8, - CMD_TGT_WRITE8, + CMD_TGT_WRITE8_SWAP, CMD_TGT_READ32, CMD_TGT_READ32_LE, CMD_TGT_READ32_SWAP, -- GitLab From bfddbc8adcd471806f2369d347a958d11e80f53b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 12 Oct 2017 10:34:18 -0700 Subject: [PATCH 1354/1507] nfp: bpf: support direct packet access in TC Add support for direct packet access in TC, note that because writing the packet will cause the verifier to generate a csum fixup prologue we won't be able to offload packet writes from TC, just yet, only the reads will work. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 139a4ebdc774b..23fb11a41cc45 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1135,12 +1135,25 @@ static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, u8 size) { + swreg dst = reg_both(meta->insn.dst_reg * 2); + switch (meta->insn.off) { case offsetof(struct sk_buff, len): if (size != FIELD_SIZEOF(struct sk_buff, len)) return -EOPNOTSUPP; - wrp_mov(nfp_prog, - reg_both(meta->insn.dst_reg * 2), plen_reg(nfp_prog)); + wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); + break; + case offsetof(struct sk_buff, data): + if (size != sizeof(void *)) + return -EOPNOTSUPP; + wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); + break; + case offsetof(struct sk_buff, cb) + + offsetof(struct bpf_skb_data_end, data_end): + if (size != sizeof(void *)) + return -EOPNOTSUPP; + emit_alu(nfp_prog, dst, + plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); break; default: return -EOPNOTSUPP; -- GitLab From ae904beaea48d369205c81dbffecc23afcec46de Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 14 Aug 2017 11:23:27 +0300 Subject: [PATCH 1355/1507] net/mlx5: File renaming towards ptp core implementation en_clock.c renamed clock.c and moved to lib/ as first step towards relocating code to core part of the driver to allow sharing between Ethernet and Infiniband. Signed-off-by: Feras Daoud Signed-off-by: Eitan Rabin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 2 +- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 4 ++-- .../ethernet/mellanox/mlx5/core/{en_clock.c => lib/clock.c} | 0 3 files changed, 3 insertions(+), 3 deletions(-) rename drivers/net/ethernet/mellanox/mlx5/core/{en_clock.c => lib/clock.c} (100%) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index fdaef00465d77..25deaa5a534c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -6,6 +6,7 @@ config MLX5_CORE tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver" depends on MAY_USE_DEVLINK depends on PCI + imply PTP_1588_CLOCK default n ---help--- Core driver for low level functionality of the ConnectX-4 and @@ -29,7 +30,6 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m - imply PTP_1588_CLOCK default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 87a3099808f3d..d9621b2152d3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -4,7 +4,7 @@ subdir-ccflags-y += -I$(src) mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ - fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \ + fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \ diag/fs_tracepoint.o mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o @@ -13,7 +13,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ - en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ + en_tx.o en_rx.o en_rx_am.o en_txrx.o vxlan.o \ en_arfs.o en_fs_ethtool.o en_selftest.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c similarity index 100% rename from drivers/net/ethernet/mellanox/mlx5/core/en_clock.c rename to drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c -- GitLab From 7c39afb394c79e72c3795b4a42d55155b34ee073 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Tue, 15 Aug 2017 13:46:04 +0300 Subject: [PATCH 1356/1507] net/mlx5: PTP code migration to driver core section PTP code is moved to core section of mlx5 driver in order to share it between ethernet and infiniband. This movement involves the following changes: - Change mlx5e_ prefix to be mlx5_ - Add clock structs to Core - Add clock object to mlx5_core_dev - Call Init/Uninit clock from core init/cleanup - Rename mlx5e_tstamp to be mlx5_clock Signed-off-by: Feras Daoud Signed-off-by: Eitan Rabin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 39 +- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 7 +- .../net/ethernet/mellanox/mlx5/core/en_main.c | 95 ++- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 17 +- .../net/ethernet/mellanox/mlx5/core/en_tx.c | 6 +- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 3 +- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 3 +- .../ethernet/mellanox/mlx5/core/lib/clock.c | 548 ++++++++---------- .../ethernet/mellanox/mlx5/core/lib/clock.h | 51 ++ .../net/ethernet/mellanox/mlx5/core/main.c | 4 + .../ethernet/mellanox/mlx5/core/mlx5_core.h | 1 + include/linux/mlx5/driver.h | 24 + 12 files changed, 416 insertions(+), 382 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index cc13d3dbd3666..2059122eb089f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -267,28 +267,6 @@ struct mlx5e_dcbx { }; #endif -#define MAX_PIN_NUM 8 -struct mlx5e_pps { - u8 pin_caps[MAX_PIN_NUM]; - struct work_struct out_work; - u64 start[MAX_PIN_NUM]; - u8 enabled; -}; - -struct mlx5e_tstamp { - rwlock_t lock; - struct cyclecounter cycles; - struct timecounter clock; - struct hwtstamp_config hwtstamp_config; - u32 nominal_c_mult; - unsigned long overflow_period; - struct delayed_work overflow_work; - struct mlx5_core_dev *mdev; - struct ptp_clock *ptp; - struct ptp_clock_info ptp_info; - struct mlx5e_pps pps_info; -}; - enum { MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_AM, @@ -375,9 +353,10 @@ struct mlx5e_txqsq { u8 min_inline_mode; u16 edge; struct device *pdev; - struct mlx5e_tstamp *tstamp; __be32 mkey_be; unsigned long state; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; /* control path */ struct mlx5_wq_ctrl wq_ctrl; @@ -543,10 +522,11 @@ struct mlx5e_rq { struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; - struct mlx5e_tstamp *tstamp; struct mlx5e_rq_stats stats; struct mlx5e_cq cq; struct mlx5e_page_cache page_cache; + struct hwtstamp_config *tstamp; + struct mlx5_clock *clock; mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_post_rx_wqes post_wqes; @@ -588,7 +568,7 @@ struct mlx5e_channel { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct mlx5e_tstamp *tstamp; + struct hwtstamp_config *tstamp; int ix; }; @@ -789,7 +769,7 @@ struct mlx5e_priv { struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; - struct mlx5e_tstamp tstamp; + struct hwtstamp_config tstamp; u16 q_counter; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx dcbx; @@ -873,12 +853,6 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); void mlx5e_set_rx_mode_work(struct work_struct *work); -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *clock, u64 timestamp, - struct skb_shared_hwtstamps *hwts); -void mlx5e_timestamp_init(struct mlx5e_priv *priv); -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv); -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event); int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val); @@ -889,6 +863,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); +void mlx5e_timestamp_set(struct mlx5e_priv *priv); struct mlx5e_redirect_rqt_param { bool is_rss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d12e9fc0d76b8..81a112e40fe32 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1417,14 +1417,15 @@ static int mlx5e_set_pauseparam(struct net_device *netdev, int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, struct ethtool_ts_info *info) { + struct mlx5_core_dev *mdev = priv->mdev; int ret; ret = ethtool_op_get_ts_info(priv->netdev, info); if (ret) return ret; - info->phc_index = priv->tstamp.ptp ? - ptp_clock_index(priv->tstamp.ptp) : -1; + info->phc_index = mdev->clock.ptp ? + ptp_clock_index(mdev->clock.ptp) : -1; if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) return 0; @@ -1754,7 +1755,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) { + if (enable && priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cc11bbbd0309d..6df00dd9745af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -373,8 +373,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, enum mlx5_dev_event event, unsigned long param) { struct mlx5e_priv *priv = vpriv; - struct ptp_clock_event ptp_event; - struct mlx5_eqe *eqe = NULL; if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state)) return; @@ -384,14 +382,6 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, case MLX5_DEV_EVENT_PORT_DOWN: queue_work(priv->wq, &priv->update_carrier_work); break; - case MLX5_DEV_EVENT_PPS: - eqe = (struct mlx5_eqe *)param; - ptp_event.index = eqe->data.pps.pin; - ptp_event.timestamp = - timecounter_cyc2time(&priv->tstamp.clock, - be64_to_cpu(eqe->data.pps.time_stamp)); - mlx5e_pps_event_handler(vpriv, &ptp_event); - break; default: break; } @@ -585,6 +575,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->pdev = c->pdev; rq->netdev = c->netdev; rq->tstamp = c->tstamp; + rq->clock = &mdev->clock; rq->channel = c; rq->ix = c->ix; rq->mdev = mdev; @@ -1123,6 +1114,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->pdev = c->pdev; sq->tstamp = c->tstamp; + sq->clock = &mdev->clock; sq->mkey_be = c->mkey_be; sq->channel = c; sq->txq_ix = txq_ix; @@ -2678,6 +2670,12 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } +void mlx5e_timestamp_set(struct mlx5e_priv *priv) +{ + priv->tstamp.tx_type = HWTSTAMP_TX_OFF; + priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -2693,7 +2691,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_activate_priv_channels(priv); if (priv->profile->update_carrier) priv->profile->update_carrier(priv); - mlx5e_timestamp_init(priv); + mlx5e_timestamp_set(priv); if (priv->profile->update_stats) queue_delayed_work(priv->wq, &priv->update_stats_work, 0); @@ -2731,7 +2729,6 @@ int mlx5e_close_locked(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); - mlx5e_timestamp_cleanup(priv); netif_carrier_off(priv->netdev); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); @@ -3403,6 +3400,80 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) return err; } +int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* TX HW timestamp */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + mutex_lock(&priv->state_lock); + /* RX HW timestamp */ + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + /* Reset CQE compression to Admin default */ + mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + /* Disable CQE compression */ + netdev_warn(priv->netdev, "Disabling cqe compression"); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + if (err) { + netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); + mutex_unlock(&priv->state_lock); + return err; + } + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + mutex_unlock(&priv->state_lock); + return -ERANGE; + } + + memcpy(&priv->tstamp, &config, sizeof(config)); + mutex_unlock(&priv->state_lock); + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) +{ + struct hwtstamp_config *cfg = &priv->tstamp; + + if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; +} + static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct mlx5e_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 15a1687483cc5..7e3bfe62ef6e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -42,10 +42,11 @@ #include "en_rep.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" -static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) +static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { - return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + return config->rx_filter == HWTSTAMP_FILTER_ALL; } static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc, @@ -661,7 +662,6 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; int lro_num_seg; lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; @@ -676,8 +676,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, rq->stats.lro_bytes += cqe_bcnt; } - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -1163,7 +1164,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, struct sk_buff *skb) { struct net_device *netdev = rq->netdev; - struct mlx5e_tstamp *tstamp = rq->tstamp; char *pseudo_header; u8 *dgid; u8 g; @@ -1188,8 +1188,9 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) - mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); + if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + skb_hwtstamps(skb)->hwtstamp = + mlx5_timecounter_cyc2time(rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 1d6925d4369af..a7c208a1ad83f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -35,6 +35,7 @@ #include "en.h" #include "ipoib/ipoib.h" #include "en_accel/ipsec_rxtx.h" +#include "lib/clock.h" #define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ @@ -452,8 +453,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) SKBTX_HW_TSTAMP)) { struct skb_shared_hwtstamps hwts = {}; - mlx5e_fill_hwstamp(sq->tstamp, - get_cqe_ts(cqe), &hwts); + hwts.hwtstamp = + mlx5_timecounter_cyc2time(sq->clock, + get_cqe_ts(cqe)); skb_tstamp_tx(skb, &hwts); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index fc606bfd1d6e2..60771865c99c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -491,8 +491,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_PPS_EVENT: - if (dev->event) - dev->event(dev, MLX5_DEV_EVENT_PPS, (unsigned long)eqe); + mlx5_pps_event(dev, eqe); break; case MLX5_EVENT_TYPE_FPGA_ERROR: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 145e392ab8497..14dfb577691b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -404,7 +404,7 @@ static int mlx5i_open(struct net_device *netdev) mlx5e_refresh_tirs(priv, false); mlx5e_activate_priv_channels(priv); - mlx5e_timestamp_init(priv); + mlx5e_timestamp_set(priv); mutex_unlock(&priv->state_lock); return 0; @@ -429,7 +429,6 @@ static int mlx5i_close(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); - mlx5e_timestamp_cleanup(priv); netif_carrier_off(priv->netdev); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 84dd63e740414..fa8aed62b2314 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -34,250 +34,164 @@ #include "en.h" enum { - MLX5E_CYCLES_SHIFT = 23 + MLX5_CYCLES_SHIFT = 23 }; enum { - MLX5E_PIN_MODE_IN = 0x0, - MLX5E_PIN_MODE_OUT = 0x1, + MLX5_PIN_MODE_IN = 0x0, + MLX5_PIN_MODE_OUT = 0x1, }; enum { - MLX5E_OUT_PATTERN_PULSE = 0x0, - MLX5E_OUT_PATTERN_PERIODIC = 0x1, + MLX5_OUT_PATTERN_PULSE = 0x0, + MLX5_OUT_PATTERN_PERIODIC = 0x1, }; enum { - MLX5E_EVENT_MODE_DISABLE = 0x0, - MLX5E_EVENT_MODE_REPETETIVE = 0x1, - MLX5E_EVENT_MODE_ONCE_TILL_ARM = 0x2, + MLX5_EVENT_MODE_DISABLE = 0x0, + MLX5_EVENT_MODE_REPETETIVE = 0x1, + MLX5_EVENT_MODE_ONCE_TILL_ARM = 0x2, }; enum { - MLX5E_MTPPS_FS_ENABLE = BIT(0x0), - MLX5E_MTPPS_FS_PATTERN = BIT(0x2), - MLX5E_MTPPS_FS_PIN_MODE = BIT(0x3), - MLX5E_MTPPS_FS_TIME_STAMP = BIT(0x4), - MLX5E_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), - MLX5E_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), + MLX5_MTPPS_FS_ENABLE = BIT(0x0), + MLX5_MTPPS_FS_PATTERN = BIT(0x2), + MLX5_MTPPS_FS_PIN_MODE = BIT(0x3), + MLX5_MTPPS_FS_TIME_STAMP = BIT(0x4), + MLX5_MTPPS_FS_OUT_PULSE_DURATION = BIT(0x5), + MLX5_MTPPS_FS_ENH_OUT_PER_ADJ = BIT(0x7), }; -void mlx5e_fill_hwstamp(struct mlx5e_tstamp *tstamp, u64 timestamp, - struct skb_shared_hwtstamps *hwts) +static u64 read_internal_timer(const struct cyclecounter *cc) { - u64 nsec; + struct mlx5_clock *clock = container_of(cc, struct mlx5_clock, cycles); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); - read_lock(&tstamp->lock); - nsec = timecounter_cyc2time(&tstamp->clock, timestamp); - read_unlock(&tstamp->lock); - - hwts->hwtstamp = ns_to_ktime(nsec); -} - -static u64 mlx5e_read_internal_timer(const struct cyclecounter *cc) -{ - struct mlx5e_tstamp *tstamp = container_of(cc, struct mlx5e_tstamp, - cycles); - - return mlx5_read_internal_timer(tstamp->mdev) & cc->mask; + return mlx5_read_internal_timer(mdev) & cc->mask; } -static void mlx5e_pps_out(struct work_struct *work) +static void mlx5_pps_out(struct work_struct *work) { - struct mlx5e_pps *pps_info = container_of(work, struct mlx5e_pps, - out_work); - struct mlx5e_tstamp *tstamp = container_of(pps_info, struct mlx5e_tstamp, - pps_info); + struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps, + out_work); + struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock, + pps_info); + struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, + clock); u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; unsigned long flags; int i; - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { + for (i = 0; i < clock->ptp_info.n_pins; i++) { u64 tstart; - write_lock_irqsave(&tstamp->lock, flags); - tstart = tstamp->pps_info.start[i]; - tstamp->pps_info.start[i] = 0; - write_unlock_irqrestore(&tstamp->lock, flags); + write_lock_irqsave(&clock->lock, flags); + tstart = clock->pps_info.start[i]; + clock->pps_info.start[i] = 0; + write_unlock_irqrestore(&clock->lock, flags); if (!tstart) continue; MLX5_SET(mtpps_reg, in, pin, i); MLX5_SET64(mtpps_reg, in, time_stamp, tstart); - MLX5_SET(mtpps_reg, in, field_select, MLX5E_MTPPS_FS_TIME_STAMP); - mlx5_set_mtpps(tstamp->mdev, in, sizeof(in)); + MLX5_SET(mtpps_reg, in, field_select, MLX5_MTPPS_FS_TIME_STAMP); + mlx5_set_mtpps(mdev, in, sizeof(in)); } } -static void mlx5e_timestamp_overflow(struct work_struct *work) +static void mlx5_timestamp_overflow(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); - struct mlx5e_tstamp *tstamp = container_of(dwork, struct mlx5e_tstamp, - overflow_work); - struct mlx5e_priv *priv = container_of(tstamp, struct mlx5e_priv, tstamp); + struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock, + overflow_work); unsigned long flags; - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); - queue_delayed_work(priv->wq, &tstamp->overflow_work, - msecs_to_jiffies(tstamp->overflow_period * 1000)); -} - -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config config; - int err; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* TX HW timestamp */ - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - mutex_lock(&priv->state_lock); - /* RX HW timestamp */ - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - /* Reset CQE compression to Admin default */ - mlx5e_modify_rx_cqe_compression_locked(priv, priv->channels.params.rx_cqe_compress_def); - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: - /* Disable CQE compression */ - netdev_warn(priv->netdev, "Disabling cqe compression"); - err = mlx5e_modify_rx_cqe_compression_locked(priv, false); - if (err) { - netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); - mutex_unlock(&priv->state_lock); - return err; - } - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - mutex_unlock(&priv->state_lock); - return -ERANGE; - } - - memcpy(&priv->tstamp.hwtstamp_config, &config, sizeof(config)); - mutex_unlock(&priv->state_lock); - - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; -} - -int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) -{ - struct hwtstamp_config *cfg = &priv->tstamp.hwtstamp_config; - - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) - return -EOPNOTSUPP; - - return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); + schedule_delayed_work(&clock->overflow_work, clock->overflow_period); } -static int mlx5e_ptp_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) +static int mlx5_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) { - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); u64 ns = timespec64_to_ns(ts); unsigned long flags; - write_lock_irqsave(&tstamp->lock, flags); - timecounter_init(&tstamp->clock, &tstamp->cycles, ns); - write_unlock_irqrestore(&tstamp->lock, flags); + write_lock_irqsave(&clock->lock, flags); + timecounter_init(&clock->tc, &clock->cycles, ns); + write_unlock_irqrestore(&clock->lock, flags); return 0; } -static int mlx5e_ptp_gettime(struct ptp_clock_info *ptp, - struct timespec64 *ts) +static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); u64 ns; unsigned long flags; - write_lock_irqsave(&tstamp->lock, flags); - ns = timecounter_read(&tstamp->clock); - write_unlock_irqrestore(&tstamp->lock, flags); + write_lock_irqsave(&clock->lock, flags); + ns = timecounter_read(&clock->tc); + write_unlock_irqrestore(&clock->lock, flags); *ts = ns_to_timespec64(ns); return 0; } -static int mlx5e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); unsigned long flags; - write_lock_irqsave(&tstamp->lock, flags); - timecounter_adjtime(&tstamp->clock, delta); - write_unlock_irqrestore(&tstamp->lock, flags); + write_lock_irqsave(&clock->lock, flags); + timecounter_adjtime(&clock->tc, delta); + write_unlock_irqrestore(&clock->lock, flags); return 0; } -static int mlx5e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) { u64 adj; u32 diff; unsigned long flags; int neg_adj = 0; - struct mlx5e_tstamp *tstamp = container_of(ptp, struct mlx5e_tstamp, - ptp_info); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, + ptp_info); if (delta < 0) { neg_adj = 1; delta = -delta; } - adj = tstamp->nominal_c_mult; + adj = clock->nominal_c_mult; adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock_irqsave(&tstamp->lock, flags); - timecounter_read(&tstamp->clock); - tstamp->cycles.mult = neg_adj ? tstamp->nominal_c_mult - diff : - tstamp->nominal_c_mult + diff; - write_unlock_irqrestore(&tstamp->lock, flags); + write_lock_irqsave(&clock->lock, flags); + timecounter_read(&clock->tc); + clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : + clock->nominal_c_mult + diff; + write_unlock_irqrestore(&clock->lock, flags); return 0; } -static int mlx5e_extts_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) +static int mlx5_extts_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) { - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; u32 field_select = 0; u8 pin_mode = 0; @@ -285,24 +199,24 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp, int pin = -1; int err = 0; - if (!MLX5_PPS_CAP(priv->mdev)) + if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; - if (rq->extts.index >= tstamp->ptp_info.n_pins) + if (rq->extts.index >= clock->ptp_info.n_pins) return -EINVAL; if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_EXTTS, rq->extts.index); + pin = ptp_find_pin(clock->ptp, PTP_PF_EXTTS, rq->extts.index); if (pin < 0) return -EBUSY; - pin_mode = MLX5E_PIN_MODE_IN; + pin_mode = MLX5_PIN_MODE_IN; pattern = !!(rq->extts.flags & PTP_FALLING_EDGE); - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE; + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE; } else { pin = rq->extts.index; - field_select = MLX5E_MTPPS_FS_ENABLE; + field_select = MLX5_MTPPS_FS_ENABLE; } MLX5_SET(mtpps_reg, in, pin, pin); @@ -311,22 +225,22 @@ static int mlx5e_extts_configure(struct ptp_clock_info *ptp, MLX5_SET(mtpps_reg, in, enable, on); MLX5_SET(mtpps_reg, in, field_select, field_select); - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); + err = mlx5_set_mtpps(mdev, in, sizeof(in)); if (err) return err; - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); } -static int mlx5e_perout_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) +static int mlx5_perout_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) { - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); - struct mlx5e_priv *priv = - container_of(tstamp, struct mlx5e_priv, tstamp); + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev = + container_of(clock, struct mlx5_core_dev, clock); u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; u64 nsec_now, nsec_delta, time_stamp = 0; u64 cycles_now, cycles_delta; @@ -339,20 +253,20 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp, int err = 0; s64 ns; - if (!MLX5_PPS_CAP(priv->mdev)) + if (!MLX5_PPS_CAP(mdev)) return -EOPNOTSUPP; - if (rq->perout.index >= tstamp->ptp_info.n_pins) + if (rq->perout.index >= clock->ptp_info.n_pins) return -EINVAL; if (on) { - pin = ptp_find_pin(tstamp->ptp, PTP_PF_PEROUT, + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index); if (pin < 0) return -EBUSY; - pin_mode = MLX5E_PIN_MODE_OUT; - pattern = MLX5E_OUT_PATTERN_PERIODIC; + pin_mode = MLX5_PIN_MODE_OUT; + pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; ts.tv_nsec = rq->perout.period.nsec; ns = timespec64_to_ns(&ts); @@ -363,21 +277,21 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp, ts.tv_sec = rq->perout.start.sec; ts.tv_nsec = rq->perout.start.nsec; ns = timespec64_to_ns(&ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); + cycles_now = mlx5_read_internal_timer(mdev); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - write_unlock_irqrestore(&tstamp->lock, flags); + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + write_unlock_irqrestore(&clock->lock, flags); time_stamp = cycles_now + cycles_delta; - field_select = MLX5E_MTPPS_FS_PIN_MODE | - MLX5E_MTPPS_FS_PATTERN | - MLX5E_MTPPS_FS_ENABLE | - MLX5E_MTPPS_FS_TIME_STAMP; + field_select = MLX5_MTPPS_FS_PIN_MODE | + MLX5_MTPPS_FS_PATTERN | + MLX5_MTPPS_FS_ENABLE | + MLX5_MTPPS_FS_TIME_STAMP; } else { pin = rq->perout.index; - field_select = MLX5E_MTPPS_FS_ENABLE; + field_select = MLX5_MTPPS_FS_ENABLE; } MLX5_SET(mtpps_reg, in, pin, pin); @@ -387,233 +301,225 @@ static int mlx5e_perout_configure(struct ptp_clock_info *ptp, MLX5_SET64(mtpps_reg, in, time_stamp, time_stamp); MLX5_SET(mtpps_reg, in, field_select, field_select); - err = mlx5_set_mtpps(priv->mdev, in, sizeof(in)); + err = mlx5_set_mtpps(mdev, in, sizeof(in)); if (err) return err; - return mlx5_set_mtppse(priv->mdev, pin, 0, - MLX5E_EVENT_MODE_REPETETIVE & on); + return mlx5_set_mtppse(mdev, pin, 0, + MLX5_EVENT_MODE_REPETETIVE & on); } -static int mlx5e_pps_configure(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) +static int mlx5_pps_configure(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) { - struct mlx5e_tstamp *tstamp = - container_of(ptp, struct mlx5e_tstamp, ptp_info); + struct mlx5_clock *clock = + container_of(ptp, struct mlx5_clock, ptp_info); - tstamp->pps_info.enabled = !!on; + clock->pps_info.enabled = !!on; return 0; } -static int mlx5e_ptp_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, - int on) +static int mlx5_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, + int on) { switch (rq->type) { case PTP_CLK_REQ_EXTTS: - return mlx5e_extts_configure(ptp, rq, on); + return mlx5_extts_configure(ptp, rq, on); case PTP_CLK_REQ_PEROUT: - return mlx5e_perout_configure(ptp, rq, on); + return mlx5_perout_configure(ptp, rq, on); case PTP_CLK_REQ_PPS: - return mlx5e_pps_configure(ptp, rq, on); + return mlx5_pps_configure(ptp, rq, on); default: return -EOPNOTSUPP; } return 0; } -static int mlx5e_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, - enum ptp_pin_function func, unsigned int chan) +static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) { return (func == PTP_PF_PHYSYNC) ? -EOPNOTSUPP : 0; } -static const struct ptp_clock_info mlx5e_ptp_clock_info = { +static const struct ptp_clock_info mlx5_ptp_clock_info = { .owner = THIS_MODULE, + .name = "mlx5_p2p", .max_adj = 100000000, .n_alarm = 0, .n_ext_ts = 0, .n_per_out = 0, .n_pins = 0, .pps = 0, - .adjfreq = mlx5e_ptp_adjfreq, - .adjtime = mlx5e_ptp_adjtime, - .gettime64 = mlx5e_ptp_gettime, - .settime64 = mlx5e_ptp_settime, + .adjfreq = mlx5_ptp_adjfreq, + .adjtime = mlx5_ptp_adjtime, + .gettime64 = mlx5_ptp_gettime, + .settime64 = mlx5_ptp_settime, .enable = NULL, .verify = NULL, }; -static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp) -{ - tstamp->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; - tstamp->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; -} - -static int mlx5e_init_pin_config(struct mlx5e_tstamp *tstamp) +static int mlx5_init_pin_config(struct mlx5_clock *clock) { int i; - tstamp->ptp_info.pin_config = - kzalloc(sizeof(*tstamp->ptp_info.pin_config) * - tstamp->ptp_info.n_pins, GFP_KERNEL); - if (!tstamp->ptp_info.pin_config) + clock->ptp_info.pin_config = + kzalloc(sizeof(*clock->ptp_info.pin_config) * + clock->ptp_info.n_pins, GFP_KERNEL); + if (!clock->ptp_info.pin_config) return -ENOMEM; - tstamp->ptp_info.enable = mlx5e_ptp_enable; - tstamp->ptp_info.verify = mlx5e_ptp_verify; - tstamp->ptp_info.pps = 1; + clock->ptp_info.enable = mlx5_ptp_enable; + clock->ptp_info.verify = mlx5_ptp_verify; + clock->ptp_info.pps = 1; - for (i = 0; i < tstamp->ptp_info.n_pins; i++) { - snprintf(tstamp->ptp_info.pin_config[i].name, - sizeof(tstamp->ptp_info.pin_config[i].name), + for (i = 0; i < clock->ptp_info.n_pins; i++) { + snprintf(clock->ptp_info.pin_config[i].name, + sizeof(clock->ptp_info.pin_config[i].name), "mlx5_pps%d", i); - tstamp->ptp_info.pin_config[i].index = i; - tstamp->ptp_info.pin_config[i].func = PTP_PF_NONE; - tstamp->ptp_info.pin_config[i].chan = i; + clock->ptp_info.pin_config[i].index = i; + clock->ptp_info.pin_config[i].func = PTP_PF_NONE; + clock->ptp_info.pin_config[i].chan = i; } return 0; } -static void mlx5e_get_pps_caps(struct mlx5e_priv *priv, - struct mlx5e_tstamp *tstamp) +static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev) { + struct mlx5_clock *clock = &mdev->clock; u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0}; - mlx5_query_mtpps(priv->mdev, out, sizeof(out)); - - tstamp->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, - cap_number_of_pps_pins); - tstamp->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_in_pins); - tstamp->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, - cap_max_num_of_pps_out_pins); - - tstamp->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); - tstamp->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); - tstamp->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); - tstamp->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); - tstamp->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); - tstamp->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); - tstamp->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); - tstamp->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); + mlx5_query_mtpps(mdev, out, sizeof(out)); + + clock->ptp_info.n_pins = MLX5_GET(mtpps_reg, out, + cap_number_of_pps_pins); + clock->ptp_info.n_ext_ts = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_in_pins); + clock->ptp_info.n_per_out = MLX5_GET(mtpps_reg, out, + cap_max_num_of_pps_out_pins); + + clock->pps_info.pin_caps[0] = MLX5_GET(mtpps_reg, out, cap_pin_0_mode); + clock->pps_info.pin_caps[1] = MLX5_GET(mtpps_reg, out, cap_pin_1_mode); + clock->pps_info.pin_caps[2] = MLX5_GET(mtpps_reg, out, cap_pin_2_mode); + clock->pps_info.pin_caps[3] = MLX5_GET(mtpps_reg, out, cap_pin_3_mode); + clock->pps_info.pin_caps[4] = MLX5_GET(mtpps_reg, out, cap_pin_4_mode); + clock->pps_info.pin_caps[5] = MLX5_GET(mtpps_reg, out, cap_pin_5_mode); + clock->pps_info.pin_caps[6] = MLX5_GET(mtpps_reg, out, cap_pin_6_mode); + clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode); } -void mlx5e_pps_event_handler(struct mlx5e_priv *priv, - struct ptp_clock_event *event) +void mlx5_pps_event(struct mlx5_core_dev *mdev, + struct mlx5_eqe *eqe) { - struct net_device *netdev = priv->netdev; - struct mlx5e_tstamp *tstamp = &priv->tstamp; + struct mlx5_clock *clock = &mdev->clock; + struct ptp_clock_event ptp_event; struct timespec64 ts; u64 nsec_now, nsec_delta; u64 cycles_now, cycles_delta; - int pin = event->index; + int pin = eqe->data.pps.pin; s64 ns; unsigned long flags; - switch (tstamp->ptp_info.pin_config[pin].func) { + switch (clock->ptp_info.pin_config[pin].func) { case PTP_PF_EXTTS: - if (tstamp->pps_info.enabled) { - event->type = PTP_CLOCK_PPSUSR; - event->pps_times.ts_real = ns_to_timespec64(event->timestamp); + if (clock->pps_info.enabled) { + ptp_event.type = PTP_CLOCK_PPSUSR; + ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp); } else { - event->type = PTP_CLOCK_EXTTS; + ptp_event.type = PTP_CLOCK_EXTTS; } - ptp_clock_event(tstamp->ptp, event); + ptp_clock_event(clock->ptp, &ptp_event); break; case PTP_PF_PEROUT: - mlx5e_ptp_gettime(&tstamp->ptp_info, &ts); - cycles_now = mlx5_read_internal_timer(tstamp->mdev); + mlx5_ptp_gettime(&clock->ptp_info, &ts); + cycles_now = mlx5_read_internal_timer(mdev); ts.tv_sec += 1; ts.tv_nsec = 0; ns = timespec64_to_ns(&ts); - write_lock_irqsave(&tstamp->lock, flags); - nsec_now = timecounter_cyc2time(&tstamp->clock, cycles_now); + write_lock_irqsave(&clock->lock, flags); + nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; - cycles_delta = div64_u64(nsec_delta << tstamp->cycles.shift, - tstamp->cycles.mult); - tstamp->pps_info.start[pin] = cycles_now + cycles_delta; - queue_work(priv->wq, &tstamp->pps_info.out_work); - write_unlock_irqrestore(&tstamp->lock, flags); + cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, + clock->cycles.mult); + clock->pps_info.start[pin] = cycles_now + cycles_delta; + schedule_work(&clock->pps_info.out_work); + write_unlock_irqrestore(&clock->lock, flags); break; default: - netdev_err(netdev, "%s: Unhandled event\n", __func__); + mlx5_core_err(mdev, " Unhandled event\n"); } } -void mlx5e_timestamp_init(struct mlx5e_priv *priv) +void mlx5_init_clock(struct mlx5_core_dev *mdev) { - struct mlx5e_tstamp *tstamp = &priv->tstamp; + struct mlx5_clock *clock = &mdev->clock; u64 ns; u64 frac = 0; u32 dev_freq; - mlx5e_timestamp_init_config(tstamp); - dev_freq = MLX5_CAP_GEN(priv->mdev, device_frequency_khz); + dev_freq = MLX5_CAP_GEN(mdev, device_frequency_khz); if (!dev_freq) { - mlx5_core_warn(priv->mdev, "invalid device_frequency_khz, aborting HW clock init\n"); + mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); return; } - rwlock_init(&tstamp->lock); - tstamp->cycles.read = mlx5e_read_internal_timer; - tstamp->cycles.shift = MLX5E_CYCLES_SHIFT; - tstamp->cycles.mult = clocksource_khz2mult(dev_freq, - tstamp->cycles.shift); - tstamp->nominal_c_mult = tstamp->cycles.mult; - tstamp->cycles.mask = CLOCKSOURCE_MASK(41); - tstamp->mdev = priv->mdev; - - timecounter_init(&tstamp->clock, &tstamp->cycles, + rwlock_init(&clock->lock); + clock->cycles.read = read_internal_timer; + clock->cycles.shift = MLX5_CYCLES_SHIFT; + clock->cycles.mult = clocksource_khz2mult(dev_freq, + clock->cycles.shift); + clock->nominal_c_mult = clock->cycles.mult; + clock->cycles.mask = CLOCKSOURCE_MASK(41); + + timecounter_init(&clock->tc, &clock->cycles, ktime_to_ns(ktime_get_real())); /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. */ - ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask, + ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, frac, &frac); do_div(ns, NSEC_PER_SEC / 2 / HZ); - tstamp->overflow_period = ns; + clock->overflow_period = ns; - INIT_WORK(&tstamp->pps_info.out_work, mlx5e_pps_out); - INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow); - if (tstamp->overflow_period) - queue_delayed_work(priv->wq, &tstamp->overflow_work, 0); + INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out); + INIT_DELAYED_WORK(&clock->overflow_work, mlx5_timestamp_overflow); + if (clock->overflow_period) + schedule_delayed_work(&clock->overflow_work, 0); else - mlx5_core_warn(priv->mdev, "invalid overflow period, overflow_work is not scheduled\n"); + mlx5_core_warn(mdev, "invalid overflow period, overflow_work is not scheduled\n"); /* Configure the PHC */ - tstamp->ptp_info = mlx5e_ptp_clock_info; - snprintf(tstamp->ptp_info.name, 16, "mlx5 ptp"); + clock->ptp_info = mlx5_ptp_clock_info; /* Initialize 1PPS data structures */ - if (MLX5_PPS_CAP(priv->mdev)) - mlx5e_get_pps_caps(priv, tstamp); - if (tstamp->ptp_info.n_pins) - mlx5e_init_pin_config(tstamp); - - tstamp->ptp = ptp_clock_register(&tstamp->ptp_info, - &priv->mdev->pdev->dev); - if (IS_ERR(tstamp->ptp)) { - mlx5_core_warn(priv->mdev, "ptp_clock_register failed %ld\n", - PTR_ERR(tstamp->ptp)); - tstamp->ptp = NULL; + if (MLX5_PPS_CAP(mdev)) + mlx5_get_pps_caps(mdev); + if (clock->ptp_info.n_pins) + mlx5_init_pin_config(clock); + + clock->ptp = ptp_clock_register(&clock->ptp_info, + &mdev->pdev->dev); + if (IS_ERR(clock->ptp)) { + mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n", + PTR_ERR(clock->ptp)); + clock->ptp = NULL; } } -void mlx5e_timestamp_cleanup(struct mlx5e_priv *priv) +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) { - struct mlx5e_tstamp *tstamp = &priv->tstamp; + struct mlx5_clock *clock = &mdev->clock; - if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) + if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) return; - if (priv->tstamp.ptp) { - ptp_clock_unregister(priv->tstamp.ptp); - priv->tstamp.ptp = NULL; + if (clock->ptp) { + ptp_clock_unregister(clock->ptp); + clock->ptp = NULL; } - cancel_work_sync(&tstamp->pps_info.out_work); - cancel_delayed_work_sync(&tstamp->overflow_work); - kfree(tstamp->ptp_info.pin_config); + cancel_work_sync(&clock->pps_info.out_work); + cancel_delayed_work_sync(&clock->overflow_work); + kfree(clock->ptp_info.pin_config); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h new file mode 100644 index 0000000000000..a8eecedd46c25 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __LIB_CLOCK_H__ +#define __LIB_CLOCK_H__ + +void mlx5_init_clock(struct mlx5_core_dev *mdev); +void mlx5_cleanup_clock(struct mlx5_core_dev *mdev); + +static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, + u64 timestamp) +{ + u64 nsec; + + read_lock(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + read_unlock(&clock->lock); + + return ns_to_ktime(nsec); +} + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0d2c8dcd6eae4..ecbe9fad22d8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -59,6 +59,7 @@ #include "lib/mlx5.h" #include "fpga/core.h" #include "accel/ipsec.h" +#include "lib/clock.h" MODULE_AUTHOR("Eli Cohen "); MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); @@ -889,6 +890,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_init_reserved_gids(dev); + mlx5_init_clock(dev); + err = mlx5_init_rl_table(dev); if (err) { dev_err(&pdev->dev, "Failed to init rate limiting\n"); @@ -949,6 +952,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); + mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b7c2900b75f9e..8f00de2fe2838 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -93,6 +93,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, struct mlx5_pagefault *pfault); +void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force); void mlx5_disable_device(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 401c8972cc3a8..08c77b7e59cbc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,8 @@ #include #include #include +#include +#include enum { MLX5_BOARD_ID_LEN = 64, @@ -760,6 +762,27 @@ struct mlx5_rsvd_gids { struct ida ida; }; +#define MAX_PIN_NUM 8 +struct mlx5_pps { + u8 pin_caps[MAX_PIN_NUM]; + struct work_struct out_work; + u64 start[MAX_PIN_NUM]; + u8 enabled; +}; + +struct mlx5_clock { + rwlock_t lock; + struct cyclecounter cycles; + struct timecounter tc; + struct hwtstamp_config hwtstamp_config; + u32 nominal_c_mult; + unsigned long overflow_period; + struct delayed_work overflow_work; + struct ptp_clock *ptp; + struct ptp_clock_info ptp_info; + struct mlx5_pps pps_info; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -800,6 +823,7 @@ struct mlx5_core_dev { #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif + struct mlx5_clock clock; }; struct mlx5_db { -- GitLab From c8249eda7fac00b55eca17ab05207be291d91a3f Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Tue, 12 Sep 2017 14:11:29 +0300 Subject: [PATCH 1357/1507] net/mlx5e: IPoIB, Move underlay QP init/uninit to separate functions During the creation of the underlay QP the PKEY index is unknown, the PKEY index is known only when calling ndo_open. PKEY index attached to the QP during state modification. Splitting the functions will also make the code symmetric and more readable. This split is also required for later PKEY support to be called with the PKEY index during ndo_open. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit Signed-off-by: Leon Romanovsky --- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 108 ++++++++++++------ 1 file changed, 70 insertions(+), 38 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 14dfb577691b6..feb94db6b921a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -108,11 +108,68 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv) /* Do nothing .. */ } +static int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_qp *qp = &ipriv->qp; + struct mlx5_qp_context *context; + int ret; + + /* QP states */ + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); + context->pri_path.port = 1; + context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); + goto err_qp_modify_to_err; + } + memset(context, 0, sizeof(*context)); + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); + if (ret) { + mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); + goto err_qp_modify_to_err; + } + + kfree(context); + return 0; + +err_qp_modify_to_err: + mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2ERR_QP, 0, &context, qp); + kfree(context); + return ret; +} + +static void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_qp_context context; + int err; + + err = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, + &ipriv->qp); + if (err) + mlx5_core_err(mdev, "Failed to modify qp 2RST, err: %d\n", err); +} + #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2 static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { - struct mlx5_qp_context *context = NULL; u32 *in = NULL; void *addr_path; int ret = 0; @@ -140,38 +197,7 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core goto out; } - /* QP states */ - context = kzalloc(sizeof(*context), GFP_KERNEL); - if (!context) { - ret = -ENOMEM; - goto out; - } - - context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); - context->pri_path.port = 1; - context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RST2INIT, err: %d\n", ret); - goto out; - } - memset(context, 0, sizeof(*context)); - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp INIT2RTR, err: %d\n", ret); - goto out; - } - - ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, context, qp); - if (ret) { - mlx5_core_err(mdev, "Failed to modify qp RTR2RTS, err: %d\n", ret); - goto out; - } - out: - kfree(context); kvfree(in); return ret; } @@ -192,13 +218,23 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } + err = mlx5i_init_underlay_qp(priv); + if (err) { + mlx5_core_warn(priv->mdev, "intilize underlay QP failed, %d\n", err); + goto err_destroy_underlay_qp; + } + err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); - return err; + goto err_destroy_underlay_qp; } return 0; + +err_destroy_underlay_qp: + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); + return err; } static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) @@ -381,12 +417,8 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); - struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5i_priv *ipriv = priv->ppriv; - struct mlx5_qp_context context; - /* detach qp from flow-steering by reset it */ - mlx5_core_qp_modify(mdev, MLX5_CMD_OP_2RST_QP, 0, &context, &ipriv->qp); + mlx5i_uninit_underlay_qp(priv); } static int mlx5i_open(struct net_device *netdev) -- GitLab From dae37456c8ac3afe8d5f306717f2b75ed5ca38d9 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Wed, 13 Sep 2017 11:37:02 +0300 Subject: [PATCH 1358/1507] net/mlx5: Support for attaching multiple underlay QPs to root flow table Previous support allowed connecting only a single QPN to the FT. Now using a linked list multiple QPNs can be attached to the same FT. Supporting attaching multiple underlay QPs is required for PKEY support in which child and parent share the same FT. The actual attaching/detaching FW commands will be called inside the function symmetrically. This change requires a change in IPoIB open and close functions, the attaching/detaching to/from the FT is done each time we open/close. Signed-off-by: Alex Vesker Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- .../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 13 +- .../net/ethernet/mellanox/mlx5/core/fs_cmd.h | 4 +- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 123 ++++++++++++++++-- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 7 +- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 78 ++++++----- 5 files changed, 171 insertions(+), 54 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 36ecc2b2e1873..881e2e55840c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -40,7 +40,8 @@ #include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, u32 underlay_qpn) + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect) { u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0}; u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0}; @@ -52,7 +53,15 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, MLX5_SET(set_flow_table_root_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ROOT); MLX5_SET(set_flow_table_root_in, in, table_type, ft->type); - MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + + if (disconnect) { + MLX5_SET(set_flow_table_root_in, in, op_mod, 1); + MLX5_SET(set_flow_table_root_in, in, table_id, 0); + } else { + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, ft->id); + } + MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn); if (ft->vport) { MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index c6d7bdf255b6b..71e2d0f37ad9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -71,8 +71,8 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, unsigned int index); int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, - struct mlx5_flow_table *ft, - u32 underlay_qpn); + struct mlx5_flow_table *ft, u32 underlay_qpn, + bool disconnect); int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5a7bea688ec87..8a1a7ba9fe539 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -693,8 +693,10 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio *prio) { struct mlx5_flow_root_namespace *root = find_root(&prio->node); + struct mlx5_ft_underlay_qp *uqp; int min_level = INT_MAX; int err; + u32 qpn; if (root->root_ft) min_level = root->root_ft->level; @@ -702,10 +704,24 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio if (ft->level >= min_level) return 0; - err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn); + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, ft, qpn, + false); + if (err) + break; + } + } + if (err) - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); else root->root_ft = ft; @@ -1661,23 +1677,43 @@ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) static int update_root_ft_destroy(struct mlx5_flow_table *ft) { struct mlx5_flow_root_namespace *root = find_root(&ft->node); + struct mlx5_ft_underlay_qp *uqp; struct mlx5_flow_table *new_root_ft = NULL; + int err = 0; + u32 qpn; if (root->root_ft != ft) return 0; new_root_ft = find_next_ft(ft); - if (new_root_ft) { - int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, - root->underlay_qpn); - if (err) { - mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n", - ft->id); - return err; + if (!new_root_ft) { + root->root_ft = NULL; + return 0; + } + + if (list_empty(&root->underlay_qpns)) { + /* Don't set any QPN (zero) in case QPN list is empty */ + qpn = 0; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, qpn, + false); + } else { + list_for_each_entry(uqp, &root->underlay_qpns, list) { + qpn = uqp->qpn; + err = mlx5_cmd_update_root_ft(root->dev, new_root_ft, + qpn, false); + if (err) + break; } } - root->root_ft = new_root_ft; + + if (err) + mlx5_core_warn(root->dev, + "Update root flow table of id(%u) qpn(%d) failed\n", + ft->id, qpn); + else + root->root_ft = new_root_ft; + return 0; } @@ -1965,6 +2001,8 @@ static struct mlx5_flow_root_namespace *create_root_ns(struct mlx5_flow_steering root_ns->dev = steering->dev; root_ns->table_type = table_type; + INIT_LIST_HEAD(&root_ns->underlay_qpns); + ns = &root_ns->ns; fs_init_namespace(ns); mutex_init(&root_ns->chain_lock); @@ -2245,17 +2283,76 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *new_uqp; + int err = 0; + + new_uqp = kzalloc(sizeof(*new_uqp), GFP_KERNEL); + if (!new_uqp) + return -ENOMEM; + + mutex_lock(&root->chain_lock); + + if (!root->root_ft) { + err = -EINVAL; + goto update_ft_fail; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, false); + if (err) { + mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n", + underlay_qpn, err); + goto update_ft_fail; + } + + new_uqp->qpn = underlay_qpn; + list_add_tail(&new_uqp->list, &root->underlay_qpns); + + mutex_unlock(&root->chain_lock); - root->underlay_qpn = underlay_qpn; return 0; + +update_ft_fail: + mutex_unlock(&root->chain_lock); + kfree(new_uqp); + return err; } EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn) { struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns; + struct mlx5_ft_underlay_qp *uqp; + bool found = false; + int err = 0; + + mutex_lock(&root->chain_lock); + list_for_each_entry(uqp, &root->underlay_qpns, list) { + if (uqp->qpn == underlay_qpn) { + found = true; + break; + } + } + + if (!found) { + mlx5_core_warn(dev, "Failed finding underlay qp (%u) in qpn list\n", + underlay_qpn); + err = -EINVAL; + goto out; + } + + err = mlx5_cmd_update_root_ft(dev, root->root_ft, underlay_qpn, true); + if (err) + mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n", + underlay_qpn, err); + + list_del(&uqp->list); + mutex_unlock(&root->chain_lock); + kfree(uqp); - root->underlay_qpn = 0; return 0; + +out: + mutex_unlock(&root->chain_lock); + return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 48dd78975062c..9bc048a89bc0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -147,6 +147,11 @@ struct mlx5_fc { struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +struct mlx5_ft_underlay_qp { + struct list_head list; + u32 qpn; +}; + #define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_600 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. @@ -212,7 +217,7 @@ struct mlx5_flow_root_namespace { struct mlx5_flow_table *root_ft; /* Should be held when chaining flow tables */ struct mutex chain_lock; - u32 underlay_qpn; + struct list_head underlay_qpns; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index feb94db6b921a..00f0e6a038bba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -218,12 +218,6 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } - err = mlx5i_init_underlay_qp(priv); - if (err) { - mlx5_core_warn(priv->mdev, "intilize underlay QP failed, %d\n", err); - goto err_destroy_underlay_qp; - } - err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); @@ -285,7 +279,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; int err; err = mlx5e_create_indirect_rqt(priv); @@ -304,18 +297,12 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_indirect_tirs; - err = mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); - if (err) - goto err_destroy_direct_tirs; - err = mlx5i_create_flow_steering(priv); if (err) - goto err_remove_rx_underlay_qpn; + goto err_destroy_direct_tirs; return 0; -err_remove_rx_underlay_qpn: - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_indirect_tirs: @@ -329,9 +316,6 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { - struct mlx5i_priv *ipriv = priv->ppriv; - - mlx5_fs_remove_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn); mlx5i_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_indirect_tirs(priv); @@ -423,49 +407,71 @@ static void mlx5i_dev_cleanup(struct net_device *dev) static int mlx5i_open(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; int err; - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - set_bit(MLX5E_STATE_OPENED, &priv->state); + set_bit(MLX5E_STATE_OPENED, &epriv->state); - err = mlx5e_open_channels(priv, &priv->channels); - if (err) + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare underlay qp state failed, %d\n", err); goto err_clear_state_opened_flag; + } - mlx5e_refresh_tirs(priv, false); - mlx5e_activate_priv_channels(priv); - mlx5e_timestamp_set(priv); + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach underlay qp to ft failed, %d\n", err); + goto err_reset_qp; + } - mutex_unlock(&priv->state_lock); + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) + goto err_remove_fs_underlay_qp; + + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mlx5e_timestamp_set(epriv); + + mutex_unlock(&epriv->state_lock); return 0; +err_remove_fs_underlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_reset_qp: + mlx5i_uninit_underlay_qp(epriv); err_clear_state_opened_flag: - clear_bit(MLX5E_STATE_OPENED, &priv->state); - mutex_unlock(&priv->state_lock); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); return err; } static int mlx5i_close(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; /* May already be CLOSED in case a previous configuration operation * (e.g RX/TX queue size change) that involves close&open failed. */ - mutex_lock(&priv->state_lock); + mutex_lock(&epriv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + if (!test_bit(MLX5E_STATE_OPENED, &epriv->state)) goto unlock; - clear_bit(MLX5E_STATE_OPENED, &priv->state); + clear_bit(MLX5E_STATE_OPENED, &epriv->state); - netif_carrier_off(priv->netdev); - mlx5e_deactivate_priv_channels(priv); - mlx5e_close_channels(&priv->channels); + netif_carrier_off(epriv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(epriv); + mlx5e_deactivate_priv_channels(epriv); + mlx5e_close_channels(&epriv->channels);; unlock: - mutex_unlock(&priv->state_lock); + mutex_unlock(&epriv->state_lock); return 0; } -- GitLab From b4b678b06f6eef18bff44a338c01870234db0bc9 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Tue, 10 Oct 2017 10:36:41 +0300 Subject: [PATCH 1359/1507] IB/ipoib: Grab rtnl lock on heavy flush when calling ndo_open/stop When ndo_open and ndo_stop are called RTNL lock should be held. In this specific case ipoib_ib_dev_open calls the offloaded ndo_open which re-sets the number of TX queue assuming RTNL lock is held. Since RTNL lock is not held, RTNL assert will fail. Signed-off-by: Alex Vesker --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 6cd61638b4414..c97384c914a42 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1203,10 +1203,15 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { + rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - if (ipoib_ib_dev_open(dev) != 0) + + result = ipoib_ib_dev_open(dev); + rtnl_unlock(); + if (result) return; + if (netif_queue_stopped(dev)) netif_start_queue(dev); } -- GitLab From 980f91c3a62852ebfd0e60387d4a9d13934d9760 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Wed, 14 Jun 2017 22:18:48 +0300 Subject: [PATCH 1360/1507] IB/ipoib: Add ability to set PKEY index to lower device driver To support passing child interfaces to the lower device a new rdma_netdev function was used, set_id. This will allow us to attach the PKEY index lower device resources such as TIS/QP. For devices that do not support offloads in IPoIB same logic will be used, setting the PKEY index to priv struct. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index c97384c914a42..fe690f82af296 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -893,13 +893,17 @@ int ipoib_ib_dev_open(struct net_device *dev) void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); + struct rdma_netdev *rn = netdev_priv(dev); if (!(priv->pkey & 0x7fff) || ib_find_pkey(priv->ca, priv->port, priv->pkey, - &priv->pkey_index)) + &priv->pkey_index)) { clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); - else + } else { + if (rn->set_id) + rn->set_id(dev, priv->pkey_index); set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); + } } void ipoib_ib_dev_up(struct net_device *dev) -- GitLab From da34f1a85b78c2220dac1ce4f4c4595dd0cab5a9 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Wed, 13 Sep 2017 12:17:50 +0300 Subject: [PATCH 1361/1507] net/mlx5e: IPoIB, Support for setting PKEY index to underlay QP Added a function to set PKEY index to IPoIB device driver using the already present set_id function. PKEY index is attached to the QP during state modification. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 9 +++++++++ drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 1 + 2 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 00f0e6a038bba..679c1f9af6424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -123,6 +123,7 @@ static int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) context->flags = cpu_to_be32(MLX5_QP_PM_MIGRATED << 11); context->pri_path.port = 1; + context->pri_path.pkey_index = cpu_to_be16(ipriv->pkey_index); context->qkey = cpu_to_be32(IB_DEFAULT_Q_KEY); ret = mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, context, qp); @@ -529,6 +530,13 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb, return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey); } +static void mlx5i_set_pkey_index(struct net_device *netdev, int id) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + ipriv->pkey_index = (u16)id; +} + static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) { if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_IB) @@ -593,6 +601,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, rn->send = mlx5i_xmit; rn->attach_mcast = mlx5i_attach_mcast; rn->detach_mcast = mlx5i_detach_mcast; + rn->set_id = mlx5i_set_pkey_index; return netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index a0f405f520f7b..9a729883c3b39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -50,6 +50,7 @@ struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ struct mlx5_core_qp qp; u32 qkey; + u16 pkey_index; char *mlx5e_priv[0]; }; -- GitLab From 7e7f4780c3402bd181eea82ca6395013623e4fbf Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 14 Sep 2017 10:27:25 +0300 Subject: [PATCH 1362/1507] net/mlx5e: IPoIB, Use hash-table to map between QPN to child netdev This change is needed for PKEY support, since the RQs are shared between the child interface and the parent. The parent is responsible for NAPI and the precessing of RX completions. Using the dqpn in the completion descriptor we set the corresponding child IPoIB netdevice on the SKB. The mapping between the dqpn and the netdevice is done using a HT, each mlx5 IPoIB interface registers its mapping on creation. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- .../net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../net/ethernet/mellanox/mlx5/core/en_rx.c | 20 ++- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 16 +++ .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 12 ++ .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 136 ++++++++++++++++++ 5 files changed, 184 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index d9621b2152d3f..100fe4ecad9b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -22,7 +22,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc. mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o -mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o +mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 7e3bfe62ef6e8..2c3f2e9b69834 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1163,11 +1163,25 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - struct net_device *netdev = rq->netdev; + struct net_device *netdev; char *pseudo_header; + u32 qpn; u8 *dgid; u8 g; + qpn = be32_to_cpu(cqe->sop_drop_qpn) & 0xffffff; + netdev = mlx5i_pkey_get_netdev(rq->netdev, qpn); + + /* No mapping present, cannot process SKB. This might happen if a child + * interface is going down while having unprocessed CQEs on parent RQ + */ + if (unlikely(!netdev)) { + /* TODO: add drop counters support */ + skb->dev = NULL; + pr_warn_once("Unable to map QPN %u to dev - dropping skb\n", qpn); + return; + } + g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET; if ((!g) || dgid[0] != 0xff) @@ -1230,6 +1244,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) goto wq_free_wqe; mlx5i_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); + if (unlikely(!skb->dev)) { + dev_kfree_skb_any(skb); + goto wq_free_wqe; + } napi_gro_receive(rq->cq.napi, skb); wq_free_wqe: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 679c1f9af6424..c479fe54a6caa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -382,6 +382,9 @@ static int mlx5i_dev_init(struct net_device *dev) dev->dev_addr[2] = (ipriv->qp.qpn >> 8) & 0xff; dev->dev_addr[3] = (ipriv->qp.qpn) & 0xff; + /* Add QPN to net-device mapping to HT */ + mlx5i_pkey_add_qpn(dev ,ipriv->qp.qpn); + return 0; } @@ -402,8 +405,12 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv = priv->ppriv; mlx5i_uninit_underlay_qp(priv); + + /* Delete QPN to net-device mapping from HT */ + mlx5i_pkey_del_qpn(dev, ipriv->qp.qpn); } static int mlx5i_open(struct net_device *netdev) @@ -590,6 +597,12 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, if (!epriv->wq) goto err_free_netdev; + err = mlx5i_pkey_qpn_ht_init(netdev); + if (err) { + mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n"); + goto destroy_wq; + } + profile->init(mdev, netdev, profile, ipriv); mlx5e_attach_netdev(epriv); @@ -605,6 +618,8 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, return netdev; +destroy_wq: + destroy_workqueue(epriv->wq); err_free_netdev: free_netdev(netdev); free_mdev_resources: @@ -623,6 +638,7 @@ void mlx5_rdma_netdev_free(struct net_device *netdev) mlx5e_detach_netdev(priv); profile->cleanup(priv); destroy_workqueue(priv->wq); + mlx5i_pkey_qpn_ht_cleanup(netdev); free_netdev(netdev); mlx5e_destroy_mdev_resources(mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 9a729883c3b39..e313f6d90729d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -51,9 +51,21 @@ struct mlx5i_priv { struct mlx5_core_qp qp; u32 qkey; u16 pkey_index; + struct mlx5i_pkey_qpn_ht *qpn_htbl; char *mlx5e_priv[0]; }; +/* Allocate/Free underlay QPN to net-device hash table */ +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev); +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev); + +/* Add/Remove an underlay QPN to net-device mapping to/from the hash table */ +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn); +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn); + +/* Get the net-device corresponding to the given underlay QPN */ +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); + /* Extract mlx5e_priv from IPoIB netdev */ #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c new file mode 100644 index 0000000000000..e4d39aa1f5523 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -0,0 +1,136 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include +#include "ipoib.h" + +#define MLX5I_MAX_LOG_PKEY_SUP 7 + +struct qpn_to_netdev { + struct net_device *netdev; + struct hlist_node hlist; + u32 underlay_qpn; +}; + +struct mlx5i_pkey_qpn_ht { + struct hlist_head buckets[1 << MLX5I_MAX_LOG_PKEY_SUP]; + spinlock_t ht_lock; /* Synchronise with NAPI */ +}; + +int mlx5i_pkey_qpn_ht_init(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *qpn_htbl; + + qpn_htbl = kzalloc(sizeof(*qpn_htbl), GFP_KERNEL); + if (!qpn_htbl) + return -ENOMEM; + + ipriv->qpn_htbl = qpn_htbl; + spin_lock_init(&qpn_htbl->ht_lock); + + return 0; +} + +void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + + kfree(ipriv->qpn_htbl); +} + +static struct qpn_to_netdev *mlx5i_find_qpn_to_netdev_node(struct hlist_head *buckets, + u32 qpn) +{ + struct hlist_head *h = &buckets[hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP)]; + struct qpn_to_netdev *node; + + hlist_for_each_entry(node, h, hlist) { + if (node->underlay_qpn == qpn) + return node; + } + + return NULL; +} + +int mlx5i_pkey_add_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + u8 key = hash_32(qpn, MLX5I_MAX_LOG_PKEY_SUP); + struct qpn_to_netdev *new_node; + + new_node = kzalloc(sizeof(*new_node), GFP_KERNEL); + if (!new_node) + return -ENOMEM; + + new_node->netdev = netdev; + new_node->underlay_qpn = qpn; + spin_lock_bh(&ht->ht_lock); + hlist_add_head(&new_node->hlist, &ht->buckets[key]); + spin_unlock_bh(&ht->ht_lock); + + return 0; +} + +int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5i_pkey_qpn_ht *ht = ipriv->qpn_htbl; + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ht->buckets, qpn); + if (!node) { + mlx5_core_warn(epriv->mdev, "QPN to netdev delete from HT failed\n"); + return -EINVAL; + } + + spin_lock_bh(&ht->ht_lock); + hlist_del_init(&node->hlist); + spin_unlock_bh(&ht->ht_lock); + kfree(node); + + return 0; +} + +struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn) +{ + struct mlx5i_priv *ipriv = netdev_priv(netdev); + struct qpn_to_netdev *node; + + node = mlx5i_find_qpn_to_netdev_node(ipriv->qpn_htbl->buckets, qpn); + if (!node) + return NULL; + + return node->netdev; +} -- GitLab From 4c6c615e3f308aee26277abebc7d4ffcd9a6abe2 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 14 Sep 2017 14:08:39 +0300 Subject: [PATCH 1363/1507] net/mlx5e: IPoIB, Add PKEY child interface nic profile Child interface profile will be called to support child interface specific behaviour. The child code is sparse compared to the parent since the RX channels are shared between the interfaces. Creating a septate profile for child and parent will make a smother code with a better ability for future expansion. The profile stuct is exposed to the parent using a getter function. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 12 +-- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 13 +++ .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 83 +++++++++++++++++++ 3 files changed, 102 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index c479fe54a6caa..196771cc599e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -70,10 +70,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, } /* Called directly after IPoIB netdevice was created to initialize SW structs */ -static void mlx5i_init(struct mlx5_core_dev *mdev, - struct net_device *netdev, - const struct mlx5e_profile *profile, - void *ppriv) +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); @@ -169,7 +169,7 @@ static void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) #define MLX5_QP_ENHANCED_ULP_STATELESS_MODE 2 -static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { u32 *in = NULL; void *addr_path; @@ -203,7 +203,7 @@ static int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core return ret; } -static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp) { mlx5_core_destroy_qp(mdev, qp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index e313f6d90729d..c9895f7a23586 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -55,6 +55,10 @@ struct mlx5i_priv { char *mlx5e_priv[0]; }; +/* Underlay QP create/destroy functions */ +int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); +void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); + /* Allocate/Free underlay QPN to net-device hash table */ int mlx5i_pkey_qpn_ht_init(struct net_device *netdev); void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev); @@ -66,6 +70,15 @@ int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn); /* Get the net-device corresponding to the given underlay QPN */ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); +/* Parent profile functions */ +void mlx5i_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv); + +/* Get child interface nic profile */ +const struct mlx5e_profile *mlx5i_pkey_get_profile(void); + /* Extract mlx5e_priv from IPoIB netdev */ #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index e4d39aa1f5523..17c508d98dbbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -134,3 +134,86 @@ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn) return node->netdev; } + +/* Called directly after IPoIB netdevice was created to initialize SW structs */ +static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, + struct net_device *netdev, + const struct mlx5e_profile *profile, + void *ppriv) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mlx5i_init(mdev, netdev, profile, ppriv); + + /* Override parent ndo */ + netdev->netdev_ops = NULL; + + /* Currently no ethtool support */ + netdev->ethtool_ops = NULL; + + /* Use dummy rqs */ + priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE; +} + +/* Called directly before IPoIB netdevice is destroyed to cleanup SW structs */ +static void mlx5i_pkey_cleanup(struct mlx5e_priv *priv) +{ + /* Do nothing .. */ +} + +static int mlx5i_pkey_init_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + int err; + + err = mlx5i_create_underlay_qp(priv->mdev, &ipriv->qp); + if (err) { + mlx5_core_warn(priv->mdev, "create child underlay QP failed, %d\n", err); + return err; + } + + return 0; +} + +static void mlx5i_pkey_cleanup_tx(struct mlx5e_priv *priv) +{ + struct mlx5i_priv *ipriv = priv->ppriv; + + mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); +} + +static int mlx5i_pkey_init_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource allocation and init + */ + return 0; +} + +static void mlx5i_pkey_cleanup_rx(struct mlx5e_priv *priv) +{ + /* Since the rx resources are shared between child and parent, the + * parent interface is taking care of rx resource free and de-init + */ +} + +static const struct mlx5e_profile mlx5i_pkey_nic_profile = { + .init = mlx5i_pkey_init, + .cleanup = mlx5i_pkey_cleanup, + .init_tx = mlx5i_pkey_init_tx, + .cleanup_tx = mlx5i_pkey_cleanup_tx, + .init_rx = mlx5i_pkey_init_rx, + .cleanup_rx = mlx5i_pkey_cleanup_rx, + .enable = NULL, + .disable = NULL, + .update_stats = NULL, + .max_nch = mlx5e_get_max_num_channels, + .rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe, + .rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */ + .max_tc = MLX5I_MAX_NUM_TC, +}; + +const struct mlx5e_profile *mlx5i_pkey_get_profile(void) +{ + return &mlx5i_pkey_nic_profile; +} -- GitLab From af98cebcb3e66d349173c33c0aaef352d108a081 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 14 Sep 2017 16:33:35 +0300 Subject: [PATCH 1364/1507] net/mlx5e: IPoIB, Add PKEY child interface ndos Child interface ndos will be called to support child interface specific behaviour. ndo_init flow: -Acquire shared QPN to net-device HT from parent -Continue with the same flow as parent interface ndo_open flow: -Initialize child underlay QP and connect to shared FT -Create child send TIS -Open child send channels Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 10 +- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 8 ++ .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 133 +++++++++++++++++- 3 files changed, 144 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 196771cc599e2..70706eb70d3e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -40,8 +40,6 @@ static int mlx5i_open(struct net_device *netdev); static int mlx5i_close(struct net_device *netdev); -static int mlx5i_dev_init(struct net_device *dev); -static void mlx5i_dev_cleanup(struct net_device *dev); static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu); static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); @@ -108,7 +106,7 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv) /* Do nothing .. */ } -static int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5i_priv *ipriv = priv->ppriv; @@ -154,7 +152,7 @@ static int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) return ret; } -static void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) { struct mlx5i_priv *ipriv = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; @@ -372,7 +370,7 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu) return err; } -static int mlx5i_dev_init(struct net_device *dev) +int mlx5i_dev_init(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv = priv->ppriv; @@ -402,7 +400,7 @@ static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } -static void mlx5i_dev_cleanup(struct net_device *dev) +void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv = priv->ppriv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index c9895f7a23586..80c0cfee71647 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -59,6 +59,10 @@ struct mlx5i_priv { int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp); +/* Underlay QP state modification init/uninit functions */ +int mlx5i_init_underlay_qp(struct mlx5e_priv *priv); +void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv); + /* Allocate/Free underlay QPN to net-device hash table */ int mlx5i_pkey_qpn_ht_init(struct net_device *netdev); void mlx5i_pkey_qpn_ht_cleanup(struct net_device *netdev); @@ -70,6 +74,10 @@ int mlx5i_pkey_del_qpn(struct net_device *netdev, u32 qpn); /* Get the net-device corresponding to the given underlay QPN */ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); +/* Shared ndo functionts */ +int mlx5i_dev_init(struct net_device *dev); +void mlx5i_dev_cleanup(struct net_device *dev); + /* Parent profile functions */ void mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 17c508d98dbbf..d99bec6855de4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -135,6 +135,137 @@ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn) return node->netdev; } +static int mlx5i_pkey_open(struct net_device *netdev); +static int mlx5i_pkey_close(struct net_device *netdev); +static int mlx5i_pkey_dev_init(struct net_device *dev); +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev); +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu); + +static const struct net_device_ops mlx5i_pkey_netdev_ops = { + .ndo_open = mlx5i_pkey_open, + .ndo_stop = mlx5i_pkey_close, + .ndo_init = mlx5i_pkey_dev_init, + .ndo_uninit = mlx5i_pkey_dev_cleanup, + .ndo_change_mtu = mlx5i_pkey_change_mtu, +}; + +/* Child NDOs */ +static int mlx5i_pkey_dev_init(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv, *parent_ipriv; + struct net_device *parent_dev; + int parent_ifindex; + + ipriv = priv->ppriv; + + /* Get QPN to netdevice hash table from parent */ + parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev); + parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex); + if (!parent_dev) { + mlx5_core_warn(priv->mdev, "failed to get parent device\n"); + return -EINVAL; + } + + parent_ipriv = netdev_priv(parent_dev); + ipriv->qpn_htbl = parent_ipriv->qpn_htbl; + dev_put(parent_dev); + + return mlx5i_dev_init(dev); +} + +static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) +{ + return mlx5i_dev_cleanup(netdev); +} + +static int mlx5i_pkey_open(struct net_device *netdev) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = epriv->ppriv; + struct mlx5_core_dev *mdev = epriv->mdev; + int err; + + mutex_lock(&epriv->state_lock); + + set_bit(MLX5E_STATE_OPENED, &epriv->state); + + err = mlx5i_init_underlay_qp(epriv); + if (err) { + mlx5_core_warn(mdev, "prepare child underlay qp state failed, %d\n", err); + goto err_release_lock; + } + + err = mlx5_fs_add_rx_underlay_qpn(mdev, ipriv->qp.qpn); + if (err) { + mlx5_core_warn(mdev, "attach child underlay qp to ft failed, %d\n", err); + goto err_unint_underlay_qp; + } + + err = mlx5e_create_tis(mdev, 0 /* tc */, ipriv->qp.qpn, &epriv->tisn[0]); + if (err) { + mlx5_core_warn(mdev, "create child tis failed, %d\n", err); + goto err_remove_rx_uderlay_qp; + } + + err = mlx5e_open_channels(epriv, &epriv->channels); + if (err) { + mlx5_core_warn(mdev, "opening child channels failed, %d\n", err); + goto err_clear_state_opened_flag; + } + mlx5e_refresh_tirs(epriv, false); + mlx5e_activate_priv_channels(epriv); + mutex_unlock(&epriv->state_lock); + + return 0; + +err_clear_state_opened_flag: + mlx5e_destroy_tis(mdev, epriv->tisn[0]); +err_remove_rx_uderlay_qp: + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); +err_unint_underlay_qp: + mlx5i_uninit_underlay_qp(epriv); +err_release_lock: + clear_bit(MLX5E_STATE_OPENED, &epriv->state); + mutex_unlock(&epriv->state_lock); + return err; +} + +static int mlx5i_pkey_close(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + clear_bit(MLX5E_STATE_OPENED, &priv->state); + + netif_carrier_off(priv->netdev); + mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); + mlx5i_uninit_underlay_qp(priv); + mlx5e_deactivate_priv_channels(priv); + mlx5e_close_channels(&priv->channels); + mlx5e_destroy_tis(mdev, priv->tisn[0]); +unlock: + mutex_unlock(&priv->state_lock); + return 0; +} + +static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + + mutex_lock(&priv->state_lock); + netdev->mtu = new_mtu; + mutex_unlock(&priv->state_lock); + + return 0; +} + /* Called directly after IPoIB netdevice was created to initialize SW structs */ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, struct net_device *netdev, @@ -146,7 +277,7 @@ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, mlx5i_init(mdev, netdev, profile, ppriv); /* Override parent ndo */ - netdev->netdev_ops = NULL; + netdev->netdev_ops = &mlx5i_pkey_netdev_ops; /* Currently no ethtool support */ netdev->ethtool_ops = NULL; -- GitLab From 6a910233c1eb19673dd0f37f1d72d7cdc419e176 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 14 Sep 2017 18:02:31 +0300 Subject: [PATCH 1365/1507] net/mlx5e: IPoIB, Add PKEY child interface ethtool ops Similar to VLAN interfaces child interfaces have limited ethtool support. In current code the main limitation that does not allow child interface ethtool configuration is due to shared resources which are managed by the parent. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 4 ++-- 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 43c126c63955d..6f338a9219c85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -250,3 +250,8 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; + +const struct ethtool_ops mlx5i_pkey_ethtool_ops = { + .get_drvinfo = mlx5i_get_drvinfo, + .get_link = ethtool_op_get_link, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 80c0cfee71647..a50c1a19550e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -39,6 +39,7 @@ #define MLX5I_MAX_NUM_TC 1 extern const struct ethtool_ops mlx5i_ethtool_ops; +extern const struct ethtool_ops mlx5i_pkey_ethtool_ops; #define MLX5_IB_GRH_BYTES 40 #define MLX5_IPOIB_ENCAP_LEN 4 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index d99bec6855de4..531b02cc979b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -279,8 +279,8 @@ static void mlx5i_pkey_init(struct mlx5_core_dev *mdev, /* Override parent ndo */ netdev->netdev_ops = &mlx5i_pkey_netdev_ops; - /* Currently no ethtool support */ - netdev->ethtool_ops = NULL; + /* Set child limited ethtool support */ + netdev->ethtool_ops = &mlx5i_pkey_ethtool_ops; /* Use dummy rqs */ priv->channels.params.log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE; -- GitLab From b5ae577741bec22b584fa704076ccd8221cad19d Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 14 Sep 2017 18:22:50 +0300 Subject: [PATCH 1366/1507] net/mlx5e: IPoIB, Modify rdma netdev allocate and free to support PKEY Resources such as FT, QPN HT and mdev resources should be allocated only by parent netdev. Shared resources are allocated and freed by the parent interface since the parent is always present and created before the IPoIB PKEY sub-interface. Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit --- .../ethernet/mellanox/mlx5/core/en_common.c | 1 + .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 52 ++++++++++++------- .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 1 + 3 files changed, 36 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index ece3fb147e3ee..157d029172379 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -134,6 +134,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_core_destroy_mkey(mdev, &res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); + memset(res, 0, sizeof(*res)); } int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 70706eb70d3e6..abf270d7f5560 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -560,12 +560,13 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, const char *name, void (*setup)(struct net_device *)) { - const struct mlx5e_profile *profile = &mlx5i_nic_profile; - int nch = profile->max_nch(mdev); + const struct mlx5e_profile *profile; struct net_device *netdev; struct mlx5i_priv *ipriv; struct mlx5e_priv *epriv; struct rdma_netdev *rn; + bool sub_interface; + int nch; int err; if (mlx5i_check_required_hca_cap(mdev)) { @@ -573,10 +574,15 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, return ERR_PTR(-EOPNOTSUPP); } - /* This function should only be called once per mdev */ - err = mlx5e_create_mdev_resources(mdev); - if (err) - return NULL; + /* TODO: Need to find a better way to check if child device*/ + sub_interface = (mdev->mlx5e_res.pdn != 0); + + if (sub_interface) + profile = mlx5i_pkey_get_profile(); + else + profile = &mlx5i_nic_profile; + + nch = profile->max_nch(mdev); netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), name, NET_NAME_UNKNOWN, @@ -585,7 +591,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, nch); if (!netdev) { mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n"); - goto free_mdev_resources; + return NULL; } ipriv = netdev_priv(netdev); @@ -595,10 +601,18 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, if (!epriv->wq) goto err_free_netdev; - err = mlx5i_pkey_qpn_ht_init(netdev); - if (err) { - mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n"); - goto destroy_wq; + ipriv->sub_interface = sub_interface; + if (!ipriv->sub_interface) { + err = mlx5i_pkey_qpn_ht_init(netdev); + if (err) { + mlx5_core_warn(mdev, "allocate qpn_to_netdev ht failed\n"); + goto destroy_wq; + } + + /* This should only be called once per mdev */ + err = mlx5e_create_mdev_resources(mdev); + if (err) + goto destroy_ht; } profile->init(mdev, netdev, profile, ipriv); @@ -616,12 +630,12 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, return netdev; +destroy_ht: + mlx5i_pkey_qpn_ht_cleanup(netdev); destroy_wq: destroy_workqueue(epriv->wq); err_free_netdev: free_netdev(netdev); -free_mdev_resources: - mlx5e_destroy_mdev_resources(mdev); return NULL; } @@ -629,16 +643,18 @@ EXPORT_SYMBOL(mlx5_rdma_netdev_alloc); void mlx5_rdma_netdev_free(struct net_device *netdev) { - struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv = priv->ppriv; const struct mlx5e_profile *profile = priv->profile; - struct mlx5_core_dev *mdev = priv->mdev; mlx5e_detach_netdev(priv); profile->cleanup(priv); destroy_workqueue(priv->wq); - mlx5i_pkey_qpn_ht_cleanup(netdev); - free_netdev(netdev); - mlx5e_destroy_mdev_resources(mdev); + if (!ipriv->sub_interface) { + mlx5i_pkey_qpn_ht_cleanup(netdev); + mlx5e_destroy_mdev_resources(priv->mdev); + } + free_netdev(netdev); } EXPORT_SYMBOL(mlx5_rdma_netdev_free); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index a50c1a19550e1..49008022c3062 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -50,6 +50,7 @@ extern const struct ethtool_ops mlx5i_pkey_ethtool_ops; struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ struct mlx5_core_qp qp; + bool sub_interface; u32 qkey; u16 pkey_index; struct mlx5i_pkey_qpn_ht *qpn_htbl; -- GitLab From ec0d0987f084cdaf7b7ff8bd8f9f946e29fb8d94 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 12 Oct 2017 16:11:32 -0500 Subject: [PATCH 1367/1507] atm: fore200e: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- drivers/atm/fore200e.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index f8b7e86907cc2..126855e6cb7d2 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -358,26 +358,33 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_COMPLETE: kfree(fore200e->stats); + /* fall through */ case FORE200E_STATE_IRQ: free_irq(fore200e->irq, fore200e->atm_dev); + /* fall through */ case FORE200E_STATE_ALLOC_BUF: fore200e_free_rx_buf(fore200e); + /* fall through */ case FORE200E_STATE_INIT_BSQ: fore200e_uninit_bs_queue(fore200e); + /* fall through */ case FORE200E_STATE_INIT_RXQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.status); fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_rxq.rpd); + /* fall through */ case FORE200E_STATE_INIT_TXQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.status); fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_txq.tpd); + /* fall through */ case FORE200E_STATE_INIT_CMDQ: fore200e->bus->dma_chunk_free(fore200e, &fore200e->host_cmdq.status); + /* fall through */ case FORE200E_STATE_INITIALIZE: /* nothing to do for that state */ @@ -390,6 +397,7 @@ fore200e_shutdown(struct fore200e* fore200e) case FORE200E_STATE_MAP: fore200e->bus->unmap(fore200e); + /* fall through */ case FORE200E_STATE_CONFIGURE: /* nothing to do for that state */ -- GitLab From 04a69a17597c1366d764926577745dca4aa6b100 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 13 Oct 2017 14:18:05 -0400 Subject: [PATCH 1368/1507] net: dsa: mv88e6xxx: setup random mac address An Ethernet switch may support having a MAC address, which can be used as the switch's source address in transmitted full-duplex Pause frames. If a DSA switch supports the related .set_addr operation, the DSA core sets the master's MAC address on the switch. This won't make sense anymore in a multi-CPU ports system, because there won't be a unique master device assigned to a switch tree. Instead, setup the switch from within the Marvell driver with a random MAC address, and remove the .set_addr implementation. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 33 ++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d74c7335c512d..76cf383dcf90c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -932,6 +932,19 @@ static int mv88e6xxx_irl_setup(struct mv88e6xxx_chip *chip) return 0; } +static int mv88e6xxx_mac_setup(struct mv88e6xxx_chip *chip) +{ + if (chip->info->ops->set_switch_mac) { + u8 addr[ETH_ALEN]; + + eth_random_addr(addr); + + return chip->info->ops->set_switch_mac(chip, addr); + } + + return 0; +} + static int mv88e6xxx_pvt_map(struct mv88e6xxx_chip *chip, int dev, int port) { u16 pvlan = 0; @@ -2013,6 +2026,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; + err = mv88e6xxx_mac_setup(chip); + if (err) + goto unlock; + err = mv88e6xxx_phy_setup(chip); if (err) goto unlock; @@ -2043,21 +2060,6 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) return err; } -static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - if (!chip->info->ops->set_switch_mac) - return -EOPNOTSUPP; - - mutex_lock(&chip->reg_lock); - err = chip->info->ops->set_switch_mac(chip, addr); - mutex_unlock(&chip->reg_lock); - - return err; -} - static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; @@ -3785,7 +3787,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .probe = mv88e6xxx_drv_probe, .get_tag_protocol = mv88e6xxx_get_tag_protocol, .setup = mv88e6xxx_setup, - .set_addr = mv88e6xxx_set_addr, .adjust_link = mv88e6xxx_adjust_link, .get_strings = mv88e6xxx_get_strings, .get_ethtool_stats = mv88e6xxx_get_ethtool_stats, -- GitLab From 1723ab4f5e9af710acb36ba754e9cbf02ee08215 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 13 Oct 2017 14:18:06 -0400 Subject: [PATCH 1369/1507] net: dsa: mv88e6060: fix switch MAC address The 88E6060 Ethernet switch always transmits the multicast bit of the switch MAC address as a zero. It re-uses the corresponding bit 8 of the register "Switch MAC Address Register Bytes 0 & 1" for "DiffAddr". If the "DiffAddr" bit is 0, then all ports transmit the same source address. If it is set to 1, then bit 2:0 are used for the port number. The mv88e6060 driver is currently wrongly shifting the MAC address byte 0 by 9. To fix this, shift it by 8 as usual and clear its bit 0. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6060.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 621cdc46ad812..d64be2b83d3cd 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -214,8 +214,14 @@ static int mv88e6060_setup(struct dsa_switch *ds) static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) { - /* Use the same MAC Address as FD Pause frames for all ports */ - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 9) | addr[1]); + u16 val = addr[0] << 8 | addr[1]; + + /* The multicast bit is always transmitted as a zero, so the switch uses + * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA. + */ + val &= 0xfeff; + + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val); REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); -- GitLab From 56c3ff9bf23e1f9e5f13e2343b0603365f8d9c7d Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 13 Oct 2017 14:18:07 -0400 Subject: [PATCH 1370/1507] net: dsa: mv88e6060: setup random mac address As for mv88e6xxx, setup the switch from within the mv88e6060 driver with a random MAC address, and remove the .set_addr implementation. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6060.c | 43 ++++++++++++++++++++++--------------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index d64be2b83d3cd..6173be889d954 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -188,6 +189,27 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) return 0; } +static int mv88e6060_setup_addr(struct dsa_switch *ds) +{ + u8 addr[ETH_ALEN]; + u16 val; + + eth_random_addr(addr); + + val = addr[0] << 8 | addr[1]; + + /* The multicast bit is always transmitted as a zero, so the switch uses + * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA. + */ + val &= 0xfeff; + + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); + REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); + + return 0; +} + static int mv88e6060_setup(struct dsa_switch *ds) { int ret; @@ -203,6 +225,10 @@ static int mv88e6060_setup(struct dsa_switch *ds) if (ret < 0) return ret; + ret = mv88e6060_setup_addr(ds); + if (ret < 0) + return ret; + for (i = 0; i < MV88E6060_PORTS; i++) { ret = mv88e6060_setup_port(ds, i); if (ret < 0) @@ -212,22 +238,6 @@ static int mv88e6060_setup(struct dsa_switch *ds) return 0; } -static int mv88e6060_set_addr(struct dsa_switch *ds, u8 *addr) -{ - u16 val = addr[0] << 8 | addr[1]; - - /* The multicast bit is always transmitted as a zero, so the switch uses - * bit 8 for "DiffAddr", where 0 means all ports transmit the same SA. - */ - val &= 0xfeff; - - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, val); - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_23, (addr[2] << 8) | addr[3]); - REG_WRITE(REG_GLOBAL, GLOBAL_MAC_45, (addr[4] << 8) | addr[5]); - - return 0; -} - static int mv88e6060_port_to_phy_addr(int port) { if (port >= 0 && port < MV88E6060_PORTS) @@ -262,7 +272,6 @@ static const struct dsa_switch_ops mv88e6060_switch_ops = { .get_tag_protocol = mv88e6060_get_tag_protocol, .probe = mv88e6060_drv_probe, .setup = mv88e6060_setup, - .set_addr = mv88e6060_set_addr, .phy_read = mv88e6060_phy_read, .phy_write = mv88e6060_phy_write, }; -- GitLab From 93004a934bc19ea52b687d74482fd1bdd25e7b87 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 13 Oct 2017 14:18:08 -0400 Subject: [PATCH 1371/1507] net: dsa: dsa_loop: remove .set_addr The .set_addr function does nothing, remove the dsa_loop implementation before getting rid of it completely in DSA. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/dsa_loop.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index d55051abf4edc..3a3f4f7ba3647 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -110,13 +110,6 @@ static void dsa_loop_get_ethtool_stats(struct dsa_switch *ds, int port, data[i] = ps->ports[port].mib[i].val; } -static int dsa_loop_set_addr(struct dsa_switch *ds, u8 *addr) -{ - dev_dbg(ds->dev, "%s\n", __func__); - - return 0; -} - static int dsa_loop_phy_read(struct dsa_switch *ds, int port, int regnum) { struct dsa_loop_priv *ps = ds->priv; @@ -263,7 +256,6 @@ static const struct dsa_switch_ops dsa_loop_driver = { .get_strings = dsa_loop_get_strings, .get_ethtool_stats = dsa_loop_get_ethtool_stats, .get_sset_count = dsa_loop_get_sset_count, - .set_addr = dsa_loop_set_addr, .phy_read = dsa_loop_phy_read, .phy_write = dsa_loop_phy_write, .port_bridge_join = dsa_loop_port_bridge_join, -- GitLab From 841f4f24053acad69240c6ab7427a1d24bc29491 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 13 Oct 2017 14:18:09 -0400 Subject: [PATCH 1372/1507] net: dsa: remove .set_addr Now that there is no user for the .set_addr function, remove it from DSA. If a switch supports this feature (like mv88e6xxx), the implementation can be done in the driver setup. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 1 - net/dsa/dsa2.c | 6 ------ net/dsa/legacy.c | 6 ------ 3 files changed, 13 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index ce1d622734d73..2746741f74cf4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -291,7 +291,6 @@ struct dsa_switch_ops { enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds); int (*setup)(struct dsa_switch *ds); - int (*set_addr)(struct dsa_switch *ds, u8 *addr); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 54ed054777bd7..6ac9e11d385c5 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -336,12 +336,6 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) if (err) return err; - if (ds->ops->set_addr) { - err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr); - if (err < 0) - return err; - } - if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 19ff6e0a21dc5..b0fefbffe082a 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -172,12 +172,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, if (ret) return ret; - if (ops->set_addr) { - ret = ops->set_addr(ds, master->dev_addr); - if (ret < 0) - return ret; - } - if (!ds->slave_mii_bus && ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) -- GitLab From 4c7787ba3a1f583dba6ff3420817229f0056df84 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 13 Oct 2017 03:50:35 +0100 Subject: [PATCH 1373/1507] nfp: Explicitly include linux/bug.h Today's -next build encountered an error due to a missing definition of WARN_ON(), caused by some header reorganization removing an implicit inclusion of linux/bug.h. Fix this with an explicit inclusion. Signed-off-by: Mark Brown Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_app.c | 1 + drivers/net/ethernet/netronome/nfp/nfp_asm.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c index 82c290763529e..5d9e2eba5b49e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c @@ -31,6 +31,7 @@ * SOFTWARE. */ +#include #include #include diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h index c26aa7e4a8396..86e7daee60995 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h @@ -35,6 +35,7 @@ #define __NFP_ASM_H__ 1 #include +#include #include #define REG_NONE 0 -- GitLab From ad75b7d32f2517a6cc92a5d70569c33455157453 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:13 +0530 Subject: [PATCH 1374/1507] cxgb4: implement ethtool dump data operations Implement operations to set/get dump data via ethtool. Also add template header that precedes dump data, which helps in decoding and extracting the dump data. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/Makefile | 2 +- drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 33 +++++++++ .../ethernet/chelsio/cxgb4/cudbg_lib_common.h | 65 +++++++++++++++++ drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 3 + .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 73 +++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h | 32 ++++++++ .../ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 56 +++++++++++++- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 3 + 8 files changed, 265 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index fecd7aab673b6..4c6041f456304 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \ cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \ - cxgb4_ptp.o cxgb4_tc_flower.o + cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h new file mode 100644 index 0000000000000..ebaa5b7063cf2 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -0,0 +1,33 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_IF_H__ +#define __CUDBG_IF_H__ + +#define CUDBG_MAJOR_VERSION 1 +#define CUDBG_MINOR_VERSION 14 + +enum cudbg_dbg_entity_type { + CUDBG_MAX_ENTITY = 70, +}; + +struct cudbg_init { + struct adapter *adap; /* Pointer to adapter structure */ + void *outbuf; /* Output buffer */ + u32 outbuf_size; /* Output buffer size */ +}; +#endif /* __CUDBG_IF_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h new file mode 100644 index 0000000000000..eb1b36b724556 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h @@ -0,0 +1,65 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_LIB_COMMON_H__ +#define __CUDBG_LIB_COMMON_H__ + +#define CUDBG_SIGNATURE 67856866 /* CUDB in ascii */ + +enum cudbg_dump_type { + CUDBG_DUMP_TYPE_MINI = 1, +}; + +enum cudbg_compression_type { + CUDBG_COMPRESSION_NONE = 1, +}; + +struct cudbg_hdr { + u32 signature; + u32 hdr_len; + u16 major_ver; + u16 minor_ver; + u32 data_len; + u32 hdr_flags; + u16 max_entities; + u8 chip_ver; + u8 dump_type:3; + u8 reserved1:1; + u8 compress_type:4; + u32 reserved[8]; +}; + +struct cudbg_entity_hdr { + u32 entity_type; + u32 start_offset; + u32 size; + int hdr_flags; + u32 sys_warn; + u32 sys_err; + u8 num_pad; + u8 flag; /* bit 0 is used to indicate ext data */ + u8 reserved1[2]; + u32 next_ext_offset; /* pointer to next extended entity meta data */ + u32 reserved[5]; +}; + +struct cudbg_buffer { + u32 size; + u32 offset; + char *data; +}; +#endif /* __CUDBG_LIB_COMMON_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 0db3ab6ad0944..a749602fdc419 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -909,6 +909,9 @@ struct adapter { /* TC flower offload */ DECLARE_HASHTABLE(flower_anymatch_tbl, 9); struct timer_list flower_stats_timer; + + /* Ethtool Dump */ + struct ethtool_dump eth_dump; }; /* Support for "sched-class" command to allow a TX Scheduling Class to be diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c new file mode 100644 index 0000000000000..a808150de2086 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -0,0 +1,73 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "cxgb4.h" +#include "cxgb4_cudbg.h" + +u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag) +{ + return 0; +} + +int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, + u32 flag) +{ + struct cudbg_init cudbg_init = { 0 }; + struct cudbg_buffer dbg_buff = { 0 }; + u32 size, min_size, total_size = 0; + struct cudbg_hdr *cudbg_hdr; + + size = *buf_size; + + cudbg_init.adap = adap; + cudbg_init.outbuf = buf; + cudbg_init.outbuf_size = size; + + dbg_buff.data = buf; + dbg_buff.size = size; + dbg_buff.offset = 0; + + cudbg_hdr = (struct cudbg_hdr *)buf; + cudbg_hdr->signature = CUDBG_SIGNATURE; + cudbg_hdr->hdr_len = sizeof(struct cudbg_hdr); + cudbg_hdr->major_ver = CUDBG_MAJOR_VERSION; + cudbg_hdr->minor_ver = CUDBG_MINOR_VERSION; + cudbg_hdr->max_entities = CUDBG_MAX_ENTITY; + cudbg_hdr->chip_ver = adap->params.chip; + cudbg_hdr->dump_type = CUDBG_DUMP_TYPE_MINI; + cudbg_hdr->compress_type = CUDBG_COMPRESSION_NONE; + + min_size = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * + cudbg_hdr->max_entities; + if (size < min_size) + return -ENOMEM; + + dbg_buff.offset += min_size; + total_size = dbg_buff.offset; + + cudbg_hdr->data_len = total_size; + *buf_size = total_size; + return 0; +} + +void cxgb4_init_ethtool_dump(struct adapter *adapter) +{ + adapter->eth_dump.flag = CXGB4_ETH_DUMP_NONE; + adapter->eth_dump.version = adapter->params.fw_vers; + adapter->eth_dump.len = 0; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h new file mode 100644 index 0000000000000..8c5dd6794f817 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h @@ -0,0 +1,32 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CXGB4_CUDBG_H__ +#define __CXGB4_CUDBG_H__ + +#include "cudbg_if.h" +#include "cudbg_lib_common.h" + +enum CXGB4_ETHTOOL_DUMP_FLAGS { + CXGB4_ETH_DUMP_NONE = ETH_FW_DUMP_DISABLE, +}; + +u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag); +int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, + u32 flag); +void cxgb4_init_ethtool_dump(struct adapter *adapter); +#endif /* __CXGB4_CUDBG_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index a71af1e587e25..796eb051cb2f0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -21,6 +21,7 @@ #include "cxgb4.h" #include "t4_regs.h" #include "t4fw_api.h" +#include "cxgb4_cudbg.h" #define EEPROM_MAGIC 0x38E2F10C @@ -1374,6 +1375,56 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, return -EOPNOTSUPP; } +static int set_dump(struct net_device *dev, struct ethtool_dump *eth_dump) +{ + struct adapter *adapter = netdev2adap(dev); + u32 len = 0; + + len = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY; + len += cxgb4_get_dump_length(adapter, eth_dump->flag); + + adapter->eth_dump.flag = eth_dump->flag; + adapter->eth_dump.len = len; + return 0; +} + +static int get_dump_flag(struct net_device *dev, struct ethtool_dump *eth_dump) +{ + struct adapter *adapter = netdev2adap(dev); + + eth_dump->flag = adapter->eth_dump.flag; + eth_dump->len = adapter->eth_dump.len; + eth_dump->version = adapter->eth_dump.version; + return 0; +} + +static int get_dump_data(struct net_device *dev, struct ethtool_dump *eth_dump, + void *buf) +{ + struct adapter *adapter = netdev2adap(dev); + u32 len = 0; + int ret = 0; + + if (adapter->eth_dump.flag == CXGB4_ETH_DUMP_NONE) + return -ENOENT; + + len = sizeof(struct cudbg_hdr) + + sizeof(struct cudbg_entity_hdr) * CUDBG_MAX_ENTITY; + len += cxgb4_get_dump_length(adapter, adapter->eth_dump.flag); + if (eth_dump->len < len) + return -ENOMEM; + + ret = cxgb4_cudbg_collect(adapter, buf, &len, adapter->eth_dump.flag); + if (ret) + return ret; + + eth_dump->flag = adapter->eth_dump.flag; + eth_dump->len = len; + eth_dump->version = adapter->eth_dump.version; + return 0; +} + static const struct ethtool_ops cxgb_ethtool_ops = { .get_link_ksettings = get_link_ksettings, .set_link_ksettings = set_link_ksettings, @@ -1404,7 +1455,10 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_rxfh = get_rss_table, .set_rxfh = set_rss_table, .flash_device = set_flash, - .get_ts_info = get_ts_info + .get_ts_info = get_ts_info, + .set_dump = set_dump, + .get_dump_flag = get_dump_flag, + .get_dump_data = get_dump_data, }; void cxgb4_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index fe4cbe22d5d73..70c395d180870 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -81,6 +81,7 @@ #include "cxgb4_tc_u32.h" #include "cxgb4_tc_flower.h" #include "cxgb4_ptp.h" +#include "cxgb4_cudbg.h" char cxgb4_driver_name[] = KBUILD_MODNAME; @@ -5035,6 +5036,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) cxgb4_set_ethtool_ops(netdev); } + cxgb4_init_ethtool_dump(adapter); + pci_set_drvdata(pdev, adapter); if (adapter->flags & FW_OK) { -- GitLab From a7975a2f9a7984de9b9b318da9d1826033db32c7 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:14 +0530 Subject: [PATCH 1375/1507] cxgb4: collect register dump Add base to collect dump entities. Collect register dump and update template header accordingly. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/Makefile | 3 +- .../net/ethernet/chelsio/cxgb4/cudbg_common.c | 54 +++++++++++ drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 5 + .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 79 ++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 28 ++++++ .../ethernet/chelsio/cxgb4/cudbg_lib_common.h | 13 +++ .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 94 ++++++++++++++++++- .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h | 11 +++ 8 files changed, 285 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index 4c6041f456304..70d4543799962 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \ cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \ - cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o + cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \ + cudbg_common.o cudbg_lib.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c new file mode 100644 index 0000000000000..f78ba1743b5af --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c @@ -0,0 +1,54 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "cxgb4.h" +#include "cudbg_if.h" +#include "cudbg_lib_common.h" + +int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size, + struct cudbg_buffer *pin_buff) +{ + u32 offset; + + offset = pdbg_buff->offset; + if (offset + size > pdbg_buff->size) + return CUDBG_STATUS_NO_MEM; + + pin_buff->data = (char *)pdbg_buff->data + offset; + pin_buff->offset = offset; + pin_buff->size = size; + pdbg_buff->size -= size; + return 0; +} + +void cudbg_put_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pdbg_buff) +{ + pdbg_buff->size += pin_buff->size; + pin_buff->data = NULL; + pin_buff->offset = 0; + pin_buff->size = 0; +} + +void cudbg_update_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pout_buff) +{ + /* We already write to buffer provided by ethool, so just + * increment offset to next free space. + */ + pout_buff->offset += pin_buff->size; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index ebaa5b7063cf2..73725a8666df4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -18,10 +18,15 @@ #ifndef __CUDBG_IF_H__ #define __CUDBG_IF_H__ +/* Error codes */ +#define CUDBG_STATUS_NO_MEM -19 +#define CUDBG_SYSTEM_ERROR -29 + #define CUDBG_MAJOR_VERSION 1 #define CUDBG_MINOR_VERSION 14 enum cudbg_dbg_entity_type { + CUDBG_REG_DUMP = 1, CUDBG_MAX_ENTITY = 70, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c new file mode 100644 index 0000000000000..b37d8f7825dd6 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -0,0 +1,79 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#include "cxgb4.h" +#include "cudbg_if.h" +#include "cudbg_lib_common.h" +#include "cudbg_lib.h" + +static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *dbg_buff) +{ + cudbg_update_buff(pin_buff, dbg_buff); + cudbg_put_buff(pin_buff, dbg_buff); +} + +/* This function will add additional padding bytes into debug_buffer to make it + * 4 byte aligned. + */ +void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, + struct cudbg_entity_hdr *entity_hdr) +{ + u8 zero_buf[4] = {0}; + u8 padding, remain; + + remain = (dbg_buff->offset - entity_hdr->start_offset) % 4; + padding = 4 - remain; + if (remain) { + memcpy(((u8 *)dbg_buff->data) + dbg_buff->offset, &zero_buf, + padding); + dbg_buff->offset += padding; + entity_hdr->num_pad = padding; + } + entity_hdr->size = dbg_buff->offset - entity_hdr->start_offset; +} + +struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i) +{ + struct cudbg_hdr *cudbg_hdr = (struct cudbg_hdr *)outbuf; + + return (struct cudbg_entity_hdr *) + ((char *)outbuf + cudbg_hdr->hdr_len + + (sizeof(struct cudbg_entity_hdr) * (i - 1))); +} + +int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + u32 buf_size = 0; + int rc = 0; + + if (is_t4(padap->params.chip)) + buf_size = T4_REGMAP_SIZE; + else if (is_t5(padap->params.chip) || is_t6(padap->params.chip)) + buf_size = T5_REGMAP_SIZE; + + rc = cudbg_get_buff(dbg_buff, buf_size, &temp_buff); + if (rc) + return rc; + t4_get_regs(padap, (void *)temp_buff.data, temp_buff.size); + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h new file mode 100644 index 0000000000000..5b0a0e9646017 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -0,0 +1,28 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_LIB_H__ +#define __CUDBG_LIB_H__ + +int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); + +struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); +void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, + struct cudbg_entity_hdr *entity_hdr); +#endif /* __CUDBG_LIB_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h index eb1b36b724556..422a5ceedd2e5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h @@ -62,4 +62,17 @@ struct cudbg_buffer { u32 offset; char *data; }; + +struct cudbg_error { + int sys_err; + int sys_warn; + int app_err; +}; + +int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size, + struct cudbg_buffer *pin_buff); +void cudbg_put_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pdbg_buff); +void cudbg_update_buff(struct cudbg_buffer *pin_buff, + struct cudbg_buffer *pout_buff); #endif /* __CUDBG_LIB_COMMON_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index a808150de2086..4ec322eec68ca 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -18,9 +18,94 @@ #include "cxgb4.h" #include "cxgb4_cudbg.h" +static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { + { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, +}; + +static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) +{ + u32 len = 0; + + switch (entity) { + case CUDBG_REG_DUMP: + switch (CHELSIO_CHIP_VERSION(adap->params.chip)) { + case CHELSIO_T4: + len = T4_REGMAP_SIZE; + break; + case CHELSIO_T5: + case CHELSIO_T6: + len = T5_REGMAP_SIZE; + break; + default: + break; + } + break; + default: + break; + } + + return len; +} + u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag) { - return 0; + u32 i, entity; + u32 len = 0; + + if (flag & CXGB4_ETH_DUMP_HW) { + for (i = 0; i < ARRAY_SIZE(cxgb4_collect_hw_dump); i++) { + entity = cxgb4_collect_hw_dump[i].entity; + len += cxgb4_get_entity_length(adap, entity); + } + } + + return len; +} + +static void cxgb4_cudbg_collect_entity(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + const struct cxgb4_collect_entity *e_arr, + u32 arr_size, void *buf, u32 *tot_size) +{ + struct adapter *adap = pdbg_init->adap; + struct cudbg_error cudbg_err = { 0 }; + struct cudbg_entity_hdr *entity_hdr; + u32 entity_size, i; + u32 total_size = 0; + int ret; + + for (i = 0; i < arr_size; i++) { + const struct cxgb4_collect_entity *e = &e_arr[i]; + + /* Skip entities that won't fit in output buffer */ + entity_size = cxgb4_get_entity_length(adap, e->entity); + if (entity_size > + pdbg_init->outbuf_size - *tot_size - total_size) + continue; + + entity_hdr = cudbg_get_entity_hdr(buf, e->entity); + entity_hdr->entity_type = e->entity; + entity_hdr->start_offset = dbg_buff->offset; + memset(&cudbg_err, 0, sizeof(struct cudbg_error)); + ret = e->collect_cb(pdbg_init, dbg_buff, &cudbg_err); + if (ret) { + entity_hdr->size = 0; + dbg_buff->offset = entity_hdr->start_offset; + } else { + cudbg_align_debug_buffer(dbg_buff, entity_hdr); + } + + /* Log error and continue with next entity */ + if (cudbg_err.sys_err) + ret = CUDBG_SYSTEM_ERROR; + + entity_hdr->hdr_flags = ret; + entity_hdr->sys_err = cudbg_err.sys_err; + entity_hdr->sys_warn = cudbg_err.sys_warn; + total_size += entity_hdr->size; + } + + *tot_size += total_size; } int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, @@ -60,6 +145,13 @@ int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, dbg_buff.offset += min_size; total_size = dbg_buff.offset; + if (flag & CXGB4_ETH_DUMP_HW) + cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff, + cxgb4_collect_hw_dump, + ARRAY_SIZE(cxgb4_collect_hw_dump), + buf, + &total_size); + cudbg_hdr->data_len = total_size; *buf_size = total_size; return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h index 8c5dd6794f817..7369a7e22b890 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h @@ -20,9 +20,20 @@ #include "cudbg_if.h" #include "cudbg_lib_common.h" +#include "cudbg_lib.h" + +typedef int (*cudbg_collect_callback_t)(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); + +struct cxgb4_collect_entity { + enum cudbg_dbg_entity_type entity; + cudbg_collect_callback_t collect_cb; +}; enum CXGB4_ETHTOOL_DUMP_FLAGS { CXGB4_ETH_DUMP_NONE = ETH_FW_DUMP_DISABLE, + CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */ }; u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag); -- GitLab From b33af022e57996dc818ec960cbdf0f07cb5130d8 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:15 +0530 Subject: [PATCH 1376/1507] cxgb4: collect on-chip memory dump Collect EDC0 and EDC1 memory dump. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cudbg_entity.h | 29 ++++ drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 8 ++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 136 ++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 6 + .../ethernet/chelsio/cxgb4/cudbg_lib_common.h | 3 + .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 38 ++++- .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h | 1 + 7 files changed, 220 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h new file mode 100644 index 0000000000000..71a426dd22f54 --- /dev/null +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -0,0 +1,29 @@ +/* + * Copyright (C) 2017 Chelsio Communications. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + */ + +#ifndef __CUDBG_ENTITY_H__ +#define __CUDBG_ENTITY_H__ + +#define EDC0_FLAG 3 +#define EDC1_FLAG 4 + +struct card_mem { + u16 size_edc0; + u16 size_edc1; + u16 mem_flag; +}; +#endif /* __CUDBG_ENTITY_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 73725a8666df4..8bcea985af771 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -20,6 +20,7 @@ /* Error codes */ #define CUDBG_STATUS_NO_MEM -19 +#define CUDBG_STATUS_ENTITY_NOT_FOUND -24 #define CUDBG_SYSTEM_ERROR -29 #define CUDBG_MAJOR_VERSION 1 @@ -27,6 +28,8 @@ enum cudbg_dbg_entity_type { CUDBG_REG_DUMP = 1, + CUDBG_EDC0 = 18, + CUDBG_EDC1 = 19, CUDBG_MAX_ENTITY = 70, }; @@ -35,4 +38,9 @@ struct cudbg_init { void *outbuf; /* Output buffer */ u32 outbuf_size; /* Output buffer size */ }; + +static inline unsigned int cudbg_mbytes_to_bytes(unsigned int size) +{ + return size * 1024 * 1024; +} #endif /* __CUDBG_IF_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index b37d8f7825dd6..fb0e97e6a6a07 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -15,10 +15,12 @@ * */ +#include "t4_regs.h" #include "cxgb4.h" #include "cudbg_if.h" #include "cudbg_lib_common.h" #include "cudbg_lib.h" +#include "cudbg_entity.h" static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff, struct cudbg_buffer *dbg_buff) @@ -27,6 +29,16 @@ static void cudbg_write_and_release_buff(struct cudbg_buffer *pin_buff, cudbg_put_buff(pin_buff, dbg_buff); } +static int is_fw_attached(struct cudbg_init *pdbg_init) +{ + struct adapter *padap = pdbg_init->adap; + + if (!(padap->flags & FW_OK) || padap->use_bd) + return 0; + + return 1; +} + /* This function will add additional padding bytes into debug_buffer to make it * 4 byte aligned. */ @@ -77,3 +89,127 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, cudbg_write_and_release_buff(&temp_buff, dbg_buff); return rc; } + +static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, u8 mem_type, + unsigned long tot_len, + struct cudbg_error *cudbg_err) +{ + unsigned long bytes, bytes_left, bytes_read = 0; + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int rc = 0; + + bytes_left = tot_len; + while (bytes_left > 0) { + bytes = min_t(unsigned long, bytes_left, + (unsigned long)CUDBG_CHUNK_SIZE); + rc = cudbg_get_buff(dbg_buff, bytes, &temp_buff); + if (rc) + return rc; + spin_lock(&padap->win0_lock); + rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type, + bytes_read, bytes, + (__be32 *)temp_buff.data, + 1); + spin_unlock(&padap->win0_lock); + if (rc) { + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + bytes_left -= bytes; + bytes_read += bytes; + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + } + return rc; +} + +static void cudbg_collect_mem_info(struct cudbg_init *pdbg_init, + struct card_mem *mem_info) +{ + struct adapter *padap = pdbg_init->adap; + u32 value; + + value = t4_read_reg(padap, MA_EDRAM0_BAR_A); + value = EDRAM0_SIZE_G(value); + mem_info->size_edc0 = (u16)value; + + value = t4_read_reg(padap, MA_EDRAM1_BAR_A); + value = EDRAM1_SIZE_G(value); + mem_info->size_edc1 = (u16)value; + + value = t4_read_reg(padap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM0_ENABLE_F) + mem_info->mem_flag |= (1 << EDC0_FLAG); + if (value & EDRAM1_ENABLE_F) + mem_info->mem_flag |= (1 << EDC1_FLAG); +} + +static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + int rc; + + if (is_fw_attached(pdbg_init)) { + /* Flush uP dcache before reading edcX/mcX */ + rc = t4_fwcache(padap, FW_PARAM_DEV_FWCACHE_FLUSH); + if (rc) + cudbg_err->sys_warn = rc; + } +} + +static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, + u8 mem_type) +{ + struct card_mem mem_info = {0}; + unsigned long flag, size; + int rc; + + cudbg_t4_fwcache(pdbg_init, cudbg_err); + cudbg_collect_mem_info(pdbg_init, &mem_info); + switch (mem_type) { + case MEM_EDC0: + flag = (1 << EDC0_FLAG); + size = cudbg_mbytes_to_bytes(mem_info.size_edc0); + break; + case MEM_EDC1: + flag = (1 << EDC1_FLAG); + size = cudbg_mbytes_to_bytes(mem_info.size_edc1); + break; + default: + rc = CUDBG_STATUS_ENTITY_NOT_FOUND; + goto err; + } + + if (mem_info.mem_flag & flag) { + rc = cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, + size, cudbg_err); + if (rc) + goto err; + } else { + rc = CUDBG_STATUS_ENTITY_NOT_FOUND; + goto err; + } +err: + return rc; +} + +int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err, + MEM_EDC0); +} + +int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err, + MEM_EDC1); +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index 5b0a0e9646017..f7be5090b1725 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -21,6 +21,12 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h index 422a5ceedd2e5..b150c5d1f7c0b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h @@ -69,6 +69,9 @@ struct cudbg_error { int app_err; }; +#define CDUMP_MAX_COMP_BUF_SIZE ((64 * 1024) - 1) +#define CUDBG_CHUNK_SIZE ((CDUMP_MAX_COMP_BUF_SIZE / 1024) * 1024) + int cudbg_get_buff(struct cudbg_buffer *pdbg_buff, u32 size, struct cudbg_buffer *pin_buff); void cudbg_put_buff(struct cudbg_buffer *pin_buff, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 4ec322eec68ca..286d172a9c198 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -15,16 +15,22 @@ * */ +#include "t4_regs.h" #include "cxgb4.h" #include "cxgb4_cudbg.h" +static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = { + { CUDBG_EDC0, cudbg_collect_edc0_meminfo }, + { CUDBG_EDC1, cudbg_collect_edc1_meminfo }, +}; + static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, }; static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) { - u32 len = 0; + u32 value, len = 0; switch (entity) { case CUDBG_REG_DUMP: @@ -40,6 +46,22 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) break; } break; + case CUDBG_EDC0: + value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM0_ENABLE_F) { + value = t4_read_reg(adap, MA_EDRAM0_BAR_A); + len = EDRAM0_SIZE_G(value); + } + len = cudbg_mbytes_to_bytes(len); + break; + case CUDBG_EDC1: + value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); + if (value & EDRAM1_ENABLE_F) { + value = t4_read_reg(adap, MA_EDRAM1_BAR_A); + len = EDRAM1_SIZE_G(value); + } + len = cudbg_mbytes_to_bytes(len); + break; default: break; } @@ -59,6 +81,13 @@ u32 cxgb4_get_dump_length(struct adapter *adap, u32 flag) } } + if (flag & CXGB4_ETH_DUMP_MEM) { + for (i = 0; i < ARRAY_SIZE(cxgb4_collect_mem_dump); i++) { + entity = cxgb4_collect_mem_dump[i].entity; + len += cxgb4_get_entity_length(adap, entity); + } + } + return len; } @@ -152,6 +181,13 @@ int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, buf, &total_size); + if (flag & CXGB4_ETH_DUMP_MEM) + cxgb4_cudbg_collect_entity(&cudbg_init, &dbg_buff, + cxgb4_collect_mem_dump, + ARRAY_SIZE(cxgb4_collect_mem_dump), + buf, + &total_size); + cudbg_hdr->data_len = total_size; *buf_size = total_size; return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h index 7369a7e22b890..c099b5aa22142 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h @@ -33,6 +33,7 @@ struct cxgb4_collect_entity { enum CXGB4_ETHTOOL_DUMP_FLAGS { CXGB4_ETH_DUMP_NONE = ETH_FW_DUMP_DISABLE, + CXGB4_ETH_DUMP_MEM = (1 << 0), /* On-Chip Memory Dumps */ CXGB4_ETH_DUMP_HW = (1 << 1), /* various FW and HW dumps */ }; -- GitLab From 844d1b6f0ef8051a1ac0403327ab881dd4d101a3 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:16 +0530 Subject: [PATCH 1377/1507] cxgb4: collect firmware mbox and device log dump Collect firmware mbox and device logs before collecting the rest of the hardware dumps to snap the firmware state before the mailbox logs are updated by other hardware dumps. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cudbg_entity.h | 6 ++ drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 2 + .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 84 +++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 6 ++ .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 9 ++ 5 files changed, 107 insertions(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index 71a426dd22f54..2b717e700bbc5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -26,4 +26,10 @@ struct card_mem { u16 size_edc1; u16 mem_flag; }; + +struct cudbg_mbox_log { + struct mbox_cmd entry; + u32 hi[MBOX_LEN / 8]; + u32 lo[MBOX_LEN / 8]; +}; #endif /* __CUDBG_ENTITY_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 8bcea985af771..0a37d9b6cd325 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -28,8 +28,10 @@ enum cudbg_dbg_entity_type { CUDBG_REG_DUMP = 1, + CUDBG_DEV_LOG = 2, CUDBG_EDC0 = 18, CUDBG_EDC1 = 19, + CUDBG_MBOX_LOG = 66, CUDBG_MAX_ENTITY = 70, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index fb0e97e6a6a07..960635e37a9dc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -90,6 +90,45 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, return rc; } +int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct devlog_params *dparams; + int rc = 0; + + rc = t4_init_devlog_params(padap); + if (rc < 0) { + cudbg_err->sys_err = rc; + return rc; + } + + dparams = &padap->params.devlog; + rc = cudbg_get_buff(dbg_buff, dparams->size, &temp_buff); + if (rc) + return rc; + + /* Collect FW devlog */ + if (dparams->start != 0) { + spin_lock(&padap->win0_lock); + rc = t4_memory_rw(padap, padap->params.drv_memwin, + dparams->memtype, dparams->start, + dparams->size, + (__be32 *)(char *)temp_buff.data, + 1); + spin_unlock(&padap->win0_lock); + if (rc) { + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, u8 mem_type, unsigned long tot_len, @@ -213,3 +252,48 @@ int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, return cudbg_collect_mem_region(pdbg_init, dbg_buff, cudbg_err, MEM_EDC1); } + +int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_mbox_log *mboxlog = NULL; + struct cudbg_buffer temp_buff = { 0 }; + struct mbox_cmd_log *log = NULL; + struct mbox_cmd *entry; + unsigned int entry_idx; + u16 mbox_cmds; + int i, k, rc; + u64 flit; + u32 size; + + log = padap->mbox_log; + mbox_cmds = padap->mbox_log->size; + size = sizeof(struct cudbg_mbox_log) * mbox_cmds; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + mboxlog = (struct cudbg_mbox_log *)temp_buff.data; + for (k = 0; k < mbox_cmds; k++) { + entry_idx = log->cursor + k; + if (entry_idx >= log->size) + entry_idx -= log->size; + + entry = mbox_cmd_log_entry(log, entry_idx); + /* skip over unused entries */ + if (entry->timestamp == 0) + continue; + + memcpy(&mboxlog->entry, entry, sizeof(struct mbox_cmd)); + for (i = 0; i < MBOX_LEN / 8; i++) { + flit = entry->cmd[i]; + mboxlog->hi[i] = (u32)(flit >> 32); + mboxlog->lo[i] = (u32)flit; + } + mboxlog++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index f7be5090b1725..690591b36d4ca 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -21,12 +21,18 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 286d172a9c198..f8c4f4199ce60 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -18,6 +18,7 @@ #include "t4_regs.h" #include "cxgb4.h" #include "cxgb4_cudbg.h" +#include "cudbg_entity.h" static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = { { CUDBG_EDC0, cudbg_collect_edc0_meminfo }, @@ -25,6 +26,8 @@ static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = { }; static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { + { CUDBG_MBOX_LOG, cudbg_collect_mbox_log }, + { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, }; @@ -46,6 +49,9 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) break; } break; + case CUDBG_DEV_LOG: + len = adap->params.devlog.size; + break; case CUDBG_EDC0: value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); if (value & EDRAM0_ENABLE_F) { @@ -62,6 +68,9 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) } len = cudbg_mbytes_to_bytes(len); break; + case CUDBG_MBOX_LOG: + len = sizeof(struct cudbg_mbox_log) * adap->mbox_log->size; + break; default: break; } -- GitLab From 5ccf9d049615994349e9b0a1f0d4b9a398b9b0c2 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:17 +0530 Subject: [PATCH 1378/1507] cxgb4: update API for TP indirect register access Try to access TP indirect registers via firmware first. If this fails, fallback and access them directly. This ensures that driver and firmware do not conflict each other while accessing the TP indirect registers. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 36 +- .../ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 13 +- .../ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 14 +- .../net/ethernet/chelsio/cxgb4/cxgb4_main.c | 4 +- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 312 +++++++++++------- 5 files changed, 239 insertions(+), 140 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index a749602fdc419..d4032e373927a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1459,7 +1459,7 @@ unsigned int qtimer_val(const struct adapter *adap, int t4_init_devlog_params(struct adapter *adapter); int t4_init_sge_params(struct adapter *adapter); -int t4_init_tp_params(struct adapter *adap); +int t4_init_tp_params(struct adapter *adap, bool sleep_ok); int t4_filter_field_shift(const struct adapter *adap, int filter_sel); int t4_init_rss_mode(struct adapter *adap, int mbox); int t4_init_portinfo(struct port_info *pi, int mbox, @@ -1473,14 +1473,15 @@ int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode, int t4_config_vi_rss(struct adapter *adapter, int mbox, unsigned int viid, unsigned int flags, unsigned int defq); int t4_read_rss(struct adapter *adapter, u16 *entries); -void t4_read_rss_key(struct adapter *adapter, u32 *key); -void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx); +void t4_read_rss_key(struct adapter *adapter, u32 *key, bool sleep_ok); +void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx, + bool sleep_ok); void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, - u32 *valp); + u32 *valp, bool sleep_ok); void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, - u32 *vfl, u32 *vfh); -u32 t4_read_rss_pf_map(struct adapter *adapter); -u32 t4_read_rss_pf_mask(struct adapter *adapter); + u32 *vfl, u32 *vfh, bool sleep_ok); +u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok); +u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok); unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx); unsigned int t4_get_tp_ch_map(struct adapter *adapter, int pidx); @@ -1511,14 +1512,18 @@ void t4_read_cong_tbl(struct adapter *adap, u16 incr[NMTUS][NCCTRL_WIN]); void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, unsigned int mask, unsigned int val); void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr); -void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st); -void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st); -void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st); -void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st); +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st, + bool sleep_ok); +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st, + bool sleep_ok); +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st, + bool sleep_ok); +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st, + bool sleep_ok); void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, - struct tp_tcp_stats *v6); + struct tp_tcp_stats *v6, bool sleep_ok); void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, - struct tp_fcoe_stats *st); + struct tp_fcoe_stats *st, bool sleep_ok); void t4_load_mtus(struct adapter *adap, const unsigned short *mtus, const unsigned short *alpha, const unsigned short *beta); @@ -1627,6 +1632,11 @@ void t4_idma_monitor(struct adapter *adapter, int hz, int ticks); int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, unsigned int naddr, u8 *addr); +void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); +void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); + void t4_uld_mem_free(struct adapter *adap); int t4_uld_mem_alloc(struct adapter *adap); void t4_uld_clean_up(struct adapter *adap); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 76540b0e082d3..917663b356030 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2211,7 +2211,7 @@ static int rss_key_show(struct seq_file *seq, void *v) { u32 key[10]; - t4_read_rss_key(seq->private, key); + t4_read_rss_key(seq->private, key, true); seq_printf(seq, "%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x\n", key[9], key[8], key[7], key[6], key[5], key[4], key[3], key[2], key[1], key[0]); @@ -2248,7 +2248,7 @@ static ssize_t rss_key_write(struct file *file, const char __user *buf, } } - t4_write_rss_key(adap, key, -1); + t4_write_rss_key(adap, key, -1, true); return count; } @@ -2325,12 +2325,13 @@ static int rss_pf_config_open(struct inode *inode, struct file *file) return -ENOMEM; pfconf = (struct rss_pf_conf *)p->data; - rss_pf_map = t4_read_rss_pf_map(adapter); - rss_pf_mask = t4_read_rss_pf_mask(adapter); + rss_pf_map = t4_read_rss_pf_map(adapter, true); + rss_pf_mask = t4_read_rss_pf_mask(adapter, true); for (pf = 0; pf < 8; pf++) { pfconf[pf].rss_pf_map = rss_pf_map; pfconf[pf].rss_pf_mask = rss_pf_mask; - t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config); + t4_read_rss_pf_config(adapter, pf, &pfconf[pf].rss_pf_config, + true); } return 0; } @@ -2393,7 +2394,7 @@ static int rss_vf_config_open(struct inode *inode, struct file *file) vfconf = (struct rss_vf_conf *)p->data; for (vf = 0; vf < vfcount; vf++) { t4_read_rss_vf_config(adapter, vf, &vfconf[vf].rss_vf_vfl, - &vfconf[vf].rss_vf_vfh); + &vfconf[vf].rss_vf_vfh, true); } return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 796eb051cb2f0..1b7f6b9ccc8b8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -336,10 +336,10 @@ static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s) memset(s, 0, sizeof(*s)); spin_lock(&adap->stats_lock); - t4_tp_get_tcp_stats(adap, &v4, &v6); - t4_tp_get_rdma_stats(adap, &rdma_stats); - t4_get_usm_stats(adap, &usm_stats); - t4_tp_get_err_stats(adap, &err_stats); + t4_tp_get_tcp_stats(adap, &v4, &v6, false); + t4_tp_get_rdma_stats(adap, &rdma_stats, false); + t4_get_usm_stats(adap, &usm_stats, false); + t4_tp_get_err_stats(adap, &err_stats, false); spin_unlock(&adap->stats_lock); s->db_drop = adap->db_stats.db_drop; @@ -389,9 +389,9 @@ static void collect_channel_stats(struct adapter *adap, struct channel_stats *s, memset(s, 0, sizeof(*s)); spin_lock(&adap->stats_lock); - t4_tp_get_cpl_stats(adap, &cpl_stats); - t4_tp_get_err_stats(adap, &err_stats); - t4_get_fcoe_stats(adap, i, &fcoe_stats); + t4_tp_get_cpl_stats(adap, &cpl_stats, false); + t4_tp_get_err_stats(adap, &err_stats, false); + t4_get_fcoe_stats(adap, i, &fcoe_stats, false); spin_unlock(&adap->stats_lock); s->cpl_req = cpl_stats.req[i]; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 70c395d180870..8d97ae6039aa4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1639,7 +1639,7 @@ void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4, struct adapter *adap = pci_get_drvdata(pdev); spin_lock(&adap->stats_lock); - t4_tp_get_tcp_stats(adap, v4, v6); + t4_tp_get_tcp_stats(adap, v4, v6, false); spin_unlock(&adap->stats_lock); } EXPORT_SYMBOL(cxgb4_get_tcp_stats); @@ -4077,7 +4077,7 @@ static int adap_init0(struct adapter *adap) } t4_init_sge_params(adap); adap->flags |= FW_OK; - t4_init_tp_params(adap); + t4_init_tp_params(adap, true); return 0; /* diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index b3fd1f4576390..0f12bf507d569 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -5052,23 +5052,26 @@ static unsigned int t4_use_ldst(struct adapter *adap) } /** - * t4_fw_tp_pio_rw - Access TP PIO through LDST - * @adap: the adapter - * @vals: where the indirect register values are stored/written - * @nregs: how many indirect registers to read/write - * @start_idx: index of first indirect register to read/write - * @rw: Read (1) or Write (0) + * t4_tp_fw_ldst_rw - Access TP indirect register through LDST + * @adap: the adapter + * @cmd: TP fw ldst address space type + * @vals: where the indirect register values are stored/written + * @nregs: how many indirect registers to read/write + * @start_idx: index of first indirect register to read/write + * @rw: Read (1) or Write (0) + * @sleep_ok: if true we may sleep while awaiting command completion * - * Access TP PIO registers through LDST + * Access TP indirect registers through LDST */ -static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs, - unsigned int start_index, unsigned int rw) +static int t4_tp_fw_ldst_rw(struct adapter *adap, int cmd, u32 *vals, + unsigned int nregs, unsigned int start_index, + unsigned int rw, bool sleep_ok) { - int ret, i; - int cmd = FW_LDST_ADDRSPC_TP_PIO; + int ret = 0; + unsigned int i; struct fw_ldst_cmd c; - for (i = 0 ; i < nregs; i++) { + for (i = 0; i < nregs; i++) { memset(&c, 0, sizeof(c)); c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F | @@ -5079,26 +5082,127 @@ static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs, c.u.addrval.addr = cpu_to_be32(start_index + i); c.u.addrval.val = rw ? 0 : cpu_to_be32(vals[i]); - ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); - if (!ret && rw) + ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, + sleep_ok); + if (ret) + return ret; + + if (rw) vals[i] = be32_to_cpu(c.u.addrval.val); } + return 0; +} + +/** + * t4_tp_indirect_rw - Read/Write TP indirect register through LDST or backdoor + * @adap: the adapter + * @reg_addr: Address Register + * @reg_data: Data register + * @buff: where the indirect register values are stored/written + * @nregs: how many indirect registers to read/write + * @start_index: index of first indirect register to read/write + * @rw: READ(1) or WRITE(0) + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read/Write TP indirect registers through LDST if possible. + * Else, use backdoor access + **/ +static void t4_tp_indirect_rw(struct adapter *adap, u32 reg_addr, u32 reg_data, + u32 *buff, u32 nregs, u32 start_index, int rw, + bool sleep_ok) +{ + int rc = -EINVAL; + int cmd; + + switch (reg_addr) { + case TP_PIO_ADDR_A: + cmd = FW_LDST_ADDRSPC_TP_PIO; + break; + case TP_MIB_INDEX_A: + cmd = FW_LDST_ADDRSPC_TP_MIB; + break; + default: + goto indirect_access; + } + + if (t4_use_ldst(adap)) + rc = t4_tp_fw_ldst_rw(adap, cmd, buff, nregs, start_index, rw, + sleep_ok); + +indirect_access: + + if (rc) { + if (rw) + t4_read_indirect(adap, reg_addr, reg_data, buff, nregs, + start_index); + else + t4_write_indirect(adap, reg_addr, reg_data, buff, nregs, + start_index); + } +} + +/** + * t4_tp_pio_read - Read TP PIO registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP PIO Registers + **/ +void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs, + start_index, 1, sleep_ok); +} + +/** + * t4_tp_pio_write - Write TP PIO registers + * @adap: the adapter + * @buff: where the indirect register values are stored + * @nregs: how many indirect registers to write + * @start_index: index of first indirect register to write + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Write TP PIO Registers + **/ +static void t4_tp_pio_write(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, buff, nregs, + start_index, 0, sleep_ok); +} + +/** + * t4_tp_mib_read - Read TP MIB registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP MIB Registers + **/ +void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, + bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, buff, nregs, + start_index, 1, sleep_ok); } /** * t4_read_rss_key - read the global RSS key * @adap: the adapter * @key: 10-entry array holding the 320-bit RSS key + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the global 320-bit RSS key. */ -void t4_read_rss_key(struct adapter *adap, u32 *key) +void t4_read_rss_key(struct adapter *adap, u32 *key, bool sleep_ok) { - if (t4_use_ldst(adap)) - t4_fw_tp_pio_rw(adap, key, 10, TP_RSS_SECRET_KEY0_A, 1); - else - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, - TP_RSS_SECRET_KEY0_A); + t4_tp_pio_read(adap, key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok); } /** @@ -5106,12 +5210,14 @@ void t4_read_rss_key(struct adapter *adap, u32 *key) * @adap: the adapter * @key: 10-entry array holding the 320-bit RSS key * @idx: which RSS key to write + * @sleep_ok: if true we may sleep while awaiting command completion * * Writes one of the RSS keys with the given 320-bit value. If @idx is * 0..15 the corresponding entry in the RSS key table is written, * otherwise the global RSS key is written. */ -void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) +void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx, + bool sleep_ok) { u8 rss_key_addr_cnt = 16; u32 vrt = t4_read_reg(adap, TP_RSS_CONFIG_VRT_A); @@ -5124,11 +5230,7 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3)) rss_key_addr_cnt = 32; - if (t4_use_ldst(adap)) - t4_fw_tp_pio_rw(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, 0); - else - t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, - TP_RSS_SECRET_KEY0_A); + t4_tp_pio_write(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, sleep_ok); if (idx >= 0 && idx < rss_key_addr_cnt) { if (rss_key_addr_cnt > 16) @@ -5146,19 +5248,15 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) * @adapter: the adapter * @index: the entry in the PF RSS table to read * @valp: where to store the returned value + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Configuration Table at the specified index and returns * the value found there. */ void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, - u32 *valp) + u32 *valp, bool sleep_ok) { - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, valp, 1, - TP_RSS_PF0_CONFIG_A + index, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - valp, 1, TP_RSS_PF0_CONFIG_A + index); + t4_tp_pio_read(adapter, valp, 1, TP_RSS_PF0_CONFIG_A + index, sleep_ok); } /** @@ -5167,12 +5265,13 @@ void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, * @index: the entry in the VF RSS table to read * @vfl: where to store the returned VFL * @vfh: where to store the returned VFH + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the VF RSS Configuration Table at the specified index and returns * the (VFL, VFH) values found there. */ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, - u32 *vfl, u32 *vfh) + u32 *vfl, u32 *vfh, bool sleep_ok) { u32 vrt, mask, data; @@ -5193,50 +5292,37 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, /* Grab the VFL/VFH values ... */ - if (t4_use_ldst(adapter)) { - t4_fw_tp_pio_rw(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, 1); - t4_fw_tp_pio_rw(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, 1); - } else { - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - vfl, 1, TP_RSS_VFL_CONFIG_A); - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - vfh, 1, TP_RSS_VFH_CONFIG_A); - } + t4_tp_pio_read(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, sleep_ok); + t4_tp_pio_read(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, sleep_ok); } /** * t4_read_rss_pf_map - read PF RSS Map * @adapter: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Map register and returns its value. */ -u32 t4_read_rss_pf_map(struct adapter *adapter) +u32 t4_read_rss_pf_map(struct adapter *adapter, bool sleep_ok) { u32 pfmap; - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &pfmap, 1, TP_RSS_PF_MAP_A); + t4_tp_pio_read(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, sleep_ok); return pfmap; } /** * t4_read_rss_pf_mask - read PF RSS Mask * @adapter: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Reads the PF RSS Mask register and returns its value. */ -u32 t4_read_rss_pf_mask(struct adapter *adapter) +u32 t4_read_rss_pf_mask(struct adapter *adapter, bool sleep_ok) { u32 pfmask; - if (t4_use_ldst(adapter)) - t4_fw_tp_pio_rw(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, 1); - else - t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &pfmask, 1, TP_RSS_PF_MSK_A); + t4_tp_pio_read(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, sleep_ok); return pfmask; } @@ -5245,12 +5331,13 @@ u32 t4_read_rss_pf_mask(struct adapter *adapter) * @adap: the adapter * @v4: holds the TCP/IP counter values * @v6: holds the TCP/IPv6 counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's TCP/IP and TCP/IPv6 MIB counters. * Either @v4 or @v6 may be %NULL to skip the corresponding stats. */ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, - struct tp_tcp_stats *v6) + struct tp_tcp_stats *v6, bool sleep_ok) { u32 val[TP_MIB_TCP_RXT_SEG_LO_A - TP_MIB_TCP_OUT_RST_A + 1]; @@ -5259,16 +5346,16 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, #define STAT64(x) (((u64)STAT(x##_HI) << 32) | STAT(x##_LO)) if (v4) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - ARRAY_SIZE(val), TP_MIB_TCP_OUT_RST_A); + t4_tp_mib_read(adap, val, ARRAY_SIZE(val), + TP_MIB_TCP_OUT_RST_A, sleep_ok); v4->tcp_out_rsts = STAT(OUT_RST); v4->tcp_in_segs = STAT64(IN_SEG); v4->tcp_out_segs = STAT64(OUT_SEG); v4->tcp_retrans_segs = STAT64(RXT_SEG); } if (v6) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - ARRAY_SIZE(val), TP_MIB_TCP_V6OUT_RST_A); + t4_tp_mib_read(adap, val, ARRAY_SIZE(val), + TP_MIB_TCP_V6OUT_RST_A, sleep_ok); v6->tcp_out_rsts = STAT(OUT_RST); v6->tcp_in_segs = STAT64(IN_SEG); v6->tcp_out_segs = STAT64(OUT_SEG); @@ -5283,63 +5370,66 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, * t4_tp_get_err_stats - read TP's error MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's error counters. */ -void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st) +void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st, + bool sleep_ok) { int nchan = adap->params.arch.nchan; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_cong_drops, nchan, TP_MIB_TNL_CNG_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_chan_drops, nchan, TP_MIB_OFD_CHN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_vlan_drops, nchan, TP_MIB_OFD_VLN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp6_in_errs, nchan, TP_MIB_TCP_V6IN_ERR_0_A); - - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A); + t4_tp_mib_read(adap, st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->tnl_cong_drops, nchan, + TP_MIB_TNL_CNG_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->ofld_chan_drops, nchan, + TP_MIB_OFD_CHN_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A, + sleep_ok); + t4_tp_mib_read(adap, st->ofld_vlan_drops, nchan, + TP_MIB_OFD_VLN_DROP_0_A, sleep_ok); + t4_tp_mib_read(adap, st->tcp6_in_errs, nchan, + TP_MIB_TCP_V6IN_ERR_0_A, sleep_ok); + t4_tp_mib_read(adap, &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A, + sleep_ok); } /** * t4_tp_get_cpl_stats - read TP's CPL MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's CPL counters. */ -void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st) +void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st, + bool sleep_ok) { int nchan = adap->params.arch.nchan; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, - nchan, TP_MIB_CPL_IN_REQ_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp, - nchan, TP_MIB_CPL_OUT_RSP_0_A); + t4_tp_mib_read(adap, st->req, nchan, TP_MIB_CPL_IN_REQ_0_A, sleep_ok); + t4_tp_mib_read(adap, st->rsp, nchan, TP_MIB_CPL_OUT_RSP_0_A, sleep_ok); } /** * t4_tp_get_rdma_stats - read TP's RDMA MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's RDMA counters. */ -void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st) +void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st, + bool sleep_ok) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->rqe_dfr_pkt, - 2, TP_MIB_RQE_DFR_PKT_A); + t4_tp_mib_read(adap, &st->rqe_dfr_pkt, 2, TP_MIB_RQE_DFR_PKT_A, + sleep_ok); } /** @@ -5347,20 +5437,24 @@ void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st) * @adap: the adapter * @idx: the port index * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's FCoE counters for the selected port. */ void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, - struct tp_fcoe_stats *st) + struct tp_fcoe_stats *st, bool sleep_ok) { u32 val[2]; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_ddp, - 1, TP_MIB_FCOE_DDP_0_A + idx); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_drop, - 1, TP_MIB_FCOE_DROP_0_A + idx); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, - 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx); + t4_tp_mib_read(adap, &st->frames_ddp, 1, TP_MIB_FCOE_DDP_0_A + idx, + sleep_ok); + + t4_tp_mib_read(adap, &st->frames_drop, 1, + TP_MIB_FCOE_DROP_0_A + idx, sleep_ok); + + t4_tp_mib_read(adap, val, 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx, + sleep_ok); + st->octets_ddp = ((u64)val[0] << 32) | val[1]; } @@ -5368,15 +5462,16 @@ void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx, * t4_get_usm_stats - read TP's non-TCP DDP MIB counters * @adap: the adapter * @st: holds the counter values + * @sleep_ok: if true we may sleep while awaiting command completion * * Returns the values of TP's counters for non-TCP directly-placed packets. */ -void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st) +void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st, + bool sleep_ok) { u32 val[4]; - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, 4, - TP_MIB_USM_PKTS_A); + t4_tp_mib_read(adap, val, 4, TP_MIB_USM_PKTS_A, sleep_ok); st->frames = val[0]; st->drops = val[1]; st->octets = ((u64)val[2] << 32) | val[3]; @@ -8663,10 +8758,11 @@ int t4_init_sge_params(struct adapter *adapter) /** * t4_init_tp_params - initialize adap->params.tp * @adap: the adapter + * @sleep_ok: if true we may sleep while awaiting command completion * * Initialize various fields of the adapter's TP Parameters structure. */ -int t4_init_tp_params(struct adapter *adap) +int t4_init_tp_params(struct adapter *adap, bool sleep_ok) { int chan; u32 v; @@ -8682,19 +8778,11 @@ int t4_init_tp_params(struct adapter *adap) /* Cache the adapter's Compressed Filter Mode and global Incress * Configuration. */ - if (t4_use_ldst(adap)) { - t4_fw_tp_pio_rw(adap, &adap->params.tp.vlan_pri_map, 1, - TP_VLAN_PRI_MAP_A, 1); - t4_fw_tp_pio_rw(adap, &adap->params.tp.ingress_config, 1, - TP_INGRESS_CONFIG_A, 1); - } else { - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &adap->params.tp.vlan_pri_map, 1, - TP_VLAN_PRI_MAP_A); - t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, - &adap->params.tp.ingress_config, 1, - TP_INGRESS_CONFIG_A); - } + t4_tp_pio_read(adap, &adap->params.tp.vlan_pri_map, 1, + TP_VLAN_PRI_MAP_A, sleep_ok); + t4_tp_pio_read(adap, &adap->params.tp.ingress_config, 1, + TP_INGRESS_CONFIG_A, sleep_ok); + /* For T6, cache the adapter's compressed error vector * and passing outer header info for encapsulated packets. */ -- GitLab From 4359cf33680c3f276c6bba11730836c41d3540a2 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:18 +0530 Subject: [PATCH 1379/1507] cxgb4: collect TP dump Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cudbg_entity.h | 72 +++++++++++ drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 1 + .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 114 ++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 3 + drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 2 + .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 21 +++- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 20 +++ drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 2 + 8 files changed, 234 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index 2b717e700bbc5..a7446fd09366e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -32,4 +32,76 @@ struct cudbg_mbox_log { u32 hi[MBOX_LEN / 8]; u32 lo[MBOX_LEN / 8]; }; + +struct ireg_field { + u32 ireg_addr; + u32 ireg_data; + u32 ireg_local_offset; + u32 ireg_offset_range; +}; + +struct ireg_buf { + struct ireg_field tp_pio; + u32 outbuf[32]; +}; + +#define IREG_NUM_ELEM 4 + +static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = { + {0x7e40, 0x7e44, 0x020, 28}, /* t6_tp_pio_regs_20_to_3b */ + {0x7e40, 0x7e44, 0x040, 10}, /* t6_tp_pio_regs_40_to_49 */ + {0x7e40, 0x7e44, 0x050, 10}, /* t6_tp_pio_regs_50_to_59 */ + {0x7e40, 0x7e44, 0x060, 14}, /* t6_tp_pio_regs_60_to_6d */ + {0x7e40, 0x7e44, 0x06F, 1}, /* t6_tp_pio_regs_6f */ + {0x7e40, 0x7e44, 0x070, 6}, /* t6_tp_pio_regs_70_to_75 */ + {0x7e40, 0x7e44, 0x130, 18}, /* t6_tp_pio_regs_130_to_141 */ + {0x7e40, 0x7e44, 0x145, 19}, /* t6_tp_pio_regs_145_to_157 */ + {0x7e40, 0x7e44, 0x160, 1}, /* t6_tp_pio_regs_160 */ + {0x7e40, 0x7e44, 0x230, 25}, /* t6_tp_pio_regs_230_to_248 */ + {0x7e40, 0x7e44, 0x24a, 3}, /* t6_tp_pio_regs_24c */ + {0x7e40, 0x7e44, 0x8C0, 1} /* t6_tp_pio_regs_8c0 */ +}; + +static const u32 t5_tp_pio_array[][IREG_NUM_ELEM] = { + {0x7e40, 0x7e44, 0x020, 28}, /* t5_tp_pio_regs_20_to_3b */ + {0x7e40, 0x7e44, 0x040, 19}, /* t5_tp_pio_regs_40_to_52 */ + {0x7e40, 0x7e44, 0x054, 2}, /* t5_tp_pio_regs_54_to_55 */ + {0x7e40, 0x7e44, 0x060, 13}, /* t5_tp_pio_regs_60_to_6c */ + {0x7e40, 0x7e44, 0x06F, 1}, /* t5_tp_pio_regs_6f */ + {0x7e40, 0x7e44, 0x120, 4}, /* t5_tp_pio_regs_120_to_123 */ + {0x7e40, 0x7e44, 0x12b, 2}, /* t5_tp_pio_regs_12b_to_12c */ + {0x7e40, 0x7e44, 0x12f, 21}, /* t5_tp_pio_regs_12f_to_143 */ + {0x7e40, 0x7e44, 0x145, 19}, /* t5_tp_pio_regs_145_to_157 */ + {0x7e40, 0x7e44, 0x230, 25}, /* t5_tp_pio_regs_230_to_248 */ + {0x7e40, 0x7e44, 0x8C0, 1} /* t5_tp_pio_regs_8c0 */ +}; + +static const u32 t6_tp_tm_pio_array[][IREG_NUM_ELEM] = { + {0x7e18, 0x7e1c, 0x0, 12} +}; + +static const u32 t5_tp_tm_pio_array[][IREG_NUM_ELEM] = { + {0x7e18, 0x7e1c, 0x0, 12} +}; + +static const u32 t6_tp_mib_index_array[6][IREG_NUM_ELEM] = { + {0x7e50, 0x7e54, 0x0, 13}, + {0x7e50, 0x7e54, 0x10, 6}, + {0x7e50, 0x7e54, 0x18, 21}, + {0x7e50, 0x7e54, 0x30, 32}, + {0x7e50, 0x7e54, 0x50, 22}, + {0x7e50, 0x7e54, 0x68, 12} +}; + +static const u32 t5_tp_mib_index_array[9][IREG_NUM_ELEM] = { + {0x7e50, 0x7e54, 0x0, 13}, + {0x7e50, 0x7e54, 0x10, 6}, + {0x7e50, 0x7e54, 0x18, 8}, + {0x7e50, 0x7e54, 0x20, 13}, + {0x7e50, 0x7e54, 0x30, 16}, + {0x7e50, 0x7e54, 0x40, 16}, + {0x7e50, 0x7e54, 0x50, 16}, + {0x7e50, 0x7e54, 0x60, 6}, + {0x7e50, 0x7e54, 0x68, 4} +}; #endif /* __CUDBG_ENTITY_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 0a37d9b6cd325..53ea447c91038 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -31,6 +31,7 @@ enum cudbg_dbg_entity_type { CUDBG_DEV_LOG = 2, CUDBG_EDC0 = 18, CUDBG_EDC1 = 19, + CUDBG_TP_INDIRECT = 36, CUDBG_MBOX_LOG = 66, CUDBG_MAX_ENTITY = 70, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 960635e37a9dc..6efa1de3723c0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -253,6 +253,120 @@ int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, MEM_EDC1); } +int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_tp_pio; + int i, rc, n = 0; + u32 size; + + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_pio_array) + + sizeof(t5_tp_tm_pio_array) + + sizeof(t5_tp_mib_index_array); + else + n = sizeof(t6_tp_pio_array) + + sizeof(t6_tp_tm_pio_array) + + sizeof(t6_tp_mib_index_array); + + n = n / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_tp_pio = (struct ireg_buf *)temp_buff.data; + + /* TP_PIO */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_pio_array[i][0]; + tp_pio->ireg_data = t5_tp_pio_array[i][1]; + tp_pio->ireg_local_offset = t5_tp_pio_array[i][2]; + tp_pio->ireg_offset_range = t5_tp_pio_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_pio_array[i][0]; + tp_pio->ireg_data = t6_tp_pio_array[i][1]; + tp_pio->ireg_local_offset = t6_tp_pio_array[i][2]; + tp_pio->ireg_offset_range = t6_tp_pio_array[i][3]; + } + t4_tp_pio_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + + /* TP_TM_PIO */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_tm_pio_array) / (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_tm_pio_array[i][0]; + tp_pio->ireg_data = t5_tp_tm_pio_array[i][1]; + tp_pio->ireg_local_offset = t5_tp_tm_pio_array[i][2]; + tp_pio->ireg_offset_range = t5_tp_tm_pio_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_tm_pio_array[i][0]; + tp_pio->ireg_data = t6_tp_tm_pio_array[i][1]; + tp_pio->ireg_local_offset = t6_tp_tm_pio_array[i][2]; + tp_pio->ireg_offset_range = t6_tp_tm_pio_array[i][3]; + } + t4_tp_tm_pio_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + + /* TP_MIB_INDEX */ + if (is_t5(padap->params.chip)) + n = sizeof(t5_tp_mib_index_array) / + (IREG_NUM_ELEM * sizeof(u32)); + else if (is_t6(padap->params.chip)) + n = sizeof(t6_tp_mib_index_array) / + (IREG_NUM_ELEM * sizeof(u32)); + + for (i = 0; i < n ; i++) { + struct ireg_field *tp_pio = &ch_tp_pio->tp_pio; + u32 *buff = ch_tp_pio->outbuf; + + if (is_t5(padap->params.chip)) { + tp_pio->ireg_addr = t5_tp_mib_index_array[i][0]; + tp_pio->ireg_data = t5_tp_mib_index_array[i][1]; + tp_pio->ireg_local_offset = + t5_tp_mib_index_array[i][2]; + tp_pio->ireg_offset_range = + t5_tp_mib_index_array[i][3]; + } else if (is_t6(padap->params.chip)) { + tp_pio->ireg_addr = t6_tp_mib_index_array[i][0]; + tp_pio->ireg_data = t6_tp_mib_index_array[i][1]; + tp_pio->ireg_local_offset = + t6_tp_mib_index_array[i][2]; + tp_pio->ireg_offset_range = + t6_tp_mib_index_array[i][3]; + } + t4_tp_mib_read(padap, buff, tp_pio->ireg_offset_range, + tp_pio->ireg_local_offset, true); + ch_tp_pio++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index 690591b36d4ca..7a927ec71a5f9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -30,6 +30,9 @@ int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index d4032e373927a..4eaca05ebd3a9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -1634,6 +1634,8 @@ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, unsigned int naddr, u8 *addr); void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, bool sleep_ok); +void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok); void t4_tp_mib_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, bool sleep_ok); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index f8c4f4199ce60..7dfee6adc51e4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -29,11 +29,12 @@ static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { { CUDBG_MBOX_LOG, cudbg_collect_mbox_log }, { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, + { CUDBG_TP_INDIRECT, cudbg_collect_tp_indirect }, }; static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) { - u32 value, len = 0; + u32 value, n = 0, len = 0; switch (entity) { case CUDBG_REG_DUMP: @@ -68,6 +69,24 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) } len = cudbg_mbytes_to_bytes(len); break; + case CUDBG_TP_INDIRECT: + switch (CHELSIO_CHIP_VERSION(adap->params.chip)) { + case CHELSIO_T5: + n = sizeof(t5_tp_pio_array) + + sizeof(t5_tp_tm_pio_array) + + sizeof(t5_tp_mib_index_array); + break; + case CHELSIO_T6: + n = sizeof(t6_tp_pio_array) + + sizeof(t6_tp_tm_pio_array) + + sizeof(t6_tp_mib_index_array); + break; + default: + break; + } + n = n / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + break; case CUDBG_MBOX_LOG: len = sizeof(struct cudbg_mbox_log) * adap->mbox_log->size; break; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 0f12bf507d569..8fa40f9e75c43 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -5118,6 +5118,9 @@ static void t4_tp_indirect_rw(struct adapter *adap, u32 reg_addr, u32 reg_data, case TP_PIO_ADDR_A: cmd = FW_LDST_ADDRSPC_TP_PIO; break; + case TP_TM_PIO_ADDR_A: + cmd = FW_LDST_ADDRSPC_TP_TM_PIO; + break; case TP_MIB_INDEX_A: cmd = FW_LDST_ADDRSPC_TP_MIB; break; @@ -5175,6 +5178,23 @@ static void t4_tp_pio_write(struct adapter *adap, u32 *buff, u32 nregs, start_index, 0, sleep_ok); } +/** + * t4_tp_tm_pio_read - Read TP TM PIO registers + * @adap: the adapter + * @buff: where the indirect register values are written + * @nregs: how many indirect registers to read + * @start_index: index of first indirect register to read + * @sleep_ok: if true we may sleep while awaiting command completion + * + * Read TP TM PIO Registers + **/ +void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, + u32 start_index, bool sleep_ok) +{ + t4_tp_indirect_rw(adap, TP_TM_PIO_ADDR_A, TP_TM_PIO_DATA_A, buff, + nregs, start_index, 1, sleep_ok); +} + /** * t4_tp_mib_read - Read TP MIB registers * @adap: the adapter diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index dac90837842bf..82614e078f505 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -1447,6 +1447,8 @@ #define LKPTBLQUEUE0_M 0x3ffU #define LKPTBLQUEUE0_G(x) (((x) >> LKPTBLQUEUE0_S) & LKPTBLQUEUE0_M) +#define TP_TM_PIO_ADDR_A 0x7e18 +#define TP_TM_PIO_DATA_A 0x7e1c #define TP_PIO_ADDR_A 0x7e40 #define TP_PIO_DATA_A 0x7e44 #define TP_MIB_INDEX_A 0x7e50 -- GitLab From 270d39bf324ecdb9ab3f9c521e6b7fd9cc6c27b8 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:19 +0530 Subject: [PATCH 1380/1507] cxgb4: collect hardware module dumps Collect SGE, PCIE, PM, UP CIM, MA and HMA dumps. Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb4/cudbg_entity.h | 74 +++++ drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 6 + .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 289 ++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 18 ++ .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 35 +++ 5 files changed, 422 insertions(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index a7446fd09366e..d7f3392f618fa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -104,4 +104,78 @@ static const u32 t5_tp_mib_index_array[9][IREG_NUM_ELEM] = { {0x7e50, 0x7e54, 0x60, 6}, {0x7e50, 0x7e54, 0x68, 4} }; + +static const u32 t5_sge_dbg_index_array[2][IREG_NUM_ELEM] = { + {0x10cc, 0x10d0, 0x0, 16}, + {0x10cc, 0x10d4, 0x0, 16}, +}; + +static const u32 t5_pcie_pdbg_array[][IREG_NUM_ELEM] = { + {0x5a04, 0x5a0c, 0x00, 0x20}, /* t5_pcie_pdbg_regs_00_to_20 */ + {0x5a04, 0x5a0c, 0x21, 0x20}, /* t5_pcie_pdbg_regs_21_to_40 */ + {0x5a04, 0x5a0c, 0x41, 0x10}, /* t5_pcie_pdbg_regs_41_to_50 */ +}; + +static const u32 t5_pcie_cdbg_array[][IREG_NUM_ELEM] = { + {0x5a10, 0x5a18, 0x00, 0x20}, /* t5_pcie_cdbg_regs_00_to_20 */ + {0x5a10, 0x5a18, 0x21, 0x18}, /* t5_pcie_cdbg_regs_21_to_37 */ +}; + +static const u32 t5_pm_rx_array[][IREG_NUM_ELEM] = { + {0x8FD0, 0x8FD4, 0x10000, 0x20}, /* t5_pm_rx_regs_10000_to_10020 */ + {0x8FD0, 0x8FD4, 0x10021, 0x0D}, /* t5_pm_rx_regs_10021_to_1002c */ +}; + +static const u32 t5_pm_tx_array[][IREG_NUM_ELEM] = { + {0x8FF0, 0x8FF4, 0x10000, 0x20}, /* t5_pm_tx_regs_10000_to_10020 */ + {0x8FF0, 0x8FF4, 0x10021, 0x1D}, /* t5_pm_tx_regs_10021_to_1003c */ +}; + +static const u32 t6_ma_ireg_array[][IREG_NUM_ELEM] = { + {0x78f8, 0x78fc, 0xa000, 23}, /* t6_ma_regs_a000_to_a016 */ + {0x78f8, 0x78fc, 0xa400, 30}, /* t6_ma_regs_a400_to_a41e */ + {0x78f8, 0x78fc, 0xa800, 20} /* t6_ma_regs_a800_to_a813 */ +}; + +static const u32 t6_ma_ireg_array2[][IREG_NUM_ELEM] = { + {0x78f8, 0x78fc, 0xe400, 17}, /* t6_ma_regs_e400_to_e600 */ + {0x78f8, 0x78fc, 0xe640, 13} /* t6_ma_regs_e640_to_e7c0 */ +}; + +static const u32 t6_up_cim_reg_array[][IREG_NUM_ELEM] = { + {0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */ + {0x7b50, 0x7b54, 0x2080, 0x1d}, /* up_cim_2080_to_20fc */ + {0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */ + {0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */ + {0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */ + {0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */ + {0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */ + {0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */ + {0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */ + {0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */ + {0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */ + {0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */ + {0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */ + +}; + +static const u32 t5_up_cim_reg_array[][IREG_NUM_ELEM] = { + {0x7b50, 0x7b54, 0x2000, 0x20}, /* up_cim_2000_to_207c */ + {0x7b50, 0x7b54, 0x2080, 0x19}, /* up_cim_2080_to_20ec */ + {0x7b50, 0x7b54, 0x00, 0x20}, /* up_cim_00_to_7c */ + {0x7b50, 0x7b54, 0x80, 0x20}, /* up_cim_80_to_fc */ + {0x7b50, 0x7b54, 0x100, 0x11}, /* up_cim_100_to_14c */ + {0x7b50, 0x7b54, 0x200, 0x10}, /* up_cim_200_to_23c */ + {0x7b50, 0x7b54, 0x240, 0x2}, /* up_cim_240_to_244 */ + {0x7b50, 0x7b54, 0x250, 0x2}, /* up_cim_250_to_254 */ + {0x7b50, 0x7b54, 0x260, 0x2}, /* up_cim_260_to_264 */ + {0x7b50, 0x7b54, 0x270, 0x2}, /* up_cim_270_to_274 */ + {0x7b50, 0x7b54, 0x280, 0x20}, /* up_cim_280_to_2fc */ + {0x7b50, 0x7b54, 0x300, 0x20}, /* up_cim_300_to_37c */ + {0x7b50, 0x7b54, 0x380, 0x14}, /* up_cim_380_to_3cc */ +}; + +static const u32 t6_hma_ireg_array[][IREG_NUM_ELEM] = { + {0x51320, 0x51324, 0xa000, 32} /* t6_hma_regs_a000_to_a01f */ +}; #endif /* __CUDBG_ENTITY_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 53ea447c91038..01d282081b2db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -32,7 +32,13 @@ enum cudbg_dbg_entity_type { CUDBG_EDC0 = 18, CUDBG_EDC1 = 19, CUDBG_TP_INDIRECT = 36, + CUDBG_SGE_INDIRECT = 37, + CUDBG_PCIE_INDIRECT = 50, + CUDBG_PM_INDIRECT = 51, + CUDBG_MA_INDIRECT = 61, + CUDBG_UP_CIM_INDIRECT = 64, CUDBG_MBOX_LOG = 66, + CUDBG_HMA_INDIRECT = 67, CUDBG_MAX_ENTITY = 70, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 6efa1de3723c0..0149f1ca9f51d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -367,6 +367,258 @@ int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, return rc; } +int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_sge_dbg; + int i, rc; + + rc = cudbg_get_buff(dbg_buff, sizeof(*ch_sge_dbg) * 2, &temp_buff); + if (rc) + return rc; + + ch_sge_dbg = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < 2; i++) { + struct ireg_field *sge_pio = &ch_sge_dbg->tp_pio; + u32 *buff = ch_sge_dbg->outbuf; + + sge_pio->ireg_addr = t5_sge_dbg_index_array[i][0]; + sge_pio->ireg_data = t5_sge_dbg_index_array[i][1]; + sge_pio->ireg_local_offset = t5_sge_dbg_index_array[i][2]; + sge_pio->ireg_offset_range = t5_sge_dbg_index_array[i][3]; + t4_read_indirect(padap, + sge_pio->ireg_addr, + sge_pio->ireg_data, + buff, + sge_pio->ireg_offset_range, + sge_pio->ireg_local_offset); + ch_sge_dbg++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_pcie; + int i, rc, n; + u32 size; + + n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_pcie = (struct ireg_buf *)temp_buff.data; + /* PCIE_PDBG */ + for (i = 0; i < n; i++) { + struct ireg_field *pcie_pio = &ch_pcie->tp_pio; + u32 *buff = ch_pcie->outbuf; + + pcie_pio->ireg_addr = t5_pcie_pdbg_array[i][0]; + pcie_pio->ireg_data = t5_pcie_pdbg_array[i][1]; + pcie_pio->ireg_local_offset = t5_pcie_pdbg_array[i][2]; + pcie_pio->ireg_offset_range = t5_pcie_pdbg_array[i][3]; + t4_read_indirect(padap, + pcie_pio->ireg_addr, + pcie_pio->ireg_data, + buff, + pcie_pio->ireg_offset_range, + pcie_pio->ireg_local_offset); + ch_pcie++; + } + + /* PCIE_CDBG */ + n = sizeof(t5_pcie_cdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *pcie_pio = &ch_pcie->tp_pio; + u32 *buff = ch_pcie->outbuf; + + pcie_pio->ireg_addr = t5_pcie_cdbg_array[i][0]; + pcie_pio->ireg_data = t5_pcie_cdbg_array[i][1]; + pcie_pio->ireg_local_offset = t5_pcie_cdbg_array[i][2]; + pcie_pio->ireg_offset_range = t5_pcie_cdbg_array[i][3]; + t4_read_indirect(padap, + pcie_pio->ireg_addr, + pcie_pio->ireg_data, + buff, + pcie_pio->ireg_offset_range, + pcie_pio->ireg_local_offset); + ch_pcie++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ch_pm; + int i, rc, n; + u32 size; + + n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ch_pm = (struct ireg_buf *)temp_buff.data; + /* PM_RX */ + for (i = 0; i < n; i++) { + struct ireg_field *pm_pio = &ch_pm->tp_pio; + u32 *buff = ch_pm->outbuf; + + pm_pio->ireg_addr = t5_pm_rx_array[i][0]; + pm_pio->ireg_data = t5_pm_rx_array[i][1]; + pm_pio->ireg_local_offset = t5_pm_rx_array[i][2]; + pm_pio->ireg_offset_range = t5_pm_rx_array[i][3]; + t4_read_indirect(padap, + pm_pio->ireg_addr, + pm_pio->ireg_data, + buff, + pm_pio->ireg_offset_range, + pm_pio->ireg_local_offset); + ch_pm++; + } + + /* PM_TX */ + n = sizeof(t5_pm_tx_array) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *pm_pio = &ch_pm->tp_pio; + u32 *buff = ch_pm->outbuf; + + pm_pio->ireg_addr = t5_pm_tx_array[i][0]; + pm_pio->ireg_data = t5_pm_tx_array[i][1]; + pm_pio->ireg_local_offset = t5_pm_tx_array[i][2]; + pm_pio->ireg_offset_range = t5_pm_tx_array[i][3]; + t4_read_indirect(padap, + pm_pio->ireg_addr, + pm_pio->ireg_data, + buff, + pm_pio->ireg_offset_range, + pm_pio->ireg_local_offset); + ch_pm++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *ma_indr; + int i, rc, n; + u32 size, j; + + if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6) + return CUDBG_STATUS_ENTITY_NOT_FOUND; + + n = sizeof(t6_ma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n * 2; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + ma_indr = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *ma_fli = &ma_indr->tp_pio; + u32 *buff = ma_indr->outbuf; + + ma_fli->ireg_addr = t6_ma_ireg_array[i][0]; + ma_fli->ireg_data = t6_ma_ireg_array[i][1]; + ma_fli->ireg_local_offset = t6_ma_ireg_array[i][2]; + ma_fli->ireg_offset_range = t6_ma_ireg_array[i][3]; + t4_read_indirect(padap, ma_fli->ireg_addr, ma_fli->ireg_data, + buff, ma_fli->ireg_offset_range, + ma_fli->ireg_local_offset); + ma_indr++; + } + + n = sizeof(t6_ma_ireg_array2) / (IREG_NUM_ELEM * sizeof(u32)); + for (i = 0; i < n; i++) { + struct ireg_field *ma_fli = &ma_indr->tp_pio; + u32 *buff = ma_indr->outbuf; + + ma_fli->ireg_addr = t6_ma_ireg_array2[i][0]; + ma_fli->ireg_data = t6_ma_ireg_array2[i][1]; + ma_fli->ireg_local_offset = t6_ma_ireg_array2[i][2]; + for (j = 0; j < t6_ma_ireg_array2[i][3]; j++) { + t4_read_indirect(padap, ma_fli->ireg_addr, + ma_fli->ireg_data, buff, 1, + ma_fli->ireg_local_offset); + buff++; + ma_fli->ireg_local_offset += 0x20; + } + ma_indr++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *up_cim; + int i, rc, n; + u32 size; + + n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + up_cim = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *up_cim_reg = &up_cim->tp_pio; + u32 *buff = up_cim->outbuf; + + if (is_t5(padap->params.chip)) { + up_cim_reg->ireg_addr = t5_up_cim_reg_array[i][0]; + up_cim_reg->ireg_data = t5_up_cim_reg_array[i][1]; + up_cim_reg->ireg_local_offset = + t5_up_cim_reg_array[i][2]; + up_cim_reg->ireg_offset_range = + t5_up_cim_reg_array[i][3]; + } else if (is_t6(padap->params.chip)) { + up_cim_reg->ireg_addr = t6_up_cim_reg_array[i][0]; + up_cim_reg->ireg_data = t6_up_cim_reg_array[i][1]; + up_cim_reg->ireg_local_offset = + t6_up_cim_reg_array[i][2]; + up_cim_reg->ireg_offset_range = + t6_up_cim_reg_array[i][3]; + } + + rc = t4_cim_read(padap, up_cim_reg->ireg_local_offset, + up_cim_reg->ireg_offset_range, buff); + if (rc) { + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + up_cim++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err) @@ -411,3 +663,40 @@ int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, cudbg_write_and_release_buff(&temp_buff, dbg_buff); return rc; } + +int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct ireg_buf *hma_indr; + int i, rc, n; + u32 size; + + if (CHELSIO_CHIP_VERSION(padap->params.chip) < CHELSIO_T6) + return CUDBG_STATUS_ENTITY_NOT_FOUND; + + n = sizeof(t6_hma_ireg_array) / (IREG_NUM_ELEM * sizeof(u32)); + size = sizeof(struct ireg_buf) * n; + rc = cudbg_get_buff(dbg_buff, size, &temp_buff); + if (rc) + return rc; + + hma_indr = (struct ireg_buf *)temp_buff.data; + for (i = 0; i < n; i++) { + struct ireg_field *hma_fli = &hma_indr->tp_pio; + u32 *buff = hma_indr->outbuf; + + hma_fli->ireg_addr = t6_hma_ireg_array[i][0]; + hma_fli->ireg_data = t6_hma_ireg_array[i][1]; + hma_fli->ireg_local_offset = t6_hma_ireg_array[i][2]; + hma_fli->ireg_offset_range = t6_hma_ireg_array[i][3]; + t4_read_indirect(padap, hma_fli->ireg_addr, hma_fli->ireg_data, + buff, hma_fli->ireg_offset_range, + hma_fli->ireg_local_offset); + hma_indr++; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index 7a927ec71a5f9..4838d823750fc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -33,9 +33,27 @@ int cudbg_collect_edc1_meminfo(struct cudbg_init *pdbg_init, int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_pm_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_ma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_up_cim_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); int cudbg_collect_mbox_log(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 7dfee6adc51e4..1f6d800dd1bec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -30,6 +30,12 @@ static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, { CUDBG_TP_INDIRECT, cudbg_collect_tp_indirect }, + { CUDBG_SGE_INDIRECT, cudbg_collect_sge_indirect }, + { CUDBG_PCIE_INDIRECT, cudbg_collect_pcie_indirect }, + { CUDBG_PM_INDIRECT, cudbg_collect_pm_indirect }, + { CUDBG_MA_INDIRECT, cudbg_collect_ma_indirect }, + { CUDBG_UP_CIM_INDIRECT, cudbg_collect_up_cim_indirect }, + { CUDBG_HMA_INDIRECT, cudbg_collect_hma_indirect }, }; static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) @@ -87,9 +93,38 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) n = n / (IREG_NUM_ELEM * sizeof(u32)); len = sizeof(struct ireg_buf) * n; break; + case CUDBG_SGE_INDIRECT: + len = sizeof(struct ireg_buf) * 2; + break; + case CUDBG_PCIE_INDIRECT: + n = sizeof(t5_pcie_pdbg_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + break; + case CUDBG_PM_INDIRECT: + n = sizeof(t5_pm_rx_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + break; + case CUDBG_MA_INDIRECT: + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + n = sizeof(t6_ma_ireg_array) / + (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n * 2; + } + break; + case CUDBG_UP_CIM_INDIRECT: + n = sizeof(t5_up_cim_reg_array) / (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + break; case CUDBG_MBOX_LOG: len = sizeof(struct cudbg_mbox_log) * adap->mbox_log->size; break; + case CUDBG_HMA_INDIRECT: + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + n = sizeof(t6_hma_ireg_array) / + (IREG_NUM_ELEM * sizeof(u32)); + len = sizeof(struct ireg_buf) * n; + } + break; default: break; } -- GitLab From 7c075ce221cf10a7aaef96b002d1d4c5dc715822 Mon Sep 17 00:00:00 2001 From: Rahul Lakkireddy Date: Fri, 13 Oct 2017 18:48:20 +0530 Subject: [PATCH 1381/1507] cxgb4: collect IBQ and OBQ dumps Signed-off-by: Rahul Lakkireddy Signed-off-by: Ganesh Goudar Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h | 14 ++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.c | 165 ++++++++++++++++++ .../net/ethernet/chelsio/cxgb4/cudbg_lib.h | 42 +++++ .../net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c | 32 ++++ 4 files changed, 253 insertions(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 01d282081b2db..9b8005e678118 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -29,10 +29,24 @@ enum cudbg_dbg_entity_type { CUDBG_REG_DUMP = 1, CUDBG_DEV_LOG = 2, + CUDBG_CIM_IBQ_TP0 = 6, + CUDBG_CIM_IBQ_TP1 = 7, + CUDBG_CIM_IBQ_ULP = 8, + CUDBG_CIM_IBQ_SGE0 = 9, + CUDBG_CIM_IBQ_SGE1 = 10, + CUDBG_CIM_IBQ_NCSI = 11, + CUDBG_CIM_OBQ_ULP0 = 12, + CUDBG_CIM_OBQ_ULP1 = 13, + CUDBG_CIM_OBQ_ULP2 = 14, + CUDBG_CIM_OBQ_ULP3 = 15, + CUDBG_CIM_OBQ_SGE = 16, + CUDBG_CIM_OBQ_NCSI = 17, CUDBG_EDC0 = 18, CUDBG_EDC1 = 19, CUDBG_TP_INDIRECT = 36, CUDBG_SGE_INDIRECT = 37, + CUDBG_CIM_OBQ_RXQ0 = 47, + CUDBG_CIM_OBQ_RXQ1 = 48, CUDBG_PCIE_INDIRECT = 50, CUDBG_PM_INDIRECT = 51, CUDBG_MA_INDIRECT = 61, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 0149f1ca9f51d..c451b2e42a6c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -129,6 +129,171 @@ int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, return rc; } +static int cudbg_read_cim_ibq(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, int qid) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int no_of_read_words, rc = 0; + u32 qsize; + + /* collect CIM IBQ */ + qsize = CIM_IBQ_SIZE * 4 * sizeof(u32); + rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff); + if (rc) + return rc; + + /* t4_read_cim_ibq will return no. of read words or error */ + no_of_read_words = t4_read_cim_ibq(padap, qid, + (u32 *)((u32 *)temp_buff.data + + temp_buff.offset), qsize); + /* no_of_read_words is less than or equal to 0 means error */ + if (no_of_read_words <= 0) { + if (!no_of_read_words) + rc = CUDBG_SYSTEM_ERROR; + else + rc = no_of_read_words; + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 0); +} + +int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 1); +} + +int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 2); +} + +int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 3); +} + +int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 4); +} + +int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_ibq(pdbg_init, dbg_buff, cudbg_err, 5); +} + +static int cudbg_read_cim_obq(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err, int qid) +{ + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + int no_of_read_words, rc = 0; + u32 qsize; + + /* collect CIM OBQ */ + qsize = 6 * CIM_OBQ_SIZE * 4 * sizeof(u32); + rc = cudbg_get_buff(dbg_buff, qsize, &temp_buff); + if (rc) + return rc; + + /* t4_read_cim_obq will return no. of read words or error */ + no_of_read_words = t4_read_cim_obq(padap, qid, + (u32 *)((u32 *)temp_buff.data + + temp_buff.offset), qsize); + /* no_of_read_words is less than or equal to 0 means error */ + if (no_of_read_words <= 0) { + if (!no_of_read_words) + rc = CUDBG_SYSTEM_ERROR; + else + rc = no_of_read_words; + cudbg_err->sys_err = rc; + cudbg_put_buff(&temp_buff, dbg_buff); + return rc; + } + temp_buff.size = no_of_read_words * 4; + cudbg_write_and_release_buff(&temp_buff, dbg_buff); + return rc; +} + +int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 0); +} + +int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 1); +} + +int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 2); +} + +int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 3); +} + +int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 4); +} + +int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 5); +} + +int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 6); +} + +int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + return cudbg_read_cim_obq(pdbg_init, dbg_buff, cudbg_err, 7); +} + static int cudbg_read_fw_mem(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, u8 mem_type, unsigned long tot_len, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index 4838d823750fc..c4440c1d01422 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -24,6 +24,42 @@ int cudbg_collect_reg_dump(struct cudbg_init *pdbg_init, int cudbg_collect_fw_devlog(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_tp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_tp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_ulp(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_sge0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_sge1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_ibq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp2(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ulp3(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_sge(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_cim_obq_ncsi(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); int cudbg_collect_edc0_meminfo(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); @@ -36,6 +72,12 @@ int cudbg_collect_tp_indirect(struct cudbg_init *pdbg_init, int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_obq_sge_rx_q0(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); +int cudbg_collect_obq_sge_rx_q1(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); int cudbg_collect_pcie_indirect(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 1f6d800dd1bec..9d97080a9d17c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -29,8 +29,22 @@ static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { { CUDBG_MBOX_LOG, cudbg_collect_mbox_log }, { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, + { CUDBG_CIM_IBQ_TP0, cudbg_collect_cim_ibq_tp0 }, + { CUDBG_CIM_IBQ_TP1, cudbg_collect_cim_ibq_tp1 }, + { CUDBG_CIM_IBQ_ULP, cudbg_collect_cim_ibq_ulp }, + { CUDBG_CIM_IBQ_SGE0, cudbg_collect_cim_ibq_sge0 }, + { CUDBG_CIM_IBQ_SGE1, cudbg_collect_cim_ibq_sge1 }, + { CUDBG_CIM_IBQ_NCSI, cudbg_collect_cim_ibq_ncsi }, + { CUDBG_CIM_OBQ_ULP0, cudbg_collect_cim_obq_ulp0 }, + { CUDBG_CIM_OBQ_ULP1, cudbg_collect_cim_obq_ulp1 }, + { CUDBG_CIM_OBQ_ULP2, cudbg_collect_cim_obq_ulp2 }, + { CUDBG_CIM_OBQ_ULP3, cudbg_collect_cim_obq_ulp3 }, + { CUDBG_CIM_OBQ_SGE, cudbg_collect_cim_obq_sge }, + { CUDBG_CIM_OBQ_NCSI, cudbg_collect_cim_obq_ncsi }, { CUDBG_TP_INDIRECT, cudbg_collect_tp_indirect }, { CUDBG_SGE_INDIRECT, cudbg_collect_sge_indirect }, + { CUDBG_CIM_OBQ_RXQ0, cudbg_collect_obq_sge_rx_q0 }, + { CUDBG_CIM_OBQ_RXQ1, cudbg_collect_obq_sge_rx_q1 }, { CUDBG_PCIE_INDIRECT, cudbg_collect_pcie_indirect }, { CUDBG_PM_INDIRECT, cudbg_collect_pm_indirect }, { CUDBG_MA_INDIRECT, cudbg_collect_ma_indirect }, @@ -59,6 +73,24 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) case CUDBG_DEV_LOG: len = adap->params.devlog.size; break; + case CUDBG_CIM_IBQ_TP0: + case CUDBG_CIM_IBQ_TP1: + case CUDBG_CIM_IBQ_ULP: + case CUDBG_CIM_IBQ_SGE0: + case CUDBG_CIM_IBQ_SGE1: + case CUDBG_CIM_IBQ_NCSI: + len = CIM_IBQ_SIZE * 4 * sizeof(u32); + break; + case CUDBG_CIM_OBQ_ULP0: + case CUDBG_CIM_OBQ_ULP1: + case CUDBG_CIM_OBQ_ULP2: + case CUDBG_CIM_OBQ_ULP3: + case CUDBG_CIM_OBQ_SGE: + case CUDBG_CIM_OBQ_NCSI: + case CUDBG_CIM_OBQ_RXQ0: + case CUDBG_CIM_OBQ_RXQ1: + len = 6 * CIM_OBQ_SIZE * 4 * sizeof(u32); + break; case CUDBG_EDC0: value = t4_read_reg(adap, MA_TARGET_MEM_ENABLE_A); if (value & EDRAM0_ENABLE_F) { -- GitLab From 5dc874252faa818426480a7c00fa05738fe05402 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 13 Oct 2017 17:29:00 +0100 Subject: [PATCH 1382/1507] cxgb4: fix missing break in switch and indent return statements The break statement for the Macronix case is missing and will fall through to the Winbond case and re-assign the size setting. Fix this by adding the missing break statement. Also correctly indent the return statements. Detected by CoverityScan, CID#1458020 ("Missing break in switch") Fixes: 96ac18f14a5a ("cxgb4: Add support for new flash parts") Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 8fa40f9e75c43..006414758f659 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -8404,7 +8404,7 @@ static int t4_get_flash_params(struct adapter *adap) default: dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n", flashid, density); - return -EINVAL; + return -EINVAL; } break; } @@ -8423,8 +8423,9 @@ static int t4_get_flash_params(struct adapter *adap) default: dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n", flashid, density); - return -EINVAL; + return -EINVAL; } + break; } case 0xef: { /* Winbond */ /* This Density -> Size decoding table is taken from Winbond @@ -8441,7 +8442,7 @@ static int t4_get_flash_params(struct adapter *adap) default: dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n", flashid, density); - return -EINVAL; + return -EINVAL; } break; } -- GitLab From 47371300dfc269dd8d150e5b872bdbbda98ba809 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 13 Oct 2017 12:28:03 -0700 Subject: [PATCH 1383/1507] hv_netvsc: Rename ind_table to rx_table Rename this variable because it is the Receive indirection table. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 2 +- drivers/net/hyperv/netvsc_drv.c | 4 ++-- drivers/net/hyperv/rndis_filter.c | 6 +++--- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index a81335e8ebe89..65ceb3aec40ed 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -179,7 +179,7 @@ struct rndis_device { u8 hw_mac_adr[ETH_ALEN]; u8 rss_key[NETVSC_HASH_KEYLEN]; - u16 ind_table[ITAB_NUM]; + u16 rx_table[ITAB_NUM]; }; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 44746de3dd4ca..8fa964e733ad5 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1434,7 +1434,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, rndis_dev = ndev->extension; if (indir) { for (i = 0; i < ITAB_NUM; i++) - indir[i] = rndis_dev->ind_table[i]; + indir[i] = rndis_dev->rx_table[i]; } if (key) @@ -1464,7 +1464,7 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, return -EINVAL; for (i = 0; i < ITAB_NUM; i++) - rndis_dev->ind_table[i] = indir[i]; + rndis_dev->rx_table[i] = indir[i]; } if (!key) { diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 065b204d8e17f..addf9f69c58c4 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -759,7 +759,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev, /* Set indirection table entries */ itab = (u32 *)(rssp + 1); for (i = 0; i < ITAB_NUM; i++) - itab[i] = rdev->ind_table[i]; + itab[i] = rdev->rx_table[i]; /* Set hask key values */ keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset); @@ -1284,8 +1284,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, net_device->num_chn = min(net_device->max_chn, device_info->num_chn); for (i = 0; i < ITAB_NUM; i++) - rndis_device->ind_table[i] = ethtool_rxfh_indir_default(i, - net_device->num_chn); + rndis_device->rx_table[i] = ethtool_rxfh_indir_default( + i, net_device->num_chn); atomic_set(&net_device->open_chn, 1); vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open); -- GitLab From 39e91cfbf6f5fb26ba64cc2e8874372baf1671e7 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 13 Oct 2017 12:28:04 -0700 Subject: [PATCH 1384/1507] hv_netvsc: Rename tx_send_table to tx_table Simplify the variable name: tx_send_table Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/hyperv_net.h | 2 +- drivers/net/hyperv/netvsc.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 65ceb3aec40ed..4958bb6b73767 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -731,7 +731,7 @@ struct net_device_context { u32 tx_checksum_mask; - u32 tx_send_table[VRSS_SEND_TAB_SIZE]; + u32 tx_table[VRSS_SEND_TAB_SIZE]; /* Ethtool settings */ u8 duplex; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 6e5194916bbee..d34cf37e949d2 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1110,7 +1110,7 @@ static void netvsc_send_table(struct hv_device *hdev, nvmsg->msg.v5_msg.send_table.offset); for (i = 0; i < count; i++) - net_device_ctx->tx_send_table[i] = tab[i]; + net_device_ctx->tx_table[i] = tab[i]; } static void netvsc_send_vf(struct net_device_context *net_device_ctx, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 8fa964e733ad5..da216ca4f2b23 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -252,8 +252,8 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev, struct sock *sk = skb->sk; int q_idx; - q_idx = ndc->tx_send_table[netvsc_get_hash(skb, ndc) & - (VRSS_SEND_TAB_SIZE - 1)]; + q_idx = ndc->tx_table[netvsc_get_hash(skb, ndc) & + (VRSS_SEND_TAB_SIZE - 1)]; /* If queue index changed record the new value */ if (q_idx != old_idx && -- GitLab From 6b0cbe315868d613123cf387052ccda5f09d49ea Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Fri, 13 Oct 2017 12:28:05 -0700 Subject: [PATCH 1385/1507] hv_netvsc: Add initialization of tx_table in netvsc_device_add() tx_table is part of the private data of kernel net_device. It is only zero-ed out when allocating net_device. We may recreate netvsc_device w/o recreating net_device, so the private netdev data, including tx_table, are not zeroed. It may contain channel numbers for the older netvsc_device. This patch adds initialization of tx_table each time we recreate netvsc_device. Signed-off-by: Haiyang Zhang Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d34cf37e949d2..5bb6a20072dd7 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1255,6 +1255,9 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, if (!net_device) return ERR_PTR(-ENOMEM); + for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) + net_device_ctx->tx_table[i] = 0; + net_device->ring_size = ring_size; /* Because the device uses NAPI, all the interrupt batching and -- GitLab From 657875944726af8f881df7d431afbbe8f50ad4d7 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 13 Oct 2017 12:58:13 -0700 Subject: [PATCH 1386/1507] net_sched: fix a compile warning in act_ife MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apparently ife_meta_id2name() is only called when CONFIG_MODULES is defined. This fixes: net/sched/act_ife.c:251:20: warning: ‘ife_meta_id2name’ defined but not used [-Wunused-function] static const char *ife_meta_id2name(u32 metaid) ^~~~~~~~~~~~~~~~ Fixes: d3f24ba895f0 ("net sched actions: fix module auto-loading") Cc: Roman Mashak Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/act_ife.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 252ee7d8c731d..3007cb1310ea9 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -248,6 +248,7 @@ static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) return ret; } +#ifdef CONFIG_MODULES static const char *ife_meta_id2name(u32 metaid) { switch (metaid) { @@ -261,6 +262,7 @@ static const char *ife_meta_id2name(u32 metaid) return "unknown"; } } +#endif /* called when adding new meta information * under ife->tcf_lock for existing action -- GitLab From e086101b150ae8e99e54ab26101ef3835fa9f48d Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 13 Oct 2017 13:03:16 -0700 Subject: [PATCH 1387/1507] tcp: add a tracepoint for tcp retransmission We need a real-time notification for tcp retransmission for monitoring. Of course we could use ftrace to dynamically instrument this kernel function too, however we can't retrieve the connection information at the same time, for example perf-tools [1] reads /proc/net/tcp for socket details, which is slow when we have a lots of connections. Therefore, this patch adds a tracepoint for __tcp_retransmit_skb() and exposes src/dst IP addresses and ports of the connection. This also makes it easier to integrate into perf. Note, I expose both IPv4 and IPv6 addresses at the same time: for a IPv4 socket, v4 mapped address is used as IPv6 addresses, for a IPv6 socket, LOOPBACK4_IPV6 is already filled by kernel. Also, add sk and skb pointers as they are useful for BPF. 1. https://github.com/brendangregg/perf-tools/blob/master/net/tcpretrans Cc: Eric Dumazet Cc: Alexei Starovoitov Cc: Hannes Frederic Sowa Cc: Brendan Gregg Cc: Neal Cardwell Signed-off-by: Cong Wang Acked-by: Alexei Starovoitov Acked-by: Brendan Gregg Signed-off-by: David S. Miller --- include/trace/events/tcp.h | 68 ++++++++++++++++++++++++++++++++++++++ net/core/net-traces.c | 1 + net/ipv4/tcp_output.c | 3 ++ 3 files changed, 72 insertions(+) create mode 100644 include/trace/events/tcp.h diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h new file mode 100644 index 0000000000000..3d1cbd072b7e5 --- /dev/null +++ b/include/trace/events/tcp.h @@ -0,0 +1,68 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tcp + +#if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TCP_H + +#include +#include +#include +#include + +TRACE_EVENT(tcp_retransmit_skb, + + TP_PROTO(struct sock *sk, struct sk_buff *skb), + + TP_ARGS(sk, skb), + + TP_STRUCT__entry( + __field(void *, skbaddr) + __field(void *, skaddr) + __field(__u16, sport) + __field(__u16, dport) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __array(__u8, saddr_v6, 16) + __array(__u8, daddr_v6, 16) + ), + + TP_fast_assign( + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct in6_addr *pin6; + __be32 *p32; + + __entry->skbaddr = skb; + __entry->skaddr = sk; + + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + + p32 = (__be32 *) __entry->saddr; + *p32 = inet->inet_saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = inet->inet_daddr; + + if (np) { + pin6 = (struct in6_addr *)__entry->saddr_v6; + *pin6 = np->saddr; + pin6 = (struct in6_addr *)__entry->daddr_v6; + *pin6 = *(np->daddr_cache); + } else { + pin6 = (struct in6_addr *)__entry->saddr_v6; + ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); + pin6 = (struct in6_addr *)__entry->daddr_v6; + ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); + } + ), + + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6 daddrv6=%pI6", + __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6) +); + +#endif /* _TRACE_TCP_H */ + +/* This part must be outside protection */ +#include diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 1132820c8e62c..f4e4fa2db5057 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 696b0a168f160..6c74f2a397787 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -42,6 +42,8 @@ #include #include +#include + /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; @@ -2875,6 +2877,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); } -- GitLab From dd6b9c2c332b40f142740d1b11fb77c653ff98ea Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 Oct 2017 13:40:24 -0700 Subject: [PATCH 1388/1507] macvlan: Only deliver one copy of the frame to the macvlan interface This patch intoduces a slight adjustment for macvlan to address the fact that in source mode I was seeing two copies of any packet addressed to the macvlan interface being delivered where there should have been only one. The issue appears to be that one copy was delivered based on the source MAC address and then the second copy was being delivered based on the destination MAC address. To fix it I am just treating a unicast address match as though it is not a match since source based macvlan isn't supposed to be matching based on the destination MAC anyway. Fixes: 79cf79abce71 ("macvlan: add source mode") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 858bd66511a27..a4ae8cd0f6606 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -480,7 +480,7 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); - if (vlan == NULL) + if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; -- GitLab From c8c41ea1bd707eb032e248c55d640f32c950ed19 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 Oct 2017 13:40:31 -0700 Subject: [PATCH 1389/1507] macvlan: Only update pkt_type if destination MAC address matches This patch updates the pkt_type to PACKET_HOST only if the destination MAC address matches on the on the source based macvlan. It didn't make sense to be updating broadcast, multicast, and non-local destined frames with PACKET_HOST. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index a4ae8cd0f6606..1e1df54c5d317 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -413,7 +413,9 @@ static void macvlan_forward_source_one(struct sk_buff *skb, len = nskb->len + ETH_HLEN; nskb->dev = dev; - nskb->pkt_type = PACKET_HOST; + + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) + nskb->pkt_type = PACKET_HOST; ret = netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); -- GitLab From ae3c33c157565301544570ff3476280279d43d7f Mon Sep 17 00:00:00 2001 From: Lucas Bates Date: Fri, 13 Oct 2017 17:51:22 -0400 Subject: [PATCH 1390/1507] tc-testing: Add test cases for flushing actions Tests for flushing gact and mirred were missing. This patch adds test cases to explicitly test the flush of any installed gact/mirred actions. Signed-off-by: Lucas Bates Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/tests.json | 49 ++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json index 6973bdc5b5bf0..2ea00652f9ab2 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json @@ -245,6 +245,27 @@ "$TC actions flush action gact" ] }, + { + "id": "3edf", + "name": "Flush gact actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions flush action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "0", + "teardown": [] + }, { "id": "63ec", "name": "Delete pass action", @@ -468,6 +489,32 @@ "$TC actions flush action mirred" ] }, + { + "id": "58c3", + "name": "Flush mirred actions", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 1 dev lo", + "$TC actions add action mirred egress redirect index 2 dev lo" + ], + "cmdUnderTest": "$TC actions show action mirred", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "[Mirror|Redirect] to device lo", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, { "id": "d7c0", "name": "Add invalid mirred direction", @@ -1162,4 +1209,4 @@ "$TC actions flush action ife" ] } -] \ No newline at end of file +] -- GitLab From 0923edf456fbd6c75031ad48ad14897a6b912954 Mon Sep 17 00:00:00 2001 From: Lucas Bates Date: Fri, 13 Oct 2017 17:51:23 -0400 Subject: [PATCH 1391/1507] tc-testing: Split test case files into smaller chunks The original submission had the test cases stored in one monolithic file. This can be unwieldy to edit, especially as more test cases are added. This patch removes the original tests.json file in favour of individual ones broken down by category. Signed-off-by: Lucas Bates Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/gact.json | 469 +++++++ .../tc-testing/tc-tests/actions/ife.json | 52 + .../tc-testing/tc-tests/actions/mirred.json | 223 +++ .../tc-testing/tc-tests/actions/simple.json | 130 ++ .../tc-testing/tc-tests/actions/skbedit.json | 320 +++++ .../tc-testing/tc-tests/actions/tests.json | 1212 ----------------- 6 files changed, 1194 insertions(+), 1212 deletions(-) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/gact.json create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/ife.json create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/simple.json create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json delete mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/tests.json diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json new file mode 100644 index 0000000000000..e2187b6e0b7ac --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json @@ -0,0 +1,469 @@ +[ + { + "id": "e89a", + "name": "Add valid pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pass index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "a02c", + "name": "Add valid pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pipe index 6", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "feef", + "name": "Add valid reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action reclassify index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "8a7a", + "name": "Add valid drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 30", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9a52", + "name": "Add valid continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action continue index 432", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "d700", + "name": "Add invalid action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pump index 386", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action.*index 386 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "9215", + "name": "Add action with duplicate index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 15" + ], + "cmdUnderTest": "$TC actions add action drop index 15", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "798e", + "name": "Add action with index exceeding 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967296", + "expExitCode": "255", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "22be", + "name": "Add action with index at 32-bit maximum", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action drop index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "ac2a", + "name": "List actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions list action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "5", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "3edf", + "name": "Flush gact actions", + "category": [ + "actions", + "gact" + ], + "setup": [ + "$TC actions add action reclassify index 101", + "$TC actions add action reclassify index 102", + "$TC actions add action reclassify index 103", + "$TC actions add action reclassify index 104", + "$TC actions add action reclassify index 105" + ], + "cmdUnderTest": "$TC actions flush action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify", + "matchCount": "0", + "teardown": [] + }, + { + "id": "63ec", + "name": "Delete pass action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pass index 1" + ], + "cmdUnderTest": "$TC actions del action gact index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "46be", + "name": "Delete pipe action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pipe index 9" + ], + "cmdUnderTest": "$TC actions del action gact index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "2e08", + "name": "Delete reclassify action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 65536" + ], + "cmdUnderTest": "$TC actions del action gact index 65536", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "99c4", + "name": "Delete drop action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 16" + ], + "cmdUnderTest": "$TC actions del action gact index 16", + "expExitCode": "0", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "fb6b", + "name": "Delete continue action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action continue index 32" + ], + "cmdUnderTest": "$TC actions del action gact index 32", + "expExitCode": "0", + "verifyCmd": "actions list action gact", + "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "0eb3", + "name": "Delete non-existent action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions del action gact index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action", + "matchCount": "0", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "f02c", + "name": "Replace gact action", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 10", + "$TC actions add action drop index 12" + ], + "cmdUnderTest": "$TC actions replace action ok index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "action order [0-9]*: gact action pass", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + }, + { + "id": "525f", + "name": "Get gact action by index", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action drop index 3900800700" + ], + "cmdUnderTest": "$TC actions get action gact index 3900800700", + "expExitCode": "0", + "verifyCmd": "$TC actions get action gact index 3900800700", + "matchPattern": "index 3900800700", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json new file mode 100644 index 0000000000000..9f34f0753969f --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -0,0 +1,52 @@ +[ + { + "id": "a568", + "name": "Add action with ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode type 0xDEAD index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xDEAD", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b983", + "name": "Add action without ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xED3E", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json new file mode 100644 index 0000000000000..0fcccf18399b6 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -0,0 +1,223 @@ +[ + { + "id": "5124", + "name": "Add mirred mirror to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "6fb4", + "name": "Add mirred redirect to egress action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "ba38", + "name": "Get mirred actions", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 1 dev lo", + "$TC actions add action mirred egress redirect index 2 dev lo" + ], + "cmdUnderTest": "$TC actions show action mirred", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "[Mirror|Redirect] to device lo", + "matchCount": "2", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "d7c0", + "name": "Add invalid mirred direction", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "e213", + "name": "Add invalid mirred action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "2d89", + "name": "Add mirred action with invalid device", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "300b", + "name": "Add mirred action with duplicate index", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 15 dev lo" + ], + "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "a70e", + "name": "Delete mirred mirror action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress mirror index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + }, + { + "id": "3fb3", + "name": "Delete mirred redirect action", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred egress redirect index 5 dev lo" + ], + "cmdUnderTest": "$TC actions del action mirred index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions list action mirred", + "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action mirred" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json new file mode 100644 index 0000000000000..e89a7aa4012d1 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json @@ -0,0 +1,130 @@ +[ + { + "id": "b078", + "name": "Add simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple .*index 60 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "6d4c", + "name": "Add simple action with duplicate index", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Aruba\" index 4" + ], + "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple .*ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "2542", + "name": "List simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Rock\"", + "$TC actions add action simple sdata \"Paper\"", + "$TC actions add action simple sdata \"Scissors\" index 98" + ], + "cmdUnderTest": "$TC actions list action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "3", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "ea67", + "name": "Delete simple action", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Blinkenlights\" index 1" + ], + "cmdUnderTest": "$TC actions delete action simple index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple .*index 1 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action simple" + ] + }, + { + "id": "8ff1", + "name": "Flush simple actions", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"Kirk\"", + "$TC actions add action simple sdata \"Spock\" index 50", + "$TC actions add action simple sdata \"McCoy\" index 9" + ], + "cmdUnderTest": "$TC actions flush action simple", + "expExitCode": "0", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", + "matchCount": "0", + "teardown": [ + "" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json new file mode 100644 index 0000000000000..99635ea4722e6 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -0,0 +1,320 @@ +[ + { + "id": "6236", + "name": "Add skbedit action with valid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 1", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "407b", + "name": "Add skbedit action with invalid mark", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 666777888999", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "081d", + "name": "Add skbedit action with priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio 99", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority :99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "cc37", + "name": "Add skbedit action with invalid priority", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit prio foo", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit priority", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "3c95", + "name": "Add skbedit action with queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping 909", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "985c", + "name": "Add skbedit action with invalid queue_mapping", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit queue_mapping", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "224f", + "name": "Add skbedit action with ptype host", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype host", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype host", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d1a3", + "name": "Add skbedit action with ptype otherhost", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype otherhost", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype otherhost", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "b9c6", + "name": "Add skbedit action with invalid ptype", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit ptype openair", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype openair", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "5172", + "name": "List skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit ptype otherhost", + "$TC actions add action skbedit ptype broadcast", + "$TC actions add action skbedit mark 59", + "$TC actions add action skbedit mark 409" + ], + "cmdUnderTest": "$TC actions list action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "4", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "a6d6", + "name": "Add skbedit action with index", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "index 4040404040", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "38f3", + "name": "Delete skbedit action", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit mark 42 index 9009" + ], + "cmdUnderTest": "$TC actions del action skbedit index 9009", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit mark 42", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "ce97", + "name": "Flush skbedit actions", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + "$TC actions add action skbedit mark 500", + "$TC actions add action skbedit mark 501", + "$TC actions add action skbedit mark 502", + "$TC actions add action skbedit mark 503", + "$TC actions add action skbedit mark 504", + "$TC actions add action skbedit mark 505", + "$TC actions add action skbedit mark 506" + ], + "cmdUnderTest": "$TC actions flush action skbedit", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbedit" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json deleted file mode 100644 index 2ea00652f9ab2..0000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json +++ /dev/null @@ -1,1212 +0,0 @@ -[ - { - "id": "e89a", - "name": "Add valid pass action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pass index 8", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pass.*index 8 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "a02c", - "name": "Add valid pipe action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pipe index 6", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pipe.*index 6 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "feef", - "name": "Add valid reclassify action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action reclassify index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify.*index 5 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "8a7a", - "name": "Add valid drop action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 30", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 30 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "9a52", - "name": "Add valid continue action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action continue index 432", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action continue.*index 432 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "d700", - "name": "Add invalid action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action pump index 386", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action.*index 386 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "9215", - "name": "Add action with duplicate index", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pipe index 15" - ], - "cmdUnderTest": "$TC actions add action drop index 15", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 15 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "798e", - "name": "Add action with index exceeding 32-bit maximum", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 4294967296", - "expExitCode": "255", - "verifyCmd": "actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 4294967296 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "22be", - "name": "Add action with index at 32-bit maximum", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action drop index 4294967295", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 4294967295 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "ac2a", - "name": "List actions", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action reclassify index 101", - "$TC actions add action reclassify index 102", - "$TC actions add action reclassify index 103", - "$TC actions add action reclassify index 104", - "$TC actions add action reclassify index 105" - ], - "cmdUnderTest": "$TC actions list action gact", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify", - "matchCount": "5", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "3edf", - "name": "Flush gact actions", - "category": [ - "actions", - "gact" - ], - "setup": [ - "$TC actions add action reclassify index 101", - "$TC actions add action reclassify index 102", - "$TC actions add action reclassify index 103", - "$TC actions add action reclassify index 104", - "$TC actions add action reclassify index 105" - ], - "cmdUnderTest": "$TC actions flush action gact", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify", - "matchCount": "0", - "teardown": [] - }, - { - "id": "63ec", - "name": "Delete pass action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pass index 1" - ], - "cmdUnderTest": "$TC actions del action gact index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pass.*index 1 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "46be", - "name": "Delete pipe action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action pipe index 9" - ], - "cmdUnderTest": "$TC actions del action gact index 9", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action pipe.*index 9 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "2e08", - "name": "Delete reclassify action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action reclassify index 65536" - ], - "cmdUnderTest": "$TC actions del action gact index 65536", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action reclassify.*index 65536 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "99c4", - "name": "Delete drop action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 16" - ], - "cmdUnderTest": "$TC actions del action gact index 16", - "expExitCode": "0", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action drop.*index 16 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "fb6b", - "name": "Delete continue action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action continue index 32" - ], - "cmdUnderTest": "$TC actions del action gact index 32", - "expExitCode": "0", - "verifyCmd": "actions list action gact", - "matchPattern": "action order [0-9]*: gact action continue.*index 32 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "0eb3", - "name": "Delete non-existent action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions del action gact index 2", - "expExitCode": "255", - "verifyCmd": "$TC actions list action gact", - "matchPattern": "action order [0-9]*: gact action", - "matchCount": "0", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "5124", - "name": "Add mirred mirror to egress action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 1 dev lo", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 1 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "6fb4", - "name": "Add mirred redirect to egress action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress redirect index 2 dev lo action pipe", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "ba38", - "name": "Get mirred actions", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress mirror index 1 dev lo", - "$TC actions add action mirred egress redirect index 2 dev lo" - ], - "cmdUnderTest": "$TC actions show action mirred", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "[Mirror|Redirect] to device lo", - "matchCount": "2", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "58c3", - "name": "Flush mirred actions", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress mirror index 1 dev lo", - "$TC actions add action mirred egress redirect index 2 dev lo" - ], - "cmdUnderTest": "$TC actions show action mirred", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "[Mirror|Redirect] to device lo", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "d7c0", - "name": "Add invalid mirred direction", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred inbound mirror index 20 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "e213", - "name": "Add invalid mirred action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress remirror index 20 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress.*to device lo\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "2d89", - "name": "Add mirred action with invalid device", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 20 dev eltoh", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device eltoh\\).*index 20 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "300b", - "name": "Add mirred action with duplicate index", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress redirect index 15 dev lo" - ], - "cmdUnderTest": "$TC actions add action mirred egress mirror index 15 dev lo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(.*to device lo\\).*index 15 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "a70e", - "name": "Delete mirred mirror action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress mirror index 5 dev lo" - ], - "cmdUnderTest": "$TC actions del action mirred index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Mirror to device lo\\).*index 5 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "3fb3", - "name": "Delete mirred redirect action", - "category": [ - "actions", - "mirred" - ], - "setup": [ - [ - "$TC actions flush action mirred", - 0, - 1, - 255 - ], - "$TC actions add action mirred egress redirect index 5 dev lo" - ], - "cmdUnderTest": "$TC actions del action mirred index 5", - "expExitCode": "0", - "verifyCmd": "$TC actions list action mirred", - "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 5 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action mirred" - ] - }, - { - "id": "b078", - "name": "Add simple action", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action simple sdata \"A triumph\" index 60", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple .*index 60 ref", - "matchCount": "1", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "6d4c", - "name": "Add simple action with duplicate index", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Aruba\" index 4" - ], - "cmdUnderTest": "$TC actions add action simple sdata \"Jamaica\" index 4", - "expExitCode": "255", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple .*ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "2542", - "name": "List simple actions", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Rock\"", - "$TC actions add action simple sdata \"Paper\"", - "$TC actions add action simple sdata \"Scissors\" index 98" - ], - "cmdUnderTest": "$TC actions list action simple", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", - "matchCount": "3", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "ea67", - "name": "Delete simple action", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Blinkenlights\" index 1" - ], - "cmdUnderTest": "$TC actions delete action simple index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple .*index 1 ref", - "matchCount": "0", - "teardown": [ - "$TC actions flush action simple" - ] - }, - { - "id": "8ff1", - "name": "Flush simple actions", - "category": [ - "actions", - "simple" - ], - "setup": [ - [ - "$TC actions flush action simple", - 0, - 1, - 255 - ], - "$TC actions add action simple sdata \"Kirk\"", - "$TC actions add action simple sdata \"Spock\" index 50", - "$TC actions add action simple sdata \"McCoy\" index 9" - ], - "cmdUnderTest": "$TC actions flush action simple", - "expExitCode": "0", - "verifyCmd": "$TC actions list action simple", - "matchPattern": "action order [0-9]*: Simple <[A-Z][a-z]*>", - "matchCount": "0", - "teardown": [ - "" - ] - }, - { - "id": "6236", - "name": "Add skbedit action with valid mark", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 1", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark 1", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "407b", - "name": "Add skbedit action with invalid mark", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 666777888999", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "081d", - "name": "Add skbedit action with priority", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit prio 99", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit priority :99", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "cc37", - "name": "Add skbedit action with invalid priority", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit prio foo", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit priority", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "3c95", - "name": "Add skbedit action with queue_mapping", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit queue_mapping 909", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "985c", - "name": "Add skbedit action with invalid queue_mapping", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit queue_mapping 67000", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit queue_mapping", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "224f", - "name": "Add skbedit action with ptype host", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype host", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype host", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "d1a3", - "name": "Add skbedit action with ptype otherhost", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype otherhost", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype otherhost", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "b9c6", - "name": "Add skbedit action with invalid ptype", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit ptype openair", - "expExitCode": "255", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit ptype openair", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "5172", - "name": "List skbedit actions", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ], - "$TC actions add action skbedit ptype otherhost", - "$TC actions add action skbedit ptype broadcast", - "$TC actions add action skbedit mark 59", - "$TC actions add action skbedit mark 409" - ], - "cmdUnderTest": "$TC actions list action skbedit", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit", - "matchCount": "4", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "a6d6", - "name": "Add skbedit action with index", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ] - ], - "cmdUnderTest": "$TC actions add action skbedit mark 808 index 4040404040", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "index 4040404040", - "matchCount": "1", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "38f3", - "name": "Delete skbedit action", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - [ - "$TC actions flush action skbedit", - 0, - 1, - 255 - ], - "$TC actions add action skbedit mark 42 index 9009" - ], - "cmdUnderTest": "$TC actions del action skbedit index 9009", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit mark 42", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "ce97", - "name": "Flush skbedit actions", - "category": [ - "actions", - "skbedit" - ], - "setup": [ - "$TC actions add action skbedit mark 500", - "$TC actions add action skbedit mark 501", - "$TC actions add action skbedit mark 502", - "$TC actions add action skbedit mark 503", - "$TC actions add action skbedit mark 504", - "$TC actions add action skbedit mark 505", - "$TC actions add action skbedit mark 506" - ], - "cmdUnderTest": "$TC actions flush action skbedit", - "expExitCode": "0", - "verifyCmd": "$TC actions list action skbedit", - "matchPattern": "action order [0-9]*: skbedit", - "matchCount": "0", - "teardown": [ - "$TC actions flush action skbedit" - ] - }, - { - "id": "f02c", - "name": "Replace gact action", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 10", - "$TC actions add action drop index 12" - ], - "cmdUnderTest": "$TC actions replace action ok index 12", - "expExitCode": "0", - "verifyCmd": "$TC actions ls action gact", - "matchPattern": "action order [0-9]*: gact action pass", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "525f", - "name": "Get gact action by index", - "category": [ - "actions", - "gact" - ], - "setup": [ - [ - "$TC actions flush action gact", - 0, - 1, - 255 - ], - "$TC actions add action drop index 3900800700" - ], - "cmdUnderTest": "$TC actions get action gact index 3900800700", - "expExitCode": "0", - "verifyCmd": "$TC actions get action gact index 3900800700", - "matchPattern": "index 3900800700", - "matchCount": "1", - "teardown": [ - "$TC actions flush action gact" - ] - }, - { - "id": "a568", - "name": "Add action with ife type", - "category": [ - "actions", - "ife" - ], - "setup": [ - [ - "$TC actions flush action ife", - 0, - 1, - 255 - ], - "$TC actions add action ife encode type 0xDEAD index 1" - ], - "cmdUnderTest": "$TC actions get action ife index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xDEAD", - "matchCount": "1", - "teardown": [ - "$TC actions flush action ife" - ] - }, - { - "id": "b983", - "name": "Add action without ife type", - "category": [ - "actions", - "ife" - ], - "setup": [ - [ - "$TC actions flush action ife", - 0, - 1, - 255 - ], - "$TC actions add action ife encode index 1" - ], - "cmdUnderTest": "$TC actions get action ife index 1", - "expExitCode": "0", - "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xED3E", - "matchCount": "1", - "teardown": [ - "$TC actions flush action ife" - ] - } -] -- GitLab From cf797ac49b94df7247cf86e801ab3882d08b786d Mon Sep 17 00:00:00 2001 From: Lucas Bates Date: Fri, 13 Oct 2017 17:51:24 -0400 Subject: [PATCH 1392/1507] tc-testing: Add test cases for police and skbmod Add basic unit tests for police and skbmod actions in tc. Signed-off-by: Lucas Bates Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- .../tc-testing/tc-tests/actions/police.json | 527 ++++++++++++++++++ .../tc-testing/tc-tests/actions/skbmod.json | 372 +++++++++++++ 2 files changed, 899 insertions(+) create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/police.json create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json new file mode 100644 index 0000000000000..0e602a3f93938 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -0,0 +1,527 @@ +[ + { + "id": "49aa", + "name": "Add valid basic police action", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 1kbit burst 10k index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 1Kbit burst 10Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "3abe", + "name": "Add police action with duplicate index", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 4Mbit burst 120k index 9" + ], + "cmdUnderTest": "$TC actions add action police rate 8kbit burst 24k index 9", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "49fa", + "name": "Add valid police action with mtu", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 1k index 98", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 98", + "matchPattern": "action order [0-9]*: police 0x62 rate 90Kbit burst 10Kb mtu 1Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "7943", + "name": "Add valid police action with peakrate", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 90kbit burst 10k mtu 2kb peakrate 100kbit index 3", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x3 rate 90Kbit burst 10Kb mtu 2Kb peakrate 100Kbit", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "055e", + "name": "Add police action with peakrate and no mtu", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 5kbit burst 6kb peakrate 10kbit index 9", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x9 rate 5Kb burst 10Kb", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "f057", + "name": "Add police action with valid overhead", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 1mbit burst 100k overhead 64 index 64", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 64", + "matchPattern": "action order [0-9]*: police 0x40 rate 1Mbit burst 100Kb mtu 2Kb action reclassify overhead 64b", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "7ffb", + "name": "Add police action with ethernet linklayer type", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer ethernet index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions show action police", + "matchPattern": "action order [0-9]*: police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "3dda", + "name": "Add police action with atm linklayer type", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 2mbit burst 200k linklayer atm index 8", + "expExitCode": "0", + "verifyCmd": "$TC actions show action police", + "matchPattern": "action order [0-9]*: police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "551b", + "name": "Add police actions with conform-exceed control continue/drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed continue/drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action continue/drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "0c70", + "name": "Add police actions with conform-exceed control pass/reclassify", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/reclassify index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x4 rate 3Mbit burst 250Kb mtu 2Kb action pass/reclassify", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "d946", + "name": "Add police actions with conform-exceed control pass/pipe", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed pass/pipe index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x5 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "336e", + "name": "Delete police action", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 5mbit burst 2m index 12" + ], + "cmdUnderTest": "$TC actions delete action police index 12", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0xc rate 5Mb burst 2Mb", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "77fa", + "name": "Get single police action from many actions", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions get action police index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 4", + "matchPattern": "action order [0-9]*: police 0x4 rate 4Mbit burst 400Kb", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "aa43", + "name": "Get single police action without specifying index", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1" + ], + "cmdUnderTest": "$TC actions get action police", + "expExitCode": "255", + "verifyCmd": "$TC actions get action police", + "matchPattern": "action order [0-9]*: police", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "858b", + "name": "List police actions", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions list action police", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x[1-8] rate [1-8]Mbit burst [1-8]00Kb", + "matchCount": "8", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "1c3a", + "name": "Flush police actions", + "category": [ + "actions", + "police" + ], + "setup": [ + "$TC actions add action police rate 1mbit burst 100k index 1", + "$TC actions add action police rate 2mbit burst 200k index 2", + "$TC actions add action police rate 3mbit burst 300k index 3", + "$TC actions add action police rate 4mbit burst 400k index 4", + "$TC actions add action police rate 5mbit burst 500k index 5", + "$TC actions add action police rate 6mbit burst 600k index 6", + "$TC actions add action police rate 7mbit burst 700k index 7", + "$TC actions add action police rate 8mbit burst 800k index 8" + ], + "cmdUnderTest": "$TC actions flush action police", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police", + "matchCount": "0", + "teardown": [ + "" + ] + }, + { + "id": "7326", + "name": "Add police action with control continue", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "34fa", + "name": "Add police action with control drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "8dd5", + "name": "Add police action with control ok", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "b9d1", + "name": "Add police action with control reclassify", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "c534", + "name": "Add police action with control pipe", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json new file mode 100644 index 0000000000000..e34075059c26c --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -0,0 +1,372 @@ +[ + { + "id": "7d50", + "name": "Add skbmod action to set destination mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set dmac 11:22:33:44:55:66 index 5", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set dmac 11:22:33:44:55:66\\s+index 5", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "9b29", + "name": "Add skbmod action to set source mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 77:88:99:AA:BB:CC index 7", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 7", + "matchPattern": "action order [0-9]*: skbmod pipe set smac 77:88:99:aa:bb:cc\\s+index 7", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "1724", + "name": "Add skbmod action with invalid mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 00:44:55:44:55", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set smac 00:44:55:44:55", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "3cf1", + "name": "Add skbmod action with valid etype", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefe", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFE", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "a749", + "name": "Add skbmod action with invalid etype", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xfefef", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0xFEFEF", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "bfe6", + "name": "Add skbmod action to swap mac", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod swap mac", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 1", + "matchPattern": "action order [0-9]*: skbmod pipe swap mac", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "839b", + "name": "Add skbmod action with control pipe", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod swap mac pipe", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe swap mac", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "c167", + "name": "Add skbmod action with control reclassify", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0xbeef reclassify", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod reclassify set etype 0xBEEF", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "0c2f", + "name": "Add skbmod action with control drop", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0x0001 drop", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 1", + "matchPattern": "action order [0-9]*: skbmod drop set etype 0x1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "d113", + "name": "Add skbmod action with control continue", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set etype 0x1 continue", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod continue set etype 0x1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "7242", + "name": "Add skbmod action with control pass", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action skbmod set smac 00:00:00:00:00:01 pass", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pass set smac 00:00:00:00:00:01", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "58cb", + "name": "List skbmod actions", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions ls action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod", + "matchCount": "5", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "9aa8", + "name": "Get a single skbmod action from a list", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions ls action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions get action skbmod index 4", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "e93a", + "name": "Delete an skbmod action", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x1111 index 909" + ], + "cmdUnderTest": "$TC actions del action skbmod index 909", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x1111\\s+index 909", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + }, + { + "id": "40c2", + "name": "Flush skbmod actions", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + "$TC actions add action skbmod set etype 0x0001", + "$TC actions add action skbmod set etype 0x0011", + "$TC actions add action skbmod set etype 0x0021", + "$TC actions add action skbmod set etype 0x0031", + "$TC actions add action skbmod set etype 0x0041" + ], + "cmdUnderTest": "$TC actions flush action skbmod", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod", + "matchCount": "0", + "teardown": [ + "$TC actions flush action skbmod" + ] + } +] -- GitLab From 7f6661a78a50c3bae8c9f71f67487abbea64dbb3 Mon Sep 17 00:00:00 2001 From: Lucas Bates Date: Fri, 13 Oct 2017 17:51:25 -0400 Subject: [PATCH 1393/1507] tc-testing: fix the -l argument bug in tdc.py This patch fixes a bug in the tdc script, where executing tdc with the -l argument would cause the tests to start running as opposed to listing all the known test cases. Signed-off-by: Lucas Bates Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- tools/testing/selftests/tc-testing/tdc.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index cd61b7844c0d4..d2391df2cf7d3 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -49,7 +49,7 @@ def exec_cmd(command, nsonly=True): stderr=subprocess.PIPE) (rawout, serr) = proc.communicate() - if proc.returncode != 0: + if proc.returncode != 0 and len(serr) > 0: foutput = serr.decode("utf-8") else: foutput = rawout.decode("utf-8") @@ -203,7 +203,7 @@ def set_args(parser): help='Run tests only from the specified category, or if no category is specified, list known categories.') parser.add_argument('-f', '--file', type=str, help='Run tests from the specified file') - parser.add_argument('-l', '--list', type=str, nargs='?', const="", metavar='CATEGORY', + parser.add_argument('-l', '--list', type=str, nargs='?', const="++", metavar='CATEGORY', help='List all test cases, or those only within the specified category') parser.add_argument('-s', '--show', type=str, nargs=1, metavar='ID', dest='showID', help='Display the test case with specified id') @@ -357,10 +357,10 @@ def set_operation_mode(args): testcases = get_categorized_testlist(alltests, ucat) if args.list: - if (len(args.list) == 0): + if (args.list == "++"): list_test_cases(alltests) exit(0) - elif(len(args.list > 0)): + elif(len(args.list) > 0): if (args.list not in ucat): print("Unknown category " + args.list) print("Available categories:") -- GitLab From 32302902ff093891d8e64439cbb8ceae83e21ef8 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 12 Oct 2017 11:38:45 -0700 Subject: [PATCH 1394/1507] mqprio: Reserve last 32 classid values for HW traffic classes and misc IDs This patch makes a slight tweak to mqprio in order to bring the classid values used back in line with what is used for mq. The general idea is to reserve values :ffe0 - :ffef to identify hardware traffic classes normally reported via dev->num_tc. By doing this we can maintain a consistent behavior with mq for classid where :1 - :ffdf will represent a physical qdisc mapped onto a Tx queue represented by classid - 1, and the traffic classes will be mapped onto a known subset of classid values reserved for our virtual qdiscs. Note I reserved the range from :fff0 - :ffff since this way we might be able to reuse these classid values with clsact and ingress which would mean that for mq, mqprio, ingress, and clsact we should be able to maintain a similar classid layout. Signed-off-by: Alexander Duyck Tested-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_mqprio.c | 79 ++++++++++++++++++++-------------- 2 files changed, 47 insertions(+), 33 deletions(-) diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index e95b5c9b9fad9..e7cc3d3c74210 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -74,6 +74,7 @@ struct tc_estimator { #define TC_H_INGRESS (0xFFFFFFF1U) #define TC_H_CLSACT TC_H_INGRESS +#define TC_H_MIN_PRIORITY 0xFFE0U #define TC_H_MIN_INGRESS 0xFFF2U #define TC_H_MIN_EGRESS 0xFFF3U diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index f1ae9be839346..cae91b4b08a60 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -153,6 +153,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -305,7 +309,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -447,38 +451,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; + + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -489,15 +490,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we @@ -550,12 +550,25 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } -- GitLab From 69d78ef25c7b0058674145500efb12255738ba8a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:00:57 +0200 Subject: [PATCH 1395/1507] net: sched: store Qdisc pointer in struct block Prepare for removal of tp->q and store Qdisc pointer in the block structure. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 ++-- include/net/sch_generic.h | 1 + net/sched/cls_api.c | 3 ++- net/sched/sch_atm.c | 4 ++-- net/sched/sch_cbq.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_dsmark.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_hfsc.c | 4 ++-- net/sched/sch_htb.c | 4 ++-- net/sched/sch_ingress.c | 6 +++--- net/sched/sch_multiq.c | 2 +- net/sched/sch_prio.c | 2 +- net/sched/sch_qfq.c | 2 +- net/sched/sch_sfb.c | 2 +- net/sched/sch_sfq.c | 2 +- 16 files changed, 23 insertions(+), 21 deletions(-) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 60d39789e4f07..e6c9e1e4d7115 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -22,7 +22,7 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create); void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain); + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q); void tcf_block_put(struct tcf_block *block); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -30,7 +30,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, #else static inline int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) { return 0; } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 684d8ed27eaae..df4032ca1b7ff 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -270,6 +270,7 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + struct Qdisc *q; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2977b8a908514..f7d3f1f539b7b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -241,7 +241,7 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, } int tcf_block_get(struct tcf_block **p_block, - struct tcf_proto __rcu **p_filter_chain) + struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); struct tcf_chain *chain; @@ -257,6 +257,7 @@ int tcf_block_get(struct tcf_block **p_block, goto err_chain_create; } tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + block->q = q; *p_block = block; return 0; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index c5fcdf1a58a08..2dbd249c0b2fc 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -281,7 +281,7 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, goto err_out; } - error = tcf_block_get(&flow->block, &flow->filter_list); + error = tcf_block_get(&flow->block, &flow->filter_list, sch); if (error) { kfree(flow); goto err_out; @@ -546,7 +546,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - err = tcf_block_get(&p->link.block, &p->link.filter_list); + err = tcf_block_get(&p->link.block, &p->link.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index dcef97fa80473..c3b92d62190e7 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1566,7 +1566,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 2d0e8d4bdc29b..753dc7a77b60e 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -412,7 +412,7 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; err = qdisc_class_hash_init(&q->clhash); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 2836c80c7aa51..fb4fb71c68cfa 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -344,7 +344,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; - err = tcf_block_get(&p->block, &p->filter_list); + err = tcf_block_get(&p->block, &p->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index de3b57ceca7bd..3c40edeff1e88 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -481,7 +481,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3f88b75488b03..a692184bd333a 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1033,7 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); return err; @@ -1405,7 +1405,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; - err = tcf_block_get(&q->root.block, &q->root.filter_list); + err = tcf_block_get(&q->root.block, &q->root.filter_list, sch); if (err) return err; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c6d7ae81b41f4..57be73c0e1d25 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1030,7 +1030,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; @@ -1393,7 +1393,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; - err = tcf_block_get(&cl->block, &cl->filter_list); + err = tcf_block_get(&cl->block, &cl->filter_list, sch); if (err) { kfree(cl); goto failure; diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 44de4ee51ce9f..9ccc1b89b0d99 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -59,7 +59,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->block, &dev->ingress_cl_list); + err = tcf_block_get(&q->block, &dev->ingress_cl_list, sch); if (err) return err; @@ -153,11 +153,11 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) struct net_device *dev = qdisc_dev(sch); int err; - err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list, sch); if (err) return err; - err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + err = tcf_block_get(&q->egress_block, &dev->egress_cl_list, sch); if (err) return err; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index ff4fc3e0facd7..31e0a284eeff9 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -245,7 +245,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 2dd6c68ae91ee..95fad348c8d78 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -212,7 +212,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ddfd4991108a..8694c7b6d2b19 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1419,7 +1419,7 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index cc39e170b4aa2..487d375f5a066 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -553,7 +553,7 @@ static int sfb_init(struct Qdisc *sch, struct nlattr *opt) struct sfb_sched_data *q = qdisc_priv(sch); int err; - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 74ea863b82400..123a53af2506b 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -725,7 +725,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, (unsigned long)sch); - err = tcf_block_get(&q->block, &q->filter_list); + err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) return err; -- GitLab From 855319becbcffec6988a4e781a861b69a71c5b58 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:00:58 +0200 Subject: [PATCH 1396/1507] net: sched: store net pointer in block and introduce qdisc_net helper Store net pointer in the block structure. Along the way, introduce qdisc_net helper which allows to easily obtain net pointer for qdisc instance. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 7 +++++++ include/net/sch_generic.h | 1 + net/sched/cls_api.c | 1 + 3 files changed, 9 insertions(+) diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 259bc191ba594..2d234af15f3ea 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -4,7 +4,9 @@ #include #include #include +#include #include +#include #include #define DEFAULT_TX_QUEUE_LEN 1000 @@ -146,4 +148,9 @@ static inline bool is_classid_clsact_egress(u32 classid) TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS); } +static inline struct net *qdisc_net(struct Qdisc *q) +{ + return dev_net(q->dev_queue->dev); +} + #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index df4032ca1b7ff..9b2cb91dc0d9e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -270,6 +270,7 @@ struct tcf_chain { struct tcf_block { struct list_head chain_list; + struct net *net; struct Qdisc *q; }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f7d3f1f539b7b..856003caa3bbe 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -257,6 +257,7 @@ int tcf_block_get(struct tcf_block **p_block, goto err_chain_create; } tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); + block->net = qdisc_net(q); block->q = q; *p_block = block; return 0; -- GitLab From 44186460c85a0121562db7cfef132d63c869118f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:00:59 +0200 Subject: [PATCH 1397/1507] net: sched: introduce tcf_block_q and tcf_block_dev helpers These helpers allows to get a q and netdev pointers for given block easily. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e6c9e1e4d7115..7bed674ba29a7 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -24,6 +24,17 @@ void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q); void tcf_block_put(struct tcf_block *block); + +static inline struct Qdisc *tcf_block_q(struct tcf_block *block) +{ + return block->q; +} + +static inline struct net_device *tcf_block_dev(struct tcf_block *block) +{ + return tcf_block_q(block)->dev_queue->dev; +} + int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -39,6 +50,16 @@ static inline void tcf_block_put(struct tcf_block *block) { } +static inline struct Qdisc *tcf_block_q(struct tcf_block *block) +{ + return NULL; +} + +static inline struct net_device *tcf_block_dev(struct tcf_block *block) +{ + return NULL; +} + static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { -- GitLab From 34e3759cf86a3e75463e34c1bb9691777406a175 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:00 +0200 Subject: [PATCH 1398/1507] net: sched: teach tcf_bind/unbind_filter to use block->q Whenever the block->q is set, it can be used instead of tp->q as it contains the same value. When it is not set, which can't happen now but it might happen with the follow-up shared blocks introduction, the class is not set in the result. That would lead to a class lookup instead of direct class pointer use for classful qdiscs. However, it is not planned to support classful qdisqs sharing filter blocks, so that may never happen. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 7bed674ba29a7..49a143e0fe650 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -74,36 +74,43 @@ __cls_set_class(unsigned long *clp, unsigned long cl) } static inline unsigned long -cls_set_class(struct tcf_proto *tp, unsigned long *clp, - unsigned long cl) +cls_set_class(struct Qdisc *q, unsigned long *clp, unsigned long cl) { unsigned long old_cl; - - tcf_tree_lock(tp); + + sch_tree_lock(q); old_cl = __cls_set_class(clp, cl); - tcf_tree_unlock(tp); - + sch_tree_unlock(q); return old_cl; } static inline void tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base) { + struct Qdisc *q = tp->chain->block->q; unsigned long cl; - cl = tp->q->ops->cl_ops->bind_tcf(tp->q, base, r->classid); - cl = cls_set_class(tp, &r->class, cl); + /* Check q as it is not set for shared blocks. In that case, + * setting class is not supported. + */ + if (!q) + return; + cl = q->ops->cl_ops->bind_tcf(q, base, r->classid); + cl = cls_set_class(q, &r->class, cl); if (cl) - tp->q->ops->cl_ops->unbind_tcf(tp->q, cl); + q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) { + struct Qdisc *q = tp->chain->block->q; unsigned long cl; + if (!q) + return; if ((cl = __cls_set_class(&r->class, 0)) != 0) - tp->q->ops->cl_ops->unbind_tcf(tp->q, cl); + q->ops->cl_ops->unbind_tcf(q, cl); } struct tcf_exts { -- GitLab From c1954561cd262b8adf7908c5552fe9ad99f82f81 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:01 +0200 Subject: [PATCH 1399/1507] net: sched: ematch: obtain net pointer from blocks Instead of using tp->q, use block to get the net pointer. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/ematch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 03b677bc07005..1331a4c2d8ff5 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -178,7 +178,7 @@ static int tcf_em_validate(struct tcf_proto *tp, struct tcf_ematch_hdr *em_hdr = nla_data(nla); int data_len = nla_len(nla) - sizeof(*em_hdr); void *data = (void *) em_hdr + sizeof(*em_hdr); - struct net *net = dev_net(qdisc_dev(tp->q)); + struct net *net = tp->chain->block->net; if (!TCF_EM_REL_VALID(em_hdr->flags)) goto errout; -- GitLab From 7fa9d974f3c2a016b9accb18f4ee2ed2a738585c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:02 +0200 Subject: [PATCH 1400/1507] net: sched: cls_u32: use block instead of q in tc_u_common tc_u_common is now per-q. With blocks, it has to be converted to be per-block. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_u32.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 094d224411a93..b6d46065f6618 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -93,7 +93,7 @@ struct tc_u_hnode { struct tc_u_common { struct tc_u_hnode __rcu *hlist; - struct Qdisc *q; + struct tcf_block *block; int refcnt; struct idr handle_idr; struct hlist_node hnode; @@ -335,11 +335,7 @@ static struct hlist_head *tc_u_common_hash; static unsigned int tc_u_hash(const struct tcf_proto *tp) { - struct net_device *dev = tp->q->dev_queue->dev; - u32 qhandle = tp->q->handle; - int ifindex = dev->ifindex; - - return hash_64((u64)ifindex << 32 | qhandle, U32_HASH_SHIFT); + return hash_64((u64) tp->chain->block, U32_HASH_SHIFT); } static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) @@ -349,7 +345,7 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp) h = tc_u_hash(tp); hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) { - if (tc->q == tp->q) + if (tc->block == tp->chain->block) return tc; } return NULL; @@ -378,7 +374,7 @@ static int u32_init(struct tcf_proto *tp) kfree(root_ht); return -ENOBUFS; } - tp_c->q = tp->q; + tp_c->block = tp->chain->block; INIT_HLIST_NODE(&tp_c->hnode); idr_init(&tp_c->handle_idr); -- GitLab From 1abf272022cf1d18469405f47b4ec49c6a3125db Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:03 +0200 Subject: [PATCH 1401/1507] net: sched: tcindex, fw, flow: use tcf_block_q helper to get struct Qdisc Use helper to get q pointer per block. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 7 +++++-- net/sched/cls_fw.c | 5 ++++- net/sched/cls_tcindex.c | 5 ++++- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2a3a60ec5b861..f3be6667a2536 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -491,8 +491,11 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, perturb_period = nla_get_u32(tb[TCA_FLOW_PERTURB]) * HZ; } - if (TC_H_MAJ(baseclass) == 0) - baseclass = TC_H_MAKE(tp->q->handle, baseclass); + if (TC_H_MAJ(baseclass) == 0) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + + baseclass = TC_H_MAKE(q->handle, baseclass); + } if (TC_H_MIN(baseclass) == 0) baseclass = TC_H_MAKE(baseclass, 1); diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 941245ad07fd4..aa1e1f3bd20c9 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -28,6 +28,7 @@ #include #include #include +#include #define HTSIZE 256 @@ -83,9 +84,11 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { + struct Qdisc *q = tcf_block_q(tp->chain->block); + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || - !(TC_H_MAJ(id ^ tp->q->handle)))) { + !(TC_H_MAJ(id ^ q->handle)))) { res->classid = id; res->class = 0; return 0; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 14a7e08b2fa9e..d732b5474a4da 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -13,6 +13,7 @@ #include #include #include +#include /* * Passing parameters to the root seems to be done more awkwardly than really @@ -90,9 +91,11 @@ static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = tcindex_lookup(p, key); if (!f) { + struct Qdisc *q = tcf_block_q(tp->chain->block); + if (!p->fall_through) return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(tp->q->handle), key); + res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); res->class = 0; pr_debug("alg 0x%x\n", res->classid); return 0; -- GitLab From 74e3be6021d22df2ffcb691eae1affeb2bd0128e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:04 +0200 Subject: [PATCH 1402/1507] net: sched: use tcf_block_q helper to get q pointer for sch_tree_lock Use tcf_block_q helper to get q pointer to be used for direct call of sch_tree_lock/unlock instead of tcf_tree_lock/unlock. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 --- net/sched/sch_api.c | 6 ++++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9b2cb91dc0d9e..0aea9e23e97a4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -359,9 +359,6 @@ static inline void sch_tree_unlock(const struct Qdisc *q) spin_unlock_bh(qdisc_root_sleeping_lock(q)); } -#define tcf_tree_lock(tp) sch_tree_lock((tp)->q) -#define tcf_tree_unlock(tp) sch_tree_unlock((tp)->q) - extern struct Qdisc noop_qdisc; extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index aa82116ed10c5..a9ac912f1d67d 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1661,9 +1661,11 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_bind_args *a = (void *)arg; if (tp->ops->bind_class) { - tcf_tree_lock(tp); + struct Qdisc *q = tcf_block_q(tp->chain->block); + + sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl); - tcf_tree_unlock(tp); + sch_tree_unlock(q); } return 0; } -- GitLab From a10fa20101ae48fed2102f8e84d98f5aac2e5c40 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 13 Oct 2017 14:01:05 +0200 Subject: [PATCH 1403/1507] net: sched: propagate q and parent from caller down to tcf_fill_node The callers have this info, they will pass it down to tcf_fill_node. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_api.c | 55 ++++++++++++++++++++++++++++----------------- 1 file changed, 35 insertions(+), 20 deletions(-) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 856003caa3bbe..2e8e87fd9d978 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -420,8 +420,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } static int tcf_fill_node(struct net *net, struct sk_buff *skb, - struct tcf_proto *tp, void *fh, u32 portid, - u32 seq, u16 flags, int event) + struct tcf_proto *tp, struct Qdisc *q, u32 parent, + void *fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -434,8 +434,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; - tcm->tcm_ifindex = qdisc_dev(tp->q)->ifindex; - tcm->tcm_parent = tp->classid; + tcm->tcm_ifindex = qdisc_dev(q)->ifindex; + tcm->tcm_parent = parent; tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; @@ -458,6 +458,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, int event, bool unicast) { struct sk_buff *skb; @@ -467,7 +468,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -482,6 +483,7 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, + struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last) { struct sk_buff *skb; @@ -492,7 +494,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, + if (tcf_fill_node(net, skb, tp, q, parent, fh, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { kfree_skb(skb); return -EINVAL; @@ -512,6 +514,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, } static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, + struct Qdisc *q, u32 parent, struct nlmsghdr *n, struct tcf_chain *chain, int event) { @@ -519,7 +522,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) - tfilter_notify(net, oskb, n, tp, 0, event, false); + tfilter_notify(net, oskb, n, tp, q, parent, 0, event, false); } /* Add/change/delete/get a filter node */ @@ -638,7 +641,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); + tfilter_notify_chain(net, skb, q, parent, n, + chain, RTM_DELTFILTER); tcf_chain_flush(chain); err = 0; goto errout; @@ -685,7 +689,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (!fh) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, + tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); err = 0; @@ -710,8 +714,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, } break; case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, fh, false, - &last); + err = tfilter_del_notify(net, skb, n, tp, q, parent, + fh, false, &last); if (err) goto errout; if (last) { @@ -720,7 +724,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, } goto errout; case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, fh, + err = tfilter_notify(net, skb, n, tp, q, parent, fh, RTM_NEWTFILTER, true); goto errout; default: @@ -734,7 +738,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err == 0) { if (tp_created) tcf_chain_tp_insert(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); + tfilter_notify(net, skb, n, tp, q, parent, fh, + RTM_NEWTFILTER, false); } else { if (tp_created) tcf_proto_destroy(tp); @@ -753,6 +758,8 @@ struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; struct netlink_callback *cb; + struct Qdisc *q; + u32 parent; }; static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -760,13 +767,14 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct tcf_dump_args *a = (void *)arg; struct net *net = sock_net(a->skb->sk); - return tcf_fill_node(net, a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, + return tcf_fill_node(net, a->skb, tp, a->q, a->parent, + n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } -static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, - struct netlink_callback *cb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, + struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { struct net *net = sock_net(skb->sk); @@ -788,7 +796,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, + if (tcf_fill_node(net, skb, tp, q, parent, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) @@ -801,6 +809,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, arg.w.fn = tcf_node_dump; arg.skb = skb; arg.cb = cb; + arg.q = q; + arg.parent = parent; arg.w.stop = 0; arg.w.skip = cb->args[1] - 1; arg.w.count = 0; @@ -826,6 +836,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) @@ -839,10 +850,13 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - if (!tcm->tcm_parent) + parent = tcm->tcm_parent; + if (!parent) { q = dev->qdisc; - else + parent = q->handle; + } else { q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + } if (!q) goto out; cops = q->ops->cl_ops; @@ -866,7 +880,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; - if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + if (!tcf_chain_dump(chain, q, parent, skb, cb, + index_start, &index)) break; } -- GitLab From 9db9583839b760fc492a7b288edfe2213184a579 Mon Sep 17 00:00:00 2001 From: Abhijit Ayarekar Date: Fri, 13 Oct 2017 12:24:06 -0700 Subject: [PATCH 1404/1507] bpf: Add -target to clang switch while cross compiling. Update to llvm excludes assembly instructions. llvm git revision is below commit 65fad7c26569 ("bpf: add inline-asm support") This change will be part of llvm release 6.0 __ASM_SYSREG_H define is not required for native compile. -target switch includes appropriate target specific files while cross compiling Tested on x86 and arm64. Signed-off-by: Abhijit Ayarekar Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- samples/bpf/Makefile | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index ebc2ad69b62c0..81f9fcd736b7a 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -180,6 +180,7 @@ CLANG ?= clang # Detect that we're cross compiling and use the cross compiler ifdef CROSS_COMPILE HOSTCC = $(CROSS_COMPILE)gcc +CLANG_ARCH_ARGS = -target $(ARCH) endif # Trick to allow make to be run from this directory @@ -229,9 +230,9 @@ $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h $(obj)/%.o: $(src)/%.c $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ -I$(srctree)/tools/testing/selftests/bpf/ \ - -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ + -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \ -D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \ -Wno-gnu-variable-sized-type-not-at-end \ -Wno-address-of-packed-member -Wno-tautological-compare \ - -Wno-unknown-warning-option \ + -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ -- GitLab From 0e80193bd8c1d97654f1a2f45934e7372e9a512e Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 13 Oct 2017 15:01:08 -0700 Subject: [PATCH 1405/1507] ipv6: check fn before doing FIB6_SUBTREE(fn) In fib6_locate(), we need to first make sure fn is not NULL before doing FIB6_SUBTREE(fn) to avoid crash. This fixes the following static checker warning: net/ipv6/ip6_fib.c:1462 fib6_locate() warn: variable dereferenced before check 'fn' (see line 1459) net/ipv6/ip6_fib.c 1458 if (src_len) { 1459 struct fib6_node *subtree = FIB6_SUBTREE(fn); ^^^^^^^^^^^^^^^^ We shifted this dereference 1460 1461 WARN_ON(saddr == NULL); 1462 if (fn && subtree) ^^ before the check for NULL. 1463 fn = fib6_locate_1(subtree, saddr, src_len, 1464 offsetof(struct rt6_info, rt6i_src) Fixes: 66f5d6ce53e6 ("ipv6: replace rwlock with rcu and spinlock in fib6_table") Reported-by: Dan Carpenter Signed-off-by: Wei Wang Acked-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c2ecd5ec638aa..548af48212fcb 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1456,13 +1456,16 @@ struct fib6_node *fib6_locate(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (src_len) { - struct fib6_node *subtree = FIB6_SUBTREE(fn); - WARN_ON(saddr == NULL); - if (fn && subtree) - fn = fib6_locate_1(subtree, saddr, src_len, + if (fn) { + struct fib6_node *subtree = FIB6_SUBTREE(fn); + + if (subtree) { + fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct rt6_info, rt6i_src), exact_match); + } + } } #endif -- GitLab From 0da4af00b2ed3dbe46788623a696c4169447eadc Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 13 Oct 2017 15:08:07 -0700 Subject: [PATCH 1406/1507] ipv6: only update __use and lastusetime once per jiffy at most In order to not dirty the cacheline too often, we try to only update dst->__use and dst->lastusetime at most once per jiffy. As dst->lastusetime is only used by ipv6 garbage collector, it should be good enough time resolution. And __use is only used in ipv6_route_seq_show() to show how many times a dst has been used. And as __use is not atomic_t right now, it does not show the precise number of usage times anyway. So we think it should be OK to only update it at most once per jiffy. According to my latest syn flood test on a machine with intel Xeon 6th gen processor and 2 10G mlx nics bonded together, each with 8 rx queues on 2 NUMA nodes: With this patch, the packet process rate increases from ~3.49Mpps to ~3.75Mpps with a 7% increase rate. Note: dst_use() is being renamed to dst_hold_and_use() to better specify the purpose of the function. Signed-off-by: Wei Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 15 ++++++++------- net/decnet/dn_route.c | 8 ++++---- 2 files changed, 12 insertions(+), 11 deletions(-) diff --git a/include/net/dst.h b/include/net/dst.h index 204c19e254568..5047e8053d6ca 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -255,17 +255,18 @@ static inline void dst_hold(struct dst_entry *dst) WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); } -static inline void dst_use(struct dst_entry *dst, unsigned long time) +static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) { - dst_hold(dst); - dst->__use++; - dst->lastuse = time; + if (time != dst->lastuse) { + dst->__use++; + dst->lastuse = time; + } } -static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) +static inline void dst_hold_and_use(struct dst_entry *dst, unsigned long time) { - dst->__use++; - dst->lastuse = time; + dst_hold(dst); + dst_use_noref(dst, time); } static inline struct dst_entry *dst_clone(struct dst_entry *dst) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0bd3afd01dd29..bff5ab88cdbb4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -338,7 +338,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - dst_use(&rth->dst, now); + dst_hold_and_use(&rth->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); dst_release_immediate(&rt->dst); @@ -351,7 +351,7 @@ static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_rou rcu_assign_pointer(rt->dst.dn_next, dn_rt_hash_table[hash].chain); rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - dst_use(&rt->dst, now); + dst_hold_and_use(&rt->dst, now); spin_unlock_bh(&dn_rt_hash_table[hash].lock); *rp = rt; return 0; @@ -1258,7 +1258,7 @@ static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn * (flp->flowidn_mark == rt->fld.flowidn_mark) && dn_is_output_route(rt) && (rt->fld.flowidn_oif == flp->flowidn_oif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock_bh(); *pprt = &rt->dst; return 0; @@ -1535,7 +1535,7 @@ static int dn_route_input(struct sk_buff *skb) (rt->fld.flowidn_oif == 0) && (rt->fld.flowidn_mark == skb->mark) && (rt->fld.flowidn_iif == cb->iif)) { - dst_use(&rt->dst, jiffies); + dst_hold_and_use(&rt->dst, jiffies); rcu_read_unlock(); skb_dst_set(skb, (struct dst_entry *)rt); return 0; -- GitLab From 9185a610f8f7f1b4e4d28c9de27d1969cf58e0f1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 12 Oct 2017 18:40:02 -0400 Subject: [PATCH 1407/1507] tracing: bpf: Hide bpf trace events when they are not used All the trace events defined in include/trace/events/bpf.h are only used when CONFIG_BPF_SYSCALL is defined. But this file gets included by include/linux/bpf_trace.h which is included by the networking code with CREATE_TRACE_POINTS defined. If a trace event is created but not used it still has data structures and functions created for its use, even though nothing is using them. To not waste space, do not define the BPF trace events in bpf.h unless CONFIG_BPF_SYSCALL is defined. Signed-off-by: Steven Rostedt (VMware) Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/trace/events/bpf.h | 5 ++++- kernel/bpf/core.c | 3 +++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h index 52c8425d144b3..1fb58faa4a44b 100644 --- a/include/trace/events/bpf.h +++ b/include/trace/events/bpf.h @@ -4,6 +4,9 @@ #if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BPF_H +/* These are only used within the BPF_SYSCALL code */ +#ifdef CONFIG_BPF_SYSCALL + #include #include #include @@ -345,7 +348,7 @@ TRACE_EVENT(bpf_map_next_key, __print_hex(__get_dynamic_array(nxt), __entry->key_len), __entry->key_trunc ? " ..." : "") ); - +#endif /* CONFIG_BPF_SYSCALL */ #endif /* _TRACE_BPF_H */ #include diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 248961af2421d..8e7c8bf2b687d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1580,5 +1580,8 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); +/* These are only used within the BPF_SYSCALL code */ +#ifdef CONFIG_BPF_SYSCALL EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); +#endif -- GitLab From 2a600d97cbb2a9311e6b42547d37e0eca9b9d6d6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Sat, 14 Oct 2017 17:04:40 +0300 Subject: [PATCH 1408/1507] pch_gbe: Switch to new PCI IRQ allocation API This removes custom flag handling. Signed-off-by: Andy Shevchenko Signed-off-by: David S. Miller --- .../net/ethernet/oki-semi/pch_gbe/pch_gbe.h | 3 +- .../ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 42 +++++++------------ 2 files changed, 17 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index 8d710a3b4db06..697e29dd4bd3a 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -613,7 +613,6 @@ struct pch_gbe_privdata { * @rx_ring: Pointer of Rx descriptor ring structure * @rx_buffer_len: Receive buffer length * @tx_queue_len: Transmit queue length - * @have_msi: PCI MSI mode flag * @pch_gbe_privdata: PCI Device ID driver_data */ @@ -623,6 +622,7 @@ struct pch_gbe_adapter { atomic_t irq_sem; struct net_device *netdev; struct pci_dev *pdev; + int irq; struct net_device *polling_netdev; struct napi_struct napi; struct pch_gbe_hw hw; @@ -637,7 +637,6 @@ struct pch_gbe_adapter { struct pch_gbe_rx_ring *rx_ring; unsigned long rx_buffer_len; unsigned long tx_queue_len; - bool have_msi; bool rx_stop_flag; int hwts_tx_en; int hwts_rx_en; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 5ae9681a2da73..457ee80307ea6 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -781,11 +781,8 @@ static void pch_gbe_free_irq(struct pch_gbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; - free_irq(adapter->pdev->irq, netdev); - if (adapter->have_msi) { - pci_disable_msi(adapter->pdev); - netdev_dbg(netdev, "call pci_disable_msi\n"); - } + free_irq(adapter->irq, netdev); + pci_free_irq_vectors(adapter->pdev); } /** @@ -799,7 +796,7 @@ static void pch_gbe_irq_disable(struct pch_gbe_adapter *adapter) atomic_inc(&adapter->irq_sem); iowrite32(0, &hw->reg->INT_EN); ioread32(&hw->reg->INT_ST); - synchronize_irq(adapter->pdev->irq); + synchronize_irq(adapter->irq); netdev_dbg(adapter->netdev, "INT_EN reg : 0x%08x\n", ioread32(&hw->reg->INT_EN)); @@ -1903,30 +1900,23 @@ static int pch_gbe_request_irq(struct pch_gbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; - int flags; - flags = IRQF_SHARED; - adapter->have_msi = false; - err = pci_enable_msi(adapter->pdev); - netdev_dbg(netdev, "call pci_enable_msi\n"); - if (err) { - netdev_dbg(netdev, "call pci_enable_msi - Error: %d\n", err); - } else { - flags = 0; - adapter->have_msi = true; - } - err = request_irq(adapter->pdev->irq, &pch_gbe_intr, - flags, netdev->name, netdev); + err = pci_alloc_irq_vectors(adapter->pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (err < 0) + return err; + + adapter->irq = pci_irq_vector(adapter->pdev, 0); + + err = request_irq(adapter->irq, &pch_gbe_intr, IRQF_SHARED, + netdev->name, netdev); if (err) netdev_err(netdev, "Unable to allocate interrupt Error: %d\n", err); - netdev_dbg(netdev, - "adapter->have_msi : %d flags : 0x%04x return : 0x%04x\n", - adapter->have_msi, flags, err); + netdev_dbg(netdev, "have_msi : %d return : 0x%04x\n", + pci_dev_msi_enabled(adapter->pdev), err); return err; } - /** * pch_gbe_up - Up GbE network device * @adapter: Board private structure @@ -2399,9 +2389,9 @@ static void pch_gbe_netpoll(struct net_device *netdev) { struct pch_gbe_adapter *adapter = netdev_priv(netdev); - disable_irq(adapter->pdev->irq); - pch_gbe_intr(adapter->pdev->irq, netdev); - enable_irq(adapter->pdev->irq); + disable_irq(adapter->irq); + pch_gbe_intr(adapter->irq, netdev); + enable_irq(adapter->irq); } #endif -- GitLab From bc28df6e8543d41abfb48d4a4c6d445638d6768c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Sun, 15 Oct 2017 13:22:10 -0500 Subject: [PATCH 1409/1507] net: dccp: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Notice that for options.c file, I placed the "fall through" comment on its own line, which is what GCC is expecting to find. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/dccp/input.c | 1 + net/dccp/options.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/net/dccp/input.c b/net/dccp/input.c index fa6be9750bb46..d28d46bff6ab4 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -534,6 +534,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, case DCCP_PKT_DATA: if (sk->sk_state == DCCP_RESPOND) break; + /* fall through */ case DCCP_PKT_DATAACK: case DCCP_PKT_ACK: /* diff --git a/net/dccp/options.c b/net/dccp/options.c index 51cdfc3bd8cad..4e40db017e198 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -227,8 +227,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. - * Fall through. */ + /* fall through */ case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) -- GitLab From 92c43fcafe9db18dc51cd2a44cdafd80a4bcb2b5 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Sun, 15 Oct 2017 22:00:52 +0100 Subject: [PATCH 1410/1507] hamradio: baycom_par: use new parport device model Modify baycom driver to use the new parallel port device model. Signed-off-by: Sudip Mukherjee Signed-off-by: David S. Miller --- drivers/net/hamradio/baycom_par.c | 48 ++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 4 deletions(-) diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c index e1783832d304b..1f7ceafd61ffa 100644 --- a/drivers/net/hamradio/baycom_par.c +++ b/drivers/net/hamradio/baycom_par.c @@ -311,7 +311,9 @@ static void par96_wakeup(void *handle) static int par96_open(struct net_device *dev) { struct baycom_state *bc = netdev_priv(dev); + struct pardev_cb par_cb; struct parport *pp; + int i; if (!dev || !bc) return -ENXIO; @@ -332,8 +334,21 @@ static int par96_open(struct net_device *dev) } memset(&bc->modem, 0, sizeof(bc->modem)); bc->hdrv.par.bitrate = 9600; - bc->pdev = parport_register_device(pp, dev->name, NULL, par96_wakeup, - par96_interrupt, PARPORT_DEV_EXCL, dev); + memset(&par_cb, 0, sizeof(par_cb)); + par_cb.wakeup = par96_wakeup; + par_cb.irq_func = par96_interrupt; + par_cb.private = (void *)dev; + par_cb.flags = PARPORT_DEV_EXCL; + for (i = 0; i < NR_PORTS; i++) + if (baycom_device[i] == dev) + break; + + if (i == NR_PORTS) { + pr_err("%s: no device found\n", bc_drvname); + parport_put_port(pp); + return -ENODEV; + } + bc->pdev = parport_register_dev_model(pp, dev->name, &par_cb, i); parport_put_port(pp); if (!bc->pdev) { printk(KERN_ERR "baycom_par: cannot register parport at 0x%lx\n", dev->base_addr); @@ -490,12 +505,34 @@ MODULE_LICENSE("GPL"); /* --------------------------------------------------------------------- */ +static int baycom_par_probe(struct pardevice *par_dev) +{ + struct device_driver *drv = par_dev->dev.driver; + int len = strlen(drv->name); + + if (strncmp(par_dev->name, drv->name, len)) + return -ENODEV; + + return 0; +} + +static struct parport_driver baycom_par_driver = { + .name = "bcp", + .probe = baycom_par_probe, + .devmodel = true, +}; + static int __init init_baycompar(void) { - int i, found = 0; + int i, found = 0, ret; char set_hw = 1; printk(bc_drvinfo); + + ret = parport_register_driver(&baycom_par_driver); + if (ret) + return ret; + /* * register net devices */ @@ -524,8 +561,10 @@ static int __init init_baycompar(void) baycom_device[i] = dev; } - if (!found) + if (!found) { + parport_unregister_driver(&baycom_par_driver); return -ENXIO; + } return 0; } @@ -539,6 +578,7 @@ static void __exit cleanup_baycompar(void) if (dev) hdlcdrv_unregister(dev); } + parport_unregister_driver(&baycom_par_driver); } module_init(init_baycompar); -- GitLab From 00fb3a7c7c14dd28feb0372a8458267e058add66 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Oct 2017 13:32:36 +0200 Subject: [PATCH 1411/1507] net: systemport: add NET_DSA dependency The notifier cause a link error when NET_DSA is a loadable module: drivers/net/ethernet/broadcom/bcmsysport.o: In function `bcm_sysport_remove': bcmsysport.c:(.text+0x1582): undefined reference to `unregister_dsa_notifier' drivers/net/ethernet/broadcom/bcmsysport.o: In function `bcm_sysport_probe': bcmsysport.c:(.text+0x278d): undefined reference to `register_dsa_notifier' This adds a dependency that forces the systemport driver to be a loadable module as well when that happens, but otherwise allows it to be built normally when DSA is either built-in or completely disabled. Fixes: d156576362c0 ("net: systemport: Establish lower/upper queue mapping") Signed-off-by: Arnd Bergmann Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 67134ece11077..af75156919edf 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -184,6 +184,7 @@ config BGMAC_PLATFORM config SYSTEMPORT tristate "Broadcom SYSTEMPORT internal MAC support" depends on OF + depends on NET_DSA || !NET_DSA select MII select PHYLIB select FIXED_PHY -- GitLab From d85969f1a981b9cd57f5037ebcb9c6d385c0bc70 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 16 Oct 2017 14:33:21 +0100 Subject: [PATCH 1412/1507] tcp: cdg: make struct tcp_cdg static The structure tcp_cdg is local to the source and does not need to be in global scope, so make it static. Cleans up sparse warning: symbol 'tcp_cdg' was not declared. Should it be static? Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- net/ipv4/tcp_cdg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 66ac69f7bd195..06fbe102a425f 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -389,7 +389,7 @@ static void tcp_cdg_release(struct sock *sk) kfree(ca->gradients); } -struct tcp_congestion_ops tcp_cdg __read_mostly = { +static struct tcp_congestion_ops tcp_cdg __read_mostly = { .cong_avoid = tcp_cdg_cong_avoid, .cwnd_event = tcp_cdg_cwnd_event, .pkts_acked = tcp_cdg_acked, -- GitLab From 070cbf5be7774dcf0ceca081c7321c6f2ae833a4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 16 Oct 2017 15:44:35 +0200 Subject: [PATCH 1413/1507] rtnetlink: place link af dump into own helper next patch will rcu-ify rtnl af_ops, i.e. allow af_ops lookup and function calls with rcu read lock held instead of rtnl mutex. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 72 ++++++++++++++++++++++++++------------------ 1 file changed, 42 insertions(+), 30 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 6a09f3d575afc..a49cad25e5771 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1382,6 +1382,47 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, return 0; } +static int rtnl_fill_link_af(struct sk_buff *skb, + const struct net_device *dev, + u32 ext_filter_mask) +{ + const struct rtnl_af_ops *af_ops; + struct nlattr *af_spec; + + af_spec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af_spec) + return -EMSGSIZE; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + struct nlattr *af; + int err; + + if (!af_ops->fill_link_af) + continue; + + af = nla_nest_start(skb, af_ops->family); + if (!af) + return -EMSGSIZE; + + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + return -EMSGSIZE; + + nla_nest_end(skb, af); + } + + nla_nest_end(skb, af_spec); + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, @@ -1389,8 +1430,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - struct nlattr *af_spec; - struct rtnl_af_ops *af_ops; ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -1477,36 +1516,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) goto nla_put_failure; - if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) + if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) goto nla_put_failure; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { - if (af_ops->fill_link_af) { - struct nlattr *af; - int err; - - if (!(af = nla_nest_start(skb, af_ops->family))) - goto nla_put_failure; - - err = af_ops->fill_link_af(skb, dev, ext_filter_mask); - - /* - * Caller may return ENODATA to indicate that there - * was no data to be dumped. This is not an error, it - * means we should trim the attribute header and - * continue. - */ - if (err == -ENODATA) - nla_nest_cancel(skb, af); - else if (err < 0) - goto nla_put_failure; - - nla_nest_end(skb, af); - } - } - - nla_nest_end(skb, af_spec); - nlmsg_end(skb, nlh); return 0; -- GitLab From 5fa85a09390c4a525cb4d06a0c4644b01a47976b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 16 Oct 2017 15:44:36 +0200 Subject: [PATCH 1414/1507] net: core: rcu-ify rtnl af_ops rtnl af_ops currently rely on rtnl mutex: unregister (called from module exit functions) takes the rtnl mutex and all users that do af_ops lookup also take the rtnl mutex. IOW, parallel rmmod will block until doit() callback is done. As none of the af_ops implementation sleep we can use rcu instead. doit functions that need the af_ops can now use rcu instead of the rtnl mutex provided the mutex isn't needed for other reasons. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 62 ++++++++++++++++++++++++++++++++------------ net/ipv4/devinet.c | 4 +-- 2 files changed, 48 insertions(+), 18 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a49cad25e5771..20b550d07fe38 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -453,7 +453,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; - list_for_each_entry(ops, &rtnl_af_ops, list) { + list_for_each_entry_rcu(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } @@ -470,7 +470,7 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) void rtnl_af_register(struct rtnl_af_ops *ops) { rtnl_lock(); - list_add_tail(&ops->list, &rtnl_af_ops); + list_add_tail_rcu(&ops->list, &rtnl_af_ops); rtnl_unlock(); } EXPORT_SYMBOL_GPL(rtnl_af_register); @@ -482,8 +482,10 @@ EXPORT_SYMBOL_GPL(rtnl_af_register); void rtnl_af_unregister(struct rtnl_af_ops *ops) { rtnl_lock(); - list_del(&ops->list); + list_del_rcu(&ops->list); rtnl_unlock(); + + synchronize_rcu(); } EXPORT_SYMBOL_GPL(rtnl_af_unregister); @@ -496,13 +498,15 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev, /* IFLA_AF_SPEC */ size = nla_total_size(sizeof(struct nlattr)); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + af_ops->get_link_af_size(dev, ext_filter_mask); } } + rcu_read_unlock(); return size; } @@ -1393,7 +1397,7 @@ static int rtnl_fill_link_af(struct sk_buff *skb, if (!af_spec) return -EMSGSIZE; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { struct nlattr *af; int err; @@ -1516,12 +1520,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) goto nla_put_failure; + rcu_read_lock(); if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) - goto nla_put_failure; + goto nla_put_failure_rcu; + rcu_read_unlock(); nlmsg_end(skb, nlh); return 0; +nla_put_failure_rcu: + rcu_read_unlock(); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -1783,17 +1791,27 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + rcu_read_lock(); + af_ops = rtnl_af_lookup(nla_type(af)); + if (!af_ops) { + rcu_read_unlock(); return -EAFNOSUPPORT; + } - if (!af_ops->set_link_af) + if (!af_ops->set_link_af) { + rcu_read_unlock(); return -EOPNOTSUPP; + } if (af_ops->validate_link_af) { err = af_ops->validate_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); return err; + } } + + rcu_read_unlock(); } } @@ -2251,13 +2269,18 @@ static int do_setlink(const struct sk_buff *skb, nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; + rcu_read_lock(); + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) BUG(); err = af_ops->set_link_af(dev, af); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); goto errout; + } + rcu_read_unlock(); status |= DO_SETLINK_NOTIFY; } } @@ -4004,25 +4027,30 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev, if (!attr) goto nla_put_failure; - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->fill_stats_af) { struct nlattr *af; int err; af = nla_nest_start(skb, af_ops->family); - if (!af) + if (!af) { + rcu_read_unlock(); goto nla_put_failure; - + } err = af_ops->fill_stats_af(skb, dev); - if (err == -ENODATA) + if (err == -ENODATA) { nla_nest_cancel(skb, af); - else if (err < 0) + } else if (err < 0) { + rcu_read_unlock(); goto nla_put_failure; + } nla_nest_end(skb, af); } } + rcu_read_unlock(); nla_nest_end(skb, attr); @@ -4091,7 +4119,8 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, /* for IFLA_STATS_AF_SPEC */ size += nla_total_size(0); - list_for_each_entry(af_ops, &rtnl_af_ops, list) { + rcu_read_lock(); + list_for_each_entry_rcu(af_ops, &rtnl_af_ops, list) { if (af_ops->get_stats_af_size) { size += nla_total_size( af_ops->get_stats_af_size(dev)); @@ -4100,6 +4129,7 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, size += nla_total_size(0); } } + rcu_read_unlock(); } return size; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7ce22a2c07ce0..6d9b072d903b0 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1757,7 +1757,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rtnl(dev)) + if (dev && !__in_dev_get_rcu(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL); @@ -1781,7 +1781,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev = __in_dev_get_rcu(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; -- GitLab From 36c0a9dfc6613242ba1de012e2d15145cdaae805 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Mon, 16 Oct 2017 16:04:51 +0200 Subject: [PATCH 1415/1507] tipc: fix rebasing error In commit 2f487712b893 ("tipc: guarantee that group broadcast doesn't bypass group unicast") there was introduced a last-minute rebasing error that broke non-group communication. We fix this here. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/tipc/link.c b/net/tipc/link.c index 723dd6998684d..870b9b8f877a2 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1052,6 +1052,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, return true; } case CONN_MANAGER: + skb_queue_tail(inputq, skb); return true; case GROUP_PROTOCOL: skb_queue_tail(mc_inputq, skb); -- GitLab From c30f5d012edf755959c44d71757fbf4648ad75a8 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Oct 2017 16:26:35 +0200 Subject: [PATCH 1416/1507] mlxsw: spectrum: Move netdevice NB to struct mlxsw_sp So far, all netdevice notifications that the driver cared about were related to its own ports, and mlxsw_sp could be retrieved from the netdevice's private data. For IP-in-IP offloading however, the driver cares about events on foreign netdevices, and getting at mlxsw_sp or router data structures from the handler is inconvenient. Therefore move the netdevice notifier blocks from global scope to struct mlxsw_sp to allow retrieval from the notifier block pointer itself. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 23 +++++++++++++------ .../net/ethernet/mellanox/mlxsw/spectrum.h | 1 + 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 321988ac57ccb..83f9c2564f617 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3667,6 +3667,9 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); } +static int mlxsw_sp_netdevice_event(struct notifier_block *unused, + unsigned long event, void *ptr); + static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info) { @@ -3736,6 +3739,16 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_router_init; } + /* Initialize netdevice notifier after router is initialized, so that + * the event handler can use router structures. + */ + mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; + err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n"); + goto err_netdev_notifier; + } + err = mlxsw_sp_span_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); @@ -3769,6 +3782,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, err_acl_init: mlxsw_sp_span_fini(mlxsw_sp); err_span_init: + unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); +err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: mlxsw_sp_afa_fini(mlxsw_sp); @@ -3795,6 +3810,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_dpipe_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); mlxsw_sp_span_fini(mlxsw_sp); + unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -4501,10 +4517,6 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused, return notifier_from_errno(err); } -static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = { - .notifier_call = mlxsw_sp_netdevice_event, -}; - static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = { .notifier_call = mlxsw_sp_inetaddr_event, .priority = 10, /* Must be called before FIB notifier block */ @@ -4532,7 +4544,6 @@ static int __init mlxsw_sp_module_init(void) { int err; - register_netdevice_notifier(&mlxsw_sp_netdevice_nb); register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); register_netevent_notifier(&mlxsw_sp_router_netevent_nb); @@ -4553,7 +4564,6 @@ static int __init mlxsw_sp_module_init(void) unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); - unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); return err; } @@ -4564,7 +4574,6 @@ static void __exit mlxsw_sp_module_exit(void) unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); - unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); } module_init(mlxsw_sp_module_init); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 8e45183dc9bbb..e1a0157c0b94f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -161,6 +161,7 @@ struct mlxsw_sp { struct { DECLARE_BITMAP(usage, MLXSW_SP_KVD_LINEAR_SIZE); } kvdl; + struct notifier_block netdevice_nb; struct mlxsw_sp_counter_pool *counter_pool; struct { -- GitLab From 6698c168bf48cb85505d7f6e77f0091a83aa497e Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Oct 2017 16:26:36 +0200 Subject: [PATCH 1417/1507] mlxsw: spectrum_router: Move mlxsw_sp_netdev_ipip_type() Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_router.c | 38 +++++++++---------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 6a356f4b99a35..c5e574bf3e08d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1295,6 +1295,25 @@ mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, return NULL; } +static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev, + enum mlxsw_sp_ipip_type *p_type) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + const struct mlxsw_sp_ipip_ops *ipip_ops; + enum mlxsw_sp_ipip_type ipipt; + + for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) { + ipip_ops = router->ipip_ops_arr[ipipt]; + if (dev->type == ipip_ops->dev_type) { + if (p_type) + *p_type = ipipt; + return true; + } + } + return false; +} + struct mlxsw_sp_neigh_key { struct neighbour *n; }; @@ -2785,25 +2804,6 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, neigh_release(n); } -static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev, - enum mlxsw_sp_ipip_type *p_type) -{ - struct mlxsw_sp_router *router = mlxsw_sp->router; - const struct mlxsw_sp_ipip_ops *ipip_ops; - enum mlxsw_sp_ipip_type ipipt; - - for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) { - ipip_ops = router->ipip_ops_arr[ipipt]; - if (dev->type == ipip_ops->dev_type) { - if (p_type) - *p_type = ipipt; - return true; - } - } - return false; -} - static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, enum mlxsw_sp_ipip_type ipipt, struct mlxsw_sp_nexthop *nh, -- GitLab From 0063587d358733008423c80302cb7b077be8e237 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Oct 2017 16:26:37 +0200 Subject: [PATCH 1418/1507] mlxsw: spectrum: Support decap-only IP-in-IP tunnels Current code for offloading IP-in-IP tunneling assumes that there is no decap without encap. But that's never true for IPv6 overlays, and is not true for IPv4 ones either, if net.ipv4.conf.*.rp_filter is unset. To support decap-only tunnels, an IPIP entry is now created as soon as an offloadable tunneling device is created. When that netdevice is up'd, a decap route is looked up and possibly offloaded. Thus decap is not handled implicitly as part of mlxsw_sp_ipip_entry_get() call anymore, but needs to be done explicitly after the get, if desired. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 8 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 6 + .../ethernet/mellanox/mlxsw/spectrum_router.c | 105 ++++++++++++++++-- 3 files changed, 109 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 83f9c2564f617..c3ae650fbe5e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4497,13 +4497,17 @@ static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr) return netif_is_l3_master(info->upper_dev); } -static int mlxsw_sp_netdevice_event(struct notifier_block *unused, +static int mlxsw_sp_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct mlxsw_sp *mlxsw_sp; int err = 0; - if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) + mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb); + if (mlxsw_sp_netdev_is_ipip(mlxsw_sp, dev)) + err = mlxsw_sp_netdevice_ipip_event(mlxsw_sp, dev, event); + else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) err = mlxsw_sp_netdevice_router_port_event(dev); else if (mlxsw_sp_is_vrf_event(event, ptr)) err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index e1a0157c0b94f..a4f21afd7f00e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -395,6 +395,12 @@ int mlxsw_sp_inet6addr_event(struct notifier_block *unused, unsigned long event, void *ptr); int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, struct netdev_notifier_changeupper_info *info); +bool mlxsw_sp_netdev_is_ipip(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); +int +mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *l3_dev, + unsigned long event); void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c5e574bf3e08d..db834220a2fe2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1206,7 +1206,6 @@ mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, { u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); struct mlxsw_sp_router *router = mlxsw_sp->router; - struct mlxsw_sp_fib_entry *decap_fib_entry; struct mlxsw_sp_ipip_entry *ipip_entry; enum mlxsw_sp_l3proto ul_proto; union mlxsw_sp_l3addr saddr; @@ -1231,11 +1230,6 @@ mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, if (IS_ERR(ipip_entry)) return ipip_entry; - decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, ipip_entry); - if (decap_fib_entry) - mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, - decap_fib_entry); - list_add_tail(&ipip_entry->ipip_list_node, &mlxsw_sp->router->ipip_list); @@ -1250,8 +1244,6 @@ mlxsw_sp_ipip_entry_put(struct mlxsw_sp *mlxsw_sp, { if (--ipip_entry->ref_count == 0) { list_del(&ipip_entry->ipip_list_node); - if (ipip_entry->decap_fib_entry) - mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); mlxsw_sp_ipip_entry_destroy(ipip_entry); } } @@ -1314,6 +1306,103 @@ static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, return false; } +bool mlxsw_sp_netdev_is_ipip(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + return mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL); +} + +static struct mlxsw_sp_ipip_entry * +mlxsw_sp_ipip_entry_find_by_ol_dev(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, + ipip_list_node) + if (ipip_entry->ol_dev == ol_dev) + return ipip_entry; + + return NULL; +} + +static int mlxsw_sp_netdevice_ipip_reg_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct mlxsw_sp_ipip_entry *ipip_entry; + enum mlxsw_sp_ipip_type ipipt; + + mlxsw_sp_netdev_ipip_type(mlxsw_sp, ol_dev, &ipipt); + if (router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, ol_dev, + MLXSW_SP_L3_PROTO_IPV4) || + router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, ol_dev, + MLXSW_SP_L3_PROTO_IPV6)) { + ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev); + if (IS_ERR(ipip_entry)) + return PTR_ERR(ipip_entry); + } + + return 0; +} + +static void mlxsw_sp_netdevice_ipip_unreg_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry) + mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry); +} + +static int mlxsw_sp_netdevice_ipip_up_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry) { + decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, + ipip_entry); + if (decap_fib_entry) + mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, + decap_fib_entry); + } + + return 0; +} + +static void mlxsw_sp_netdevice_ipip_down_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (ipip_entry && ipip_entry->decap_fib_entry) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); +} + +int mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev, + unsigned long event) +{ + switch (event) { + case NETDEV_REGISTER: + return mlxsw_sp_netdevice_ipip_reg_event(mlxsw_sp, ol_dev); + case NETDEV_UNREGISTER: + mlxsw_sp_netdevice_ipip_unreg_event(mlxsw_sp, ol_dev); + return 0; + case NETDEV_UP: + return mlxsw_sp_netdevice_ipip_up_event(mlxsw_sp, ol_dev); + case NETDEV_DOWN: + mlxsw_sp_netdevice_ipip_down_event(mlxsw_sp, ol_dev); + return 0; + } + return 0; +} + struct mlxsw_sp_neigh_key { struct neighbour *n; }; -- GitLab From f63ce4e54a424d9f99bad2ba099c972a07eab517 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Oct 2017 16:26:38 +0200 Subject: [PATCH 1419/1507] mlxsw: spectrum: Support IPIP overlay VRF migration IPIP entries are created as soon as an offloadable device is created. That means that when such a device is later moved to a different VRF, the loopback device that backs the tunnel is wrong. Thus when an offloadable encapsulating netdevice moves from one VRF to another, make sure that the loopback is updated as necessary. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- .../net/ethernet/mellanox/mlxsw/spectrum.h | 3 +- .../ethernet/mellanox/mlxsw/spectrum_router.c | 47 ++++++++++++++++++- 3 files changed, 49 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c3ae650fbe5e9..e1e11c726c16a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4506,7 +4506,7 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb, mlxsw_sp = container_of(nb, struct mlxsw_sp, netdevice_nb); if (mlxsw_sp_netdev_is_ipip(mlxsw_sp, dev)) - err = mlxsw_sp_netdevice_ipip_event(mlxsw_sp, dev, event); + err = mlxsw_sp_netdevice_ipip_event(mlxsw_sp, dev, event, ptr); else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU) err = mlxsw_sp_netdevice_router_port_event(dev); else if (mlxsw_sp_is_vrf_event(event, ptr)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a4f21afd7f00e..28feb745a38a5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -400,7 +400,8 @@ bool mlxsw_sp_netdev_is_ipip(const struct mlxsw_sp *mlxsw_sp, int mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, - unsigned long event); + unsigned long event, + struct netdev_notifier_changeupper_info *info); void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index db834220a2fe2..082cf00eaadb8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1384,9 +1384,49 @@ static void mlxsw_sp_netdevice_ipip_down_event(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); } +static int mlxsw_sp_netdevice_ipip_vrf_event(struct mlxsw_sp *mlxsw_sp, + struct net_device *ol_dev) +{ + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + struct mlxsw_sp_rif_ipip_lb *lb_rif; + + ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (!ipip_entry) + return 0; + + /* When a tunneling device is moved to a different VRF, we need to + * update the backing loopback. Since RIFs can't be edited, we need to + * destroy and recreate it. That might create a window of opportunity + * where RALUE and RATR registers end up referencing a RIF that's + * already gone. RATRs are handled by the RIF destroy, and to take care + * of RALUE, demote the decap route back. + */ + if (ipip_entry->decap_fib_entry) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); + + lb_rif = mlxsw_sp_ipip_ol_ipip_lb_create(mlxsw_sp, ipip_entry->ipipt, + ol_dev); + if (IS_ERR(lb_rif)) + return PTR_ERR(lb_rif); + mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); + ipip_entry->ol_lb = lb_rif; + + if (ol_dev->flags & IFF_UP) { + decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, + ipip_entry); + if (decap_fib_entry) + mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, + decap_fib_entry); + } + + return 0; +} + int mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, struct net_device *ol_dev, - unsigned long event) + unsigned long event, + struct netdev_notifier_changeupper_info *info) { switch (event) { case NETDEV_REGISTER: @@ -1399,6 +1439,11 @@ int mlxsw_sp_netdevice_ipip_event(struct mlxsw_sp *mlxsw_sp, case NETDEV_DOWN: mlxsw_sp_netdevice_ipip_down_event(mlxsw_sp, ol_dev); return 0; + case NETDEV_CHANGEUPPER: + if (netif_is_l3_master(info->upper_dev)) + return mlxsw_sp_netdevice_ipip_vrf_event(mlxsw_sp, + ol_dev); + return 0; } return 0; } -- GitLab From 4cccb737d2fd0d78b939a97b5ac1831b9a27d4c0 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 16 Oct 2017 16:26:39 +0200 Subject: [PATCH 1420/1507] mlxsw: spectrum: Drop refcounting of IPIP entries Formerly, IPIP entries were created lazily by next hops that referenced an offloadable IP-in-IP netdevice. However now that they are created eagerly as a reaction to events on such netdevices, the reference counting is useless. Hence drop it. The routes whose next hops reference an offloaded IP-in-IP netdevice actually linger around a bit after their device is unregistered. However, mlxsw_sp_ipip_entry_destroy() also destroys the backing loopback, and mlxsw_sp_rif_destroy() transitively (via mlxsw_sp_nexthop_rif_gone_sync()) calls mlxsw_sp_nexthop_ipip_fini(), which unlinks the IPIP entry from a next hop. Thus no dangling pointers are left behind for the brief window after netdevice is gone, but routes not yet. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_ipip.h | 1 - .../ethernet/mellanox/mlxsw/spectrum_router.c | 49 ++++++++----------- 2 files changed, 20 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index 1c2db831d83b1..6fb49129ce878 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -47,7 +47,6 @@ struct mlxsw_sp_ipip_entry { enum mlxsw_sp_ipip_type ipipt; struct net_device *ol_dev; /* Overlay. */ struct mlxsw_sp_rif_ipip_lb *ol_lb; - unsigned int ref_count; /* Number of next hops using the tunnel. */ struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 082cf00eaadb8..3330120f2f8e2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1002,9 +1002,8 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, } static void -mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp_ipip_entry *ipip_entry) { - WARN_ON(ipip_entry->ref_count > 0); mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); kfree(ipip_entry); } @@ -1200,9 +1199,9 @@ mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp, } static struct mlxsw_sp_ipip_entry * -mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_ipip_type ipipt, - struct net_device *ol_dev) +mlxsw_sp_ipip_entry_create(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct net_device *ol_dev) { u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); struct mlxsw_sp_router *router = mlxsw_sp->router; @@ -1210,15 +1209,12 @@ mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, enum mlxsw_sp_l3proto ul_proto; union mlxsw_sp_l3addr saddr; + /* The configuration where several tunnels have the same local address + * in the same underlay table needs special treatment in the HW. That is + * currently not implemented in the driver. + */ list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, ipip_list_node) { - if (ipip_entry->ol_dev == ol_dev) - goto inc_ref_count; - - /* The configuration where several tunnels have the same local - * address in the same underlay table needs special treatment in - * the HW. That is currently not implemented in the driver. - */ ul_proto = router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); if (mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, saddr, @@ -1233,19 +1229,15 @@ mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, list_add_tail(&ipip_entry->ipip_list_node, &mlxsw_sp->router->ipip_list); -inc_ref_count: - ++ipip_entry->ref_count; return ipip_entry; } static void -mlxsw_sp_ipip_entry_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry) +mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) { - if (--ipip_entry->ref_count == 0) { - list_del(&ipip_entry->ipip_list_node); - mlxsw_sp_ipip_entry_destroy(ipip_entry); - } + list_del(&ipip_entry->ipip_list_node); + mlxsw_sp_ipip_entry_dealloc(ipip_entry); } static bool @@ -1338,7 +1330,8 @@ static int mlxsw_sp_netdevice_ipip_reg_event(struct mlxsw_sp *mlxsw_sp, MLXSW_SP_L3_PROTO_IPV4) || router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, ol_dev, MLXSW_SP_L3_PROTO_IPV6)) { - ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev); + ipip_entry = mlxsw_sp_ipip_entry_create(mlxsw_sp, ipipt, + ol_dev); if (IS_ERR(ipip_entry)) return PTR_ERR(ipip_entry); } @@ -1353,7 +1346,7 @@ static void mlxsw_sp_netdevice_ipip_unreg_event(struct mlxsw_sp *mlxsw_sp, ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); if (ipip_entry) - mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry); + mlxsw_sp_ipip_entry_destroy(mlxsw_sp, ipip_entry); } static int mlxsw_sp_netdevice_ipip_up_event(struct mlxsw_sp *mlxsw_sp, @@ -2939,16 +2932,15 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_ipip_type ipipt, struct mlxsw_sp_nexthop *nh, struct net_device *ol_dev) { if (!nh->nh_grp->gateway || nh->ipip_entry) return 0; - nh->ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev); - if (IS_ERR(nh->ipip_entry)) - return PTR_ERR(nh->ipip_entry); + nh->ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); + if (!nh->ipip_entry) + return -ENOENT; __mlxsw_sp_nexthop_neigh_update(nh, false); return 0; @@ -2963,7 +2955,6 @@ static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp, return; __mlxsw_sp_nexthop_neigh_update(nh, true); - mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry); nh->ipip_entry = NULL; } @@ -3007,7 +2998,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV4)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev); if (err) return err; mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); @@ -4269,7 +4260,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, MLXSW_SP_L3_PROTO_IPV6)) { nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; - err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + err = mlxsw_sp_nexthop_ipip_init(mlxsw_sp, nh, dev); if (err) return err; mlxsw_sp_nexthop_rif_init(nh, &nh->ipip_entry->ol_lb->common); -- GitLab From 8a5f2166a6288ee4b5a393f1ebc8cfb26b0510f0 Mon Sep 17 00:00:00 2001 From: Henrik Austad Date: Tue, 17 Oct 2017 12:10:10 +0200 Subject: [PATCH 1421/1507] net: export netdev_txq_to_tc to allow sch_mqprio to compile as module In commit 32302902ff09 ("mqprio: Reserve last 32 classid values for HW traffic classes and misc IDs") sch_mqprio started using netdev_txq_to_tc to find the correct tc instead of dev->tc_to_txq[] However, when mqprio is compiled as a module, it cannot resolve the symbol, leading to this error: ERROR: "netdev_txq_to_tc" [net/sched/sch_mqprio.ko] undefined! This adds an EXPORT_SYMBOL() since the other user in the kernel (netif_set_xps_queue) is also EXPORT_SYMBOL() (and not _GPL) or in a sysfs-callback. Cc: Alexander Duyck Cc: Jesus Sanchez-Palencia Cc: David S. Miller Signed-off-by: Henrik Austad Reviewed-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/dev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/dev.c b/net/core/dev.c index fcddccb6be41e..d2b20e73080e8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2040,6 +2040,7 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) return 0; } +EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static DEFINE_MUTEX(xps_map_mutex); -- GitLab From 4b70c62b9eafcee0505b440732d2e00c50f3085d Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Fri, 13 Oct 2017 12:16:38 +0800 Subject: [PATCH 1422/1507] net: ftgmac100: Request clock and set speed According to the ASPEED datasheet, gigabit speeds require a clock of 100MHz or higher. Other speeds require 25MHz or higher. This patch configures a 100MHz clock if the system has a direct-attached PHY, or 25MHz if the system is running NC-SI which is limited to 100MHz. There appear to be no other upstream users of the FTGMAC100 driver it is hard to know the clocking requirements of other platforms. Therefore a conservative approach was taken with enabling clocks. If the platform is not ASPEED, both requesting the clock and configuring the speed is skipped. Signed-off-by: Joel Stanley Tested-by: Andrew Jeffery Signed-off-by: David S. Miller --- drivers/net/ethernet/faraday/ftgmac100.c | 26 ++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 9ed8e4b815304..78db8e62a83f1 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -21,6 +21,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -59,6 +60,9 @@ /* Min number of tx ring entries before stopping queue */ #define TX_THRESHOLD (MAX_SKB_FRAGS + 1) +#define FTGMAC_100MHZ 100000000 +#define FTGMAC_25MHZ 25000000 + struct ftgmac100 { /* Registers */ struct resource *res; @@ -96,6 +100,7 @@ struct ftgmac100 { struct napi_struct napi; struct work_struct reset_task; struct mii_bus *mii_bus; + struct clk *clk; /* Link management */ int cur_speed; @@ -1734,6 +1739,22 @@ static void ftgmac100_ncsi_handler(struct ncsi_dev *nd) nd->link_up ? "up" : "down"); } +static void ftgmac100_setup_clk(struct ftgmac100 *priv) +{ + priv->clk = devm_clk_get(priv->dev, NULL); + if (IS_ERR(priv->clk)) + return; + + clk_prepare_enable(priv->clk); + + /* Aspeed specifies a 100MHz clock is required for up to + * 1000Mbit link speeds. As NCSI is limited to 100Mbit, 25MHz + * is sufficient + */ + clk_set_rate(priv->clk, priv->use_ncsi ? FTGMAC_25MHZ : + FTGMAC_100MHZ); +} + static int ftgmac100_probe(struct platform_device *pdev) { struct resource *res; @@ -1830,6 +1851,9 @@ static int ftgmac100_probe(struct platform_device *pdev) goto err_setup_mdio; } + if (priv->is_aspeed) + ftgmac100_setup_clk(priv); + /* Default ring sizes */ priv->rx_q_entries = priv->new_rx_q_entries = DEF_RX_QUEUE_ENTRIES; priv->tx_q_entries = priv->new_tx_q_entries = DEF_TX_QUEUE_ENTRIES; @@ -1883,6 +1907,8 @@ static int ftgmac100_remove(struct platform_device *pdev) unregister_netdev(netdev); + clk_disable_unprepare(priv->clk); + /* There's a small chance the reset task will have been re-queued, * during stop, make sure it's gone before we free the structure. */ -- GitLab From 6710e1126934d8b4372b4d2f9ae1646cd3f151bf Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:28 +0200 Subject: [PATCH 1423/1507] bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP The 'cpumap' is primarily used as a backend map for XDP BPF helper call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. This patch implement the main part of the map. It is not connected to the XDP redirect system yet, and no SKB allocation are done yet. The main concern in this patch is to ensure the datapath can run without any locking. This adds complexity to the setup and tear-down procedure, which assumptions are extra carefully documented in the code comments. V2: - make sure array isn't larger than NR_CPUS - make sure CPUs added is a valid possible CPU V3: fix nitpicks from Jakub Kicinski V5: - Restrict map allocation to root / CAP_SYS_ADMIN - WARN_ON_ONCE if queue is not empty on tear-down - Return -EPERM on memlock limit instead of -ENOMEM - Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup() - Moved cpu_map_enqueue() to next patch V6: all notice by Daniel Borkmann - Fix err return code in cpu_map_alloc() introduced in V5 - Move cpu_possible() check after max_entries boundary check - Forbid usage initially in check_map_func_compatibility() V7: - Fix alloc error path spotted by Daniel Borkmann - Did stress test adding+removing CPUs from the map concurrently - Fixed refcnt issue on cpu_map_entry, kthread started too soon - Make sure packets are flushed during tear-down, involved use of rcu_barrier() and kthread_run only exit after queue is empty - Fix alloc error path in __cpu_map_entry_alloc() for ptr_ring V8: - Nitpicking comments and gramma by Edward Cree - Fix missing semi-colon introduced in V7 due to rebasing - Move struct bpf_cpu_map_entry members cpu+map_id to tracepoint patch Signed-off-by: Jesper Dangaard Brouer Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/cpumap.c | 560 +++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 8 +- kernel/bpf/verifier.c | 5 + tools/include/uapi/linux/bpf.h | 1 + 7 files changed, 576 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/cpumap.c diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 6f1a567667b8b..814c1081a4a98 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6db9e1d679cd3..4303fb6c38171 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 53fb09f92e3fc..e597daae61201 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += cpumap.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c new file mode 100644 index 0000000000000..e1e25ddba038d --- /dev/null +++ b/kernel/bpf/cpumap.c @@ -0,0 +1,560 @@ +/* bpf/cpumap.c + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ + +/* The 'cpumap' is primarily used as a backend map for XDP BPF helper + * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. + * + * Unlike devmap which redirects XDP frames out another NIC device, + * this map type redirects raw XDP frames to another CPU. The remote + * CPU will do SKB-allocation and call the normal network stack. + * + * This is a scalability and isolation mechanism, that allow + * separating the early driver network XDP layer, from the rest of the + * netstack, and assigning dedicated CPUs for this stage. This + * basically allows for 10G wirespeed pre-filtering via bpf. + */ +#include +#include +#include + +#include +#include +#include +#include + +/* General idea: XDP packets getting XDP redirected to another CPU, + * will maximum be stored/queued for one driver ->poll() call. It is + * guaranteed that setting flush bit and flush operation happen on + * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() + * which queue in bpf_cpu_map_entry contains packets. + */ + +#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct xdp_bulk_queue { + void *q[CPU_MAP_BULK_SIZE]; + unsigned int count; +}; + +/* Struct for every remote "destination" CPU in map */ +struct bpf_cpu_map_entry { + u32 qsize; /* Queue size placeholder for map lookup */ + + /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ + struct xdp_bulk_queue __percpu *bulkq; + + /* Queue with potential multi-producers, and single-consumer kthread */ + struct ptr_ring *queue; + struct task_struct *kthread; + struct work_struct kthread_stop_wq; + + atomic_t refcnt; /* Control when this struct can be free'ed */ + struct rcu_head rcu; +}; + +struct bpf_cpu_map { + struct bpf_map map; + /* Below members specific for map type */ + struct bpf_cpu_map_entry **cpu_map; + unsigned long __percpu *flush_needed; +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq); + +static u64 cpu_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) +{ + struct bpf_cpu_map *cmap; + int err = -ENOMEM; + u64 cost; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + cmap = kzalloc(sizeof(*cmap), GFP_USER); + if (!cmap) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + cmap->map.map_type = attr->map_type; + cmap->map.key_size = attr->key_size; + cmap->map.value_size = attr->value_size; + cmap->map.max_entries = attr->max_entries; + cmap->map.map_flags = attr->map_flags; + cmap->map.numa_node = bpf_map_attr_numa_node(attr); + + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (cmap->map.max_entries > NR_CPUS) { + err = -E2BIG; + goto free_cmap; + } + + /* make sure page count doesn't overflow */ + cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); + cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_cmap; + cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + ret = bpf_map_precharge_memlock(cmap->map.pages); + if (ret) { + err = ret; + goto free_cmap; + } + + /* A per cpu bitfield with a bit per possible CPU in map */ + cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!cmap->flush_needed) + goto free_cmap; + + /* Alloc array for possible remote "destination" CPUs */ + cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * + sizeof(struct bpf_cpu_map_entry *), + cmap->map.numa_node); + if (!cmap->cpu_map) + goto free_percpu; + + return &cmap->map; +free_percpu: + free_percpu(cmap->flush_needed); +free_cmap: + kfree(cmap); + return ERR_PTR(err); +} + +void __cpu_map_queue_destructor(void *ptr) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + if (WARN_ON_ONCE(ptr)) + page_frag_free(ptr); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); + kfree(rcpu->queue); + kfree(rcpu); + } +} + +static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + atomic_inc(&rcpu->refcnt); +} + +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + kthread_stop(rcpu->kthread); +} + +static int cpu_map_kthread_run(void *data) +{ + struct bpf_cpu_map_entry *rcpu = data; + + set_current_state(TASK_INTERRUPTIBLE); + + /* When kthread gives stop order, then rcpu have been disconnected + * from map, thus no new packets can enter. Remaining in-flight + * per CPU stored packets are flushed to this queue. Wait honoring + * kthread_stop signal until queue is empty. + */ + while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + struct xdp_pkt *xdp_pkt; + + schedule(); + /* Do work */ + while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) { + /* For now just "refcnt-free" */ + page_frag_free(xdp_pkt); + } + __set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + put_cpu_map_entry(rcpu); + return 0; +} + +struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +{ + gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + struct bpf_cpu_map_entry *rcpu; + int numa, err; + + /* Have map->numa_node, but choose node of redirect target CPU */ + numa = cpu_to_node(cpu); + + rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + if (!rcpu) + return NULL; + + /* Alloc percpu bulkq */ + rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), + sizeof(void *), gfp); + if (!rcpu->bulkq) + goto free_rcu; + + /* Alloc queue */ + rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + if (!rcpu->queue) + goto free_bulkq; + + err = ptr_ring_init(rcpu->queue, qsize, gfp); + if (err) + goto free_queue; + + rcpu->qsize = qsize; + + /* Setup kthread */ + rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, + "cpumap/%d/map:%d", cpu, map_id); + if (IS_ERR(rcpu->kthread)) + goto free_ptr_ring; + + get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ + get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + + /* Make sure kthread runs on a single CPU */ + kthread_bind(rcpu->kthread, cpu); + wake_up_process(rcpu->kthread); + + return rcpu; + +free_ptr_ring: + ptr_ring_cleanup(rcpu->queue, NULL); +free_queue: + kfree(rcpu->queue); +free_bulkq: + free_percpu(rcpu->bulkq); +free_rcu: + kfree(rcpu); + return NULL; +} + +void __cpu_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_cpu_map_entry *rcpu; + int cpu; + + /* This cpu_map_entry have been disconnected from map and one + * RCU graze-period have elapsed. Thus, XDP cannot queue any + * new packets and cannot change/set flush_needed that can + * find this entry. + */ + rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + + /* Flush remaining packets in percpu bulkq */ + for_each_online_cpu(cpu) { + struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); + + /* No concurrent bq_enqueue can run at this point */ + bq_flush_to_queue(rcpu, bq); + } + free_percpu(rcpu->bulkq); + /* Cannot kthread_stop() here, last put free rcpu resources */ + put_cpu_map_entry(rcpu); +} + +/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to + * ensure any driver rcu critical sections have completed, but this + * does not guarantee a flush has happened yet. Because driver side + * rcu_read_lock/unlock only protects the running XDP program. The + * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a + * pending flush op doesn't fail. + * + * The bpf_cpu_map_entry is still used by the kthread, and there can + * still be pending packets (in queue and percpu bulkq). A refcnt + * makes sure to last user (kthread_stop vs. call_rcu) free memory + * resources. + * + * The rcu callback __cpu_map_entry_free flush remaining packets in + * percpu bulkq to queue. Due to caller map_delete_elem() disable + * preemption, cannot call kthread_stop() to make sure queue is empty. + * Instead a work_queue is started for stopping kthread, + * cpu_map_kthread_stop, which waits for an RCU graze period before + * stopping kthread, emptying the queue. + */ +void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +{ + struct bpf_cpu_map_entry *old_rcpu; + + old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + if (old_rcpu) { + call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); + INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); + schedule_work(&old_rcpu->kthread_stop_wq); + } +} + +int cpu_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 key_cpu = *(u32 *)key; + + if (key_cpu >= map->max_entries) + return -EINVAL; + + /* notice caller map_delete_elem() use preempt_disable() */ + __cpu_map_entry_replace(cmap, key_cpu, NULL); + return 0; +} + +int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + /* Array index key correspond to CPU number */ + u32 key_cpu = *(u32 *)key; + /* Value is the queue size */ + u32 qsize = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(key_cpu >= cmap->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + return -EOVERFLOW; + + /* Make sure CPU is a valid possible cpu */ + if (!cpu_possible(key_cpu)) + return -ENODEV; + + if (qsize == 0) { + rcpu = NULL; /* Same as deleting */ + } else { + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + if (!rcpu) + return -ENOMEM; + } + rcu_read_lock(); + __cpu_map_entry_replace(cmap, key_cpu, rcpu); + rcu_read_unlock(); + return 0; +} + +void cpu_map_free(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + int cpu; + u32 i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the bpf programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. + * It does __not__ ensure pending flush operations (if any) are + * complete. + */ + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + + while (!bitmap_empty(bitmap, cmap->map.max_entries)) + cond_resched(); + } + + /* For cpu_map the remote CPUs can still be using the entries + * (struct bpf_cpu_map_entry). + */ + for (i = 0; i < cmap->map.max_entries; i++) { + struct bpf_cpu_map_entry *rcpu; + + rcpu = READ_ONCE(cmap->cpu_map[i]); + if (!rcpu) + continue; + + /* bq flush and cleanup happens after RCU graze-period */ + __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + } + free_percpu(cmap->flush_needed); + bpf_map_area_free(cmap->cpu_map); + kfree(cmap); +} + +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + if (key >= map->max_entries) + return NULL; + + rcpu = READ_ONCE(cmap->cpu_map[key]); + return rcpu; +} + +static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map_entry *rcpu = + __cpu_map_lookup_elem(map, *(u32 *)key); + + return rcpu ? &rcpu->qsize : NULL; +} + +static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= cmap->map.max_entries) { + *next = 0; + return 0; + } + + if (index == cmap->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +const struct bpf_map_ops cpu_map_ops = { + .map_alloc = cpu_map_alloc, + .map_free = cpu_map_free, + .map_delete_elem = cpu_map_delete_elem, + .map_update_elem = cpu_map_update_elem, + .map_lookup_elem = cpu_map_lookup_elem, + .map_get_next_key = cpu_map_get_next_key, +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq) +{ + struct ptr_ring *q; + int i; + + if (unlikely(!bq->count)) + return 0; + + q = rcpu->queue; + spin_lock(&q->producer_lock); + + for (i = 0; i < bq->count; i++) { + void *xdp_pkt = bq->q[i]; + int err; + + err = __ptr_ring_produce(q, xdp_pkt); + if (err) { + /* Free xdp_pkt */ + page_frag_free(xdp_pkt); + } + } + bq->count = 0; + spin_unlock(&q->producer_lock); + + return 0; +} + +/* Notice: Will change in later patch */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; +}; + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + + if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) + bq_flush_to_queue(rcpu, bq); + + /* Notice, xdp_buff/page MUST be queued here, long enough for + * driver to code invoking us to finished, due to driver + * (e.g. ixgbe) recycle tricks based on page-refcnt. + * + * Thus, incoming xdp_pkt is always queued here (else we race + * with another CPU on page-refcnt and remaining driver code). + * Queue time is very short, as driver will invoke flush + * operation, when completing napi->poll call. + */ + bq->q[bq->count++] = xdp_pkt; + return 0; +} + +void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + + __set_bit(bit, bitmap); +} + +void __cpu_map_flush(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + u32 bit; + + /* The napi->poll softirq makes sure __cpu_map_insert_ctx() + * and __cpu_map_flush() happen on same CPU. Thus, the percpu + * bitmap indicate which percpu bulkq have packets. + */ + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); + struct xdp_bulk_queue *bq; + + /* This is possible if entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!rcpu)) + continue; + + __clear_bit(bit, bitmap); + + /* Flush all frames in bulkq to real queue */ + bq = this_cpu_ptr(rcpu->bulkq); + bq_flush_to_queue(rcpu, bq); + + /* If already running, costs spin_lock_irqsave + smb_mb */ + wake_up_process(rcpu->kthread); + } +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d124e702e040e..54fba06942f5e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -592,6 +592,12 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* Need to create a kthread, thus must support schedule */ + if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + err = map->ops->map_update_elem(map, key, value, attr->flags); + goto out; + } + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ @@ -622,7 +628,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_update_elem(map, ufd, key, value); free_value: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9755279d94cb8..cefa64be9a2fc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1444,6 +1444,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; + /* Restrict bpf side of cpumap, open when use-cases appear */ + case BPF_MAP_TYPE_CPUMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fb4fb81ce5b03..fa93033dc521e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { -- GitLab From 9c270af37bb62e708e3e4415d653ce73e713df02 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:34 +0200 Subject: [PATCH 1424/1507] bpf: XDP_REDIRECT enable use of cpumap This patch connects cpumap to the xdp_do_redirect_map infrastructure. Still no SKB allocation are done yet. The XDP frames are transferred to the other CPU, but they are simply refcnt decremented on the remote CPU. This served as a good benchmark for measuring the overhead of remote refcnt decrement. If driver page recycle cache is not efficient then this, exposes a bottleneck in the page allocator. A shout-out to MST's ptr_ring, which is the secret behind is being so efficient to transfer memory pointers between CPUs, without constantly bouncing cache-lines between CPUs. V3: Handle !CONFIG_BPF_SYSCALL pointed out by kbuild test robot. V4: Make Generic-XDP aware of cpumap type, but don't allow redirect yet, as implementation require a separate upstream discussion. V5: - Fix a maybe-uninitialized pointed out by kbuild test robot. - Restrict bpf-prog side access to cpumap, open when use-cases appear - Implement cpu_map_enqueue() as a more simple void pointer enqueue V6: - Allow cpumap type for usage in helper bpf_redirect_map, general bpf-prog side restriction moved to earlier patch. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/bpf.h | 31 +++++++- include/trace/events/xdp.h | 10 ++- kernel/bpf/cpumap.c | 22 +++++- kernel/bpf/verifier.c | 3 +- net/core/filter.c | 140 +++++++++++++++++++++++++++++-------- 5 files changed, 172 insertions(+), 34 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4373125de1f33..6d4dd844828a1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -355,6 +355,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key); +void __cpu_map_insert_ctx(struct bpf_map *map, u32 index); +void __cpu_map_flush(struct bpf_map *map); +struct xdp_buff; +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx); + /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { @@ -362,7 +369,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } -#else +#else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); @@ -425,6 +432,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) static inline void __dev_map_flush(struct bpf_map *map) { } + +static inline +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} + +static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __cpu_map_flush(struct bpf_map *map) +{ +} + +struct xdp_buff; +static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, + struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return 0; +} #endif /* CONFIG_BPF_SYSCALL */ #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 4e16c43fba10a..eb2ece96c1a2b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -136,12 +136,18 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err, __entry->map_id, __entry->map_index) ); +#define devmap_ifindex(fwd, map) \ + (!fwd ? 0 : \ + (!map ? 0 : \ + ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((struct net_device *)fwd)->ifindex : 0))) + #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ - trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \ + trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ 0, map, idx) #define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \ - trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \ + trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \ err, map, idx) #endif /* _TRACE_XDP_H */ diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e1e25ddba038d..768da6a2c2655 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -500,7 +500,7 @@ struct xdp_pkt { /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) { struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); @@ -520,6 +520,26 @@ int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) return 0; } +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct xdp_pkt *xdp_pkt; + int headroom; + + /* For now this is just used as a void pointer to data_hard_start. + * Followup patch will generalize this. + */ + xdp_pkt = xdp->data_hard_start; + + /* Fake writing into xdp_pkt->data to measure overhead */ + headroom = xdp->data - xdp->data_hard_start; + if (headroom < sizeof(*xdp_pkt)) + xdp_pkt->data = xdp->data; + + bq_enqueue(rcpu, xdp_pkt); + return 0; +} + void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index cefa64be9a2fc..e4d5136725a2f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1486,7 +1486,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_redirect_map: - if (map->map_type != BPF_MAP_TYPE_DEVMAP) + if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_CPUMAP) goto error; break; case BPF_FUNC_sk_redirect_map: diff --git a/net/core/filter.c b/net/core/filter.c index 140fa9f9c0f41..4d88e0665c413 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2526,10 +2526,36 @@ static int __bpf_tx_xdp(struct net_device *dev, err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); if (err) return err; - if (map) + dev->netdev_ops->ndo_xdp_flush(dev); + return 0; +} + +static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, + struct bpf_map *map, + struct xdp_buff *xdp, + u32 index) +{ + int err; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + struct net_device *dev = fwd; + + if (!dev->netdev_ops->ndo_xdp_xmit) + return -EOPNOTSUPP; + + err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + if (err) + return err; __dev_map_insert_ctx(map, index); - else - dev->netdev_ops->ndo_xdp_flush(dev); + + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + struct bpf_cpu_map_entry *rcpu = fwd; + + err = cpu_map_enqueue(rcpu, xdp, dev_rx); + if (err) + return err; + __cpu_map_insert_ctx(map, index); + } return 0; } @@ -2539,11 +2565,33 @@ void xdp_do_flush_map(void) struct bpf_map *map = ri->map_to_flush; ri->map_to_flush = NULL; - if (map) - __dev_map_flush(map); + if (map) { + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: + __dev_map_flush(map); + break; + case BPF_MAP_TYPE_CPUMAP: + __cpu_map_flush(map); + break; + default: + break; + } + } } EXPORT_SYMBOL_GPL(xdp_do_flush_map); +static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) +{ + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: + return __dev_map_lookup_elem(map, index); + case BPF_MAP_TYPE_CPUMAP: + return __cpu_map_lookup_elem(map, index); + default: + return NULL; + } +} + static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog, unsigned long aux) { @@ -2556,8 +2604,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; - struct net_device *fwd = NULL; u32 index = ri->ifindex; + void *fwd = NULL; int err; ri->ifindex = 0; @@ -2570,7 +2618,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, goto err; } - fwd = __dev_map_lookup_elem(map, index); + fwd = __xdp_map_lookup_elem(map, index); if (!fwd) { err = -EINVAL; goto err; @@ -2578,7 +2626,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, if (ri->map_to_flush && ri->map_to_flush != map) xdp_do_flush_map(); - err = __bpf_tx_xdp(fwd, map, xdp, index); + err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index); if (unlikely(err)) goto err; @@ -2620,54 +2668,88 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, } EXPORT_SYMBOL_GPL(xdp_do_redirect); -int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog) +static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) +{ + unsigned int len; + + if (unlikely(!(fwd->flags & IFF_UP))) + return -ENETDOWN; + + len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; + if (skb->len > len) + return -EMSGSIZE; + + return 0; +} + +int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; struct net_device *fwd = NULL; u32 index = ri->ifindex; - unsigned int len; int err = 0; ri->ifindex = 0; ri->map = NULL; ri->map_owner = 0; - if (map) { - if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { - err = -EFAULT; - map = NULL; - goto err; - } - fwd = __dev_map_lookup_elem(map, index); - } else { - fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) { + err = -EFAULT; + map = NULL; + goto err; } + fwd = __xdp_map_lookup_elem(map, index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } - if (unlikely(!(fwd->flags & IFF_UP))) { - err = -ENETDOWN; + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; + } else { + /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ + err = -EBADRQC; goto err; } - len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; - if (skb->len > len) { - err = -EMSGSIZE; + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + return 0; +err: + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); + return err; +} + +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + u32 index = ri->ifindex; + struct net_device *fwd; + int err = 0; + + if (ri->map) + return xdp_do_generic_redirect_map(dev, skb, xdp_prog); + + ri->ifindex = 0; + fwd = dev_get_by_index_rcu(dev_net(dev), index); + if (unlikely(!fwd)) { + err = -EINVAL; goto err; } + if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + goto err; + skb->dev = fwd; - map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index) - : _trace_xdp_redirect(dev, xdp_prog, index); + _trace_xdp_redirect(dev, xdp_prog, index); return 0; err: - map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err) - : _trace_xdp_redirect_err(dev, xdp_prog, index, err); + _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); -- GitLab From 1c601d829ab0d7ac3ac44853f83db2206afe67fc Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:39 +0200 Subject: [PATCH 1425/1507] bpf: cpumap xdp_buff to skb conversion and allocation This patch makes cpumap functional, by adding SKB allocation and invoking the network stack on the dequeuing CPU. For constructing the SKB on the remote CPU, the xdp_buff in converted into a struct xdp_pkt, and it mapped into the top headroom of the packet, to avoid allocating separate mem. For now, struct xdp_pkt is just a cpumap internal data structure, with info carried between enqueue to dequeue. If a driver doesn't have enough headroom it is simply dropped, with return code -EOVERFLOW. This will be picked up the xdp tracepoint infrastructure, to allow users to catch this. V2: take into account xdp->data_meta V4: - Drop busypoll tricks, keeping it more simple. - Skip RPS and Generic-XDP-recursive-reinjection, suggested by Alexei V5: correct RCU read protection around __netif_receive_skb_core. V6: Setting TASK_RUNNING vs TASK_INTERRUPTIBLE based on talk with Rik van Riel Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + kernel/bpf/cpumap.c | 152 ++++++++++++++++++++++++++++++++------ net/core/dev.c | 27 +++++++ 3 files changed, 158 insertions(+), 22 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 31bb3010c69b1..bf014afcb914e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3260,6 +3260,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); +int netif_receive_skb_core(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 768da6a2c2655..ee7adf4352dd4 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -25,6 +25,9 @@ #include #include +#include /* netif_receive_skb_core */ +#include /* eth_type_trans */ + /* General idea: XDP packets getting XDP redirected to another CPU, * will maximum be stored/queued for one driver ->poll() call. It is * guaranteed that setting flush bit and flush operation happen on @@ -179,6 +182,92 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } +/* For now, xdp_pkt is a cpumap internal data structure, with info + * carried between enqueue to dequeue. It is mapped into the top + * headroom of the packet, to avoid allocating separate mem. + */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; + u16 metasize; + struct net_device *dev_rx; +}; + +/* Convert xdp_buff to xdp_pkt */ +static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) +{ + struct xdp_pkt *xdp_pkt; + int metasize; + int headroom; + + /* Assure headroom is available for storing info */ + headroom = xdp->data - xdp->data_hard_start; + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if ((headroom - metasize) < sizeof(*xdp_pkt)) + return NULL; + + /* Store info in top of packet */ + xdp_pkt = xdp->data_hard_start; + + xdp_pkt->data = xdp->data; + xdp_pkt->len = xdp->data_end - xdp->data; + xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); + xdp_pkt->metasize = metasize; + + return xdp_pkt; +} + +struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, + struct xdp_pkt *xdp_pkt) +{ + unsigned int frame_size; + void *pkt_data_start; + struct sk_buff *skb; + + /* build_skb need to place skb_shared_info after SKB end, and + * also want to know the memory "truesize". Thus, need to + * know the memory frame size backing xdp_buff. + * + * XDP was designed to have PAGE_SIZE frames, but this + * assumption is not longer true with ixgbe and i40e. It + * would be preferred to set frame_size to 2048 or 4096 + * depending on the driver. + * frame_size = 2048; + * frame_len = frame_size - sizeof(*xdp_pkt); + * + * Instead, with info avail, skb_shared_info in placed after + * packet len. This, unfortunately fakes the truesize. + * Another disadvantage of this approach, the skb_shared_info + * is not at a fixed memory location, with mixed length + * packets, which is bad for cache-line hotness. + */ + frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + skb = build_skb(pkt_data_start, frame_size); + if (!skb) + return NULL; + + skb_reserve(skb, xdp_pkt->headroom); + __skb_put(skb, xdp_pkt->len); + if (xdp_pkt->metasize) + skb_metadata_set(skb, xdp_pkt->metasize); + + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + return skb; +} + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -191,15 +280,45 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + unsigned int processed = 0, drops = 0; struct xdp_pkt *xdp_pkt; - schedule(); - /* Do work */ - while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) { - /* For now just "refcnt-free" */ - page_frag_free(xdp_pkt); + /* Release CPU reschedule checks */ + if (__ptr_ring_empty(rcpu->queue)) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } else { + cond_resched(); + } + __set_current_state(TASK_RUNNING); + + /* Process packets in rcpu->queue */ + local_bh_disable(); + /* + * The bpf_cpu_map_entry is single consumer, with this + * kthread CPU pinned. Lockless access to ptr_ring + * consume side valid as no-resize allowed of queue. + */ + while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + struct sk_buff *skb; + int ret; + + skb = cpu_map_build_skb(rcpu, xdp_pkt); + if (!skb) { + page_frag_free(xdp_pkt); + continue; + } + + /* Inject into network stack */ + ret = netif_receive_skb_core(skb); + if (ret == NET_RX_DROP) + drops++; + + /* Limit BH-disable period */ + if (++processed == 8) + break; } - __set_current_state(TASK_INTERRUPTIBLE); + local_bh_enable(); /* resched point, may call do_softirq() */ } __set_current_state(TASK_RUNNING); @@ -490,13 +609,6 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, return 0; } -/* Notice: Will change in later patch */ -struct xdp_pkt { - void *data; - u16 len; - u16 headroom; -}; - /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ @@ -524,17 +636,13 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) { struct xdp_pkt *xdp_pkt; - int headroom; - /* For now this is just used as a void pointer to data_hard_start. - * Followup patch will generalize this. - */ - xdp_pkt = xdp->data_hard_start; + xdp_pkt = convert_to_xdp_pkt(xdp); + if (!xdp_pkt) + return -EOVERFLOW; - /* Fake writing into xdp_pkt->data to measure overhead */ - headroom = xdp->data - xdp->data_hard_start; - if (headroom < sizeof(*xdp_pkt)) - xdp_pkt->data = xdp->data; + /* Info needed when constructing SKB on remote CPU */ + xdp_pkt->dev_rx = dev_rx; bq_enqueue(rcpu, xdp_pkt); return 0; diff --git a/net/core/dev.c b/net/core/dev.c index d2b20e73080e8..cf5894f0e6eb4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4492,6 +4492,33 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) return ret; } +/** + * netif_receive_skb_core - special purpose version of netif_receive_skb + * @skb: buffer to process + * + * More direct receive version of netif_receive_skb(). It should + * only be used by callers that have a need to skip RPS and Generic XDP. + * Caller must also take care of handling if (page_is_)pfmemalloc. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb_core(struct sk_buff *skb) +{ + int ret; + + rcu_read_lock(); + ret = __netif_receive_skb_core(skb, false); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(netif_receive_skb_core); + static int __netif_receive_skb(struct sk_buff *skb) { int ret; -- GitLab From f9419f7bd7a5318b636a941a0214c5cdfa6f6530 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:44 +0200 Subject: [PATCH 1426/1507] bpf: cpumap add tracepoints This adds two tracepoint to the cpumap. One for the enqueue side trace_xdp_cpumap_enqueue() and one for the kthread dequeue side trace_xdp_cpumap_kthread(). To mitigate the tracepoint overhead, these are invoked during the enqueue/dequeue bulking phases, thus amortizing the cost. The obvious use-cases are for debugging and monitoring. The non-intuitive use-case is using these as a feedback loop to know the system load. One can imagine auto-scaling by reducing, adding or activating more worker CPUs on demand. V4: tracepoint remove time_limit info, instead add sched info V8: intro struct bpf_cpu_map_entry members cpu+map_id in this patch Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/trace/events/xdp.h | 70 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/cpumap.c | 24 ++++++++++--- 2 files changed, 89 insertions(+), 5 deletions(-) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index eb2ece96c1a2b..0c8dec61987e0 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -150,6 +150,76 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err, trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \ err, map, idx) +TRACE_EVENT(xdp_cpumap_kthread, + + TP_PROTO(int map_id, unsigned int processed, unsigned int drops, + int sched), + + TP_ARGS(map_id, processed, drops, sched), + + TP_STRUCT__entry( + __field(int, map_id) + __field(u32, act) + __field(int, cpu) + __field(unsigned int, drops) + __field(unsigned int, processed) + __field(int, sched) + ), + + TP_fast_assign( + __entry->map_id = map_id; + __entry->act = XDP_REDIRECT; + __entry->cpu = smp_processor_id(); + __entry->drops = drops; + __entry->processed = processed; + __entry->sched = sched; + ), + + TP_printk("kthread" + " cpu=%d map_id=%d action=%s" + " processed=%u drops=%u" + " sched=%d", + __entry->cpu, __entry->map_id, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->processed, __entry->drops, + __entry->sched) +); + +TRACE_EVENT(xdp_cpumap_enqueue, + + TP_PROTO(int map_id, unsigned int processed, unsigned int drops, + int to_cpu), + + TP_ARGS(map_id, processed, drops, to_cpu), + + TP_STRUCT__entry( + __field(int, map_id) + __field(u32, act) + __field(int, cpu) + __field(unsigned int, drops) + __field(unsigned int, processed) + __field(int, to_cpu) + ), + + TP_fast_assign( + __entry->map_id = map_id; + __entry->act = XDP_REDIRECT; + __entry->cpu = smp_processor_id(); + __entry->drops = drops; + __entry->processed = processed; + __entry->to_cpu = to_cpu; + ), + + TP_printk("enqueue" + " cpu=%d map_id=%d action=%s" + " processed=%u drops=%u" + " to_cpu=%d", + __entry->cpu, __entry->map_id, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->processed, __entry->drops, + __entry->to_cpu) +); + #endif /* _TRACE_XDP_H */ #include diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ee7adf4352dd4..b4358d84ddf19 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,6 +24,7 @@ #include #include #include +#include #include /* netif_receive_skb_core */ #include /* eth_type_trans */ @@ -43,6 +44,8 @@ struct xdp_bulk_queue { /* Struct for every remote "destination" CPU in map */ struct bpf_cpu_map_entry { + u32 cpu; /* kthread CPU and map index */ + int map_id; /* Back reference to map */ u32 qsize; /* Queue size placeholder for map lookup */ /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ @@ -280,15 +283,16 @@ static int cpu_map_kthread_run(void *data) * kthread_stop signal until queue is empty. */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { - unsigned int processed = 0, drops = 0; + unsigned int processed = 0, drops = 0, sched = 0; struct xdp_pkt *xdp_pkt; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { __set_current_state(TASK_INTERRUPTIBLE); schedule(); + sched = 1; } else { - cond_resched(); + sched = cond_resched(); } __set_current_state(TASK_RUNNING); @@ -318,6 +322,9 @@ static int cpu_map_kthread_run(void *data) if (++processed == 8) break; } + /* Feedback loop via tracepoint */ + trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched); + local_bh_enable(); /* resched point, may call do_softirq() */ } __set_current_state(TASK_RUNNING); @@ -354,7 +361,9 @@ struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) if (err) goto free_queue; - rcpu->qsize = qsize; + rcpu->cpu = cpu; + rcpu->map_id = map_id; + rcpu->qsize = qsize; /* Setup kthread */ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, @@ -584,6 +593,8 @@ const struct bpf_map_ops cpu_map_ops = { static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, struct xdp_bulk_queue *bq) { + unsigned int processed = 0, drops = 0; + const int to_cpu = rcpu->cpu; struct ptr_ring *q; int i; @@ -599,13 +610,16 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, err = __ptr_ring_produce(q, xdp_pkt); if (err) { - /* Free xdp_pkt */ - page_frag_free(xdp_pkt); + drops++; + page_frag_free(xdp_pkt); /* Free xdp_pkt */ } + processed++; } bq->count = 0; spin_unlock(&q->producer_lock); + /* Feedback loop via tracepoints */ + trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); return 0; } -- GitLab From fad3917e361b115f776563366415ffb2fc706bf1 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:49 +0200 Subject: [PATCH 1427/1507] samples/bpf: add cpumap sample program xdp_redirect_cpu This sample program show how to use cpumap and the associated tracepoints. It provides command line stats, which shows how the XDP-RX process, cpumap-enqueue and cpumap kthread dequeue is cooperating on a per CPU basis. It also utilize the xdp_exception and xdp_redirect_err transpoints to allow users quickly to identify setup issues. One issue with ixgbe driver is that the driver reset the link when loading XDP. This reset the procfs smp_affinity settings. Thus, after loading the program, these must be reconfigured. The easiest workaround it to reduce the RX-queue to e.g. two via: # ethtool --set-channels ixgbe1 combined 2 And then add CPUs above 0 and 1, like: # xdp_redirect_cpu --dev ixgbe1 --prog 2 --cpu 2 --cpu 3 --cpu 4 Another issue with ixgbe is that the page recycle mechanism is tied to the RX-ring size. And the default setting of 512 elements is too small. This is the same issue with regular devmap XDP_REDIRECT. To overcome this I've been using 1024 rx-ring size: # ethtool -G ixgbe1 rx 1024 tx 1024 V3: - whitespace cleanups - bpf tracepoint cannot access top part of struct V4: - report on kthread sched events, according to tracepoint change - report average bulk enqueue size V5: - bpf_map_lookup_elem on cpumap not allowed from bpf_prog use separate map to mark CPUs not available V6: - correct kthread sched summary output V7: - Added a --stress-mode for concurrently changing underlying cpumap Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- samples/bpf/Makefile | 4 + samples/bpf/xdp_redirect_cpu_kern.c | 609 ++++++++++++++++++++++++ samples/bpf/xdp_redirect_cpu_user.c | 697 ++++++++++++++++++++++++++++ 3 files changed, 1310 insertions(+) create mode 100644 samples/bpf/xdp_redirect_cpu_kern.c create mode 100644 samples/bpf/xdp_redirect_cpu_user.c diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 81f9fcd736b7a..3534ccfb59209 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -39,6 +39,7 @@ hostprogs-y += per_socket_stats_example hostprogs-y += load_sock_ops hostprogs-y += xdp_redirect hostprogs-y += xdp_redirect_map +hostprogs-y += xdp_redirect_cpu hostprogs-y += xdp_monitor hostprogs-y += syscall_tp @@ -84,6 +85,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o +xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o @@ -129,6 +131,7 @@ always += tcp_iw_kern.o always += tcp_clamp_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o +always += xdp_redirect_cpu_kern.o always += xdp_monitor_kern.o always += syscall_tp_kern.o @@ -169,6 +172,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf HOSTLOADLIBES_test_map_in_map += -lelf HOSTLOADLIBES_xdp_redirect += -lelf HOSTLOADLIBES_xdp_redirect_map += -lelf +HOSTLOADLIBES_xdp_redirect_cpu += -lelf HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_syscall_tp += -lelf diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c new file mode 100644 index 0000000000000..303e9e7161f31 --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_kern.c @@ -0,0 +1,609 @@ +/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP) + * + * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include "bpf_helpers.h" + +#define MAX_CPUS 12 /* WARNING - sync with _user.c */ + +/* Special map type that can XDP_REDIRECT frames to another CPU */ +struct bpf_map_def SEC("maps") cpu_map = { + .type = BPF_MAP_TYPE_CPUMAP, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; + +/* Common stats data record to keep userspace more simple */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; + +/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success + * feedback. Redirect TX errors can be caught via a tracepoint. + */ +struct bpf_map_def SEC("maps") rx_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") redirect_err_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 2, + /* TODO: have entries for all possible errno's */ +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = MAX_CPUS, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") cpumap_kthread_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Set of maps controlling available CPU, and for iterating through + * selectable redirect CPUs. + */ +struct bpf_map_def SEC("maps") cpus_available = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = MAX_CPUS, +}; +struct bpf_map_def SEC("maps") cpus_count = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; +struct bpf_map_def SEC("maps") cpus_iterator = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(u32), + .max_entries = 1, +}; + +/* Used by trace point */ +struct bpf_map_def SEC("maps") exception_cnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(u32), + .value_size = sizeof(struct datarec), + .max_entries = 1, +}; + +/* Helper parse functions */ + +/* Parse Ethernet layer 2, extract network layer 3 offset and protocol + * + * Returns false on error and non-supported ether-type + */ +struct vlan_hdr { + __be16 h_vlan_TCI; + __be16 h_vlan_encapsulated_proto; +}; + +static __always_inline +bool parse_eth(struct ethhdr *eth, void *data_end, + u16 *eth_proto, u64 *l3_offset) +{ + u16 eth_type; + u64 offset; + + offset = sizeof(*eth); + if ((void *)eth + offset > data_end) + return false; + + eth_type = eth->h_proto; + + /* Skip non 802.3 Ethertypes */ + if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN)) + return false; + + /* Handle VLAN tagged packet */ + if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) { + struct vlan_hdr *vlan_hdr; + + vlan_hdr = (void *)eth + offset; + offset += sizeof(*vlan_hdr); + if ((void *)eth + offset > data_end) + return false; + eth_type = vlan_hdr->h_vlan_encapsulated_proto; + } + /* TODO: Handle double VLAN tagged packet */ + + *eth_proto = ntohs(eth_type); + *l3_offset = offset; + return true; +} + +static __always_inline +u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + struct udphdr *udph; + u16 dport; + + if (iph + 1 > data_end) + return 0; + if (!(iph->protocol == IPPROTO_UDP)) + return 0; + + udph = (void *)(iph + 1); + if (udph + 1 > data_end) + return 0; + + dport = ntohs(udph->dest); + return dport; +} + +static __always_inline +int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct iphdr *iph = data + nh_off; + + if (iph + 1 > data_end) + return 0; + return iph->protocol; +} + +static __always_inline +int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ipv6hdr *ip6h = data + nh_off; + + if (ip6h + 1 > data_end) + return 0; + return ip6h->nexthdr; +} + +SEC("xdp_cpu_map0") +int xdp_prognum0_no_touch(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map1_touch_data") +int xdp_prognum1_touch_data(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 *cpu_selected; + u32 cpu_dest; + u16 eth_type; + u32 key = 0; + + /* Only use first entry in cpus_available */ + cpu_selected = bpf_map_lookup_elem(&cpus_available, &key); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Validate packet length is minimum Eth header size */ + if (eth + 1 > data_end) + return XDP_ABORTED; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + /* Read packet data, and use it (drop non 802.3 Ethertypes) */ + eth_type = eth->h_proto; + if (ntohs(eth_type) < ETH_P_802_3_MIN) { + rec->dropped++; + return XDP_DROP; + } + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map2_round_robin") +int xdp_prognum2_round_robin(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + struct datarec *rec; + u32 cpu_dest; + u32 *cpu_lookup; + u32 key0 = 0; + + u32 *cpu_selected; + u32 *cpu_iterator; + u32 *cpu_max; + u32 cpu_idx; + + cpu_max = bpf_map_lookup_elem(&cpus_count, &key0); + if (!cpu_max) + return XDP_ABORTED; + + cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0); + if (!cpu_iterator) + return XDP_ABORTED; + cpu_idx = *cpu_iterator; + + *cpu_iterator += 1; + if (*cpu_iterator == *cpu_max) + *cpu_iterator = 0; + + cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_selected) + return XDP_ABORTED; + cpu_dest = *cpu_selected; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key0); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map3_proto_separate") +int xdp_prognum3_proto_separate(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + +SEC("xdp_cpu_map4_ddos_filter_pktgen") +int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct ethhdr *eth = data; + u8 ip_proto = IPPROTO_UDP; + struct datarec *rec; + u16 eth_proto = 0; + u64 l3_offset = 0; + u32 cpu_dest = 0; + u32 cpu_idx = 0; + u16 dest_port; + u32 *cpu_lookup; + u32 key = 0; + + /* Count RX packet in map */ + rec = bpf_map_lookup_elem(&rx_cnt, &key); + if (!rec) + return XDP_ABORTED; + rec->processed++; + + if (!(parse_eth(eth, data_end, ð_proto, &l3_offset))) + return XDP_PASS; /* Just skip */ + + /* Extract L4 protocol */ + switch (eth_proto) { + case ETH_P_IP: + ip_proto = get_proto_ipv4(ctx, l3_offset); + break; + case ETH_P_IPV6: + ip_proto = get_proto_ipv6(ctx, l3_offset); + break; + case ETH_P_ARP: + cpu_idx = 0; /* ARP packet handled on separate CPU */ + break; + default: + cpu_idx = 0; + } + + /* Choose CPU based on L4 protocol */ + switch (ip_proto) { + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + cpu_idx = 2; + break; + case IPPROTO_TCP: + cpu_idx = 0; + break; + case IPPROTO_UDP: + cpu_idx = 1; + /* DDoS filter UDP port 9 (pktgen) */ + dest_port = get_dest_port_ipv4_udp(ctx, l3_offset); + if (dest_port == 9) { + if (rec) + rec->dropped++; + return XDP_DROP; + } + break; + default: + cpu_idx = 0; + } + + cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx); + if (!cpu_lookup) + return XDP_ABORTED; + cpu_dest = *cpu_lookup; + + if (cpu_dest >= MAX_CPUS) { + rec->issue++; + return XDP_ABORTED; + } + + return bpf_redirect_map(&cpu_map, cpu_dest, 0); +} + + +char _license[] SEC("license") = "GPL"; + +/*** Trace point code ***/ + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_redirect_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12 size:4; signed:0; + int ifindex; // offset:16 size:4; signed:1; + int err; // offset:20 size:4; signed:1; + int to_ifindex; // offset:24 size:4; signed:1; + u32 map_id; // offset:28 size:4; signed:0; + int map_index; // offset:32 size:4; signed:1; +}; // offset:36 + +enum { + XDP_REDIRECT_SUCCESS = 0, + XDP_REDIRECT_ERROR = 1 +}; + +static __always_inline +int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx) +{ + u32 key = XDP_REDIRECT_ERROR; + struct datarec *rec; + int err = ctx->err; + + if (!err) + key = XDP_REDIRECT_SUCCESS; + + rec = bpf_map_lookup_elem(&redirect_err_cnt, &key); + if (!rec) + return 0; + rec->dropped += 1; + + return 0; /* Indicate event was filtered (no further processing)*/ + /* + * Returning 1 here would allow e.g. a perf-record tracepoint + * to see and record these events, but it doesn't work well + * in-practice as stopping perf-record also unload this + * bpf_prog. Plus, there is additional overhead of doing so. + */ +} + +SEC("tracepoint/xdp/xdp_redirect_err") +int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + +SEC("tracepoint/xdp/xdp_redirect_map_err") +int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx) +{ + return xdp_redirect_collect_stat(ctx); +} + +/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct xdp_exception_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int prog_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int ifindex; // offset:16; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_exception") +int trace_xdp_exception(struct xdp_exception_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&exception_cnt, &key); + if (!rec) + return 1; + rec->dropped += 1; + + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_enqueue_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int to_cpu; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_enqueue") +int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx) +{ + u32 to_cpu = ctx->to_cpu; + struct datarec *rec; + + if (to_cpu >= MAX_CPUS) + return 1; + + rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Record bulk events, then userspace can calc average bulk size */ + if (ctx->processed > 0) + rec->issue += 1; + + /* Inception: It's possible to detect overload situations, via + * this tracepoint. This can be used for creating a feedback + * loop to XDP, which can take appropriate actions to mitigate + * this overload situation. + */ + return 0; +} + +/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format + * Code in: kernel/include/trace/events/xdp.h + */ +struct cpumap_kthread_ctx { + u64 __pad; // First 8 bytes are not accessible by bpf code + int map_id; // offset:8; size:4; signed:1; + u32 act; // offset:12; size:4; signed:0; + int cpu; // offset:16; size:4; signed:1; + unsigned int drops; // offset:20; size:4; signed:0; + unsigned int processed; // offset:24; size:4; signed:0; + int sched; // offset:28; size:4; signed:1; +}; + +SEC("tracepoint/xdp/xdp_cpumap_kthread") +int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) +{ + struct datarec *rec; + u32 key = 0; + + rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key); + if (!rec) + return 0; + rec->processed += ctx->processed; + rec->dropped += ctx->drops; + + /* Count times kthread yielded CPU via schedule call */ + if (ctx->sched) + rec->issue++; + + return 0; +} diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c new file mode 100644 index 0000000000000..35fec9fecb57c --- /dev/null +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -0,0 +1,697 @@ +/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc. + */ +static const char *__doc__ = + " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\""; + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define MAX_CPUS 12 /* WARNING - sync with _kern.c */ + +/* How many xdp_progs are defined in _kern.c */ +#define MAX_PROG 5 + +/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead + * use bpf/libbpf.h), but cannot as (currently) needed for XDP + * attaching to a device via set_link_xdp_fd() + */ +#include "libbpf.h" +#include "bpf_load.h" + +#include "bpf_util.h" + +static int ifindex = -1; +static char ifname_buf[IF_NAMESIZE]; +static char *ifname; + +static __u32 xdp_flags; + +/* Exit return codes */ +#define EXIT_OK 0 +#define EXIT_FAIL 1 +#define EXIT_FAIL_OPTION 2 +#define EXIT_FAIL_XDP 3 +#define EXIT_FAIL_BPF 4 +#define EXIT_FAIL_MEM 5 + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"dev", required_argument, NULL, 'd' }, + {"skb-mode", no_argument, NULL, 'S' }, + {"debug", no_argument, NULL, 'D' }, + {"sec", required_argument, NULL, 's' }, + {"prognum", required_argument, NULL, 'p' }, + {"qsize", required_argument, NULL, 'q' }, + {"cpu", required_argument, NULL, 'c' }, + {"stress-mode", no_argument, NULL, 'x' }, + {"no-separators", no_argument, NULL, 'z' }, + {0, 0, NULL, 0 } +}; + +static void int_exit(int sig) +{ + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + if (ifindex > -1) + set_link_xdp_fd(ifindex, -1, xdp_flags); + exit(EXIT_OK); +} + +static void usage(char *argv[]) +{ + int i; + + printf("\nDOCUMENTATION:\n%s\n", __doc__); + printf("\n"); + printf(" Usage: %s (options-see-below)\n", argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)", + *long_options[i].flag); + else + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n"); +} + +/* gettime returns the current time of day in nanoseconds. + * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC) + * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE) + */ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(void) +{ + struct timespec t; + int res; + + res = clock_gettime(CLOCK_MONOTONIC, &t); + if (res < 0) { + fprintf(stderr, "Error with gettimeofday! (%i)\n", res); + exit(EXIT_FAIL); + } + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +/* Common stats data record shared with _kern.c */ +struct datarec { + __u64 processed; + __u64 dropped; + __u64 issue; +}; +struct record { + __u64 timestamp; + struct datarec total; + struct datarec *cpu; +}; +struct stats_record { + struct record rx_cnt; + struct record redir_err; + struct record kthread; + struct record exception; + struct record enq[MAX_CPUS]; +}; + +static bool map_collect_percpu(int fd, __u32 key, struct record *rec) +{ + /* For percpu maps, userspace gets a value per possible CPU */ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec values[nr_cpus]; + __u64 sum_processed = 0; + __u64 sum_dropped = 0; + __u64 sum_issue = 0; + int i; + + if ((bpf_map_lookup_elem(fd, &key, values)) != 0) { + fprintf(stderr, + "ERR: bpf_map_lookup_elem failed key:0x%X\n", key); + return false; + } + /* Get time as close as possible to reading map contents */ + rec->timestamp = gettime(); + + /* Record and sum values from each CPU */ + for (i = 0; i < nr_cpus; i++) { + rec->cpu[i].processed = values[i].processed; + sum_processed += values[i].processed; + rec->cpu[i].dropped = values[i].dropped; + sum_dropped += values[i].dropped; + rec->cpu[i].issue = values[i].issue; + sum_issue += values[i].issue; + } + rec->total.processed = sum_processed; + rec->total.dropped = sum_dropped; + rec->total.issue = sum_issue; + return true; +} + +static struct datarec *alloc_record_per_cpu(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + struct datarec *array; + size_t size; + + size = sizeof(struct datarec) * nr_cpus; + array = malloc(size); + memset(array, 0, size); + if (!array) { + fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus); + exit(EXIT_FAIL_MEM); + } + return array; +} + +static struct stats_record *alloc_stats_record(void) +{ + struct stats_record *rec; + int i; + + rec = malloc(sizeof(*rec)); + memset(rec, 0, sizeof(*rec)); + if (!rec) { + fprintf(stderr, "Mem alloc error\n"); + exit(EXIT_FAIL_MEM); + } + rec->rx_cnt.cpu = alloc_record_per_cpu(); + rec->redir_err.cpu = alloc_record_per_cpu(); + rec->kthread.cpu = alloc_record_per_cpu(); + rec->exception.cpu = alloc_record_per_cpu(); + for (i = 0; i < MAX_CPUS; i++) + rec->enq[i].cpu = alloc_record_per_cpu(); + + return rec; +} + +static void free_stats_record(struct stats_record *r) +{ + int i; + + for (i = 0; i < MAX_CPUS; i++) + free(r->enq[i].cpu); + free(r->exception.cpu); + free(r->kthread.cpu); + free(r->redir_err.cpu); + free(r->rx_cnt.cpu); + free(r); +} + +static double calc_period(struct record *r, struct record *p) +{ + double period_ = 0; + __u64 period = 0; + + period = r->timestamp - p->timestamp; + if (period > 0) + period_ = ((double) period / NANOSEC_PER_SEC); + + return period_; +} + +static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->processed - p->processed; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->dropped - p->dropped; + pps = packets / period_; + } + return pps; +} + +static __u64 calc_errs_pps(struct datarec *r, + struct datarec *p, double period_) +{ + __u64 packets = 0; + __u64 pps = 0; + + if (period_ > 0) { + packets = r->issue - p->issue; + pps = packets / period_; + } + return pps; +} + +static void stats_print(struct stats_record *stats_rec, + struct stats_record *stats_prev, + int prog_num) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + double pps = 0, drop = 0, err = 0; + struct record *rec, *prev; + int to_cpu; + double t; + int i; + + /* Header */ + printf("Running XDP/eBPF prog_num:%d\n", prog_num); + printf("%-15s %-7s %-14s %-11s %-9s\n", + "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info"); + + /* XDP rx_cnt */ + { + char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n"; + char *errstr = ""; + + rec = &stats_rec->rx_cnt; + prev = &stats_prev->rx_cnt; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + errstr = "cpu-dest/err"; + if (pps > 0) + printf(fmt_rx, "XDP-RX", + i, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + printf(fm2_rx, "XDP-RX", "total", pps, drop); + } + + /* cpumap enqueue stats */ + for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) { + char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n"; + char *errstr = ""; + + rec = &stats_rec->enq[to_cpu]; + prev = &stats_prev->enq[to_cpu]; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + if (pps > 0) + printf(fmt, "cpumap-enqueue", + i, to_cpu, pps, drop, err, errstr); + } + pps = calc_pps(&rec->total, &prev->total, t); + if (pps > 0) { + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) { + errstr = "bulk-average"; + err = pps / err; /* calc average bulk size */ + } + printf(fm2, "cpumap-enqueue", + "sum", to_cpu, pps, drop, err, errstr); + } + } + + /* cpumap kthread stats */ + { + char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n"; + char *e_str = ""; + + rec = &stats_rec->kthread; + prev = &stats_prev->kthread; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + err = calc_errs_pps(r, p, t); + if (err > 0) + e_str = "sched"; + if (pps > 0) + printf(fmt_k, "cpumap_kthread", + i, pps, drop, err, e_str); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + err = calc_errs_pps(&rec->total, &prev->total, t); + if (err > 0) + e_str = "sched-sum"; + printf(fm2_k, "cpumap_kthread", "total", pps, drop, err, e_str); + } + + /* XDP redirect err tracepoints (very unlikely) */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->redir_err; + prev = &stats_prev->redir_err; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "redirect_err", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "redirect_err", "total", pps, drop); + } + + /* XDP general exception tracepoints */ + { + char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n"; + char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n"; + + rec = &stats_rec->exception; + prev = &stats_prev->exception; + t = calc_period(rec, prev); + for (i = 0; i < nr_cpus; i++) { + struct datarec *r = &rec->cpu[i]; + struct datarec *p = &prev->cpu[i]; + + pps = calc_pps(r, p, t); + drop = calc_drop_pps(r, p, t); + if (pps > 0) + printf(fmt_err, "xdp_exception", i, pps, drop); + } + pps = calc_pps(&rec->total, &prev->total, t); + drop = calc_drop_pps(&rec->total, &prev->total, t); + printf(fm2_err, "xdp_exception", "total", pps, drop); + } + + printf("\n"); + fflush(stdout); +} + +static void stats_collect(struct stats_record *rec) +{ + int fd, i; + + fd = map_fd[1]; /* map: rx_cnt */ + map_collect_percpu(fd, 0, &rec->rx_cnt); + + fd = map_fd[2]; /* map: redirect_err_cnt */ + map_collect_percpu(fd, 1, &rec->redir_err); + + fd = map_fd[3]; /* map: cpumap_enqueue_cnt */ + for (i = 0; i < MAX_CPUS; i++) + map_collect_percpu(fd, i, &rec->enq[i]); + + fd = map_fd[4]; /* map: cpumap_kthread_cnt */ + map_collect_percpu(fd, 0, &rec->kthread); + + fd = map_fd[8]; /* map: exception_cnt */ + map_collect_percpu(fd, 0, &rec->exception); +} + + +/* Pointer swap trick */ +static inline void swap(struct stats_record **a, struct stats_record **b) +{ + struct stats_record *tmp; + + tmp = *a; + *a = *b; + *b = tmp; +} + +static int create_cpu_entry(__u32 cpu, __u32 queue_size, + __u32 avail_idx, bool new) +{ + __u32 curr_cpus_count = 0; + __u32 key = 0; + int ret; + + /* Add a CPU entry to cpumap, as this allocate a cpu entry in + * the kernel for the cpu. + */ + ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0); + if (ret) { + fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); + exit(EXIT_FAIL_BPF); + } + + /* Inform bpf_prog's that a new CPU is available to select + * from via some control maps. + */ + /* map_fd[5] = cpus_available */ + ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0); + if (ret) { + fprintf(stderr, "Add to avail CPUs failed\n"); + exit(EXIT_FAIL_BPF); + } + + /* When not replacing/updating existing entry, bump the count */ + /* map_fd[6] = cpus_count */ + ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count); + if (ret) { + fprintf(stderr, "Failed reading curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + if (new) { + curr_cpus_count++; + ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0); + if (ret) { + fprintf(stderr, "Failed write curr cpus_count\n"); + exit(EXIT_FAIL_BPF); + } + } + /* map_fd[7] = cpus_iterator */ + printf("%s CPU:%u as idx:%u queue_size:%d (total cpus_count:%u)\n", + new ? "Add-new":"Replace", cpu, avail_idx, + queue_size, curr_cpus_count); + + return 0; +} + +/* CPUs are zero-indexed. Thus, add a special sentinel default value + * in map cpus_available to mark CPU index'es not configured + */ +static void mark_cpus_unavailable(void) +{ + __u32 invalid_cpu = MAX_CPUS; + int ret, i; + + for (i = 0; i < MAX_CPUS; i++) { + /* map_fd[5] = cpus_available */ + ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0); + if (ret) { + fprintf(stderr, "Failed marking CPU unavailable\n"); + exit(EXIT_FAIL_BPF); + } + } +} + +/* Stress cpumap management code by concurrently changing underlying cpumap */ +static void stress_cpumap(void) +{ + /* Changing qsize will cause kernel to free and alloc a new + * bpf_cpu_map_entry, with an associated/complicated tear-down + * procedure. + */ + create_cpu_entry(1, 1024, 0, false); + create_cpu_entry(1, 128, 0, false); + create_cpu_entry(1, 16000, 0, false); +} + +static void stats_poll(int interval, bool use_separators, int prog_num, + bool stress_mode) +{ + struct stats_record *record, *prev; + + record = alloc_stats_record(); + prev = alloc_stats_record(); + stats_collect(record); + + /* Trick to pretty printf with thousands separators use %' */ + if (use_separators) + setlocale(LC_NUMERIC, "en_US"); + + while (1) { + swap(&prev, &record); + stats_collect(record); + stats_print(record, prev, prog_num); + sleep(interval); + if (stress_mode) + stress_cpumap(); + } + + free_stats_record(record); + free_stats_record(prev); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + bool use_separators = true; + bool stress_mode = false; + char filename[256]; + bool debug = false; + int added_cpus = 0; + int longindex = 0; + int interval = 2; + int prog_num = 0; + int add_cpu = -1; + __u32 qsize; + int opt; + + /* Notice: choosing he queue size is very important with the + * ixgbe driver, because it's driver page recycling trick is + * dependend on pages being returned quickly. The number of + * out-standing packets in the system must be less-than 2x + * RX-ring size. + */ + qsize = 128+64; + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (load_bpf_file(filename)) { + fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf); + return EXIT_FAIL; + } + + if (!prog_fd[0]) { + fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno)); + return EXIT_FAIL; + } + + mark_cpus_unavailable(); + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hSd:", + long_options, &longindex)) != -1) { + switch (opt) { + case 'd': + if (strlen(optarg) >= IF_NAMESIZE) { + fprintf(stderr, "ERR: --dev name too long\n"); + goto error; + } + ifname = (char *)&ifname_buf; + strncpy(ifname, optarg, IF_NAMESIZE); + ifindex = if_nametoindex(ifname); + if (ifindex == 0) { + fprintf(stderr, + "ERR: --dev name unknown err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 's': + interval = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'D': + debug = true; + break; + case 'x': + stress_mode = true; + break; + case 'z': + use_separators = false; + break; + case 'p': + /* Selecting eBPF prog to load */ + prog_num = atoi(optarg); + if (prog_num < 0 || prog_num >= MAX_PROG) { + fprintf(stderr, + "--prognum too large err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + break; + case 'c': + /* Add multiple CPUs */ + add_cpu = strtoul(optarg, NULL, 0); + if (add_cpu >= MAX_CPUS) { + fprintf(stderr, + "--cpu nr too large for cpumap err(%d):%s\n", + errno, strerror(errno)); + goto error; + } + create_cpu_entry(add_cpu, qsize, added_cpus, true); + added_cpus++; + break; + case 'q': + qsize = atoi(optarg); + break; + case 'h': + error: + default: + usage(argv); + return EXIT_FAIL_OPTION; + } + } + /* Required option */ + if (ifindex == -1) { + fprintf(stderr, "ERR: required option --dev missing\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + /* Required option */ + if (add_cpu == -1) { + fprintf(stderr, "ERR: required option --cpu missing\n"); + fprintf(stderr, " Specify multiple --cpu option to add more\n"); + usage(argv); + return EXIT_FAIL_OPTION; + } + + /* Remove XDP program when program is interrupted */ + signal(SIGINT, int_exit); + + if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + fprintf(stderr, "link set xdp fd failed\n"); + return EXIT_FAIL_XDP; + } + + if (debug) { + printf("Debug-mode reading trace pipe (fix #define DEBUG)\n"); + read_trace_pipe(); + } + + stats_poll(interval, use_separators, prog_num, stress_mode); + return EXIT_OK; +} -- GitLab From a2084f5650624edd0805dc78260d097df4f38eb6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 16 Oct 2017 16:57:49 +0200 Subject: [PATCH 1428/1507] netlink: use NETLINK_CB(in_skb).sk instead of looking it up When netlink_ack() reports an allocation error to the sending socket, there's no need to look up the sending socket since it's available in the SKB's CB. Use that instead of going to the trouble of looking it up. Note that the pointer is only available since Eric Biederman's commit 3fbc290540a1 ("netlink: Make the sending netlink socket availabe in NETLINK_CB") which is far newer than the original lookup code (Oct 2003) (though the field was called 'ssk' in that commit and only got renamed to 'sk' later, I'd actually argue 'ssk' was better - or perhaps it should've been 'source_sk' - since there are so many different 'sk's involved.) Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f34750691c5c0..336d9c6dcad93 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2336,16 +2336,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { - struct sock *sk; - - sk = netlink_lookup(sock_net(in_skb->sk), - in_skb->sk->sk_protocol, - NETLINK_CB(in_skb).portid); - if (sk) { - sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); - sock_put(sk); - } + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); return; } -- GitLab From a5b930e0598dc46184af0282c23c75b2167d9384 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:13 -0400 Subject: [PATCH 1429/1507] net: dsa: use port's cpu_dp when creating a slave When dsa_slave_create is called, the related port already has a CPU port assigned to it, available in its cpu_dp member. Use it instead of the unique tree cpu_dp. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 45f4ea845c077..c6f4829645bf0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1117,16 +1117,13 @@ int dsa_slave_resume(struct net_device *slave_dev) int dsa_slave_create(struct dsa_port *port, const char *name) { struct dsa_notifier_register_info rinfo = { }; + struct dsa_port *cpu_dp = port->cpu_dp; + struct net_device *master = cpu_dp->netdev; struct dsa_switch *ds = port->ds; - struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; - struct dsa_port *cpu_dp; int ret; - cpu_dp = ds->dst->cpu_dp; - master = cpu_dp->netdev; - if (!ds->num_tx_queues) ds->num_tx_queues = 1; -- GitLab From 6158eaa7a717b469b1b0c0ae6d79910737686279 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:14 -0400 Subject: [PATCH 1430/1507] net: dsa: add slave notify helper Both DSA slave create and destroy functions call call_dsa_notifiers with respectively DSA_PORT_REGISTER and DSA_PORT_UNREGISTER and the same dsa_notifier_register_info structure. Wrap this in a dsa_slave_notify helper so prevent cluttering these functions. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c6f4829645bf0..f31737256f69f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1114,9 +1114,23 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } +static void dsa_slave_notify(struct net_device *dev, unsigned long val) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct net_device *master = dsa_master_netdev(p); + struct dsa_port *dp = p->dp; + struct dsa_notifier_register_info rinfo = { + .switch_number = dp->ds->index, + .port_number = dp->index, + .master = master, + .info.dev = dev, + }; + + call_dsa_notifiers(val, dev, &rinfo.info); +} + int dsa_slave_create(struct dsa_port *port, const char *name) { - struct dsa_notifier_register_info rinfo = { }; struct dsa_port *cpu_dp = port->cpu_dp; struct net_device *master = cpu_dp->netdev; struct dsa_switch *ds = port->ds; @@ -1175,11 +1189,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) goto out_free; } - rinfo.info.dev = slave_dev; - rinfo.master = master; - rinfo.port_number = p->dp->index; - rinfo.switch_number = p->dp->ds->index; - call_dsa_notifiers(DSA_PORT_REGISTER, slave_dev, &rinfo.info); + dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); ret = register_netdev(slave_dev); if (ret) { @@ -1204,7 +1214,6 @@ int dsa_slave_create(struct dsa_port *port, const char *name) void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct dsa_notifier_register_info rinfo = { }; struct device_node *port_dn; port_dn = p->dp->dn; @@ -1216,11 +1225,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) if (of_phy_is_fixed_link(port_dn)) of_phy_deregister_fixed_link(port_dn); } - rinfo.info.dev = slave_dev; - rinfo.master = p->dp->cpu_dp->netdev; - rinfo.port_number = p->dp->index; - rinfo.switch_number = p->dp->ds->index; - call_dsa_notifiers(DSA_PORT_UNREGISTER, slave_dev, &rinfo.info); + dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); free_percpu(p->stats64); free_netdev(slave_dev); -- GitLab From d945097bb19501bd95790d8220d4eeb418b6ebb2 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:15 -0400 Subject: [PATCH 1431/1507] net: dsa: add slave to port helper Many portions of DSA core code require to get the dsa_port structure corresponding to a slave net_device. For this purpose, introduce a dsa_slave_to_port() helper. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 7 ++ net/dsa/legacy.c | 6 +- net/dsa/slave.c | 167 +++++++++++++++++++++--------------------- net/dsa/tag_brcm.c | 9 +-- net/dsa/tag_dsa.c | 10 +-- net/dsa/tag_edsa.c | 10 +-- net/dsa/tag_ksz.c | 4 +- net/dsa/tag_lan9303.c | 4 +- net/dsa/tag_mtk.c | 4 +- net/dsa/tag_qca.c | 5 +- net/dsa/tag_trailer.c | 4 +- 11 files changed, 115 insertions(+), 115 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2850077cc9ccb..569a4929b4c90 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -169,6 +169,13 @@ int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + + return p->dp; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index b0fefbffe082a..cc28c6f792a34 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -740,8 +740,7 @@ int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], const unsigned char *addr, u16 vid, u16 flags) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_add(dp, addr, vid); } @@ -750,8 +749,7 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_del(dp, addr, vid); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index f31737256f69f..894602c88b096 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -72,8 +72,8 @@ static int dsa_slave_get_iflink(const struct net_device *dev) static int dsa_slave_open(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; struct net_device *master = dsa_master_netdev(p); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; if (!(master->flags & IFF_UP)) @@ -122,7 +122,7 @@ static int dsa_slave_close(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct net_device *master = dsa_master_netdev(p); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); if (dev->phydev) phy_stop(dev->phydev); @@ -246,14 +246,13 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; int err; err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); @@ -274,8 +273,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int ret; switch (attr->id) { @@ -301,8 +299,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; /* For the prepare phase, ensure the full set of changes is feasable in @@ -329,8 +326,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err; switch (obj->id) { @@ -351,8 +347,8 @@ static int dsa_slave_port_obj_del(struct net_device *dev, static int dsa_slave_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: @@ -431,11 +427,11 @@ static void dsa_slave_get_drvinfo(struct net_device *dev, static int dsa_slave_get_regs_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) - return ds->ops->get_regs_len(ds, p->dp->index); + return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } @@ -443,11 +439,11 @@ static int dsa_slave_get_regs_len(struct net_device *dev) static void dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) - ds->ops->get_regs(ds, p->dp->index, regs, _p); + ds->ops->get_regs(ds, dp->index, regs, _p); } static u32 dsa_slave_get_link(struct net_device *dev) @@ -462,8 +458,8 @@ static u32 dsa_slave_get_link(struct net_device *dev) static int dsa_slave_get_eeprom_len(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; @@ -477,8 +473,8 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) static int dsa_slave_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); @@ -489,8 +485,8 @@ static int dsa_slave_get_eeprom(struct net_device *dev, static int dsa_slave_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); @@ -501,8 +497,8 @@ static int dsa_slave_set_eeprom(struct net_device *dev, static void dsa_slave_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { int len = ETH_GSTRING_LEN; @@ -512,7 +508,7 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) - ds->ops->get_strings(ds, p->dp->index, data + 4 * len); + ds->ops->get_strings(ds, dp->index, data + 4 * len); } } @@ -520,8 +516,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; @@ -543,13 +540,13 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, p->dp->index, data + 4); + ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_slave_get_sset_count(struct net_device *dev, int sset) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count; @@ -566,29 +563,29 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (ds->ops->get_wol) - ds->ops->get_wol(ds, p->dp->index, w); + ds->ops->get_wol(ds, dp->index, w); } static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; if (ds->ops->set_wol) - ret = ds->ops->set_wol(ds, p->dp->index, w); + ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ @@ -598,7 +595,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->set_mac_eee(ds, p->dp->index, e); + ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; @@ -613,8 +610,8 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; int ret; /* Port's PHY and MAC both need to be EEE capable */ @@ -624,7 +621,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) if (!ds->ops->get_mac_eee) return -EOPNOTSUPP; - ret = ds->ops->get_mac_eee(ds, p->dp->index, e); + ret = ds->ops->get_mac_eee(ds, dp->index, e); if (ret) return ret; @@ -676,9 +673,9 @@ static void dsa_slave_poll_controller(struct net_device *dev) static int dsa_slave_get_phys_port_name(struct net_device *dev, char *name, size_t len) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); - if (snprintf(name, len, "p%d", p->dp->index) >= len) + if (snprintf(name, len, "p%d", dp->index) >= len) return -EINVAL; return 0; @@ -701,14 +698,15 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; __be16 protocol = cls->common.protocol; - struct dsa_switch *ds = p->dp->ds; struct net *net = dev_net(dev); - struct dsa_slave_priv *to_p; + struct dsa_switch *ds = dp->ds; struct net_device *to_dev; const struct tc_action *a; + struct dsa_port *to_dp; int err = -EOPNOTSUPP; LIST_HEAD(actions); int ifindex; @@ -741,13 +739,12 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; - to_p = netdev_priv(to_dev); + to_dp = dsa_slave_to_port(to_dev); - mirror->to_local_port = to_p->dp->index; + mirror->to_local_port = to_dp->index; mirror->ingress = ingress; - err = ds->ops->port_mirror_add(ds, p->dp->index, mirror, - ingress); + err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress); if (err) { kfree(mall_tc_entry); return err; @@ -762,9 +759,9 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, static void dsa_slave_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; if (!ds->ops->port_mirror_del) return; @@ -777,8 +774,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: - ds->ops->port_mirror_del(ds, p->dp->index, - &mall_tc_entry->mirror); + ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; default: WARN_ON(1); @@ -855,25 +851,25 @@ static void dsa_slave_get_stats64(struct net_device *dev, static int dsa_slave_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; - return ds->ops->get_rxnfc(ds, p->dp->index, nfc, rule_locs); + return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_slave_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; - return ds->ops->set_rxnfc(ds, p->dp->index, nfc); + return ds->ops->set_rxnfc(ds, dp->index, nfc); } static const struct ethtool_ops dsa_slave_ethtool_ops = { @@ -933,8 +929,9 @@ static struct device_type dsa_type = { static void dsa_slave_adjust_link(struct net_device *dev) { + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; unsigned int status_changed = 0; if (p->old_link != dev->phydev->link) { @@ -953,7 +950,7 @@ static void dsa_slave_adjust_link(struct net_device *dev) } if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, p->dp->index, dev->phydev); + ds->ops->adjust_link(ds, dp->index, dev->phydev); if (status_changed) phy_print_status(dev->phydev); @@ -962,14 +959,14 @@ static void dsa_slave_adjust_link(struct net_device *dev) static int dsa_slave_fixed_link_update(struct net_device *dev, struct fixed_phy_status *status) { - struct dsa_slave_priv *p; struct dsa_switch *ds; + struct dsa_port *dp; if (dev) { - p = netdev_priv(dev); - ds = p->dp->ds; + dp = dsa_slave_to_port(dev); + ds = dp->ds; if (ds->ops->fixed_link_update) - ds->ops->fixed_link_update(ds, p->dp->index, status); + ds->ops->fixed_link_update(ds, dp->index, status); } return 0; @@ -978,8 +975,9 @@ static int dsa_slave_fixed_link_update(struct net_device *dev, /* slave device setup *******************************************************/ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct dsa_switch *ds = p->dp->ds; + struct dsa_switch *ds = dp->ds; slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); if (!slave_dev->phydev) { @@ -997,14 +995,15 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) static int dsa_slave_phy_setup(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct dsa_switch *ds = p->dp->ds; - struct device_node *phy_dn, *port_dn; + struct device_node *port_dn = dp->dn; + struct dsa_switch *ds = dp->ds; + struct device_node *phy_dn; bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; - port_dn = p->dp->dn; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; @@ -1025,7 +1024,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) } if (ds->ops->get_phy_flags) - phy_flags = ds->ops->get_phy_flags(ds, p->dp->index); + phy_flags = ds->ops->get_phy_flags(ds, dp->index); if (phy_dn) { int phy_id = of_mdio_parse_addr(&slave_dev->dev, phy_dn); @@ -1061,10 +1060,10 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * MDIO bus instead */ if (!slave_dev->phydev) { - ret = dsa_slave_phy_connect(slave_dev, p->dp->index); + ret = dsa_slave_phy_connect(slave_dev, dp->index); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", - p->dp->index, ret); + dp->index, ret); if (phy_is_fixed) of_phy_deregister_fixed_link(port_dn); return ret; @@ -1118,7 +1117,7 @@ static void dsa_slave_notify(struct net_device *dev, unsigned long val) { struct dsa_slave_priv *p = netdev_priv(dev); struct net_device *master = dsa_master_netdev(p); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_notifier_register_info rinfo = { .switch_number = dp->ds->index, .port_number = dp->index, @@ -1202,8 +1201,8 @@ int dsa_slave_create(struct dsa_port *port, const char *name) out_phy: phy_disconnect(slave_dev->phydev); - if (of_phy_is_fixed_link(p->dp->dn)) - of_phy_deregister_fixed_link(p->dp->dn); + if (of_phy_is_fixed_link(port->dn)) + of_phy_deregister_fixed_link(port->dn); out_free: free_percpu(p->stats64); free_netdev(slave_dev); @@ -1213,10 +1212,9 @@ int dsa_slave_create(struct dsa_port *port, const char *name) void dsa_slave_destroy(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct device_node *port_dn; - - port_dn = p->dp->dn; + struct device_node *port_dn = dp->dn; netif_carrier_off(slave_dev); if (slave_dev->phydev) { @@ -1239,8 +1237,7 @@ static bool dsa_slave_dev_check(struct net_device *dev) static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_port *dp = p->dp; + struct dsa_port *dp = dsa_slave_to_port(dev); int err = NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev)) { @@ -1283,14 +1280,14 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) container_of(work, struct dsa_switchdev_event_work, work); struct net_device *dev = switchdev_work->dev; struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); int err; rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_add(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb add failed err=%d\n", err); break; @@ -1301,7 +1298,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - err = dsa_port_fdb_del(p->dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb del failed err=%d\n", err); dev_close(dev); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cc4f472fbd772..2a0fa9f9f7ca8 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -61,7 +61,7 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; @@ -82,15 +82,14 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT); brcm_tag[1] = 0; brcm_tag[2] = 0; - if (p->dp->index == 8) + if (dp->index == 8) brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; - brcm_tag[3] = (1 << p->dp->index) & BRCM_IG_DSTMAP1_MASK; + brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; /* Now tell the master network device about the desired output queue * as well */ - skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(p->dp->index, - queue)); + skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); return skb; } diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index c77218f173d1b..fe3c9700a8c84 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -18,7 +18,7 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *dsa_header; /* @@ -34,8 +34,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct tagged FROM_CPU DSA tag from 802.1q tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x60 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x60 | dp->ds->index; + dsa_header[1] = dp->index << 3; /* * Move CFI field from byte 2 to byte 1. @@ -55,8 +55,8 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * Construct untagged FROM_CPU DSA tag. */ dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x40 | p->dp->ds->index; - dsa_header[1] = p->dp->index << 3; + dsa_header[0] = 0x40 | dp->ds->index; + dsa_header[1] = dp->index << 3; dsa_header[2] = 0x00; dsa_header[3] = 0x00; } diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 0b83cbe0c9e8a..c683e240bafcf 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -19,7 +19,7 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *edsa_header; /* @@ -43,8 +43,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x60 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x60 | dp->ds->index; + edsa_header[5] = dp->index << 3; /* * Move CFI field from byte 6 to byte 5. @@ -68,8 +68,8 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[1] = ETH_P_EDSA & 0xff; edsa_header[2] = 0x00; edsa_header[3] = 0x00; - edsa_header[4] = 0x40 | p->dp->ds->index; - edsa_header[5] = p->dp->index << 3; + edsa_header[4] = 0x40 | dp->ds->index; + edsa_header[5] = dp->index << 3; edsa_header[6] = 0x00; edsa_header[7] = 0x00; } diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index b241c990cde08..66e443fd76757 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -34,7 +34,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *tag; @@ -72,7 +72,7 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); tag[0] = 0; - tag[1] = 1 << p->dp->index; /* destination port */ + tag[1] = 1 << dp->index; /* destination port */ return nskb; } diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 4f211e56c81fe..c709adb5efd97 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -42,7 +42,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *lan9303_tag; /* insert a special VLAN tag between the MAC addresses @@ -62,7 +62,7 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN); lan9303_tag[0] = htons(ETH_P_8021Q); - lan9303_tag[1] = htons(p->dp->index | BIT(4)); + lan9303_tag[1] = htons(dp->index | BIT(4)); return skb; } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 968586c5d40e8..5abebbfd70607 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -23,7 +23,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u8 *mtk_tag; if (skb_cow_head(skb, MTK_HDR_LEN) < 0) @@ -36,7 +36,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Build the tag after the MAC Source Address */ mtk_tag = skb->data + 2 * ETH_ALEN; mtk_tag[0] = 0; - mtk_tag[1] = (1 << p->dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; + mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; mtk_tag[2] = 0; mtk_tag[3] = 0; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 8d33d9ebf910d..b0274b6781cb0 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -38,7 +38,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); u16 *phdr, hdr; dev->stats.tx_packets++; @@ -54,8 +54,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) /* Set the version field, and set destination port information */ hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | - BIT(p->dp->index); + QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); *phdr = htons(hdr); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 61668be267f5d..8b205bb5f5211 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -16,7 +16,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_slave_to_port(dev); struct sk_buff *nskb; int padlen; u8 *trailer; @@ -48,7 +48,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) trailer = skb_put(nskb, 4); trailer[0] = 0x80; - trailer[1] = 1 << p->dp->index; + trailer[1] = 1 << dp->index; trailer[2] = 0x10; trailer[3] = 0x00; -- GitLab From d0006b002208936d36af8e4dce1f6dfeebb2dfba Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:16 -0400 Subject: [PATCH 1432/1507] net: dsa: add slave to master helper Many part of the DSA slave code require to get the master device assigned to a slave device. Remove dsa_master_netdev() in favor of a dsa_slave_to_master() helper which does that. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 13 ++++++++----- net/dsa/slave.c | 26 +++++++++----------------- 2 files changed, 17 insertions(+), 22 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 569a4929b4c90..eedda1f1b0992 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -176,6 +176,14 @@ static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) return p->dp; } +static inline struct net_device * +dsa_slave_to_master(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return dp->cpu_dp->netdev; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); @@ -204,9 +212,4 @@ extern const struct dsa_device_ops qca_netdev_ops; /* tag_trailer.c */ extern const struct dsa_device_ops trailer_netdev_ops; -static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) -{ - return p->dp->cpu_dp->netdev; -} - #endif diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 894602c88b096..b72e07503a40a 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -64,15 +64,12 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) /* slave device handling ****************************************************/ static int dsa_slave_get_iflink(const struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - - return dsa_master_netdev(p)->ifindex; + return dsa_slave_to_master(dev)->ifindex; } static int dsa_slave_open(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); int err; @@ -120,8 +117,7 @@ static int dsa_slave_open(struct net_device *dev) static int dsa_slave_close(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); if (dev->phydev) @@ -144,8 +140,7 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); if (change & IFF_ALLMULTI) dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); @@ -155,8 +150,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change) static void dsa_slave_set_rx_mode(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); dev_mc_sync(master, dev); dev_uc_sync(master, dev); @@ -164,8 +158,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev) static int dsa_slave_set_mac_address(struct net_device *dev, void *a) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct sockaddr *addr = a; int err; @@ -409,7 +402,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - nskb->dev = dsa_master_netdev(p); + nskb->dev = dsa_slave_to_master(dev); dev_queue_xmit(nskb); return NETDEV_TX_OK; @@ -632,8 +625,8 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) static int dsa_slave_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); struct netpoll *netpoll; int err = 0; @@ -1115,8 +1108,7 @@ int dsa_slave_resume(struct net_device *slave_dev) static void dsa_slave_notify(struct net_device *dev, unsigned long val) { - struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = dsa_master_netdev(p); + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_notifier_register_info rinfo = { .switch_number = dp->ds->index, -- GitLab From 2231c43b560403675217f52204b18c1c59c0ee76 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:17 -0400 Subject: [PATCH 1433/1507] net: dsa: rename dsa_master_get_slave The dsa_master_get_slave is slightly confusing since the idiomatic "get" term often suggests reference counting, in symmetry to "put". Rename it to dsa_master_find_slave to make the look up operation clear. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- net/dsa/dsa_priv.h | 4 ++-- net/dsa/tag_brcm.c | 2 +- net/dsa/tag_dsa.c | 2 +- net/dsa/tag_edsa.c | 2 +- net/dsa/tag_ksz.c | 2 +- net/dsa/tag_lan9303.c | 2 +- net/dsa/tag_mtk.c | 2 +- net/dsa/tag_qca.c | 2 +- net/dsa/tag_trailer.c | 2 +- 9 files changed, 10 insertions(+), 10 deletions(-) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index eedda1f1b0992..623c22b75e814 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -113,8 +113,8 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], int dsa_master_ethtool_setup(struct net_device *dev); void dsa_master_ethtool_restore(struct net_device *dev); -static inline struct net_device *dsa_master_get_slave(struct net_device *dev, - int device, int port) +static inline struct net_device *dsa_master_find_slave(struct net_device *dev, + int device, int port) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 2a0fa9f9f7ca8..9e082bae3cb0c 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -119,7 +119,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index fe3c9700a8c84..dbbcdafed8c30 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -91,7 +91,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_get_slave(dev, source_device, source_port); + skb->dev = dsa_master_find_slave(dev, source_device, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index c683e240bafcf..f38a626b3a055 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -104,7 +104,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, source_device = edsa_header[0] & 0x1f; source_port = (edsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_get_slave(dev, source_device, source_port); + skb->dev = dsa_master_find_slave(dev, source_device, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 66e443fd76757..0f62effad88f5 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -87,7 +87,7 @@ static struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, source_port = tag[0] & 7; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index c709adb5efd97..57519597c6fc7 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -94,7 +94,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, source_port = ntohs(lan9303_tag[1]) & 0x3; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 5abebbfd70607..8475434af7d58 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -69,7 +69,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_get_slave(dev, 0, port); + skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index b0274b6781cb0..613f4ee977716 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -91,7 +91,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* Get source port information */ port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_get_slave(dev, 0, port); + skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 8b205bb5f5211..7d20e1f3de28a 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -71,7 +71,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, source_port = trailer[1] & 7; - skb->dev = dsa_master_get_slave(dev, 0, source_port); + skb->dev = dsa_master_find_slave(dev, 0, source_port); if (!skb->dev) return NULL; -- GitLab From f8b8b1cd5aadd221742b45eb0ee3c8a80abf036a Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:18 -0400 Subject: [PATCH 1434/1507] net: dsa: split dsa_port's netdev member The dsa_port structure has a "netdev" member, which can be used for either the master device, or the slave device, depending on its type. It is true that today, CPU port are not exposed to userspace, thus the port's netdev member can be used to point to its master interface. But it is still slightly confusing, so split it into more explicit "master" and "slave" members inside an anonymous union. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 6 +++--- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- include/net/dsa.h | 9 ++++++++- net/dsa/dsa.c | 6 +++--- net/dsa/dsa2.c | 20 ++++++++++---------- net/dsa/dsa_priv.h | 4 ++-- net/dsa/legacy.c | 14 +++++++------- net/dsa/slave.c | 6 +++--- 9 files changed, 38 insertions(+), 31 deletions(-) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 32025b990437c..b43c063b9634a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -601,7 +601,7 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, * state machine and make it go in PHY_FORCING state instead. */ if (!status->link) - netif_carrier_off(ds->ports[port].netdev); + netif_carrier_off(ds->ports[port].slave); status->duplex = 1; } else { status->link = 1; @@ -690,7 +690,7 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->ports[port].cpu_dp->netdev; + struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_wolinfo pwol; @@ -713,7 +713,7 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->ports[port].cpu_dp->netdev; + struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->ports[port].cpu_dp->index; struct ethtool_wolinfo pwol; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 034241696ce21..fea2e665d0cb2 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -933,7 +933,7 @@ mt7530_setup(struct dsa_switch *ds) * controller also is the container for two GMACs nodes representing * as two netdev instances. */ - dn = ds->ports[MT7530_CPU_PORT].netdev->dev.of_node->parent; + dn = ds->ports[MT7530_CPU_PORT].master->dev.of_node->parent; priv->ethernet = syscon_node_to_regmap(dn); if (IS_ERR(priv->ethernet)) return PTR_ERR(priv->ethernet); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 76cf383dcf90c..88b47fa09b41d 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1137,7 +1137,7 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i)) continue; - if (!ds->ports[port].netdev) + if (!ds->ports[port].slave) continue; if (vlan.member[i] == diff --git a/include/net/dsa.h b/include/net/dsa.h index 2746741f74cf4..6ed1a17ed1bd9 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -164,6 +164,14 @@ struct dsa_mall_tc_entry { struct dsa_port { + /* A CPU port is physically connected to a master device. + * A user port exposed to userspace has a slave device. + */ + union { + struct net_device *master; + struct net_device *slave; + }; + /* CPU port tagging operations used by master or slave devices */ const struct dsa_device_ops *tag_ops; @@ -176,7 +184,6 @@ struct dsa_port { unsigned int index; const char *name; struct dsa_port *cpu_dp; - struct net_device *netdev; struct device_node *dn; unsigned int ageing_time; u8 stp_state; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 832c659ff9936..a3abf7a7b9a25 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -201,7 +201,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, #ifdef CONFIG_PM_SLEEP static bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; + return ds->enabled_port_mask & (1 << p) && ds->ports[p].slave; } int dsa_switch_suspend(struct dsa_switch *ds) @@ -213,7 +213,7 @@ int dsa_switch_suspend(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_suspend(ds->ports[i].netdev); + ret = dsa_slave_suspend(ds->ports[i].slave); if (ret) return ret; } @@ -240,7 +240,7 @@ int dsa_switch_resume(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_resume(ds->ports[i].netdev); + ret = dsa_slave_resume(ds->ports[i].slave); if (ret) return ret; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 6ac9e11d385c5..9e8b8aab049dc 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -279,7 +279,7 @@ static int dsa_user_port_apply(struct dsa_port *port) if (err) { dev_warn(ds->dev, "Failed to create slave %d: %d\n", port->index, err); - port->netdev = NULL; + port->slave = NULL; return err; } @@ -289,7 +289,7 @@ static int dsa_user_port_apply(struct dsa_port *port) if (err) return err; - devlink_port_type_eth_set(&port->devlink_port, port->netdev); + devlink_port_type_eth_set(&port->devlink_port, port->slave); return 0; } @@ -297,9 +297,9 @@ static int dsa_user_port_apply(struct dsa_port *port) static void dsa_user_port_unapply(struct dsa_port *port) { devlink_port_unregister(&port->devlink_port); - if (port->netdev) { - dsa_slave_destroy(port->netdev); - port->netdev = NULL; + if (port->slave) { + dsa_slave_destroy(port->slave); + port->slave = NULL; port->ds->enabled_port_mask &= ~(1 << port->index); } } @@ -432,9 +432,9 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) * sent to the tag format's receive function. */ wmb(); - dst->cpu_dp->netdev->dsa_ptr = dst->cpu_dp; + dst->cpu_dp->master->dsa_ptr = dst->cpu_dp; - err = dsa_master_ethtool_setup(dst->cpu_dp->netdev); + err = dsa_master_ethtool_setup(dst->cpu_dp->master); if (err) return err; @@ -451,9 +451,9 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) if (!dst->applied) return; - dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dsa_master_ethtool_restore(dst->cpu_dp->master); - dst->cpu_dp->netdev->dsa_ptr = NULL; + dst->cpu_dp->master->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -499,7 +499,7 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!dst->cpu_dp) { dst->cpu_dp = port; - dst->cpu_dp->netdev = ethernet_dev; + dst->cpu_dp->master = ethernet_dev; } /* Initialize cpu_port_mask now for drv->setup() diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 623c22b75e814..1e9914062d0b2 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -130,7 +130,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, if (port < 0 || port >= ds->num_ports) return NULL; - return ds->ports[port].netdev; + return ds->ports[port].slave; } /* port.c */ @@ -181,7 +181,7 @@ dsa_slave_to_master(const struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - return dp->cpu_dp->netdev; + return dp->cpu_dp->master; } /* switch.c */ diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index cc28c6f792a34..b6c88fd33d4f0 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -120,7 +120,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, return -EINVAL; } dst->cpu_dp = &ds->ports[i]; - dst->cpu_dp->netdev = master; + dst->cpu_dp->master = master; ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; @@ -261,10 +261,10 @@ static void dsa_switch_destroy(struct dsa_switch *ds) if (!(ds->enabled_port_mask & (1 << port))) continue; - if (!ds->ports[port].netdev) + if (!ds->ports[port].slave) continue; - dsa_slave_destroy(ds->ports[port].netdev); + dsa_slave_destroy(ds->ports[port].slave); } /* Disable configuration of the CPU and DSA ports */ @@ -601,7 +601,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, wmb(); dev->dsa_ptr = dst->cpu_dp; - return dsa_master_ethtool_setup(dst->cpu_dp->netdev); + return dsa_master_ethtool_setup(dst->cpu_dp->master); } static int dsa_probe(struct platform_device *pdev) @@ -666,9 +666,9 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; - dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dsa_master_ethtool_restore(dst->cpu_dp->master); - dst->cpu_dp->netdev->dsa_ptr = NULL; + dst->cpu_dp->master->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -683,7 +683,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dev_put(dst->cpu_dp->netdev); + dev_put(dst->cpu_dp->master); } static int dsa_remove(struct platform_device *pdev) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index b72e07503a40a..6906de0f0050d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1123,7 +1123,7 @@ static void dsa_slave_notify(struct net_device *dev, unsigned long val) int dsa_slave_create(struct dsa_port *port, const char *name) { struct dsa_port *cpu_dp = port->cpu_dp; - struct net_device *master = cpu_dp->netdev; + struct net_device *master = cpu_dp->master; struct dsa_switch *ds = port->ds; struct net_device *slave_dev; struct dsa_slave_priv *p; @@ -1170,7 +1170,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) p->old_link = -1; p->old_duplex = -1; - port->netdev = slave_dev; + port->slave = slave_dev; netif_carrier_off(slave_dev); @@ -1198,7 +1198,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) out_free: free_percpu(p->stats64); free_netdev(slave_dev); - port->netdev = NULL; + port->slave = NULL; return ret; } -- GitLab From c8652c83bc84ac8db44060ced0036de7628aa5e5 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 16 Oct 2017 11:12:19 -0400 Subject: [PATCH 1435/1507] net: dsa: add dsa_to_port helper The dsa_port structure is part of DSA core data and must only be updated by the later. It is OK and sometimes necessary for the DSA drivers to access this data, but this has to be read only. For that purpose, add a dsa_to_port() helper which returns a const pointer to a dsa_port structure which must be used by DSA drivers from now on instead of digging into ds->ports[] themselves. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 4 ++-- drivers/net/dsa/lan9303-core.c | 2 +- drivers/net/dsa/mt7530.c | 4 ++-- drivers/net/dsa/mv88e6060.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 8 ++++---- drivers/net/dsa/qca8k.c | 4 ++-- include/net/dsa.h | 5 +++++ 7 files changed, 17 insertions(+), 12 deletions(-) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d4ce092def839..b48cf0487b43f 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1354,7 +1354,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan); b53_for_each_port(dev, i) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Add this local port to the remote port VLAN control @@ -1390,7 +1390,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_for_each_port(dev, i) { /* Don't touch the remaining ports */ - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), ®); diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index fecfe1fe67ea0..09a748327fc64 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -863,7 +863,7 @@ static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); - if (ds->ports[1].bridge_dev == ds->ports[2].bridge_dev) { + if (dsa_to_port(ds, 1)->bridge_dev == dsa_to_port(ds, 2)->bridge_dev) { lan9303_bridge_ports(chip); chip->is_bridged = true; /* unleash stp_state_set() */ } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index fea2e665d0cb2..21431be2831ee 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -782,7 +782,7 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, * and not being setup until the port becomes enabled. */ if (ds->enabled_port_mask & BIT(i) && i != port) { - if (ds->ports[i].bridge_dev != bridge) + if (dsa_to_port(ds, i)->bridge_dev != bridge) continue; if (priv->ports[i].enable) mt7530_set(priv, MT7530_PCR_P(i), @@ -819,7 +819,7 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port, * is kept and not being setup until the port becomes enabled. */ if (ds->enabled_port_mask & BIT(i) && i != port) { - if (ds->ports[i].bridge_dev != bridge) + if (dsa_to_port(ds, i)->bridge_dev != bridge) continue; if (priv->ports[i].enable) mt7530_clear(priv, MT7530_PCR_P(i), diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 6173be889d954..f78b9e13be1cb 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -177,7 +177,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | (dsa_is_cpu_port(ds, p) ? ds->enabled_port_mask : - BIT(ds->ports[p].cpu_dp->index))); + BIT(dsa_to_port(ds, p)->cpu_dp->index))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 88b47fa09b41d..677d6902807ec 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -851,7 +851,7 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) if (dsa_is_cpu_port(chip->ds, i) || dsa_is_dsa_port(chip->ds, i) || - (br && chip->ds->ports[i].bridge_dev == br)) + (br && dsa_to_port(chip->ds, i)->bridge_dev == br)) pvlan |= BIT(i); return pvlan; @@ -1144,16 +1144,16 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER) continue; - if (ds->ports[i].bridge_dev == + if (dsa_to_port(ds, i)->bridge_dev == ds->ports[port].bridge_dev) break; /* same bridge, check next VLAN */ - if (!ds->ports[i].bridge_dev) + if (!dsa_to_port(ds, i)->bridge_dev) continue; dev_err(ds->dev, "p%d: hw VLAN %d already used by %s\n", port, vlan.vid, - netdev_name(ds->ports[i].bridge_dev)); + netdev_name(dsa_to_port(ds, i)->bridge_dev)); err = -EOPNOTSUPP; goto unlock; } diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 82f09711ac1a4..d1b0b1fb632f7 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -700,7 +700,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) int i; for (i = 1; i < QCA8K_NUM_PORTS; i++) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Add this port to the portvlan mask of the other ports * in the bridge @@ -725,7 +725,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) int i; for (i = 1; i < QCA8K_NUM_PORTS; i++) { - if (ds->ports[i].bridge_dev != br) + if (dsa_to_port(ds, i)->bridge_dev != br) continue; /* Remove this port to the portvlan mask of the other ports * in the bridge diff --git a/include/net/dsa.h b/include/net/dsa.h index 6ed1a17ed1bd9..38961ef91d3db 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -269,6 +269,11 @@ static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); } +static inline const struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) +{ + return &ds->ports[p]; +} + static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; -- GitLab From eb4ddaf474285a4c6986f4a1c3205bdb0bed2da9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:45 -0700 Subject: [PATCH 1436/1507] net/decnet: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Johannes Berg Cc: David Ahern Cc: linux-decnet-user@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/net/dn.h | 7 ------- include/net/dn_nsp.h | 1 - net/decnet/af_decnet.c | 4 ---- net/decnet/dn_dev.c | 12 +++++------- net/decnet/dn_nsp_out.c | 11 ----------- 5 files changed, 5 insertions(+), 30 deletions(-) diff --git a/include/net/dn.h b/include/net/dn.h index 913b73d239f54..4394f7d5cfe84 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -122,13 +122,6 @@ struct dn_scp /* Session Control Port */ unsigned long keepalive; void (*keepalive_fxn)(struct sock *sk); - /* - * This stuff is for the fast timer for delayed acks - */ - struct timer_list delack_timer; - int delack_pending; - void (*delack_fxn)(struct sock *sk); - }; static inline struct dn_scp *DN_SK(struct sock *sk) diff --git a/include/net/dn_nsp.h b/include/net/dn_nsp.h index 3a3e33d184562..413a15e5339cb 100644 --- a/include/net/dn_nsp.h +++ b/include/net/dn_nsp.h @@ -17,7 +17,6 @@ void dn_nsp_send_data_ack(struct sock *sk); void dn_nsp_send_oth_ack(struct sock *sk); -void dn_nsp_delayed_ack(struct sock *sk); void dn_send_conn_ack(struct sock *sk); void dn_send_conn_conf(struct sock *sk, gfp_t gfp); void dn_nsp_send_disc(struct sock *sk, unsigned char type, diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 73a0399dc7a27..d4c9a8bbad3e3 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -533,10 +533,6 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf scp->keepalive = 10 * HZ; scp->keepalive_fxn = dn_keepalive; - init_timer(&scp->delack_timer); - scp->delack_pending = 0; - scp->delack_fxn = dn_nsp_delayed_ack; - dn_start_slow_timer(sk); out: return sk; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4d339de56862c..92dbaa3f1eaec 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -1038,14 +1038,14 @@ static void dn_eth_down(struct net_device *dev) static void dn_dev_set_timer(struct net_device *dev); -static void dn_dev_timer_func(unsigned long arg) +static void dn_dev_timer_func(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - struct dn_dev *dn_db; + struct dn_dev *dn_db = from_timer(dn_db, t, timer); + struct net_device *dev; struct dn_ifaddr *ifa; rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); + dev = dn_db->dev; if (dn_db->t3 <= dn_db->parms.t2) { if (dn_db->parms.timer3) { for (ifa = rcu_dereference(dn_db->ifa_list); @@ -1070,8 +1070,6 @@ static void dn_dev_set_timer(struct net_device *dev) if (dn_db->parms.t2 > dn_db->parms.t3) dn_db->parms.t2 = dn_db->parms.t3; - dn_db->timer.data = (unsigned long)dev; - dn_db->timer.function = dn_dev_timer_func; dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ); add_timer(&dn_db->timer); @@ -1100,7 +1098,7 @@ static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) rcu_assign_pointer(dev->dn_ptr, dn_db); dn_db->dev = dev; - init_timer(&dn_db->timer); + timer_setup(&dn_db->timer, dn_dev_timer_func, 0); dn_db->uptime = jiffies; diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 66f035e476eae..e50a4adfcf7e7 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -491,17 +491,6 @@ void dn_send_conn_ack (struct sock *sk) dn_nsp_send(skb); } -void dn_nsp_delayed_ack(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->ackxmt_oth != scp->numoth_rcv) - dn_nsp_send_oth_ack(sk); - - if (scp->ackxmt_dat != scp->numdat_rcv) - dn_nsp_send_data_ack(sk); -} - static int dn_nsp_retrans_conn_conf(struct sock *sk) { struct dn_scp *scp = DN_SK(sk); -- GitLab From 83a37b3292f4aca799b355179ad6fbdd78a08e10 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:46 -0700 Subject: [PATCH 1437/1507] net/lapb: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Hans Liljestrand Cc: "Reshetova, Elena" Cc: linux-x25@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/lapb/lapb_iface.c | 4 ++-- net/lapb/lapb_timer.c | 18 ++++++++---------- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index e15314e3b464b..db6e0afe3a20b 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -127,8 +127,8 @@ static struct lapb_cb *lapb_create_cb(void) skb_queue_head_init(&lapb->write_queue); skb_queue_head_init(&lapb->ack_queue); - init_timer(&lapb->t1timer); - init_timer(&lapb->t2timer); + timer_setup(&lapb->t1timer, NULL, 0); + timer_setup(&lapb->t2timer, NULL, 0); lapb->t1 = LAPB_DEFAULT_T1; lapb->t2 = LAPB_DEFAULT_T2; diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c index 1a5535bc3b8d8..8bb469cb3abeb 100644 --- a/net/lapb/lapb_timer.c +++ b/net/lapb/lapb_timer.c @@ -35,15 +35,14 @@ #include #include -static void lapb_t1timer_expiry(unsigned long); -static void lapb_t2timer_expiry(unsigned long); +static void lapb_t1timer_expiry(struct timer_list *); +static void lapb_t2timer_expiry(struct timer_list *); void lapb_start_t1timer(struct lapb_cb *lapb) { del_timer(&lapb->t1timer); - lapb->t1timer.data = (unsigned long)lapb; - lapb->t1timer.function = &lapb_t1timer_expiry; + lapb->t1timer.function = (TIMER_FUNC_TYPE)lapb_t1timer_expiry; lapb->t1timer.expires = jiffies + lapb->t1; add_timer(&lapb->t1timer); @@ -53,8 +52,7 @@ void lapb_start_t2timer(struct lapb_cb *lapb) { del_timer(&lapb->t2timer); - lapb->t2timer.data = (unsigned long)lapb; - lapb->t2timer.function = &lapb_t2timer_expiry; + lapb->t2timer.function = (TIMER_FUNC_TYPE)lapb_t2timer_expiry; lapb->t2timer.expires = jiffies + lapb->t2; add_timer(&lapb->t2timer); @@ -75,9 +73,9 @@ int lapb_t1timer_running(struct lapb_cb *lapb) return timer_pending(&lapb->t1timer); } -static void lapb_t2timer_expiry(unsigned long param) +static void lapb_t2timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t2timer); if (lapb->condition & LAPB_ACK_PENDING_CONDITION) { lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; @@ -85,9 +83,9 @@ static void lapb_t2timer_expiry(unsigned long param) } } -static void lapb_t1timer_expiry(unsigned long param) +static void lapb_t1timer_expiry(struct timer_list *t) { - struct lapb_cb *lapb = (struct lapb_cb *)param; + struct lapb_cb *lapb = from_timer(lapb, t, t1timer); switch (lapb->state) { -- GitLab From 4966babd904d7f8e9e20735f3637a98fd7ca538c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:47 -0700 Subject: [PATCH 1438/1507] net/rose: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Ralf Baechle Cc: "David S. Miller" Cc: linux-hams@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/rose/af_rose.c | 17 +++++++++-------- net/rose/rose_link.c | 16 +++++++--------- net/rose/rose_loopback.c | 9 +++------ net/rose/rose_route.c | 8 ++++---- net/rose/rose_timer.c | 30 +++++++++++++----------------- 5 files changed, 36 insertions(+), 44 deletions(-) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4a97292570236..6a5c4992cf618 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -318,9 +318,11 @@ void rose_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void rose_destroy_timer(unsigned long data) +static void rose_destroy_timer(struct timer_list *t) { - rose_destroy_socket((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + rose_destroy_socket(sk); } /* @@ -353,8 +355,7 @@ void rose_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - setup_timer(&sk->sk_timer, rose_destroy_timer, - (unsigned long)sk); + timer_setup(&sk->sk_timer, rose_destroy_timer, 0); sk->sk_timer.expires = jiffies + 10 * HZ; add_timer(&sk->sk_timer); } else @@ -538,8 +539,8 @@ static int rose_create(struct net *net, struct socket *sock, int protocol, sock->ops = &rose_proto_ops; sk->sk_protocol = protocol; - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); rose->t1 = msecs_to_jiffies(sysctl_rose_call_request_timeout); rose->t2 = msecs_to_jiffies(sysctl_rose_reset_request_timeout); @@ -582,8 +583,8 @@ static struct sock *rose_make_new(struct sock *osk) sk->sk_state = TCP_ESTABLISHED; sock_copy_flags(sk, osk); - init_timer(&rose->timer); - init_timer(&rose->idletimer); + timer_setup(&rose->timer, NULL, 0); + timer_setup(&rose->idletimer, NULL, 0); orose = rose_sk(osk); rose->t1 = orose->t1; diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index c76638cc2cd53..cda4c6678ef16 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -27,8 +27,8 @@ #include #include -static void rose_ftimer_expiry(unsigned long); -static void rose_t0timer_expiry(unsigned long); +static void rose_ftimer_expiry(struct timer_list *); +static void rose_t0timer_expiry(struct timer_list *); static void rose_transmit_restart_confirmation(struct rose_neigh *neigh); static void rose_transmit_restart_request(struct rose_neigh *neigh); @@ -37,8 +37,7 @@ void rose_start_ftimer(struct rose_neigh *neigh) { del_timer(&neigh->ftimer); - neigh->ftimer.data = (unsigned long)neigh; - neigh->ftimer.function = &rose_ftimer_expiry; + neigh->ftimer.function = (TIMER_FUNC_TYPE)rose_ftimer_expiry; neigh->ftimer.expires = jiffies + msecs_to_jiffies(sysctl_rose_link_fail_timeout); @@ -49,8 +48,7 @@ static void rose_start_t0timer(struct rose_neigh *neigh) { del_timer(&neigh->t0timer); - neigh->t0timer.data = (unsigned long)neigh; - neigh->t0timer.function = &rose_t0timer_expiry; + neigh->t0timer.function = (TIMER_FUNC_TYPE)rose_t0timer_expiry; neigh->t0timer.expires = jiffies + msecs_to_jiffies(sysctl_rose_restart_request_timeout); @@ -77,13 +75,13 @@ static int rose_t0timer_running(struct rose_neigh *neigh) return timer_pending(&neigh->t0timer); } -static void rose_ftimer_expiry(unsigned long param) +static void rose_ftimer_expiry(struct timer_list *t) { } -static void rose_t0timer_expiry(unsigned long param) +static void rose_t0timer_expiry(struct timer_list *t) { - struct rose_neigh *neigh = (struct rose_neigh *)param; + struct rose_neigh *neigh = from_timer(neigh, t, t0timer); rose_transmit_restart_request(neigh); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 344456206b70b..7af4f99c4a932 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -19,12 +19,13 @@ static struct sk_buff_head loopback_queue; static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); +static void rose_loopback_timer(struct timer_list *unused); void rose_loopback_init(void) { skb_queue_head_init(&loopback_queue); - init_timer(&loopback_timer); + timer_setup(&loopback_timer, rose_loopback_timer, 0); } static int rose_loopback_running(void) @@ -50,20 +51,16 @@ int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) return 1; } -static void rose_loopback_timer(unsigned long); static void rose_set_loopback_timer(void) { del_timer(&loopback_timer); - loopback_timer.data = 0; - loopback_timer.function = &rose_loopback_timer; loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); } -static void rose_loopback_timer(unsigned long param) +static void rose_loopback_timer(struct timer_list *unused) { struct sk_buff *skb; struct net_device *dev; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 452bbb38d9432..65921cd103233 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -104,8 +104,8 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route, skb_queue_head_init(&rose_neigh->queue); - init_timer(&rose_neigh->ftimer); - init_timer(&rose_neigh->t0timer); + timer_setup(&rose_neigh->ftimer, NULL, 0); + timer_setup(&rose_neigh->t0timer, NULL, 0); if (rose_route->ndigis != 0) { rose_neigh->digipeat = @@ -390,8 +390,8 @@ void rose_add_loopback_neigh(void) skb_queue_head_init(&sn->queue); - init_timer(&sn->ftimer); - init_timer(&sn->t0timer); + timer_setup(&sn->ftimer, NULL, 0); + timer_setup(&sn->t0timer, NULL, 0); spin_lock_bh(&rose_neigh_list_lock); sn->next = rose_neigh_list; diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index bc5469d6d9cb5..3b89d66f15bbe 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -29,8 +29,8 @@ #include static void rose_heartbeat_expiry(unsigned long); -static void rose_timer_expiry(unsigned long); -static void rose_idletimer_expiry(unsigned long); +static void rose_timer_expiry(struct timer_list *); +static void rose_idletimer_expiry(struct timer_list *); void rose_start_heartbeat(struct sock *sk) { @@ -49,8 +49,7 @@ void rose_start_t1timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t1; add_timer(&rose->timer); @@ -62,8 +61,7 @@ void rose_start_t2timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t2; add_timer(&rose->timer); @@ -75,8 +73,7 @@ void rose_start_t3timer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->t3; add_timer(&rose->timer); @@ -88,8 +85,7 @@ void rose_start_hbtimer(struct sock *sk) del_timer(&rose->timer); - rose->timer.data = (unsigned long)sk; - rose->timer.function = &rose_timer_expiry; + rose->timer.function = (TIMER_FUNC_TYPE)rose_timer_expiry; rose->timer.expires = jiffies + rose->hb; add_timer(&rose->timer); @@ -102,8 +98,7 @@ void rose_start_idletimer(struct sock *sk) del_timer(&rose->idletimer); if (rose->idle > 0) { - rose->idletimer.data = (unsigned long)sk; - rose->idletimer.function = &rose_idletimer_expiry; + rose->idletimer.function = (TIMER_FUNC_TYPE)rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle; add_timer(&rose->idletimer); @@ -163,10 +158,10 @@ static void rose_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_timer_expiry(unsigned long param) +static void rose_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct rose_sock *rose = rose_sk(sk); + struct rose_sock *rose = from_timer(rose, t, timer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); switch (rose->state) { @@ -192,9 +187,10 @@ static void rose_timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void rose_idletimer_expiry(unsigned long param) +static void rose_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct rose_sock *rose = from_timer(rose, t, idletimer); + struct sock *sk = &rose->sock; bh_lock_sock(sk); rose_clear_queues(sk); -- GitLab From 0010e3f8b3537b8e7c8a8e7249f9d184e92df1a5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:50 -0700 Subject: [PATCH 1439/1507] net/ti/tlan: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Samuel Chessman Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/tlan.c | 32 +++++++++++++------------------- 1 file changed, 13 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index c8d53d8c83eeb..8f53d762fbc40 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -172,7 +172,8 @@ static u32 tlan_handle_tx_eoc(struct net_device *, u16); static u32 tlan_handle_status_check(struct net_device *, u16); static u32 tlan_handle_rx_eoc(struct net_device *, u16); -static void tlan_timer(unsigned long); +static void tlan_timer(struct timer_list *t); +static void tlan_phy_monitor(struct timer_list *t); static void tlan_reset_lists(struct net_device *); static void tlan_free_lists(struct net_device *); @@ -190,7 +191,6 @@ static void tlan_phy_power_up(struct net_device *); static void tlan_phy_reset(struct net_device *); static void tlan_phy_start_link(struct net_device *); static void tlan_phy_finish_auto_neg(struct net_device *); -static void tlan_phy_monitor(unsigned long); /* static int tlan_phy_nop(struct net_device *); @@ -254,11 +254,10 @@ tlan_set_timer(struct net_device *dev, u32 ticks, u32 type) spin_unlock_irqrestore(&priv->lock, flags); return; } - priv->timer.function = tlan_timer; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); - priv->timer.data = (unsigned long) dev; priv->timer_set_at = jiffies; priv->timer_type = type; mod_timer(&priv->timer, jiffies + ticks); @@ -926,8 +925,8 @@ static int tlan_open(struct net_device *dev) return err; } - init_timer(&priv->timer); - init_timer(&priv->media_timer); + timer_setup(&priv->timer, NULL, 0); + timer_setup(&priv->media_timer, tlan_phy_monitor, 0); tlan_start(dev); @@ -1426,8 +1425,7 @@ static u32 tlan_handle_tx_eof(struct net_device *dev, u16 host_int) tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); if (priv->timer.function == NULL) { - priv->timer.function = tlan_timer; - priv->timer.data = (unsigned long) dev; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; priv->timer_set_at = jiffies; priv->timer_type = TLAN_TIMER_ACTIVITY; @@ -1578,8 +1576,7 @@ static u32 tlan_handle_rx_eof(struct net_device *dev, u16 host_int) tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); if (priv->timer.function == NULL) { - priv->timer.function = tlan_timer; - priv->timer.data = (unsigned long) dev; + priv->timer.function = (TIMER_FUNC_TYPE)tlan_timer; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; priv->timer_set_at = jiffies; priv->timer_type = TLAN_TIMER_ACTIVITY; @@ -1836,10 +1833,10 @@ ThunderLAN driver timer function * **************************************************************/ -static void tlan_timer(unsigned long data) +static void tlan_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct tlan_priv *priv = netdev_priv(dev); + struct tlan_priv *priv = from_timer(priv, t, timer); + struct net_device *dev = priv->dev; u32 elapsed; unsigned long flags = 0; @@ -1872,7 +1869,6 @@ static void tlan_timer(unsigned long data) tlan_dio_write8(dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK); } else { - priv->timer.function = tlan_timer; priv->timer.expires = priv->timer_set_at + TLAN_TIMER_ACT_DELAY; spin_unlock_irqrestore(&priv->lock, flags); @@ -2317,8 +2313,6 @@ tlan_finish_reset(struct net_device *dev) } else netdev_info(dev, "Link active\n"); /* Enabling link beat monitoring */ - priv->media_timer.function = tlan_phy_monitor; - priv->media_timer.data = (unsigned long) dev; priv->media_timer.expires = jiffies + HZ; add_timer(&priv->media_timer); } @@ -2763,10 +2757,10 @@ static void tlan_phy_finish_auto_neg(struct net_device *dev) * *******************************************************************/ -static void tlan_phy_monitor(unsigned long data) +static void tlan_phy_monitor(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct tlan_priv *priv = netdev_priv(dev); + struct tlan_priv *priv = from_timer(priv, t, media_timer); + struct net_device *dev = priv->dev; u16 phy; u16 phy_status; -- GitLab From 2183c1a61ccc952a836a533c88288289affa2a59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:51 -0700 Subject: [PATCH 1440/1507] net/usb/usbnet: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Since the callback is called from both a timer and a tasklet, adjust the tasklet to pass the timer address too. When tasklets have their .data field removed, this can be refactored to call a central function after resolving the correct container_of() for a separate callback function for timer and tasklet. Cc: Oliver Neukum Cc: netdev@vger.kernel.org Cc: linux-usb@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Oliver Neukum Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 6510e5cc1817c..80348b6a86466 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1509,9 +1509,9 @@ static int rx_alloc_submit(struct usbnet *dev, gfp_t flags) // tasklet (work deferred from completions, in_irq) or timer -static void usbnet_bh (unsigned long param) +static void usbnet_bh (struct timer_list *t) { - struct usbnet *dev = (struct usbnet *) param; + struct usbnet *dev = from_timer(dev, t, delay); struct sk_buff *skb; struct skb_data *entry; @@ -1694,13 +1694,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) skb_queue_head_init (&dev->txq); skb_queue_head_init (&dev->done); skb_queue_head_init(&dev->rxq_pause); - dev->bh.func = usbnet_bh; - dev->bh.data = (unsigned long) dev; + dev->bh.func = (void (*)(unsigned long))usbnet_bh; + dev->bh.data = (unsigned long)&dev->delay; INIT_WORK (&dev->kevent, usbnet_deferred_kevent); init_usb_anchor(&dev->deferred); - dev->delay.function = usbnet_bh; - dev->delay.data = (unsigned long) dev; - init_timer (&dev->delay); + timer_setup(&dev->delay, usbnet_bh, 0); mutex_init (&dev->phy_mutex); mutex_init(&dev->interrupt_mutex); dev->interrupt_count = 0; -- GitLab From d8eb7e262d0d438b23e69d836175b9cec3e4bb90 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:52 -0700 Subject: [PATCH 1441/1507] net/wireless/ray_cs: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Kalle Valo Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/wireless/ray_cs.c | 53 ++++++++++++++++------------------- 1 file changed, 24 insertions(+), 29 deletions(-) diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 170cd504e8ff9..d8afcdfca1ed6 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -92,7 +92,7 @@ static const struct iw_handler_def ray_handler_def; /***** Prototypes for raylink functions **************************************/ static void authenticate(ray_dev_t *local); static int build_auth_frame(ray_dev_t *local, UCHAR *dest, int auth_type); -static void authenticate_timeout(u_long); +static void authenticate_timeout(struct timer_list *t); static int get_free_ccs(ray_dev_t *local); static int get_free_tx_ccs(ray_dev_t *local); static void init_startup_params(ray_dev_t *local); @@ -102,7 +102,7 @@ static int ray_init(struct net_device *dev); static int interrupt_ecf(ray_dev_t *local, int ccs); static void ray_reset(struct net_device *dev); static void ray_update_parm(struct net_device *dev, UCHAR objid, UCHAR *value, int len); -static void verify_dl_startup(u_long); +static void verify_dl_startup(struct timer_list *t); /* Prototypes for interrpt time functions **********************************/ static irqreturn_t ray_interrupt(int reg, void *dev_id); @@ -120,9 +120,8 @@ static void associate(ray_dev_t *local); /* Card command functions */ static int dl_startup_params(struct net_device *dev); -static void join_net(u_long local); -static void start_net(u_long local); -/* void start_net(ray_dev_t *local); */ +static void join_net(struct timer_list *t); +static void start_net(struct timer_list *t); /*===========================================================================*/ /* Parameters that can be set with 'insmod' */ @@ -323,7 +322,7 @@ static int ray_probe(struct pcmcia_device *p_dev) dev_dbg(&p_dev->dev, "ray_cs ray_attach calling ether_setup.)\n"); netif_stop_queue(dev); - init_timer(&local->timer); + timer_setup(&local->timer, NULL, 0); this_device = p_dev; return ray_config(p_dev); @@ -570,8 +569,7 @@ static int dl_startup_params(struct net_device *dev) local->card_status = CARD_DL_PARAM; /* Start kernel timer to wait for dl startup to complete. */ local->timer.expires = jiffies + HZ / 2; - local->timer.data = (long)local; - local->timer.function = verify_dl_startup; + local->timer.function = (TIMER_FUNC_TYPE)verify_dl_startup; add_timer(&local->timer); dev_dbg(&link->dev, "ray_cs dl_startup_params started timer for verify_dl_startup\n"); @@ -641,9 +639,9 @@ static void init_startup_params(ray_dev_t *local) } /* init_startup_params */ /*===========================================================================*/ -static void verify_dl_startup(u_long data) +static void verify_dl_startup(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs = ccs_base(local) + local->dl_param_ccs; UCHAR status; struct pcmcia_device *link = local->finder; @@ -676,16 +674,16 @@ static void verify_dl_startup(u_long data) return; } if (local->sparm.b4.a_network_type == ADHOC) - start_net((u_long) local); + start_net(&local->timer); else - join_net((u_long) local); + join_net(&local->timer); } /* end verify_dl_startup */ /*===========================================================================*/ /* Command card to start a network */ -static void start_net(u_long data) +static void start_net(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs; int ccsindex; struct pcmcia_device *link = local->finder; @@ -710,9 +708,9 @@ static void start_net(u_long data) /*===========================================================================*/ /* Command card to join a network */ -static void join_net(u_long data) +static void join_net(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); struct ccs __iomem *pccs; int ccsindex; @@ -1639,13 +1637,13 @@ static int get_free_ccs(ray_dev_t *local) } /* get_free_ccs */ /*===========================================================================*/ -static void authenticate_timeout(u_long data) +static void authenticate_timeout(struct timer_list *t) { - ray_dev_t *local = (ray_dev_t *) data; + ray_dev_t *local = from_timer(local, t, timer); del_timer(&local->timer); printk(KERN_INFO "ray_cs Authentication with access point failed" " - timeout\n"); - join_net((u_long) local); + join_net(&local->timer); } /*===========================================================================*/ @@ -1945,17 +1943,16 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) del_timer(&local->timer); local->timer.expires = jiffies + HZ * 5; - local->timer.data = (long)local; if (status == CCS_START_NETWORK) { dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" start failed\n", memtmp); - local->timer.function = start_net; + local->timer.function = (TIMER_FUNC_TYPE)start_net; } else { dev_dbg(&link->dev, "ray_cs interrupt network \"%s\" join failed\n", memtmp); - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; } add_timer(&local->timer); } @@ -1967,7 +1964,7 @@ static irqreturn_t ray_interrupt(int irq, void *dev_id) } else { dev_dbg(&link->dev, "ray_cs association failed,\n"); local->card_status = CARD_ASSOC_FAILED; - join_net((u_long) local); + join_net(&local->timer); } break; case CCS_TX_REQUEST: @@ -2420,12 +2417,11 @@ static void authenticate(ray_dev_t *local) del_timer(&local->timer); if (build_auth_frame(local, local->bss_id, OPEN_AUTH_REQUEST)) { - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; } else { - local->timer.function = authenticate_timeout; + local->timer.function = (TIMER_FUNC_TYPE)authenticate_timeout; } local->timer.expires = jiffies + HZ * 2; - local->timer.data = (long)local; add_timer(&local->timer); local->authentication_state = AWAITING_RESPONSE; } /* end authenticate */ @@ -2468,7 +2464,7 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs, } else { pr_debug("Authentication refused\n"); local->card_status = CARD_AUTH_REFUSED; - join_net((u_long) local); + join_net(&local->timer); local->authentication_state = UNAUTHENTICATED; } @@ -2506,8 +2502,7 @@ static void associate(ray_dev_t *local) del_timer(&local->timer); local->timer.expires = jiffies + HZ * 2; - local->timer.data = (long)local; - local->timer.function = join_net; + local->timer.function = (TIMER_FUNC_TYPE)join_net; add_timer(&local->timer); local->card_status = CARD_ASSOC_FAILED; return; -- GitLab From 5e8b824d91b43baa3125ab941e42137ef458e72f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:54 -0700 Subject: [PATCH 1442/1507] isdn/hisax: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Karsten Keil Cc: Geliang Tang Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/hisax/amd7930_fn.c | 6 +++--- drivers/isdn/hisax/arcofi.c | 6 +++--- drivers/isdn/hisax/diva.c | 9 ++++----- drivers/isdn/hisax/elsa.c | 10 +++++----- drivers/isdn/hisax/fsm.c | 7 +++---- drivers/isdn/hisax/hfc4s8s_l1.c | 6 +++--- drivers/isdn/hisax/hfc_2bds0.c | 4 ++-- drivers/isdn/hisax/hfc_pci.c | 9 +++++---- drivers/isdn/hisax/hfc_sx.c | 9 +++++---- drivers/isdn/hisax/hfc_usb.c | 10 ++++++---- drivers/isdn/hisax/hfcscard.c | 5 +++-- drivers/isdn/hisax/icc.c | 6 +++--- drivers/isdn/hisax/ipacx.c | 8 ++++---- drivers/isdn/hisax/isac.c | 6 +++--- drivers/isdn/hisax/isar.c | 9 ++++----- drivers/isdn/hisax/isdnl3.c | 6 +++--- drivers/isdn/hisax/saphir.c | 7 +++---- drivers/isdn/hisax/teleint.c | 5 +++-- drivers/isdn/hisax/w6692.c | 7 +++---- 19 files changed, 68 insertions(+), 67 deletions(-) diff --git a/drivers/isdn/hisax/amd7930_fn.c b/drivers/isdn/hisax/amd7930_fn.c index dcf4c2a9fcea1..77debda2221b1 100644 --- a/drivers/isdn/hisax/amd7930_fn.c +++ b/drivers/isdn/hisax/amd7930_fn.c @@ -398,7 +398,6 @@ Amd7930_fill_Dfifo(struct IsdnCardState *cs) debugl1(cs, "Amd7930: fill_Dfifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dbusytimer); @@ -686,8 +685,9 @@ DC_Close_Amd7930(struct IsdnCardState *cs) { static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); u_long flags; struct PStack *stptr; WORD dtcr, der; @@ -790,5 +790,5 @@ void Amd7930_init(struct IsdnCardState *cs) void setup_Amd7930(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, Amd7930_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/arcofi.c b/drivers/isdn/hisax/arcofi.c index 9826bad49e2c1..2f784f96d439c 100644 --- a/drivers/isdn/hisax/arcofi.c +++ b/drivers/isdn/hisax/arcofi.c @@ -23,7 +23,6 @@ add_arcofi_timer(struct IsdnCardState *cs) { if (test_and_set_bit(FLG_ARCOFI_TIMER, &cs->HW_Flags)) { del_timer(&cs->dc.isac.arcofitimer); } - init_timer(&cs->dc.isac.arcofitimer); cs->dc.isac.arcofitimer.expires = jiffies + ((ARCOFI_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dc.isac.arcofitimer); } @@ -112,7 +111,8 @@ arcofi_fsm(struct IsdnCardState *cs, int event, void *data) { } static void -arcofi_timer(struct IsdnCardState *cs) { +arcofi_timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dc.isac.arcofitimer); arcofi_fsm(cs, ARCOFI_TIMEOUT, NULL); } @@ -125,7 +125,7 @@ clear_arcofi(struct IsdnCardState *cs) { void init_arcofi(struct IsdnCardState *cs) { - setup_timer(&cs->dc.isac.arcofitimer, (void *)arcofi_timer, (long)cs); + timer_setup(&cs->dc.isac.arcofitimer, arcofi_timer, 0); init_waitqueue_head(&cs->dc.isac.arcofi_wait); test_and_set_bit(HW_ARCOFI, &cs->HW_Flags); } diff --git a/drivers/isdn/hisax/diva.c b/drivers/isdn/hisax/diva.c index 3fc94e7741ae7..38bdd3f7b9600 100644 --- a/drivers/isdn/hisax/diva.c +++ b/drivers/isdn/hisax/diva.c @@ -798,8 +798,9 @@ reset_diva(struct IsdnCardState *cs) #define DIVA_ASSIGN 1 static void -diva_led_handler(struct IsdnCardState *cs) +diva_led_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.diva.tl); int blink = 0; if ((cs->subtyp == DIVA_IPAC_ISA) || @@ -828,7 +829,6 @@ diva_led_handler(struct IsdnCardState *cs) byteout(cs->hw.diva.ctrl, cs->hw.diva.ctrl_reg); if (blink) { - init_timer(&cs->hw.diva.tl); cs->hw.diva.tl.expires = jiffies + ((blink * HZ) / 1000); add_timer(&cs->hw.diva.tl); } @@ -900,7 +900,7 @@ Diva_card_msg(struct IsdnCardState *cs, int mt, void *arg) (cs->subtyp != DIVA_IPAC_PCI) && (cs->subtyp != DIVA_IPACX_PCI)) { spin_lock_irqsave(&cs->lock, flags); - diva_led_handler(cs); + diva_led_handler(&cs->hw.diva.tl); spin_unlock_irqrestore(&cs->lock, flags); } return (0); @@ -978,8 +978,7 @@ static int setup_diva_common(struct IsdnCardState *cs) printk(KERN_INFO "Diva: IPACX Design Id: %x\n", MemReadISAC_IPACX(cs, IPACX_ID) & 0x3F); } else { /* DIVA 2.0 */ - setup_timer(&cs->hw.diva.tl, (void *)diva_led_handler, - (long)cs); + timer_setup(&cs->hw.diva.tl, diva_led_handler, 0); cs->readisac = &ReadISAC; cs->writeisac = &WriteISAC; cs->readisacfifo = &ReadISACfifo; diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c index 03bc5d504e226..b21c05820f449 100644 --- a/drivers/isdn/hisax/elsa.c +++ b/drivers/isdn/hisax/elsa.c @@ -606,8 +606,9 @@ check_arcofi(struct IsdnCardState *cs) #endif /* ARCOFI_USE */ static void -elsa_led_handler(struct IsdnCardState *cs) +elsa_led_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.elsa.tl); int blink = 0; if (cs->subtyp == ELSA_PCMCIA || cs->subtyp == ELSA_PCMCIA_IPAC) @@ -640,7 +641,6 @@ elsa_led_handler(struct IsdnCardState *cs) } else byteout(cs->hw.elsa.ctrl, cs->hw.elsa.ctrl_reg); if (blink) { - init_timer(&cs->hw.elsa.tl); cs->hw.elsa.tl.expires = jiffies + ((blink * HZ) / 1000); add_timer(&cs->hw.elsa.tl); } @@ -715,7 +715,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg) init_modem(cs); } #endif - elsa_led_handler(cs); + elsa_led_handler(&cs->hw.elsa.tl); return (ret); case (MDL_REMOVE | REQUEST): cs->hw.elsa.status &= 0; @@ -767,7 +767,7 @@ Elsa_card_msg(struct IsdnCardState *cs, int mt, void *arg) else cs->hw.elsa.status &= ~ELSA_BAD_PWR; } - elsa_led_handler(cs); + elsa_led_handler(&cs->hw.elsa.tl); return (ret); } @@ -1147,7 +1147,7 @@ static int setup_elsa_common(struct IsdnCard *card) init_arcofi(cs); #endif setup_isac(cs); - setup_timer(&cs->hw.elsa.tl, (void *)elsa_led_handler, (long)cs); + timer_setup(&cs->hw.elsa.tl, elsa_led_handler, 0); /* Teste Timer */ if (cs->hw.elsa.timer) { byteout(cs->hw.elsa.trig, 0xff); diff --git a/drivers/isdn/hisax/fsm.c b/drivers/isdn/hisax/fsm.c index d63266fa8cbdb..3e020ec0f65e0 100644 --- a/drivers/isdn/hisax/fsm.c +++ b/drivers/isdn/hisax/fsm.c @@ -85,8 +85,9 @@ FsmChangeState(struct FsmInst *fi, int newstate) } static void -FsmExpireTimer(struct FsmTimer *ft) +FsmExpireTimer(struct timer_list *t) { + struct FsmTimer *ft = from_timer(ft, t, tl); #if FSM_TIMER_DEBUG if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft); @@ -102,7 +103,7 @@ FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft) if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmInitTimer %lx", (long) ft); #endif - setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft); + timer_setup(&ft->tl, FsmExpireTimer, 0); } void @@ -131,7 +132,6 @@ FsmAddTimer(struct FsmTimer *ft, ft->fi->printdebug(ft->fi, "FsmAddTimer already active!"); return -1; } - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; @@ -152,7 +152,6 @@ FsmRestartTimer(struct FsmTimer *ft, if (timer_pending(&ft->tl)) del_timer(&ft->tl); - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 9090cc1e1f299..e9bb8fb67ad08 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -591,8 +591,9 @@ bch_l2l1(struct hisax_if *ifc, int pr, void *arg) /* layer 1 timer function */ /**************************/ static void -hfc_l1_timer(struct hfc4s8s_l1 *l1) +hfc_l1_timer(struct timer_list *t) { + struct hfc4s8s_l1 *l1 = from_timer(l1, t, l1_timer); u_long flags; if (!l1->enabled) @@ -1396,8 +1397,7 @@ setup_instance(hfc4s8s_hw *hw) l1p = hw->l1 + i; spin_lock_init(&l1p->lock); l1p->hw = hw; - setup_timer(&l1p->l1_timer, (void *)hfc_l1_timer, - (long)(l1p)); + timer_setup(&l1p->l1_timer, hfc_l1_timer, 0); l1p->st_num = i; skb_queue_head_init(&l1p->d_tx_queue); l1p->d_if.ifc.priv = hw->l1 + i; diff --git a/drivers/isdn/hisax/hfc_2bds0.c b/drivers/isdn/hisax/hfc_2bds0.c index ad8597a1a07ef..86b82172e9927 100644 --- a/drivers/isdn/hisax/hfc_2bds0.c +++ b/drivers/isdn/hisax/hfc_2bds0.c @@ -1014,7 +1014,7 @@ setstack_hfcd(struct PStack *st, struct IsdnCardState *cs) } static void -hfc_dbusy_timer(struct IsdnCardState *cs) +hfc_dbusy_timer(struct timer_list *t) { } @@ -1073,6 +1073,6 @@ set_cs_func(struct IsdnCardState *cs) cs->writeisacfifo = &dummyf; cs->BC_Read_Reg = &ReadReg; cs->BC_Write_Reg = &WriteReg; - setup_timer(&cs->dbusytimer, (void *)hfc_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfc_dbusy_timer, 0); INIT_WORK(&cs->tqueue, hfcd_bh); } diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c index f9ca35cc32b13..8e5b03161b2ff 100644 --- a/drivers/isdn/hisax/hfc_pci.c +++ b/drivers/isdn/hisax/hfc_pci.c @@ -165,8 +165,9 @@ reset_hfcpci(struct IsdnCardState *cs) /* Timer function called when kernel timer expires */ /***************************************************/ static void -hfcpci_Timer(struct IsdnCardState *cs) +hfcpci_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcpci.timer); cs->hw.hfcpci.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcpci.ctmt | 0x80); @@ -1095,7 +1096,7 @@ hfcpci_interrupt(int intno, void *dev_id) /* timer callback for D-chan busy resolution. Currently no function */ /********************************************************************/ static void -hfcpci_dbusy_timer(struct IsdnCardState *cs) +hfcpci_dbusy_timer(struct timer_list *t) { } @@ -1582,7 +1583,7 @@ inithfcpci(struct IsdnCardState *cs) cs->bcs[1].BC_SetStack = setstack_2b; cs->bcs[0].BC_Close = close_hfcpci; cs->bcs[1].BC_Close = close_hfcpci; - setup_timer(&cs->dbusytimer, (void *)hfcpci_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfcpci_dbusy_timer, 0); mode_hfcpci(cs->bcs, 0, 0); mode_hfcpci(cs->bcs + 1, 0, 1); } @@ -1744,7 +1745,7 @@ setup_hfcpci(struct IsdnCard *card) cs->BC_Write_Reg = NULL; cs->irq_func = &hfcpci_interrupt; cs->irq_flags |= IRQF_SHARED; - setup_timer(&cs->hw.hfcpci.timer, (void *)hfcpci_Timer, (long)cs); + timer_setup(&cs->hw.hfcpci.timer, hfcpci_Timer, 0); cs->cardmsg = &hfcpci_card_msg; cs->auxcmd = &hfcpci_auxcmd; diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c index 3aef8e1a90e44..d925f579bc802 100644 --- a/drivers/isdn/hisax/hfc_sx.c +++ b/drivers/isdn/hisax/hfc_sx.c @@ -418,8 +418,9 @@ reset_hfcsx(struct IsdnCardState *cs) /* Timer function called when kernel timer expires */ /***************************************************/ static void -hfcsx_Timer(struct IsdnCardState *cs) +hfcsx_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcsx.timer); cs->hw.hfcsx.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcsx.ctmt | 0x80); @@ -860,7 +861,7 @@ hfcsx_interrupt(int intno, void *dev_id) /* timer callback for D-chan busy resolution. Currently no function */ /********************************************************************/ static void -hfcsx_dbusy_timer(struct IsdnCardState *cs) +hfcsx_dbusy_timer(struct timer_list *t) { } @@ -1495,7 +1496,7 @@ int setup_hfcsx(struct IsdnCard *card) } else return (0); /* no valid card type */ - setup_timer(&cs->dbusytimer, (void *)hfcsx_dbusy_timer, (long)cs); + timer_setup(&cs->dbusytimer, hfcsx_dbusy_timer, 0); INIT_WORK(&cs->tqueue, hfcsx_bh); cs->readisac = NULL; cs->writeisac = NULL; @@ -1507,7 +1508,7 @@ int setup_hfcsx(struct IsdnCard *card) cs->hw.hfcsx.b_fifo_size = 0; /* fifo size still unknown */ cs->hw.hfcsx.cirm = ccd_sp_irqtab[cs->irq & 0xF]; /* RAM not evaluated */ - setup_timer(&cs->hw.hfcsx.timer, (void *)hfcsx_Timer, (long)cs); + timer_setup(&cs->hw.hfcsx.timer, hfcsx_Timer, 0); reset_hfcsx(cs); cs->cardmsg = &hfcsx_card_msg; diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c index e8212185d3867..97ecb30730456 100644 --- a/drivers/isdn/hisax/hfc_usb.c +++ b/drivers/isdn/hisax/hfc_usb.c @@ -343,8 +343,9 @@ handle_led(hfcusb_data *hfc, int event) /* ISDN l1 timer T3 expires */ static void -l1_timer_expire_t3(hfcusb_data *hfc) +l1_timer_expire_t3(struct timer_list *t) { + hfcusb_data *hfc = from_timer(hfc, t, t3_timer); hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION, NULL); @@ -360,8 +361,9 @@ l1_timer_expire_t3(hfcusb_data *hfc) /* ISDN l1 timer T4 expires */ static void -l1_timer_expire_t4(hfcusb_data *hfc) +l1_timer_expire_t4(struct timer_list *t) { + hfcusb_data *hfc = from_timer(hfc, t, t4_timer); hfc->d_if.ifc.l1l2(&hfc->d_if.ifc, PH_DEACTIVATE | INDICATION, NULL); @@ -1165,10 +1167,10 @@ hfc_usb_init(hfcusb_data *hfc) hfc->old_led_state = 0; /* init the t3 timer */ - setup_timer(&hfc->t3_timer, (void *)l1_timer_expire_t3, (long)hfc); + timer_setup(&hfc->t3_timer, l1_timer_expire_t3, 0); /* init the t4 timer */ - setup_timer(&hfc->t4_timer, (void *)l1_timer_expire_t4, (long)hfc); + timer_setup(&hfc->t4_timer, l1_timer_expire_t4, 0); /* init the background machinery for control requests */ hfc->ctrl_read.bRequestType = 0xc0; diff --git a/drivers/isdn/hisax/hfcscard.c b/drivers/isdn/hisax/hfcscard.c index 467287096918a..380bbeda9c74f 100644 --- a/drivers/isdn/hisax/hfcscard.c +++ b/drivers/isdn/hisax/hfcscard.c @@ -41,8 +41,9 @@ hfcs_interrupt(int intno, void *dev_id) } static void -hfcs_Timer(struct IsdnCardState *cs) +hfcs_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfcD.timer); cs->hw.hfcD.timer.expires = jiffies + 75; /* WD RESET */ /* WriteReg(cs, HFCD_DATA, HFCD_CTMT, cs->hw.hfcD.ctmt | 0x80); @@ -253,7 +254,7 @@ int setup_hfcs(struct IsdnCard *card) outb(0x57, cs->hw.hfcD.addr | 1); } set_cs_func(cs); - setup_timer(&cs->hw.hfcD.timer, (void *)hfcs_Timer, (long)cs); + timer_setup(&cs->hw.hfcD.timer, hfcs_Timer, 0); cs->cardmsg = &hfcs_card_msg; cs->irq_func = &hfcs_interrupt; return (1); diff --git a/drivers/isdn/hisax/icc.c b/drivers/isdn/hisax/icc.c index 8d1804572b328..831dd1bb81ef0 100644 --- a/drivers/isdn/hisax/icc.c +++ b/drivers/isdn/hisax/icc.c @@ -168,7 +168,6 @@ icc_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "icc_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -580,8 +579,9 @@ DC_Close_icc(struct IsdnCardState *cs) { } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; @@ -676,5 +676,5 @@ clear_pending_icc_ints(struct IsdnCardState *cs) void setup_icc(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, icc_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/ipacx.c b/drivers/isdn/hisax/ipacx.c index c426b4fea28a3..c7086c1534bdf 100644 --- a/drivers/isdn/hisax/ipacx.c +++ b/drivers/isdn/hisax/ipacx.c @@ -35,7 +35,7 @@ static void ph_command(struct IsdnCardState *cs, unsigned int command); static inline void cic_int(struct IsdnCardState *cs); static void dch_l2l1(struct PStack *st, int pr, void *arg); -static void dbusy_timer_handler(struct IsdnCardState *cs); +static void dbusy_timer_handler(struct timer_list *t); static void dch_empty_fifo(struct IsdnCardState *cs, int count); static void dch_fill_fifo(struct IsdnCardState *cs); static inline void dch_int(struct IsdnCardState *cs); @@ -198,8 +198,9 @@ dch_l2l1(struct PStack *st, int pr, void *arg) //---------------------------------------------------------- //---------------------------------------------------------- static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *st; int rbchd, stard; @@ -298,7 +299,6 @@ dch_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "dch_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); @@ -424,7 +424,7 @@ dch_init(struct IsdnCardState *cs) cs->setstack_d = dch_setstack; - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); cs->writeisac(cs, IPACX_TR_CONF0, 0x00); // clear LDD cs->writeisac(cs, IPACX_TR_CONF2, 0x00); // enable transmitter diff --git a/drivers/isdn/hisax/isac.c b/drivers/isdn/hisax/isac.c index ea965f29a555c..bd40e0671ded2 100644 --- a/drivers/isdn/hisax/isac.c +++ b/drivers/isdn/hisax/isac.c @@ -171,7 +171,6 @@ isac_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "isac_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -584,8 +583,9 @@ DC_Close_isac(struct IsdnCardState *cs) } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; @@ -677,5 +677,5 @@ void clear_pending_isac_ints(struct IsdnCardState *cs) void setup_isac(struct IsdnCardState *cs) { INIT_WORK(&cs->tqueue, isac_bh); - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); } diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c index 98b4b67ea3378..d01ff116797b9 100644 --- a/drivers/isdn/hisax/isar.c +++ b/drivers/isdn/hisax/isar.c @@ -1267,7 +1267,8 @@ isar_int_main(struct IsdnCardState *cs) } static void -ftimer_handler(struct BCState *bcs) { +ftimer_handler(struct timer_list *t) { + struct BCState *bcs = from_timer(bcs, t, hw.isar.ftimer); if (bcs->cs->debug) debugl1(bcs->cs, "ftimer flags %04lx", bcs->Flag); @@ -1902,8 +1903,6 @@ void initisar(struct IsdnCardState *cs) cs->bcs[1].BC_SetStack = setstack_isar; cs->bcs[0].BC_Close = close_isarstate; cs->bcs[1].BC_Close = close_isarstate; - setup_timer(&cs->bcs[0].hw.isar.ftimer, (void *)ftimer_handler, - (long)&cs->bcs[0]); - setup_timer(&cs->bcs[1].hw.isar.ftimer, (void *)ftimer_handler, - (long)&cs->bcs[1]); + timer_setup(&cs->bcs[0].hw.isar.ftimer, ftimer_handler, 0); + timer_setup(&cs->bcs[1].hw.isar.ftimer, ftimer_handler, 0); } diff --git a/drivers/isdn/hisax/isdnl3.c b/drivers/isdn/hisax/isdnl3.c index 569ce52c567b2..bb3f9ec62749e 100644 --- a/drivers/isdn/hisax/isdnl3.c +++ b/drivers/isdn/hisax/isdnl3.c @@ -160,8 +160,9 @@ newl3state(struct l3_process *pc, int state) } static void -L3ExpireTimer(struct L3Timer *t) +L3ExpireTimer(struct timer_list *timer) { + struct L3Timer *t = from_timer(t, timer, tl); t->pc->st->lli.l4l3(t->pc->st, t->event, t->pc); } @@ -169,7 +170,7 @@ void L3InitTimer(struct l3_process *pc, struct L3Timer *t) { t->pc = pc; - setup_timer(&t->tl, (void *)L3ExpireTimer, (long)t); + timer_setup(&t->tl, L3ExpireTimer, 0); } void @@ -186,7 +187,6 @@ L3AddTimer(struct L3Timer *t, printk(KERN_WARNING "L3AddTimer: timer already active!\n"); return -1; } - init_timer(&t->tl); t->event = event; t->tl.expires = jiffies + (millisec * HZ) / 1000; add_timer(&t->tl); diff --git a/drivers/isdn/hisax/saphir.c b/drivers/isdn/hisax/saphir.c index 6b2d0eccdd562..db906cb37a3fe 100644 --- a/drivers/isdn/hisax/saphir.c +++ b/drivers/isdn/hisax/saphir.c @@ -159,8 +159,9 @@ saphir_interrupt(int intno, void *dev_id) } static void -SaphirWatchDog(struct IsdnCardState *cs) +SaphirWatchDog(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.saphir.timer); u_long flags; spin_lock_irqsave(&cs->lock, flags); @@ -268,9 +269,7 @@ int setup_saphir(struct IsdnCard *card) cs->irq, cs->hw.saphir.cfg_reg); setup_isac(cs); - cs->hw.saphir.timer.function = (void *) SaphirWatchDog; - cs->hw.saphir.timer.data = (long) cs; - init_timer(&cs->hw.saphir.timer); + timer_setup(&cs->hw.saphir.timer, SaphirWatchDog, 0); cs->hw.saphir.timer.expires = jiffies + 4 * HZ; add_timer(&cs->hw.saphir.timer); if (saphir_reset(cs)) { diff --git a/drivers/isdn/hisax/teleint.c b/drivers/isdn/hisax/teleint.c index 950399f066ef1..247aa33076b10 100644 --- a/drivers/isdn/hisax/teleint.c +++ b/drivers/isdn/hisax/teleint.c @@ -179,8 +179,9 @@ TeleInt_interrupt(int intno, void *dev_id) } static void -TeleInt_Timer(struct IsdnCardState *cs) +TeleInt_Timer(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, hw.hfc.timer); int stat = 0; u_long flags; @@ -278,7 +279,7 @@ int setup_TeleInt(struct IsdnCard *card) cs->bcs[0].hw.hfc.send = NULL; cs->bcs[1].hw.hfc.send = NULL; cs->hw.hfc.fifosize = 7 * 1024 + 512; - setup_timer(&cs->hw.hfc.timer, (void *)TeleInt_Timer, (long)cs); + timer_setup(&cs->hw.hfc.timer, TeleInt_Timer, 0); if (!request_region(cs->hw.hfc.addr, 2, "TeleInt isdn")) { printk(KERN_WARNING "HiSax: TeleInt config port %x-%x already in use\n", diff --git a/drivers/isdn/hisax/w6692.c b/drivers/isdn/hisax/w6692.c index 6f6733b7c1e41..c4be1644f5bb5 100644 --- a/drivers/isdn/hisax/w6692.c +++ b/drivers/isdn/hisax/w6692.c @@ -188,7 +188,6 @@ W6692_fill_fifo(struct IsdnCardState *cs) debugl1(cs, "W6692_fill_fifo dbusytimer running"); del_timer(&cs->dbusytimer); } - init_timer(&cs->dbusytimer); cs->dbusytimer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&cs->dbusytimer); if (cs->debug & L1_DEB_ISAC_FIFO) { @@ -684,8 +683,9 @@ DC_Close_W6692(struct IsdnCardState *cs) } static void -dbusy_timer_handler(struct IsdnCardState *cs) +dbusy_timer_handler(struct timer_list *t) { + struct IsdnCardState *cs = from_timer(cs, t, dbusytimer); struct PStack *stptr; int rbch, star; u_long flags; @@ -904,8 +904,7 @@ static void initW6692(struct IsdnCardState *cs, int part) if (part & 1) { cs->setstack_d = setstack_W6692; cs->DC_Close = DC_Close_W6692; - setup_timer(&cs->dbusytimer, (void *)dbusy_timer_handler, - (long)cs); + timer_setup(&cs->dbusytimer, dbusy_timer_handler, 0); resetW6692(cs); ph_command(cs, W_L1CMD_RST); cs->dc.w6692.ph_state = W_L1CMD_RST; -- GitLab From 8e763de0b91d9cdc68a80c4e5efd545f5fb644de Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:55 -0700 Subject: [PATCH 1443/1507] net/hamradio/6pack: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Andreas Koensgen Cc: linux-hams@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/hamradio/6pack.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 97fe8dfb602d8..bbc7b7808a31c 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -136,9 +136,9 @@ static int encode_sixpack(unsigned char *, unsigned char *, int, unsigned char); * Note that in case of DAMA operation, the data is not sent here. */ -static void sp_xmit_on_air(unsigned long channel) +static void sp_xmit_on_air(struct timer_list *t) { - struct sixpack *sp = (struct sixpack *) channel; + struct sixpack *sp = from_timer(sp, t, tx_t); int actual, when = sp->slottime; static unsigned char random; @@ -229,7 +229,7 @@ static void sp_encaps(struct sixpack *sp, unsigned char *icp, int len) sp->xleft = count; sp->xhead = sp->xbuff; sp->status2 = count; - sp_xmit_on_air((unsigned long)sp); + sp_xmit_on_air(&sp->tx_t); } return; @@ -500,9 +500,9 @@ static inline void tnc_set_sync_state(struct sixpack *sp, int new_tnc_state) __tnc_set_sync_state(sp, new_tnc_state); } -static void resync_tnc(unsigned long channel) +static void resync_tnc(struct timer_list *t) { - struct sixpack *sp = (struct sixpack *) channel; + struct sixpack *sp = from_timer(sp, t, resync_t); static char resync_cmd = 0xe8; /* clear any data that might have been received */ @@ -526,8 +526,6 @@ static void resync_tnc(unsigned long channel) /* Start resync timer again -- the TNC might be still absent */ del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; add_timer(&sp->resync_t); } @@ -541,8 +539,6 @@ static inline int tnc_init(struct sixpack *sp) sp->tty->ops->write(sp->tty, &inbyte, 1); del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; add_timer(&sp->resync_t); @@ -623,9 +619,9 @@ static int sixpack_open(struct tty_struct *tty) netif_start_queue(dev); - setup_timer(&sp->tx_t, sp_xmit_on_air, (unsigned long)sp); + timer_setup(&sp->tx_t, sp_xmit_on_air, 0); - init_timer(&sp->resync_t); + timer_setup(&sp->resync_t, resync_tnc, 0); spin_unlock_bh(&sp->lock); @@ -926,8 +922,6 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd) if (sp->tnc_state == TNC_IN_SYNC) { del_timer(&sp->resync_t); - sp->resync_t.data = (unsigned long) sp; - sp->resync_t.function = resync_tnc; sp->resync_t.expires = jiffies + SIXP_INIT_RESYNC_TIMEOUT; add_timer(&sp->resync_t); } -- GitLab From c3aed70953c39274bb55fe98e9b8344af1a7af75 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:56 -0700 Subject: [PATCH 1444/1507] xfrm: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() helper to pass the timer pointer explicitly. Cc: Steffen Klassert Cc: Herbert Xu Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/xfrm/xfrm_policy.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f06253969972a..4838329bb43a7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -57,7 +57,7 @@ static __read_mostly seqcount_t xfrm_policy_hash_generation; static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); -static void xfrm_policy_queue_process(unsigned long arg); +static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, @@ -179,9 +179,9 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static void xfrm_policy_timer(unsigned long data) +static void xfrm_policy_timer(struct timer_list *t) { - struct xfrm_policy *xp = (struct xfrm_policy *)data; + struct xfrm_policy *xp = from_timer(xp, t, timer); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -267,10 +267,9 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); - setup_timer(&policy->timer, xfrm_policy_timer, - (unsigned long)policy); - setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process, - (unsigned long)policy); + timer_setup(&policy->timer, xfrm_policy_timer, 0); + timer_setup(&policy->polq.hold_timer, + xfrm_policy_queue_process, 0); } return policy; } @@ -1852,12 +1851,12 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, return xdst; } -static void xfrm_policy_queue_process(unsigned long arg) +static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; - struct xfrm_policy *pol = (struct xfrm_policy *)arg; + struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; -- GitLab From eb8c6b5b4402581a805a5d8a736a7058c4c5abb7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:57 -0700 Subject: [PATCH 1445/1507] ethernet/broadcom: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() helper to pass the timer pointer explicitly. Cc: Florian Fainelli Cc: bcm-kernel-feedback-list@broadcom.com Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Jarod Wilson Cc: netdev@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 24 ++++++++------------ 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index f6bc13fe8a997..d9346e2ac7205 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -295,16 +295,13 @@ static int bcm_enet_refill_rx(struct net_device *dev) /* * timer callback to defer refill rx queue in case we're OOM */ -static void bcm_enet_refill_rx_timer(unsigned long data) +static void bcm_enet_refill_rx_timer(struct timer_list *t) { - struct net_device *dev; - struct bcm_enet_priv *priv; - - dev = (struct net_device *)data; - priv = netdev_priv(dev); + struct bcm_enet_priv *priv = from_timer(priv, t, rx_timeout); + struct net_device *dev = priv->net_dev; spin_lock(&priv->rx_lock); - bcm_enet_refill_rx((struct net_device *)data); + bcm_enet_refill_rx(dev); spin_unlock(&priv->rx_lock); } @@ -1860,8 +1857,7 @@ static int bcm_enet_probe(struct platform_device *pdev) spin_lock_init(&priv->rx_lock); /* init rx timeout (used for oom) */ - setup_timer(&priv->rx_timeout, bcm_enet_refill_rx_timer, - (unsigned long)dev); + timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0); /* init the mib update lock&work */ mutex_init(&priv->mib_update_lock); @@ -2015,9 +2011,9 @@ static inline int bcm_enet_port_is_rgmii(int portid) /* * enet sw PHY polling */ -static void swphy_poll_timer(unsigned long data) +static void swphy_poll_timer(struct timer_list *t) { - struct bcm_enet_priv *priv = (struct bcm_enet_priv *)data; + struct bcm_enet_priv *priv = from_timer(priv, t, swphy_poll); unsigned int i; for (i = 0; i < priv->num_ports; i++) { @@ -2326,7 +2322,7 @@ static int bcm_enetsw_open(struct net_device *dev) } /* start phy polling timer */ - setup_timer(&priv->swphy_poll, swphy_poll_timer, (unsigned long)priv); + timer_setup(&priv->swphy_poll, swphy_poll_timer, 0); mod_timer(&priv->swphy_poll, jiffies); return 0; @@ -2743,9 +2739,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev) spin_lock_init(&priv->rx_lock); /* init rx timeout (used for oom) */ - init_timer(&priv->rx_timeout); - priv->rx_timeout.function = bcm_enet_refill_rx_timer; - priv->rx_timeout.data = (unsigned long)dev; + timer_setup(&priv->rx_timeout, bcm_enet_refill_rx_timer, 0); /* register netdevice */ dev->netdev_ops = &bcm_enetsw_ops; -- GitLab From 41fce7034bf39721a30d7e6f2cb479808d7aea78 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:58 -0700 Subject: [PATCH 1446/1507] net: tulip: de2104x: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: "yuval.shaia@oracle.com" Cc: Tobias Klauser Cc: Jarod Wilson Cc: Philippe Reynes Cc: netdev@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/dec/tulip/de2104x.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index c87b8cc429638..13430f75496cc 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -333,8 +333,8 @@ static void de_set_rx_mode (struct net_device *dev); static void de_tx (struct de_private *de); static void de_clean_rings (struct de_private *de); static void de_media_interrupt (struct de_private *de, u32 status); -static void de21040_media_timer (unsigned long data); -static void de21041_media_timer (unsigned long data); +static void de21040_media_timer (struct timer_list *t); +static void de21041_media_timer (struct timer_list *t); static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media); @@ -959,9 +959,9 @@ static void de_next_media (struct de_private *de, const u32 *media, } } -static void de21040_media_timer (unsigned long data) +static void de21040_media_timer (struct timer_list *t) { - struct de_private *de = (struct de_private *) data; + struct de_private *de = from_timer(de, t, media_timer); struct net_device *dev = de->dev; u32 status = dr32(SIAStatus); unsigned int carrier; @@ -1040,9 +1040,9 @@ static unsigned int de_ok_to_advertise (struct de_private *de, u32 new_media) return 1; } -static void de21041_media_timer (unsigned long data) +static void de21041_media_timer (struct timer_list *t) { - struct de_private *de = (struct de_private *) data; + struct de_private *de = from_timer(de, t, media_timer); struct net_device *dev = de->dev; u32 status = dr32(SIAStatus); unsigned int carrier; @@ -1999,12 +1999,9 @@ static int de_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) de->msg_enable = (debug < 0 ? DE_DEF_MSG_ENABLE : debug); de->board_idx = board_idx; spin_lock_init (&de->lock); - init_timer(&de->media_timer); - if (de->de21040) - de->media_timer.function = de21040_media_timer; - else - de->media_timer.function = de21041_media_timer; - de->media_timer.data = (unsigned long) de; + timer_setup(&de->media_timer, + de->de21040 ? de21040_media_timer : de21041_media_timer, + 0); netif_carrier_off(dev); -- GitLab From 80c5a20b537996f848c61ddb8a6734c66b65abfd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:28:59 -0700 Subject: [PATCH 1447/1507] pcmcia/electra_cf: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Michael Ellerman Cc: linux-pcmcia@lists.infradead.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/pcmcia/electra_cf.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c index c6fe2a4a7a6a8..9671ded549f03 100644 --- a/drivers/pcmcia/electra_cf.c +++ b/drivers/pcmcia/electra_cf.c @@ -79,9 +79,9 @@ static int electra_cf_ss_init(struct pcmcia_socket *s) } /* the timer is primarily to kick this socket's pccardd */ -static void electra_cf_timer(unsigned long _cf) +static void electra_cf_timer(struct timer_list *t) { - struct electra_cf_socket *cf = (void *) _cf; + struct electra_cf_socket *cf = from_timer(cf, t, timer); int present = electra_cf_present(cf); if (present != cf->present) { @@ -95,7 +95,9 @@ static void electra_cf_timer(unsigned long _cf) static irqreturn_t electra_cf_irq(int irq, void *_cf) { - electra_cf_timer((unsigned long)_cf); + struct electra_cf_socket *cf = _cf; + + electra_cf_timer(&cf->timer); return IRQ_HANDLED; } @@ -206,7 +208,7 @@ static int electra_cf_probe(struct platform_device *ofdev) if (!cf) return -ENOMEM; - setup_timer(&cf->timer, electra_cf_timer, (unsigned long)cf); + timer_setup(&cf->timer, electra_cf_timer, 0); cf->irq = 0; cf->ofdev = ofdev; @@ -305,7 +307,7 @@ static int electra_cf_probe(struct platform_device *ofdev) cf->mem_phys, io.start, cf->irq); cf->active = 1; - electra_cf_timer((unsigned long)cf); + electra_cf_timer(&cf->timer); return 0; fail3: -- GitLab From abec4be3ee68c8572adb39da68fbfd86e63daa84 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:00 -0700 Subject: [PATCH 1448/1507] net: ethernet: stmmac: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- .../ethernet/stmicro/stmmac/altr_tse_pcs.c | 22 +++++++++---------- 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index 6a9c954492f22..8b50afcdb52df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -118,10 +118,9 @@ int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs) return ret; } -static void pcs_link_timer_callback(unsigned long data) +static void pcs_link_timer_callback(struct tse_pcs *pcs) { u16 val = 0; - struct tse_pcs *pcs = (struct tse_pcs *)data; void __iomem *tse_pcs_base = pcs->tse_pcs_base; void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; @@ -138,12 +137,11 @@ static void pcs_link_timer_callback(unsigned long data) } } -static void auto_nego_timer_callback(unsigned long data) +static void auto_nego_timer_callback(struct tse_pcs *pcs) { u16 val = 0; u16 speed = 0; u16 duplex = 0; - struct tse_pcs *pcs = (struct tse_pcs *)data; void __iomem *tse_pcs_base = pcs->tse_pcs_base; void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; @@ -201,14 +199,14 @@ static void auto_nego_timer_callback(unsigned long data) } } -static void aneg_link_timer_callback(unsigned long data) +static void aneg_link_timer_callback(struct timer_list *t) { - struct tse_pcs *pcs = (struct tse_pcs *)data; + struct tse_pcs *pcs = from_timer(pcs, t, aneg_link_timer); if (pcs->autoneg == AUTONEG_ENABLE) - auto_nego_timer_callback(data); + auto_nego_timer_callback(pcs); else if (pcs->autoneg == AUTONEG_DISABLE) - pcs_link_timer_callback(data); + pcs_link_timer_callback(pcs); } void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, @@ -237,8 +235,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, tse_pcs_reset(tse_pcs_base, pcs); - setup_timer(&pcs->aneg_link_timer, - aneg_link_timer_callback, (unsigned long)pcs); + timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, + 0); mod_timer(&pcs->aneg_link_timer, jiffies + msecs_to_jiffies(AUTONEGO_LINK_TIMER)); } else if (phy_dev->autoneg == AUTONEG_DISABLE) { @@ -270,8 +268,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, tse_pcs_reset(tse_pcs_base, pcs); - setup_timer(&pcs->aneg_link_timer, - aneg_link_timer_callback, (unsigned long)pcs); + timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, + 0); mod_timer(&pcs->aneg_link_timer, jiffies + msecs_to_jiffies(AUTONEGO_LINK_TIMER)); } -- GitLab From d3e99b2d19b06030593761c658b648fd6427eaa1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:01 -0700 Subject: [PATCH 1449/1507] net/cw1200: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Solomon Peachy Cc: Kalle Valo Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/wireless/st/cw1200/pm.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index d2202ae92bdd8..ded23df1ac1d7 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -91,7 +91,7 @@ struct cw1200_suspend_state { u8 prev_ps_mode; }; -static void cw1200_pm_stay_awake_tmo(unsigned long arg) +static void cw1200_pm_stay_awake_tmo(struct timer_list *unused) { /* XXX what's the point of this ? */ } @@ -101,8 +101,7 @@ int cw1200_pm_init(struct cw1200_pm_state *pm, { spin_lock_init(&pm->lock); - setup_timer(&pm->stay_awake, cw1200_pm_stay_awake_tmo, - (unsigned long)pm); + timer_setup(&pm->stay_awake, cw1200_pm_stay_awake_tmo, 0); return 0; } -- GitLab From 5a3a8962035277210098a6b498680769a8eb36b6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:02 -0700 Subject: [PATCH 1450/1507] net: vxge: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Jon Mason Cc: "David S. Miller" Cc: Miroslav Lichvar Cc: Jarod Wilson Cc: Eric Dumazet Cc: stephen hemminger Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/neterion/vxge/vxge-main.c | 12 ++++++------ drivers/net/ethernet/neterion/vxge/vxge-main.h | 8 +++----- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50ea69d88480c..5d5b9855e24eb 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2597,9 +2597,9 @@ static int vxge_add_isr(struct vxgedev *vdev) return VXGE_HW_OK; } -static void vxge_poll_vp_reset(unsigned long data) +static void vxge_poll_vp_reset(struct timer_list *t) { - struct vxgedev *vdev = (struct vxgedev *)data; + struct vxgedev *vdev = from_timer(vdev, t, vp_reset_timer); int i, j = 0; for (i = 0; i < vdev->no_of_vpath; i++) { @@ -2616,9 +2616,9 @@ static void vxge_poll_vp_reset(unsigned long data) mod_timer(&vdev->vp_reset_timer, jiffies + HZ / 2); } -static void vxge_poll_vp_lockup(unsigned long data) +static void vxge_poll_vp_lockup(struct timer_list *t) { - struct vxgedev *vdev = (struct vxgedev *)data; + struct vxgedev *vdev = from_timer(vdev, t, vp_lockup_timer); enum vxge_hw_status status = VXGE_HW_OK; struct vxge_vpath *vpath; struct vxge_ring *ring; @@ -2858,12 +2858,12 @@ static int vxge_open(struct net_device *dev) vdev->config.rx_pause_enable); if (vdev->vp_reset_timer.function == NULL) - vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset, vdev, + vxge_os_timer(&vdev->vp_reset_timer, vxge_poll_vp_reset, HZ / 2); /* There is no need to check for RxD leak and RxD lookup on Titan1A */ if (vdev->titan1 && vdev->vp_lockup_timer.function == NULL) - vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup, vdev, + vxge_os_timer(&vdev->vp_lockup_timer, vxge_poll_vp_lockup, HZ / 2); set_bit(__VXGE_STATE_CARD_UP, &vdev->state); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.h b/drivers/net/ethernet/neterion/vxge/vxge-main.h index 3a79d93b84453..59a57ff5e96af 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.h +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.h @@ -417,12 +417,10 @@ struct vxge_tx_priv { module_param(p, int, 0) static inline -void vxge_os_timer(struct timer_list *timer, void (*func)(unsigned long data), - struct vxgedev *vdev, unsigned long timeout) +void vxge_os_timer(struct timer_list *timer, void (*func)(struct timer_list *), + unsigned long timeout) { - init_timer(timer); - timer->function = func; - timer->data = (unsigned long)vdev; + timer_setup(timer, func, 0); mod_timer(timer, jiffies + timeout); } -- GitLab From 847f03ee16cd4dbe1f15fe09989f52300e43ca10 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:03 -0700 Subject: [PATCH 1451/1507] drivers/atm/suni: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Passes NULL timer when doing non- timer call. Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/atm/suni.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c index b0363149b2fda..b8825f2d79e02 100644 --- a/drivers/atm/suni.c +++ b/drivers/atm/suni.c @@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(sunis_lock); if (atomic_read(&stats->s) < 0) atomic_set(&stats->s,INT_MAX); -static void suni_hz(unsigned long from_timer) +static void suni_hz(struct timer_list *timer) { struct suni_priv *walk; struct atm_dev *dev; @@ -85,7 +85,7 @@ static void suni_hz(unsigned long from_timer) ((GET(TACP_TCC) & 0xff) << 8) | ((GET(TACP_TCCM) & 7) << 16)); } - if (from_timer) mod_timer(&poll_timer,jiffies+HZ); + if (timer) mod_timer(&poll_timer,jiffies+HZ); } @@ -322,13 +322,11 @@ static int suni_start(struct atm_dev *dev) printk(KERN_WARNING "%s(itf %d): no signal\n",dev->type, dev->number); PRIV(dev)->loop_mode = ATM_LM_NONE; - suni_hz(0); /* clear SUNI counters */ + suni_hz(NULL); /* clear SUNI counters */ (void) fetch_stats(dev,NULL,1); /* clear kernel counters */ if (first) { - init_timer(&poll_timer); + timer_setup(&poll_timer, suni_hz, 0); poll_timer.expires = jiffies+HZ; - poll_timer.function = suni_hz; - poll_timer.data = 1; #if 0 printk(KERN_DEBUG "[u] p=0x%lx,n=0x%lx\n",(unsigned long) poll_timer.list.prev, (unsigned long) poll_timer.list.next); -- GitLab From 3d2ceaa63b81f41cd95e8954555130cc801c4452 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:04 -0700 Subject: [PATCH 1452/1507] atm: idt77252: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. This required adding a pointer back to vc_map, and adjusting the locking around removal a bit. Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/atm/idt77252.c | 21 ++++++++++++--------- drivers/atm/idt77252.h | 3 +++ 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 47f3c4ae05947..0e3b9c44c8089 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -2073,21 +2073,19 @@ idt77252_rate_logindex(struct idt77252_dev *card, int pcr) } static void -idt77252_est_timer(unsigned long data) +idt77252_est_timer(struct timer_list *t) { - struct vc_map *vc = (struct vc_map *)data; + struct rate_estimator *est = from_timer(est, t, timer); + struct vc_map *vc = est->vc; struct idt77252_dev *card = vc->card; - struct rate_estimator *est; unsigned long flags; u32 rate, cps; u64 ncells; u8 lacr; spin_lock_irqsave(&vc->lock, flags); - est = vc->estimator; - if (!est) + if (!vc->estimator) goto out; - ncells = est->cells; rate = ((u32)(ncells - est->last_cells)) << (7 - est->interval); @@ -2126,10 +2124,11 @@ idt77252_init_est(struct vc_map *vc, int pcr) est->maxcps = pcr < 0 ? -pcr : pcr; est->cps = est->maxcps; est->avcps = est->cps << 5; + est->vc = vc; est->interval = 2; /* XXX: make this configurable */ est->ewma_log = 2; /* XXX: make this configurable */ - setup_timer(&est->timer, idt77252_est_timer, (unsigned long)vc); + timer_setup(&est->timer, idt77252_est_timer, 0); mod_timer(&est->timer, jiffies + ((HZ / 4) << est->interval)); return est; @@ -2209,16 +2208,20 @@ static int idt77252_init_ubr(struct idt77252_dev *card, struct vc_map *vc, struct atm_vcc *vcc, struct atm_qos *qos) { + struct rate_estimator *est = NULL; unsigned long flags; int tcr; spin_lock_irqsave(&vc->lock, flags); if (vc->estimator) { - del_timer(&vc->estimator->timer); - kfree(vc->estimator); + est = vc->estimator; vc->estimator = NULL; } spin_unlock_irqrestore(&vc->lock, flags); + if (est) { + del_timer_sync(&est->timer); + kfree(est); + } tcr = atm_pcr_goal(&qos->txtp); if (tcr == 0) diff --git a/drivers/atm/idt77252.h b/drivers/atm/idt77252.h index 3a82cc23a0532..9339197d701c4 100644 --- a/drivers/atm/idt77252.h +++ b/drivers/atm/idt77252.h @@ -184,6 +184,8 @@ struct aal1 { unsigned char sequence; }; +struct vc_map; + struct rate_estimator { struct timer_list timer; unsigned int interval; @@ -193,6 +195,7 @@ struct rate_estimator { long avcps; u32 cps; u32 maxcps; + struct vc_map *vc; }; struct vc_map { -- GitLab From a8c22a2bbc67d001479696c5696ae11c84116701 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:05 -0700 Subject: [PATCH 1453/1507] net: tulip: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: David Howells Cc: Jarod Wilson Cc: Stephen Hemminger Cc: Johannes Berg Cc: Eric Dumazet Cc: Philippe Reynes Cc: "yuval.shaia@oracle.com" Cc: netdev@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/dec/tulip/de4x5.c | 12 ++++++------ drivers/net/ethernet/dec/tulip/dmfe.c | 10 +++++----- drivers/net/ethernet/dec/tulip/interrupt.c | 6 +++--- drivers/net/ethernet/dec/tulip/pnic.c | 6 +++--- drivers/net/ethernet/dec/tulip/pnic2.c | 6 +++--- drivers/net/ethernet/dec/tulip/timer.c | 12 ++++++------ drivers/net/ethernet/dec/tulip/tulip.h | 12 ++++++------ drivers/net/ethernet/dec/tulip/tulip_core.c | 14 ++++++-------- drivers/net/ethernet/dec/tulip/uli526x.c | 10 +++++----- drivers/net/ethernet/dec/tulip/winbond-840.c | 10 +++++----- 10 files changed, 48 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 299812e92db7d..a31b4df3e7ffb 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -912,7 +912,7 @@ static int de4x5_init(struct net_device *dev); static int de4x5_sw_reset(struct net_device *dev); static int de4x5_rx(struct net_device *dev); static int de4x5_tx(struct net_device *dev); -static void de4x5_ast(struct net_device *dev); +static void de4x5_ast(struct timer_list *t); static int de4x5_txur(struct net_device *dev); static int de4x5_rx_ovfc(struct net_device *dev); @@ -1147,8 +1147,7 @@ de4x5_hw_init(struct net_device *dev, u_long iobase, struct device *gendev) lp->timeout = -1; lp->gendev = gendev; spin_lock_init(&lp->lock); - setup_timer(&lp->timer, (void (*)(unsigned long))de4x5_ast, - (unsigned long)dev); + timer_setup(&lp->timer, de4x5_ast, 0); de4x5_parse_params(dev); /* @@ -1741,9 +1740,10 @@ de4x5_tx(struct net_device *dev) } static void -de4x5_ast(struct net_device *dev) +de4x5_ast(struct timer_list *t) { - struct de4x5_private *lp = netdev_priv(dev); + struct de4x5_private *lp = from_timer(lp, t, timer); + struct net_device *dev = dev_get_drvdata(lp->gendev); int next_tick = DE4X5_AUTOSENSE_MS; int dt; @@ -2369,7 +2369,7 @@ autoconf_media(struct net_device *dev) lp->media = INIT; lp->tcount = 0; - de4x5_ast(dev); + de4x5_ast(&lp->timer); return lp->media; } diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index 6585f737d08b3..17ef7a28873d9 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -331,7 +331,7 @@ static void dmfe_phy_write_1bit(void __iomem *, u32); static u16 dmfe_phy_read_1bit(void __iomem *); static u8 dmfe_sense_speed(struct dmfe_board_info *); static void dmfe_process_mode(struct dmfe_board_info *); -static void dmfe_timer(unsigned long); +static void dmfe_timer(struct timer_list *); static inline u32 cal_CRC(unsigned char *, unsigned int, u8); static void dmfe_rx_packet(struct net_device *, struct dmfe_board_info *); static void dmfe_free_tx_pkt(struct net_device *, struct dmfe_board_info *); @@ -596,7 +596,7 @@ static int dmfe_open(struct net_device *dev) netif_wake_queue(dev); /* set and active a timer process */ - setup_timer(&db->timer, dmfe_timer, (unsigned long)dev); + timer_setup(&db->timer, dmfe_timer, 0); db->timer.expires = DMFE_TIMER_WUT + HZ * 2; add_timer(&db->timer); @@ -1128,10 +1128,10 @@ static const struct ethtool_ops netdev_ethtool_ops = { * Dynamic media sense, allocate Rx buffer... */ -static void dmfe_timer(unsigned long data) +static void dmfe_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct dmfe_board_info *db = netdev_priv(dev); + struct dmfe_board_info *db = from_timer(db, t, timer); + struct net_device *dev = pci_get_drvdata(db->pdev); void __iomem *ioaddr = db->ioaddr; u32 tmp_cr8; unsigned char tmp_cr12; diff --git a/drivers/net/ethernet/dec/tulip/interrupt.c b/drivers/net/ethernet/dec/tulip/interrupt.c index 8df80880ecaaa..c1ca0765d56d4 100644 --- a/drivers/net/ethernet/dec/tulip/interrupt.c +++ b/drivers/net/ethernet/dec/tulip/interrupt.c @@ -102,10 +102,10 @@ int tulip_refill_rx(struct net_device *dev) #ifdef CONFIG_TULIP_NAPI -void oom_timer(unsigned long data) +void oom_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, oom_timer); + napi_schedule(&tp->napi); } diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c index 7bcccf5cac7ac..3fb39e32e1b45 100644 --- a/drivers/net/ethernet/dec/tulip/pnic.c +++ b/drivers/net/ethernet/dec/tulip/pnic.c @@ -84,10 +84,10 @@ void pnic_lnk_change(struct net_device *dev, int csr5) } } -void pnic_timer(unsigned long data) +void pnic_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c index 5895fc43f6e0d..412adaa7fdf82 100644 --- a/drivers/net/ethernet/dec/tulip/pnic2.c +++ b/drivers/net/ethernet/dec/tulip/pnic2.c @@ -76,10 +76,10 @@ #include -void pnic2_timer(unsigned long data) +void pnic2_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c index 523d9dde50a22..642e9dfc54515 100644 --- a/drivers/net/ethernet/dec/tulip/timer.c +++ b/drivers/net/ethernet/dec/tulip/timer.c @@ -137,10 +137,10 @@ void tulip_media_task(struct work_struct *work) } -void mxic_timer(unsigned long data) +void mxic_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; void __iomem *ioaddr = tp->base_addr; int next_tick = 60*HZ; @@ -154,10 +154,10 @@ void mxic_timer(unsigned long data) } -void comet_timer(unsigned long data) +void comet_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; int next_tick = 2*HZ; if (tulip_debug > 1) diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h index 06660dbc44b7e..b458140aeaef9 100644 --- a/drivers/net/ethernet/dec/tulip/tulip.h +++ b/drivers/net/ethernet/dec/tulip/tulip.h @@ -43,7 +43,7 @@ struct tulip_chip_table { int io_size; int valid_intrs; /* CSR7 interrupt enable settings */ int flags; - void (*media_timer) (unsigned long); + void (*media_timer) (struct timer_list *); work_func_t media_task; }; @@ -476,7 +476,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5); /* PNIC2.c */ void pnic2_lnk_change(struct net_device *dev, int csr5); -void pnic2_timer(unsigned long data); +void pnic2_timer(struct timer_list *t); void pnic2_start_nway(struct net_device *dev); void pnic2_lnk_change(struct net_device *dev, int csr5); @@ -504,19 +504,19 @@ void tulip_find_mii (struct net_device *dev, int board_idx); /* pnic.c */ void pnic_do_nway(struct net_device *dev); void pnic_lnk_change(struct net_device *dev, int csr5); -void pnic_timer(unsigned long data); +void pnic_timer(struct timer_list *t); /* timer.c */ void tulip_media_task(struct work_struct *work); -void mxic_timer(unsigned long data); -void comet_timer(unsigned long data); +void mxic_timer(struct timer_list *t); +void comet_timer(struct timer_list *t); /* tulip_core.c */ extern int tulip_debug; extern const char * const medianame[]; extern const char tulip_media_cap[]; extern const struct tulip_chip_table tulip_tbl[]; -void oom_timer(unsigned long data); +void oom_timer(struct timer_list *t); extern u8 t21040_csr13[]; static inline void tulip_start_rxtx(struct tulip_private *tp) diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 851b6d1f5a42a..00d02a0967d07 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -123,10 +123,10 @@ int tulip_debug = TULIP_DEBUG; int tulip_debug = 1; #endif -static void tulip_timer(unsigned long data) +static void tulip_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct tulip_private *tp = netdev_priv(dev); + struct tulip_private *tp = from_timer(tp, t, timer); + struct net_device *dev = tp->dev; if (netif_running(dev)) schedule_work(&tp->media_work); @@ -505,7 +505,7 @@ static void tulip_up(struct net_device *dev) tp->timer.expires = RUN_AT(next_tick); add_timer(&tp->timer); #ifdef CONFIG_TULIP_NAPI - setup_timer(&tp->oom_timer, oom_timer, (unsigned long)dev); + timer_setup(&tp->oom_timer, oom_timer, 0); #endif } @@ -780,8 +780,7 @@ static void tulip_down (struct net_device *dev) spin_unlock_irqrestore (&tp->lock, flags); - setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer, - (unsigned long)dev); + timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0); dev->if_port = tp->saved_if_port; @@ -1470,8 +1469,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->csr0 = csr0; spin_lock_init(&tp->lock); spin_lock_init(&tp->mii_lock); - setup_timer(&tp->timer, tulip_tbl[tp->chip_id].media_timer, - (unsigned long)dev); + timer_setup(&tp->timer, tulip_tbl[tp->chip_id].media_timer, 0); INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task); diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index 5fbbc0caba994..488a744084c94 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -241,7 +241,7 @@ static void phy_write_1bit(struct uli526x_board_info *db, u32); static u16 phy_read_1bit(struct uli526x_board_info *db); static u8 uli526x_sense_speed(struct uli526x_board_info *); static void uli526x_process_mode(struct uli526x_board_info *); -static void uli526x_timer(unsigned long); +static void uli526x_timer(struct timer_list *t); static void uli526x_rx_packet(struct net_device *, struct uli526x_board_info *); static void uli526x_free_tx_pkt(struct net_device *, struct uli526x_board_info *); static void uli526x_reuse_skb(struct uli526x_board_info *, struct sk_buff *); @@ -491,7 +491,7 @@ static int uli526x_open(struct net_device *dev) netif_wake_queue(dev); /* set and active a timer process */ - setup_timer(&db->timer, uli526x_timer, (unsigned long)dev); + timer_setup(&db->timer, uli526x_timer, 0); db->timer.expires = ULI526X_TIMER_WUT + HZ * 2; add_timer(&db->timer); @@ -1021,10 +1021,10 @@ static const struct ethtool_ops netdev_ethtool_ops = { * Dynamic media sense, allocate Rx buffer... */ -static void uli526x_timer(unsigned long data) +static void uli526x_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct uli526x_board_info *db = netdev_priv(dev); + struct uli526x_board_info *db = from_timer(db, t, timer); + struct net_device *dev = pci_get_drvdata(db->pdev); struct uli_phy_ops *phy = &db->phy; void __iomem *ioaddr = db->ioaddr; unsigned long flags; diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 6f88d687b6d28..70cb2d689c2cb 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -327,7 +327,7 @@ static int mdio_read(struct net_device *dev, int phy_id, int location); static void mdio_write(struct net_device *dev, int phy_id, int location, int value); static int netdev_open(struct net_device *dev); static int update_link(struct net_device *dev); -static void netdev_timer(unsigned long data); +static void netdev_timer(struct timer_list *t); static void init_rxtx_rings(struct net_device *dev); static void free_rxtx_rings(struct netdev_private *np); static void init_registers(struct net_device *dev); @@ -655,7 +655,7 @@ static int netdev_open(struct net_device *dev) netdev_dbg(dev, "Done netdev_open()\n"); /* Set the timer to check for link beat. */ - setup_timer(&np->timer, netdev_timer, (unsigned long)dev); + timer_setup(&np->timer, netdev_timer, 0); np->timer.expires = jiffies + 1*HZ; add_timer(&np->timer); return 0; @@ -772,10 +772,10 @@ static inline void update_csr6(struct net_device *dev, int new) np->mii_if.full_duplex = 1; } -static void netdev_timer(unsigned long data) +static void netdev_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct netdev_private *np = netdev_priv(dev); + struct netdev_private *np = from_timer(np, t, timer); + struct net_device *dev = pci_get_drvdata(np->pci_dev); void __iomem *ioaddr = np->base_addr; if (debug > 2) -- GitLab From 1fccb565e8b09e54467d41111f6faf08fcc9c3c1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:06 -0700 Subject: [PATCH 1454/1507] net: can: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Oliver Hartkopp Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: linux-can@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/can/af_can.c | 4 ++-- net/can/af_can.h | 2 +- net/can/proc.c | 8 ++++---- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/net/can/af_can.c b/net/can/af_can.c index 88edac0f3e366..1f75e11ac35ae 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -882,8 +882,8 @@ static int can_pernet_init(struct net *net) if (IS_ENABLED(CONFIG_PROC_FS)) { /* the statistics are updated every second (timer triggered) */ if (stats_timer) { - setup_timer(&net->can.can_stattimer, can_stat_update, - (unsigned long)net); + timer_setup(&net->can.can_stattimer, can_stat_update, + 0); mod_timer(&net->can.can_stattimer, round_jiffies(jiffies + HZ)); } diff --git a/net/can/af_can.h b/net/can/af_can.h index d0ef45bb2a727..eca6463c6213f 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -113,6 +113,6 @@ struct s_pstats { /* function prototypes for the CAN networklayer procfs (proc.c) */ void can_init_proc(struct net *net); void can_remove_proc(struct net *net); -void can_stat_update(unsigned long data); +void can_stat_update(struct timer_list *t); #endif /* AF_CAN_H */ diff --git a/net/can/proc.c b/net/can/proc.c index 83045f00c63c1..d979b3dc49a6b 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -115,9 +115,9 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, return rate; } -void can_stat_update(unsigned long data) +void can_stat_update(struct timer_list *t) { - struct net *net = (struct net *)data; + struct net *net = from_timer(net, t, can.can_stattimer); struct s_stats *can_stats = net->can.can_stats; unsigned long j = jiffies; /* snapshot */ @@ -221,7 +221,7 @@ static int can_stats_proc_show(struct seq_file *m, void *v) seq_putc(m, '\n'); - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, " %8ld %% total match ratio (RXMR)\n", can_stats->total_rx_match_ratio); @@ -291,7 +291,7 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v) user_reset = 1; - if (net->can.can_stattimer.function == can_stat_update) { + if (net->can.can_stattimer.function == (TIMER_FUNC_TYPE)can_stat_update) { seq_printf(m, "Scheduled statistic reset #%ld.\n", can_pstats->stats_reset + 1); } else { -- GitLab From 7974c0f3622b21825160a37d28b7b1f35ee4cbac Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:07 -0700 Subject: [PATCH 1455/1507] drivers/net/3com: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Steffen Klassert Cc: "David S. Miller" Cc: Jarod Wilson Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/3com/3c574_cs.c | 12 +++++------- drivers/net/ethernet/3com/3c589_cs.c | 10 +++++----- drivers/net/ethernet/3com/3c59x.c | 20 ++++++++++---------- 3 files changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index 47c844cc9d273..48bc7fa0258c9 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -225,7 +225,7 @@ static unsigned short read_eeprom(unsigned int ioaddr, int index); static void tc574_wait_for_completion(struct net_device *dev, int cmd); static void tc574_reset(struct net_device *dev); -static void media_check(unsigned long arg); +static void media_check(struct timer_list *t); static int el3_open(struct net_device *dev); static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct net_device *dev); @@ -377,7 +377,7 @@ static int tc574_config(struct pcmcia_device *link) lp->autoselect = config & Autoselect ? 1 : 0; } - init_timer(&lp->media); + timer_setup(&lp->media, media_check, 0); { int phy; @@ -681,8 +681,6 @@ static int el3_open(struct net_device *dev) netif_start_queue(dev); tc574_reset(dev); - lp->media.function = media_check; - lp->media.data = (unsigned long) dev; lp->media.expires = jiffies + HZ; add_timer(&lp->media); @@ -859,10 +857,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) (and as a last resort, poll the NIC for events), and to monitor the MII, reporting changes in cable status. */ -static void media_check(unsigned long arg) +static void media_check(struct timer_list *t) { - struct net_device *dev = (struct net_device *) arg; - struct el3_private *lp = netdev_priv(dev); + struct el3_private *lp = from_timer(lp, t, media); + struct net_device *dev = lp->p_dev->priv; unsigned int ioaddr = dev->base_addr; unsigned long flags; unsigned short /* cable, */ media, partner; diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index e28254a005997..2b2695311bda9 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -163,7 +163,7 @@ static void tc589_release(struct pcmcia_device *link); static u16 read_eeprom(unsigned int ioaddr, int index); static void tc589_reset(struct net_device *dev); -static void media_check(unsigned long arg); +static void media_check(struct timer_list *t); static int el3_config(struct net_device *dev, struct ifmap *map); static int el3_open(struct net_device *dev); static netdev_tx_t el3_start_xmit(struct sk_buff *skb, @@ -517,7 +517,7 @@ static int el3_open(struct net_device *dev) netif_start_queue(dev); tc589_reset(dev); - setup_timer(&lp->media, media_check, (unsigned long)dev); + timer_setup(&lp->media, media_check, 0); mod_timer(&lp->media, jiffies + HZ); dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", @@ -676,10 +676,10 @@ static irqreturn_t el3_interrupt(int irq, void *dev_id) return IRQ_RETVAL(handled); } -static void media_check(unsigned long arg) +static void media_check(struct timer_list *t) { - struct net_device *dev = (struct net_device *)(arg); - struct el3_private *lp = netdev_priv(dev); + struct el3_private *lp = from_timer(lp, t, media); + struct net_device *dev = lp->p_dev->priv; unsigned int ioaddr = dev->base_addr; u16 media, errs; unsigned long flags; diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 402d9090ad290..f4e13a7014bde 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -759,8 +759,8 @@ static int vortex_open(struct net_device *dev); static void mdio_sync(struct vortex_private *vp, int bits); static int mdio_read(struct net_device *dev, int phy_id, int location); static void mdio_write(struct net_device *vp, int phy_id, int location, int value); -static void vortex_timer(unsigned long arg); -static void rx_oom_timer(unsigned long arg); +static void vortex_timer(struct timer_list *t); +static void rx_oom_timer(struct timer_list *t); static netdev_tx_t vortex_start_xmit(struct sk_buff *skb, struct net_device *dev); static netdev_tx_t boomerang_start_xmit(struct sk_buff *skb, @@ -1599,9 +1599,9 @@ vortex_up(struct net_device *dev) dev->name, media_tbl[dev->if_port].name); } - setup_timer(&vp->timer, vortex_timer, (unsigned long)dev); + timer_setup(&vp->timer, vortex_timer, 0); mod_timer(&vp->timer, RUN_AT(media_tbl[dev->if_port].wait)); - setup_timer(&vp->rx_oom_timer, rx_oom_timer, (unsigned long)dev); + timer_setup(&vp->rx_oom_timer, rx_oom_timer, 0); if (vortex_debug > 1) pr_debug("%s: Initial media type %s.\n", @@ -1784,10 +1784,10 @@ vortex_open(struct net_device *dev) } static void -vortex_timer(unsigned long data) +vortex_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct vortex_private *vp = netdev_priv(dev); + struct vortex_private *vp = from_timer(vp, t, timer); + struct net_device *dev = vp->mii.dev; void __iomem *ioaddr = vp->ioaddr; int next_tick = 60*HZ; int ok = 0; @@ -2687,10 +2687,10 @@ boomerang_rx(struct net_device *dev) * for some memory. Otherwise there is no way to restart the rx process. */ static void -rx_oom_timer(unsigned long arg) +rx_oom_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - struct vortex_private *vp = netdev_priv(dev); + struct vortex_private *vp = from_timer(vp, t, rx_oom_timer); + struct net_device *dev = vp->mii.dev; spin_lock_irq(&vp->lock); if ((vp->cur_rx - vp->dirty_rx) == RX_RING_SIZE) /* This test is redundant, but makes me feel good */ -- GitLab From cacd2b3fb9815ec29b778342a8aaa80edc0f98d3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:08 -0700 Subject: [PATCH 1456/1507] chelsio: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Johannes Berg Cc: Eric Dumazet Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb/sge.c | 29 +++++++++++-------------- 1 file changed, 13 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 75e4399187009..30de26ef3da4b 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -1882,10 +1882,10 @@ netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev) /* * Callback for the Tx buffer reclaim timer. Runs with softirqs disabled. */ -static void sge_tx_reclaim_cb(unsigned long data) +static void sge_tx_reclaim_cb(struct timer_list *t) { int i; - struct sge *sge = (struct sge *)data; + struct sge *sge = from_timer(sge, t, tx_reclaim_timer); for (i = 0; i < SGE_CMDQ_N; ++i) { struct cmdQ *q = &sge->cmdQ[i]; @@ -1978,10 +1978,10 @@ void t1_sge_start(struct sge *sge) /* * Callback for the T2 ESPI 'stuck packet feature' workaorund */ -static void espibug_workaround_t204(unsigned long data) +static void espibug_workaround_t204(struct timer_list *t) { - struct adapter *adapter = (struct adapter *)data; - struct sge *sge = adapter->sge; + struct sge *sge = from_timer(sge, t, espibug_timer); + struct adapter *adapter = sge->adapter; unsigned int nports = adapter->params.nports; u32 seop[MAX_NPORTS]; @@ -2021,10 +2021,10 @@ static void espibug_workaround_t204(unsigned long data) mod_timer(&sge->espibug_timer, jiffies + sge->espibug_timeout); } -static void espibug_workaround(unsigned long data) +static void espibug_workaround(struct timer_list *t) { - struct adapter *adapter = (struct adapter *)data; - struct sge *sge = adapter->sge; + struct sge *sge = from_timer(sge, t, espibug_timer); + struct adapter *adapter = sge->adapter; if (netif_running(adapter->port[0].dev)) { struct sk_buff *skb = sge->espibug_skb[0]; @@ -2075,18 +2075,15 @@ struct sge *t1_sge_create(struct adapter *adapter, struct sge_params *p) goto nomem_port; } - setup_timer(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, - (unsigned long)sge); + timer_setup(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, 0); if (is_T2(sge->adapter)) { - init_timer(&sge->espibug_timer); + timer_setup(&sge->espibug_timer, + adapter->params.nports > 1 ? espibug_workaround_t204 : espibug_workaround, + 0); - if (adapter->params.nports > 1) { + if (adapter->params.nports > 1) tx_sched_init(sge); - sge->espibug_timer.function = espibug_workaround_t204; - } else - sge->espibug_timer.function = espibug_workaround; - sge->espibug_timer.data = (unsigned long)sge->adapter; sge->espibug_timeout = 1; /* for T204, every 10ms */ -- GitLab From 495ad9864f17bb2f4e085f9398328d14bfdb4d88 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:09 -0700 Subject: [PATCH 1457/1507] net: amd8111e: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jarod Wilson Cc: Philippe Reynes Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/amd8111e.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 7f22af6e37e0e..358f7ab77c70b 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1669,9 +1669,9 @@ static int amd8111e_resume(struct pci_dev *pci_dev) return 0; } -static void amd8111e_config_ipg(struct net_device *dev) +static void amd8111e_config_ipg(struct timer_list *t) { - struct amd8111e_priv *lp = netdev_priv(dev); + struct amd8111e_priv *lp = from_timer(lp, t, ipg_data.ipg_timer); struct ipg_info *ipg_data = &lp->ipg_data; void __iomem *mmio = lp->mmio; unsigned int prev_col_cnt = ipg_data->col_cnt; @@ -1883,8 +1883,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* Initialize software ipg timer */ if(lp->options & OPTION_DYN_IPG_ENABLE){ - setup_timer(&lp->ipg_data.ipg_timer, - (void *)&amd8111e_config_ipg, (unsigned long)dev); + timer_setup(&lp->ipg_data.ipg_timer, amd8111e_config_ipg, 0); lp->ipg_data.ipg_timer.expires = jiffies + IPG_CONVERGE_JIFFIES; lp->ipg_data.ipg = DEFAULT_IPG; -- GitLab From b09064b78f396ed0840895b11e8bd90e8380afd5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:10 -0700 Subject: [PATCH 1458/1507] bna: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Rasesh Mody Cc: Sudarsana Kalluru Cc: Dept-GELinuxNICDev@cavium.com Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bnad.c | 43 +++++++++++-------------- 1 file changed, 19 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 6e13c937d715e..a843076597ecb 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -1693,9 +1693,9 @@ bnad_rx_res_alloc(struct bnad *bnad, struct bna_res_info *res_info, /* Timer callbacks */ /* a) IOC timer */ static void -bnad_ioc_timeout(unsigned long data) +bnad_ioc_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.ioc_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1704,9 +1704,9 @@ bnad_ioc_timeout(unsigned long data) } static void -bnad_ioc_hb_check(unsigned long data) +bnad_ioc_hb_check(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.hb_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1715,9 +1715,9 @@ bnad_ioc_hb_check(unsigned long data) } static void -bnad_iocpf_timeout(unsigned long data) +bnad_iocpf_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.iocpf_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1726,9 +1726,9 @@ bnad_iocpf_timeout(unsigned long data) } static void -bnad_iocpf_sem_timeout(unsigned long data) +bnad_iocpf_sem_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, bna.ioceth.ioc.sem_timer); unsigned long flags; spin_lock_irqsave(&bnad->bna_lock, flags); @@ -1748,9 +1748,9 @@ bnad_iocpf_sem_timeout(unsigned long data) /* b) Dynamic Interrupt Moderation Timer */ static void -bnad_dim_timeout(unsigned long data) +bnad_dim_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, dim_timer); struct bnad_rx_info *rx_info; struct bnad_rx_ctrl *rx_ctrl; int i, j; @@ -1781,9 +1781,9 @@ bnad_dim_timeout(unsigned long data) /* c) Statistics Timer */ static void -bnad_stats_timeout(unsigned long data) +bnad_stats_timeout(struct timer_list *t) { - struct bnad *bnad = (struct bnad *)data; + struct bnad *bnad = from_timer(bnad, t, stats_timer); unsigned long flags; if (!netif_running(bnad->netdev) || @@ -1804,8 +1804,7 @@ bnad_dim_timer_start(struct bnad *bnad) { if (bnad->cfg_flags & BNAD_CF_DIM_ENABLED && !test_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags)) { - setup_timer(&bnad->dim_timer, bnad_dim_timeout, - (unsigned long)bnad); + timer_setup(&bnad->dim_timer, bnad_dim_timeout, 0); set_bit(BNAD_RF_DIM_TIMER_RUNNING, &bnad->run_flags); mod_timer(&bnad->dim_timer, jiffies + msecs_to_jiffies(BNAD_DIM_TIMER_FREQ)); @@ -1823,8 +1822,7 @@ bnad_stats_timer_start(struct bnad *bnad) spin_lock_irqsave(&bnad->bna_lock, flags); if (!test_and_set_bit(BNAD_RF_STATS_TIMER_RUNNING, &bnad->run_flags)) { - setup_timer(&bnad->stats_timer, bnad_stats_timeout, - (unsigned long)bnad); + timer_setup(&bnad->stats_timer, bnad_stats_timeout, 0); mod_timer(&bnad->stats_timer, jiffies + msecs_to_jiffies(BNAD_STATS_TIMER_FREQ)); } @@ -3692,14 +3690,11 @@ bnad_pci_probe(struct pci_dev *pdev, goto res_free; /* Set up timers */ - setup_timer(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout, - (unsigned long)bnad); - setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout, - (unsigned long)bnad); + timer_setup(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout, 0); + timer_setup(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check, 0); + timer_setup(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout, 0); + timer_setup(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout, + 0); /* * Start the chip -- GitLab From 6fa35bd0e9e4e0d1ba3b6a6c7968b8c926317507 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:11 -0700 Subject: [PATCH 1459/1507] net: dl2k: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Jarod Wilson Cc: Tobias Klauser Cc: Philippe Reynes Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Tobias Klauser Signed-off-by: David S. Miller --- drivers/net/ethernet/dlink/dl2k.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 778f974e2928b..a2f6758d38ddc 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -68,7 +68,7 @@ static const int max_intrloop = 50; static const int multicast_filter_limit = 0x40; static int rio_open (struct net_device *dev); -static void rio_timer (unsigned long data); +static void rio_timer (struct timer_list *t); static void rio_tx_timeout (struct net_device *dev); static netdev_tx_t start_xmit (struct sk_buff *skb, struct net_device *dev); static irqreturn_t rio_interrupt (int irq, void *dev_instance); @@ -644,7 +644,7 @@ static int rio_open(struct net_device *dev) return i; } - setup_timer(&np->timer, rio_timer, (unsigned long)dev); + timer_setup(&np->timer, rio_timer, 0); np->timer.expires = jiffies + 1 * HZ; add_timer(&np->timer); @@ -655,10 +655,10 @@ static int rio_open(struct net_device *dev) } static void -rio_timer (unsigned long data) +rio_timer (struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; - struct netdev_private *np = netdev_priv(dev); + struct netdev_private *np = from_timer(np, t, timer); + struct net_device *dev = pci_get_drvdata(np->pdev); unsigned int entry; int next_tick = 1*HZ; unsigned long flags; -- GitLab From 11dd894e4afa7995d8e4bd6008cbd79840c3a8bd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:12 -0700 Subject: [PATCH 1460/1507] net: ksz884x: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Johannes Berg Cc: Jarod Wilson Cc: Masahiro Yamada Cc: Philippe Reynes Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/micrel/ksz884x.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index e798fbe086001..52207508744ca 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -4338,11 +4338,11 @@ static void ksz_stop_timer(struct ksz_timer_info *info) } static void ksz_init_timer(struct ksz_timer_info *info, int period, - void (*function)(unsigned long), void *data) + void (*function)(struct timer_list *)) { info->max = 0; info->period = period; - setup_timer(&info->timer, function, (unsigned long)data); + timer_setup(&info->timer, function, 0); } static void ksz_update_timer(struct ksz_timer_info *info) @@ -6689,9 +6689,9 @@ static void mib_read_work(struct work_struct *work) } } -static void mib_monitor(unsigned long ptr) +static void mib_monitor(struct timer_list *t) { - struct dev_info *hw_priv = (struct dev_info *) ptr; + struct dev_info *hw_priv = from_timer(hw_priv, t, mib_timer_info.timer); mib_read_work(&hw_priv->mib_read); @@ -6716,10 +6716,10 @@ static void mib_monitor(unsigned long ptr) * * This routine is run in a kernel timer to monitor the network device. */ -static void dev_monitor(unsigned long ptr) +static void dev_monitor(struct timer_list *t) { - struct net_device *dev = (struct net_device *) ptr; - struct dev_priv *priv = netdev_priv(dev); + struct dev_priv *priv = from_timer(priv, t, monitor_timer_info.timer); + struct net_device *dev = priv->mii_if.dev; struct dev_info *hw_priv = priv->adapter; struct ksz_hw *hw = &hw_priv->hw; struct ksz_port *port = &priv->port; @@ -6789,7 +6789,7 @@ static int __init netdev_init(struct net_device *dev) /* 500 ms timeout */ ksz_init_timer(&priv->monitor_timer_info, 500 * HZ / 1000, - dev_monitor, dev); + dev_monitor); /* 500 ms timeout */ dev->watchdog_timeo = HZ / 2; @@ -7065,7 +7065,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) /* 500 ms timeout */ ksz_init_timer(&hw_priv->mib_timer_info, 500 * HZ / 1000, - mib_monitor, hw_priv); + mib_monitor); for (i = 0; i < hw->dev_count; i++) { dev = alloc_etherdev(sizeof(struct dev_priv)); -- GitLab From d99356797a8f3abaa57e13c5d1f50e4392eca037 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:13 -0700 Subject: [PATCH 1461/1507] forcedeth: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Zhu Yanjun Cc: Philippe Reynes Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/nvidia/forcedeth.c | 28 ++++++++++++------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a235e8881af91..88128ce61471c 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1884,10 +1884,9 @@ static int nv_alloc_rx_optimized(struct net_device *dev) } /* If rx bufs are exhausted called after 50ms to attempt to refresh */ -static void nv_do_rx_refill(unsigned long data) +static void nv_do_rx_refill(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, oom_kick); /* Just reschedule NAPI rx processing */ napi_schedule(&np->napi); @@ -4065,10 +4064,10 @@ static void nv_free_irq(struct net_device *dev) } } -static void nv_do_nic_poll(unsigned long data) +static void nv_do_nic_poll(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, nic_poll); + struct net_device *dev = np->dev; u8 __iomem *base = get_hwbase(dev); u32 mask = 0; unsigned long flags; @@ -4176,16 +4175,18 @@ static void nv_do_nic_poll(unsigned long data) #ifdef CONFIG_NET_POLL_CONTROLLER static void nv_poll_controller(struct net_device *dev) { - nv_do_nic_poll((unsigned long) dev); + struct fe_priv *np = netdev_priv(dev); + + nv_do_nic_poll(&np->nic_poll); } #endif -static void nv_do_stats_poll(unsigned long data) +static void nv_do_stats_poll(struct timer_list *t) __acquires(&netdev_priv(dev)->hwstats_lock) __releases(&netdev_priv(dev)->hwstats_lock) { - struct net_device *dev = (struct net_device *) data; - struct fe_priv *np = netdev_priv(dev); + struct fe_priv *np = from_timer(np, t, stats_poll); + struct net_device *dev = np->dev; /* If lock is currently taken, the stats are being refreshed * and hence fresh enough */ @@ -5631,10 +5632,9 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) u64_stats_init(&np->swstats_rx_syncp); u64_stats_init(&np->swstats_tx_syncp); - setup_timer(&np->oom_kick, nv_do_rx_refill, (unsigned long)dev); - setup_timer(&np->nic_poll, nv_do_nic_poll, (unsigned long)dev); - setup_deferrable_timer(&np->stats_poll, nv_do_stats_poll, - (unsigned long)dev); + timer_setup(&np->oom_kick, nv_do_rx_refill, 0); + timer_setup(&np->nic_poll, nv_do_nic_poll, 0); + timer_setup(&np->stats_poll, nv_do_stats_poll, TIMER_DEFERRABLE); err = pci_enable_device(pci_dev); if (err) -- GitLab From e313ac12eb13a9738116192848695da54c38b1ae Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:14 -0700 Subject: [PATCH 1462/1507] mISDN: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Karsten Keil Cc: Geliang Tang Cc: "David S. Miller" Cc: Masahiro Yamada Cc: Andrew Morton Cc: Anton Vasilyev Cc: Ingo Molnar Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/hardware/mISDN/mISDNipac.c | 7 +++---- drivers/isdn/hardware/mISDN/w6692.c | 7 +++---- drivers/isdn/mISDN/dsp.h | 2 +- drivers/isdn/mISDN/dsp_core.c | 6 ++---- drivers/isdn/mISDN/dsp_tones.c | 6 ++---- drivers/isdn/mISDN/fsm.c | 7 +++---- drivers/isdn/mISDN/l1oip_core.c | 15 +++++++-------- drivers/isdn/mISDN/timerdev.c | 6 +++--- 8 files changed, 24 insertions(+), 32 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index e240010b93fa0..4d78f870435ec 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -172,7 +172,6 @@ isac_fill_fifo(struct isac_hw *isac) pr_debug("%s: %s dbusytimer running\n", isac->name, __func__); del_timer(&isac->dch.timer); } - init_timer(&isac->dch.timer); isac->dch.timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ)/1000); add_timer(&isac->dch.timer); if (isac->dch.debug & DEBUG_HW_DFIFO) { @@ -727,8 +726,9 @@ isac_release(struct isac_hw *isac) } static void -dbusy_timer_handler(struct isac_hw *isac) +dbusy_timer_handler(struct timer_list *t) { + struct isac_hw *isac = from_timer(isac, t, dch.timer); int rbch, star; u_long flags; @@ -796,8 +796,7 @@ isac_init(struct isac_hw *isac) } isac->mon_tx = NULL; isac->mon_rx = NULL; - setup_timer(&isac->dch.timer, (void *)dbusy_timer_handler, - (long)isac); + timer_setup(&isac->dch.timer, dbusy_timer_handler, 0); isac->mocr = 0xaa; if (isac->type & IPAC_TYPE_ISACX) { /* Disable all IRQ */ diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index d80072fef4341..536d5137f49d6 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -311,7 +311,6 @@ W6692_fill_Dfifo(struct w6692_hw *card) pr_debug("%s: fill_Dfifo dbusytimer running\n", card->name); del_timer(&dch->timer); } - init_timer(&dch->timer); dch->timer.expires = jiffies + ((DBUSY_TIMER_VALUE * HZ) / 1000); add_timer(&dch->timer); if (debug & DEBUG_HW_DFIFO) { @@ -819,8 +818,9 @@ w6692_irq(int intno, void *dev_id) } static void -dbusy_timer_handler(struct dchannel *dch) +dbusy_timer_handler(struct timer_list *t) { + struct dchannel *dch = from_timer(dch, t, timer); struct w6692_hw *card = dch->hw; int rbch, star; u_long flags; @@ -852,8 +852,7 @@ static void initW6692(struct w6692_hw *card) { u8 val; - setup_timer(&card->dch.timer, (void *)dbusy_timer_handler, - (u_long)&card->dch); + timer_setup(&card->dch.timer, dbusy_timer_handler, 0); w6692_mode(&card->bc[0], ISDN_P_NONE); w6692_mode(&card->bc[1], ISDN_P_NONE); WriteW6692(card, W_D_CTL, 0x00); diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fc1733a088459..fa09d511a8eda 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -259,7 +259,7 @@ extern u8 *dsp_dtmf_goertzel_decode(struct dsp *dsp, u8 *data, int len, extern int dsp_tone(struct dsp *dsp, int tone); extern void dsp_tone_copy(struct dsp *dsp, u8 *data, int len); -extern void dsp_tone_timeout(void *arg); +extern void dsp_tone_timeout(struct timer_list *t); extern void dsp_bf_encrypt(struct dsp *dsp, u8 *data, int len); extern void dsp_bf_decrypt(struct dsp *dsp, u8 *data, int len); diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 880e9d367a399..cd036e87335a6 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1092,7 +1092,7 @@ dspcreate(struct channel_req *crq) ndsp->pcm_bank_tx = -1; ndsp->hfc_conf = -1; /* current conference number */ /* set tone timer */ - setup_timer(&ndsp->tone.tl, (void *)dsp_tone_timeout, (long)ndsp); + timer_setup(&ndsp->tone.tl, dsp_tone_timeout, 0); if (dtmfthreshold < 20 || dtmfthreshold > 500) dtmfthreshold = 200; @@ -1202,9 +1202,7 @@ static int __init dsp_init(void) } /* set sample timer */ - dsp_spl_tl.function = (void *)dsp_cmx_send; - dsp_spl_tl.data = 0; - init_timer(&dsp_spl_tl); + timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); diff --git a/drivers/isdn/mISDN/dsp_tones.c b/drivers/isdn/mISDN/dsp_tones.c index 057e0d6a369b6..8389e2105cdcf 100644 --- a/drivers/isdn/mISDN/dsp_tones.c +++ b/drivers/isdn/mISDN/dsp_tones.c @@ -457,9 +457,9 @@ dsp_tone_hw_message(struct dsp *dsp, u8 *sample, int len) * timer expires * *****************/ void -dsp_tone_timeout(void *arg) +dsp_tone_timeout(struct timer_list *t) { - struct dsp *dsp = arg; + struct dsp *dsp = from_timer(dsp, t, tone.tl); struct dsp_tone *tone = &dsp->tone; struct pattern *pat = (struct pattern *)tone->pattern; int index = tone->index; @@ -478,7 +478,6 @@ dsp_tone_timeout(void *arg) else dsp_tone_hw_message(dsp, pat->data[index], *(pat->siz[index])); /* set timer */ - init_timer(&tone->tl); tone->tl.expires = jiffies + (pat->seq[index] * HZ) / 8000; add_timer(&tone->tl); } @@ -541,7 +540,6 @@ dsp_tone(struct dsp *dsp, int tone) /* set timer */ if (timer_pending(&tonet->tl)) del_timer(&tonet->tl); - init_timer(&tonet->tl); tonet->tl.expires = jiffies + (pat->seq[0] * HZ) / 8000; add_timer(&tonet->tl); } else { diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c index 92e6570b11435..cabcb906e0b56 100644 --- a/drivers/isdn/mISDN/fsm.c +++ b/drivers/isdn/mISDN/fsm.c @@ -100,8 +100,9 @@ mISDN_FsmChangeState(struct FsmInst *fi, int newstate) EXPORT_SYMBOL(mISDN_FsmChangeState); static void -FsmExpireTimer(struct FsmTimer *ft) +FsmExpireTimer(struct timer_list *t) { + struct FsmTimer *ft = from_timer(ft, t, tl); #if FSM_TIMER_DEBUG if (ft->fi->debug) ft->fi->printdebug(ft->fi, "FsmExpireTimer %lx", (long) ft); @@ -117,7 +118,7 @@ mISDN_FsmInitTimer(struct FsmInst *fi, struct FsmTimer *ft) if (ft->fi->debug) ft->fi->printdebug(ft->fi, "mISDN_FsmInitTimer %lx", (long) ft); #endif - setup_timer(&ft->tl, (void *)FsmExpireTimer, (long)ft); + timer_setup(&ft->tl, FsmExpireTimer, 0); } EXPORT_SYMBOL(mISDN_FsmInitTimer); @@ -153,7 +154,6 @@ mISDN_FsmAddTimer(struct FsmTimer *ft, } return -1; } - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; @@ -175,7 +175,6 @@ mISDN_FsmRestartTimer(struct FsmTimer *ft, if (timer_pending(&ft->tl)) del_timer(&ft->tl); - init_timer(&ft->tl); ft->event = event; ft->arg = arg; ft->tl.expires = jiffies + (millisec * HZ) / 1000; diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index 6be2041248d34..b5d590e378ace 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -842,17 +842,18 @@ l1oip_send_bh(struct work_struct *work) * timer stuff */ static void -l1oip_keepalive(void *data) +l1oip_keepalive(struct timer_list *t) { - struct l1oip *hc = (struct l1oip *)data; + struct l1oip *hc = from_timer(hc, t, keep_tl); schedule_work(&hc->workq); } static void -l1oip_timeout(void *data) +l1oip_timeout(struct timer_list *t) { - struct l1oip *hc = (struct l1oip *)data; + struct l1oip *hc = from_timer(hc, t, + timeout_tl); struct dchannel *dch = hc->chan[hc->d_idx].dch; if (debug & DEBUG_L1OIP_MSG) @@ -1437,13 +1438,11 @@ init_card(struct l1oip *hc, int pri, int bundle) if (ret) return ret; - hc->keep_tl.function = (void *)l1oip_keepalive; - hc->keep_tl.data = (ulong)hc; - init_timer(&hc->keep_tl); + timer_setup(&hc->keep_tl, l1oip_keepalive, 0); hc->keep_tl.expires = jiffies + 2 * HZ; /* two seconds first time */ add_timer(&hc->keep_tl); - setup_timer(&hc->timeout_tl, (void *)l1oip_timeout, (ulong)hc); + timer_setup(&hc->timeout_tl, l1oip_timeout, 0); hc->timeout_on = 0; /* state that we have timer off */ return 0; diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index b1e135fc1fb50..c50a34340f67c 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -162,9 +162,9 @@ mISDN_poll(struct file *filep, poll_table *wait) } static void -dev_expire_timer(unsigned long data) +dev_expire_timer(struct timer_list *t) { - struct mISDNtimer *timer = (void *)data; + struct mISDNtimer *timer = from_timer(timer, t, tl); u_long flags; spin_lock_irqsave(&timer->dev->lock, flags); @@ -189,7 +189,7 @@ misdn_add_timer(struct mISDNtimerdev *dev, int timeout) if (!timer) return -ENOMEM; timer->dev = dev; - setup_timer(&timer->tl, dev_expire_timer, (long)timer); + timer_setup(&timer->tl, dev_expire_timer, 0); spin_lock_irq(&dev->lock); id = timer->id = dev->next_id++; if (dev->next_id < 0) -- GitLab From c788dd2c64322f97e4fdc04ea3948c4209fbc8a7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:15 -0700 Subject: [PATCH 1463/1507] isdn/gigaset: Use kzalloc instead of open-coded field zeroing This replaces a kmalloc followed by a bunch of per-field zeroing with a single kzalloc call, reducing the lines of code. Cc: Paul Bolle Cc: Karsten Keil Cc: "David S. Miller" Cc: Johan Hovold Cc: gigaset307x-common@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/gigaset/bas-gigaset.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index 2da3ff650e1d5..33151f05e7442 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -2200,7 +2200,7 @@ static int gigaset_initcshw(struct cardstate *cs) { struct bas_cardstate *ucs; - cs->hw.bas = ucs = kmalloc(sizeof *ucs, GFP_KERNEL); + cs->hw.bas = ucs = kzalloc(sizeof(*ucs), GFP_KERNEL); if (!ucs) { pr_err("out of memory\n"); return -ENOMEM; @@ -2212,15 +2212,7 @@ static int gigaset_initcshw(struct cardstate *cs) return -ENOMEM; } - ucs->urb_cmd_in = NULL; - ucs->urb_cmd_out = NULL; - ucs->rcvbuf = NULL; - ucs->rcvbuf_size = 0; - spin_lock_init(&ucs->lock); - ucs->pending = 0; - - ucs->basstate = 0; setup_timer(&ucs->timer_ctrl, req_timeout, (unsigned long) cs); setup_timer(&ucs->timer_atrdy, atrdy_timeout, (unsigned long) cs); setup_timer(&ucs->timer_cmd_in, cmd_in_timeout, (unsigned long) cs); -- GitLab From 4cfea08e6251d1468b3a694e9543131a12be3ac9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:16 -0700 Subject: [PATCH 1464/1507] isdn/gigaset: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Paul Bolle Cc: Karsten Keil Cc: "David S. Miller" Cc: Johan Hovold Cc: gigaset307x-common@lists.sourceforge.net Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/gigaset/bas-gigaset.c | 36 +++++++++++++++++------------- drivers/isdn/gigaset/common.c | 7 +++--- 2 files changed, 23 insertions(+), 20 deletions(-) diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index 33151f05e7442..c990c6bbffc25 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -433,10 +433,11 @@ static void check_pending(struct bas_cardstate *ucs) * argument: * controller state structure */ -static void cmd_in_timeout(unsigned long data) +static void cmd_in_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_cmd_in); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int rc; if (!ucs->rcvbuf_size) { @@ -639,10 +640,11 @@ static void int_in_work(struct work_struct *work) * argument: * controller state structure */ -static void int_in_resubmit(unsigned long data) +static void int_in_resubmit(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_int_in); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int rc; if (ucs->retry_int_in++ >= BAS_RETRY) { @@ -1441,10 +1443,11 @@ static void read_iso_tasklet(unsigned long data) * argument: * controller state structure */ -static void req_timeout(unsigned long data) +static void req_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_ctrl); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; int pending; unsigned long flags; @@ -1837,10 +1840,11 @@ static void write_command_callback(struct urb *urb) * argument: * controller state structure */ -static void atrdy_timeout(unsigned long data) +static void atrdy_timeout(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; - struct bas_cardstate *ucs = cs->hw.bas; + struct bas_cardstate *ucs = from_timer(ucs, t, timer_atrdy); + struct urb *urb = ucs->urb_int_in; + struct cardstate *cs = urb->context; dev_warn(cs->dev, "timeout waiting for HD_READY_SEND_ATDATA\n"); @@ -2213,10 +2217,10 @@ static int gigaset_initcshw(struct cardstate *cs) } spin_lock_init(&ucs->lock); - setup_timer(&ucs->timer_ctrl, req_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_atrdy, atrdy_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_cmd_in, cmd_in_timeout, (unsigned long) cs); - setup_timer(&ucs->timer_int_in, int_in_resubmit, (unsigned long) cs); + timer_setup(&ucs->timer_ctrl, req_timeout, 0); + timer_setup(&ucs->timer_atrdy, atrdy_timeout, 0); + timer_setup(&ucs->timer_cmd_in, cmd_in_timeout, 0); + timer_setup(&ucs->timer_int_in, int_in_resubmit, 0); init_waitqueue_head(&ucs->waitqueue); INIT_WORK(&ucs->int_in_wq, int_in_work); diff --git a/drivers/isdn/gigaset/common.c b/drivers/isdn/gigaset/common.c index 7c7814497e3ea..15482c5de33c1 100644 --- a/drivers/isdn/gigaset/common.c +++ b/drivers/isdn/gigaset/common.c @@ -153,9 +153,9 @@ static int test_timeout(struct at_state_t *at_state) return 1; } -static void timer_tick(unsigned long data) +static void timer_tick(struct timer_list *t) { - struct cardstate *cs = (struct cardstate *) data; + struct cardstate *cs = from_timer(cs, t, timer); unsigned long flags; unsigned channel; struct at_state_t *at_state; @@ -687,7 +687,7 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, cs->ignoreframes = ignoreframes; INIT_LIST_HEAD(&cs->temp_at_states); cs->running = 0; - init_timer(&cs->timer); /* clear next & prev */ + timer_setup(&cs->timer, timer_tick, 0); spin_lock_init(&cs->ev_lock); cs->ev_tail = 0; cs->ev_head = 0; @@ -768,7 +768,6 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, spin_lock_irqsave(&cs->lock, flags); cs->running = 1; spin_unlock_irqrestore(&cs->lock, flags); - setup_timer(&cs->timer, timer_tick, (unsigned long) cs); cs->timer.expires = jiffies + msecs_to_jiffies(GIG_TICK); add_timer(&cs->timer); -- GitLab From cdeabbb881343c1d554b83687a71f45280c592e0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:17 -0700 Subject: [PATCH 1465/1507] net: sched: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Add pointer back to Qdisc. Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/sched/cls_flow.c | 7 +++---- net/sched/sch_generic.c | 6 +++--- net/sched/sch_pie.c | 10 ++++++---- net/sched/sch_red.c | 10 ++++++---- net/sched/sch_sfq.c | 10 +++++----- 5 files changed, 23 insertions(+), 20 deletions(-) diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index f3be6667a2536..6b29cef90becf 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -345,9 +345,9 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; } -static void flow_perturbation(unsigned long arg) +static void flow_perturbation(struct timer_list *t) { - struct flow_filter *f = (struct flow_filter *)arg; + struct flow_filter *f = from_timer(f, t, perturb_timer); get_random_bytes(&f->hashrnd, 4); if (f->perturb_period) @@ -505,8 +505,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, get_random_bytes(&fnew->hashrnd, 4); } - setup_deferrable_timer(&fnew->perturb_timer, flow_perturbation, - (unsigned long)fnew); + timer_setup(&fnew->perturb_timer, flow_perturbation, TIMER_DEFERRABLE); netif_keep_dst(qdisc_dev(tp->q)); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a0a198768aad7..6ced7c89c141c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -288,9 +288,9 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); -static void dev_watchdog(unsigned long arg) +static void dev_watchdog(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct net_device *dev = from_timer(dev, t, watchdog_timer); netif_tx_lock(dev); if (!qdisc_tx_is_noop(dev)) { @@ -954,7 +954,7 @@ void dev_init_scheduler(struct net_device *dev) if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev); + timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } static void shutdown_scheduler_queue(struct net_device *dev, diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 6c2791d6102da..776c694c77c71 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -74,6 +74,7 @@ struct pie_sched_data { struct pie_vars vars; struct pie_stats stats; struct timer_list adapt_timer; + struct Qdisc *sch; }; static void pie_params_init(struct pie_params *params) @@ -422,10 +423,10 @@ static void calculate_probability(struct Qdisc *sch) pie_vars_init(&q->vars); } -static void pie_timer(unsigned long arg) +static void pie_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct pie_sched_data *q = qdisc_priv(sch); + struct pie_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -446,7 +447,8 @@ static int pie_init(struct Qdisc *sch, struct nlattr *opt) pie_vars_init(&q->vars); sch->limit = q->params.limit; - setup_timer(&q->adapt_timer, pie_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, pie_timer, 0); if (opt) { int err = pie_change(sch, opt); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 93b9d70a9b28f..fdfdb56aaae26 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -40,6 +40,7 @@ struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct timer_list adapt_timer; + struct Qdisc *sch; struct red_parms parms; struct red_vars vars; struct red_stats stats; @@ -221,10 +222,10 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static inline void red_adaptative_timer(unsigned long arg) +static inline void red_adaptative_timer(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct red_sched_data *q = qdisc_priv(sch); + struct red_sched_data *q = from_timer(q, t, adapt_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -238,7 +239,8 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) struct red_sched_data *q = qdisc_priv(sch); q->qdisc = &noop_qdisc; - setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch); + q->sch = sch; + timer_setup(&q->adapt_timer, red_adaptative_timer, 0); return red_change(sch, opt); } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 123a53af2506b..5a9c95149c5c1 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -145,6 +145,7 @@ struct sfq_sched_data { int perturb_period; unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ struct timer_list perturb_timer; + struct Qdisc *sch; }; /* @@ -604,10 +605,10 @@ static void sfq_rehash(struct Qdisc *sch) qdisc_tree_reduce_backlog(sch, dropped, drop_len); } -static void sfq_perturbation(unsigned long arg) +static void sfq_perturbation(struct timer_list *t) { - struct Qdisc *sch = (struct Qdisc *)arg; - struct sfq_sched_data *q = qdisc_priv(sch); + struct sfq_sched_data *q = from_timer(q, t, perturb_timer); + struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -722,8 +723,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) int i; int err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); + timer_setup(&q->perturb_timer, sfq_perturbation, TIMER_DEFERRABLE); err = tcf_block_get(&q->block, &q->filter_list, sch); if (err) -- GitLab From a92c5751b97cca55d8140ec0bf26a53c7e00bfa5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:18 -0700 Subject: [PATCH 1466/1507] netfilter: ipset: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. This introduces a pointer back to the struct ip_set, which is used instead of the struct timer_list .data field. Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Florian Westphal Cc: "David S. Miller" Cc: Stephen Hemminger Cc: simran singhal Cc: Muhammad Falak R Wani Cc: netfilter-devel@vger.kernel.org Cc: coreteam@netfilter.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/netfilter/ipset/ip_set_bitmap_gen.h | 10 +++++----- net/netfilter/ipset/ip_set_bitmap_ip.c | 2 ++ net/netfilter/ipset/ip_set_bitmap_ipmac.c | 2 ++ net/netfilter/ipset/ip_set_bitmap_port.c | 2 ++ net/netfilter/ipset/ip_set_hash_gen.h | 12 +++++++----- net/netfilter/ipset/ip_set_list_set.c | 12 +++++++----- 6 files changed, 25 insertions(+), 15 deletions(-) diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 8ad2b52a0b328..5ca18f07683b5 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -37,11 +37,11 @@ #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct mtype *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -272,10 +272,10 @@ mtype_list(const struct ip_set *set, } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct mtype *map = set->data; + struct mtype *map = from_timer(map, t, gc); + struct ip_set *set = map->set; void *x; u32 id; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index 4783efff0bde6..d8975a0b4282e 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -48,6 +48,7 @@ struct bitmap_ip { size_t memsize; /* members size */ u8 netmask; /* subnet netmask */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -232,6 +233,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, map->netmask = netmask; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 9a065f672d3a5..4c279fbd2d5de 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -52,6 +52,7 @@ struct bitmap_ipmac { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collector */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* MAC + data extensions */ __aligned(__alignof__(u64)); }; @@ -307,6 +308,7 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, map->elements = elements; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_IPV4; diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 7f0c733358a42..7f9bbd7c98b55 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -40,6 +40,7 @@ struct bitmap_port { u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[0] /* data extensions */ __aligned(__alignof__(u64)); }; @@ -214,6 +215,7 @@ init_map_port(struct ip_set *set, struct bitmap_port *map, map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; + map->set = set; set->data = map; set->family = NFPROTO_UNSPEC; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 51063d9ed0f75..efffc8eabafea 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -280,6 +280,7 @@ htable_bits(u32 hashsize) struct htype { struct htable __rcu *table; /* the hash table */ struct timer_list gc; /* garbage collection when timeout enabled */ + struct ip_set *set; /* attached to this ip_set */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -429,11 +430,11 @@ mtype_destroy(struct ip_set *set) } static void -mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct htype *h = set->data; - setup_timer(&h->gc, gc, (unsigned long)set); + timer_setup(&h->gc, gc, 0); mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); pr_debug("gc initialized, run in every %u\n", IPSET_GC_PERIOD(set->timeout)); @@ -526,10 +527,10 @@ mtype_expire(struct ip_set *set, struct htype *h) } static void -mtype_gc(unsigned long ul_set) +mtype_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct htype *h = set->data; + struct htype *h = from_timer(h, t, gc); + struct ip_set *set = h->set; pr_debug("called\n"); spin_lock_bh(&set->lock); @@ -1314,6 +1315,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, t->htable_bits = hbits; RCU_INIT_POINTER(h->table, t); + h->set = set; set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 178d4eba013b4..c9b4e05ad940c 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -44,6 +44,7 @@ struct set_adt_elem { struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ + struct ip_set *set; /* attached to this ip_set */ struct net *net; /* namespace */ struct list_head members; /* the set members */ }; @@ -571,10 +572,10 @@ static const struct ip_set_type_variant set_variant = { }; static void -list_set_gc(unsigned long ul_set) +list_set_gc(struct timer_list *t) { - struct ip_set *set = (struct ip_set *)ul_set; - struct list_set *map = set->data; + struct list_set *map = from_timer(map, t, gc); + struct ip_set *set = map->set; spin_lock_bh(&set->lock); set_cleanup_entries(set); @@ -585,11 +586,11 @@ list_set_gc(unsigned long ul_set) } static void -list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set)) +list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct list_set *map = set->data; - setup_timer(&map->gc, gc, (unsigned long)set); + timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } @@ -606,6 +607,7 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) map->size = size; map->net = net; + map->set = set; INIT_LIST_HEAD(&map->members); set->data = map; -- GitLab From 59f379f9046a9e0532ffd19b44e3c32fe79ec51b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:19 -0700 Subject: [PATCH 1467/1507] inet/connection_sock: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Gerrit Renker Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Cc: netdev@vger.kernel.org Cc: dccp@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 6 +++--- net/dccp/timer.c | 18 ++++++++++-------- net/ipv4/inet_connection_sock.c | 21 +++++++++------------ net/ipv4/tcp_timer.c | 18 +++++++++++------- 4 files changed, 33 insertions(+), 30 deletions(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 13e4c89a8231b..0358745ea0598 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -169,9 +169,9 @@ enum inet_csk_ack_state_t { }; void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)); + void (*retransmit_handler)(struct timer_list *), + void (*delack_handler)(struct timer_list *), + void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 3a2c340277586..1e35526bf4368 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -125,10 +125,11 @@ static void dccp_retransmit_timer(struct sock *sk) __sk_dst_reset(sk); } -static void dccp_write_timer(unsigned long data) +static void dccp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; int event = 0; bh_lock_sock(sk); @@ -161,19 +162,20 @@ static void dccp_write_timer(unsigned long data) sock_put(sk); } -static void dccp_keepalive_timer(unsigned long data) +static void dccp_keepalive_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */ -static void dccp_delack_timer(unsigned long data) +static void dccp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8a91ebbf0c017..5c965ecc96a04 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -494,17 +494,15 @@ EXPORT_SYMBOL(inet_csk_accept); * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, - void (*retransmit_handler)(unsigned long), - void (*delack_handler)(unsigned long), - void (*keepalive_handler)(unsigned long)) + void (*retransmit_handler)(struct timer_list *t), + void (*delack_handler)(struct timer_list *t), + void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); - setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler, - (unsigned long)sk); - setup_timer(&icsk->icsk_delack_timer, delack_handler, - (unsigned long)sk); - setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk); + timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); + timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); @@ -676,9 +674,9 @@ void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); -static void reqsk_timer_handler(unsigned long data) +static void reqsk_timer_handler(struct timer_list *t) { - struct request_sock *req = (struct request_sock *)data; + struct request_sock *req = from_timer(req, t, rsk_timer); struct sock *sk_listener = req->rsk_listener; struct net *net = sock_net(sk_listener); struct inet_connection_sock *icsk = inet_csk(sk_listener); @@ -749,8 +747,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, req->num_timeout = 0; req->sk = NULL; - setup_pinned_timer(&req->rsk_timer, reqsk_timer_handler, - (unsigned long)req); + timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); inet_ehash_insert(req_to_sk(req), NULL); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7014cc00c74c7..804a8d34ce86c 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -288,15 +288,17 @@ void tcp_delack_timer_handler(struct sock *sk) * * Returns: Nothing (void) */ -static void tcp_delack_timer(unsigned long data) +static void tcp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - inet_csk(sk)->icsk_ack.blocked = 1; + icsk->icsk_ack.blocked = 1; __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) @@ -576,9 +578,11 @@ void tcp_write_timer_handler(struct sock *sk) sk_mem_reclaim(sk); } -static void tcp_write_timer(unsigned long data) +static void tcp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + from_timer(icsk, t, icsk_retransmit_timer); + struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { @@ -613,9 +617,9 @@ void tcp_set_keepalive(struct sock *sk, int val) EXPORT_SYMBOL_GPL(tcp_set_keepalive); -static void tcp_keepalive_timer (unsigned long data) +static void tcp_keepalive_timer (struct timer_list *t) { - struct sock *sk = (struct sock *) data; + struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; -- GitLab From 78802011fbe34331bdef6f2dfb1634011f0e4c32 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:20 -0700 Subject: [PATCH 1468/1507] inet: frags: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Alexander Aring Cc: Stefan Schmidt Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Florian Westphal Cc: linux-wpan@vger.kernel.org Cc: netdev@vger.kernel.org Cc: netfilter-devel@vger.kernel.org Cc: coreteam@netfilter.org Signed-off-by: Kees Cook Acked-by: Stefan Schmidt # for ieee802154 Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- net/ieee802154/6lowpan/reassembly.c | 5 +++-- net/ipv4/inet_fragment.c | 4 ++-- net/ipv4/ip_fragment.c | 5 +++-- net/ipv6/netfilter/nf_conntrack_reasm.c | 5 +++-- net/ipv6/reassembly.c | 5 +++-- 6 files changed, 15 insertions(+), 11 deletions(-) diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index fc59e0775e001..c695807ca7071 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -95,7 +95,7 @@ struct inet_frags { void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); - void (*frag_expire)(unsigned long data); + void (*frag_expire)(struct timer_list *t); struct kmem_cache *frags_cachep; const char *frags_cache_name; }; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index f85b08baff160..85bf86ad6b180 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) fq->daddr = *arg->dst; } -static void lowpan_frag_expire(unsigned long data) +static void lowpan_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); spin_lock(&fq->q.lock); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index af74d0433453d..7f3ef5c287a10 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -147,7 +147,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) spin_unlock(&hb->chain_lock); hlist_for_each_entry_safe(fq, n, &expired, list_evictor) - f->frag_expire((unsigned long) fq); + f->frag_expire(&fq->timer); return evicted; } @@ -366,7 +366,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, f->constructor(q, arg); add_frag_mem_limit(nf, f->qsize); - setup_timer(&q->timer, f->frag_expire, (unsigned long)q); + timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 1); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 46408c220d9dc..9215654a401fe 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -190,12 +190,13 @@ static bool frag_expire_skip_icmp(u32 user) /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ -static void ip_expire(unsigned long arg) +static void ip_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct ipq *qp; struct net *net; - qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); + qp = container_of(frag, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); rcu_read_lock(); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b263bf3a19f7a..977d8900cfd12 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_ct_frag6_expire(unsigned long data) +static void nf_ct_frag6_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, nf_frag.frags); ip6_expire_frag_queue(net, fq, &nf_frags); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 846012eae5268..afbc000ad4f29 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -170,12 +170,13 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, } EXPORT_SYMBOL(ip6_expire_frag_queue); -static void ip6_frag_expire(unsigned long data) +static void ip6_frag_expire(struct timer_list *t) { + struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; struct net *net; - fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + fq = container_of(frag, struct frag_queue, q); net = container_of(fq->q.net, struct net, ipv6.frags); ip6_expire_frag_queue(net, fq, &ip6_frags); -- GitLab From 9f12a77e467b8ec0296cf1c3481447e1b1811f59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:21 -0700 Subject: [PATCH 1469/1507] net/core: Collapse redundant sk_timer callback data assignments The core sk_timer initializer can provide the common .data assignment instead of it being set separately in users. Cc: "David S. Miller" Cc: Ralf Baechle Cc: Andrew Hendry Cc: Eric Dumazet Cc: Paolo Abeni Cc: David Howells Cc: Colin Ian King Cc: Ingo Molnar Cc: linzhang Cc: netdev@vger.kernel.org Cc: linux-hams@vger.kernel.org Cc: linux-x25@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- net/netrom/nr_timer.c | 1 - net/rose/rose_timer.c | 1 - net/x25/af_x25.c | 1 - net/x25/x25_timer.c | 1 - 5 files changed, 1 insertion(+), 5 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 23953b741a41f..f577df17bcf24 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2683,7 +2683,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk_init_common(sk); sk->sk_send_head = NULL; - init_timer(&sk->sk_timer); + setup_timer(&sk->sk_timer, NULL, (unsigned long)sk); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 94d05806a9a24..f84ce71f1f5f6 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -45,7 +45,6 @@ void nr_init_timers(struct sock *sk) setup_timer(&nr->idletimer, nr_idletimer_expiry, (unsigned long)sk); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; sk->sk_timer.function = &nr_heartbeat_expiry; } diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index 3b89d66f15bbe..e082011852145 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -36,7 +36,6 @@ void rose_start_heartbeat(struct sock *sk) { del_timer(&sk->sk_timer); - sk->sk_timer.data = (unsigned long)sk; sk->sk_timer.function = &rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ac095936552d9..c590c0bd13933 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -414,7 +414,6 @@ static void __x25_destroy_socket(struct sock *sk) /* Defer: outstanding buffers */ sk->sk_timer.expires = jiffies + 10 * HZ; sk->sk_timer.function = x25_destroy_timer; - sk->sk_timer.data = (unsigned long)sk; add_timer(&sk->sk_timer); } else { /* drop last reference so sock_put will free */ diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index 5c5db1a36399d..de5cec41d1008 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -36,7 +36,6 @@ void x25_init_timers(struct sock *sk) setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk); /* initialized by sock_init_data */ - sk->sk_timer.data = (unsigned long)sk; sk->sk_timer.function = &x25_heartbeat_expiry; } -- GitLab From d26c089e78298843b8c5202ffb43146d17c15bde Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:22 -0700 Subject: [PATCH 1470/1507] hdlc: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. This adds a pointer back to the net_device, and drops needless open-coded resetting of the .function and .data fields. Cc: David S. Miller Cc: Krzysztof Halasa Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/wan/hdlc_cisco.c | 13 ++++++------- drivers/net/wan/hdlc_fr.c | 12 ++++++------ 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index c696d42f4502c..320039d329c7d 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -54,6 +54,7 @@ struct cisco_state { cisco_proto settings; struct timer_list timer; + struct net_device *dev; spinlock_t lock; unsigned long last_poll; int up; @@ -257,11 +258,10 @@ static int cisco_rx(struct sk_buff *skb) -static void cisco_timer(unsigned long arg) +static void cisco_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; - hdlc_device *hdlc = dev_to_hdlc(dev); - struct cisco_state *st = state(hdlc); + struct cisco_state *st = from_timer(st, t, timer); + struct net_device *dev = st->dev; spin_lock(&st->lock); if (st->up && @@ -276,8 +276,6 @@ static void cisco_timer(unsigned long arg) spin_unlock(&st->lock); st->timer.expires = jiffies + st->settings.interval * HZ; - st->timer.function = cisco_timer; - st->timer.data = arg; add_timer(&st->timer); } @@ -293,7 +291,8 @@ static void cisco_start(struct net_device *dev) st->up = st->txseq = st->rxseq = 0; spin_unlock_irqrestore(&st->lock, flags); - setup_timer(&st->timer, cisco_timer, (unsigned long)dev); + st->dev = dev; + timer_setup(&st->timer, cisco_timer, 0); st->timer.expires = jiffies + HZ; /* First poll after 1 s */ add_timer(&st->timer); } diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 425a47ffed25b..038236a9c60ee 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -140,6 +140,7 @@ struct frad_state { int dce_pvc_count; struct timer_list timer; + struct net_device *dev; unsigned long last_poll; int reliable; int dce_changed; @@ -597,9 +598,10 @@ static void fr_set_link_state(int reliable, struct net_device *dev) } -static void fr_timer(unsigned long arg) +static void fr_timer(struct timer_list *t) { - struct net_device *dev = (struct net_device *)arg; + struct frad_state *st = from_timer(st, t, timer); + struct net_device *dev = st->dev; hdlc_device *hdlc = dev_to_hdlc(dev); int i, cnt = 0, reliable; u32 list; @@ -644,8 +646,6 @@ static void fr_timer(unsigned long arg) state(hdlc)->settings.t391 * HZ; } - state(hdlc)->timer.function = fr_timer; - state(hdlc)->timer.data = arg; add_timer(&state(hdlc)->timer); } @@ -1003,8 +1003,8 @@ static void fr_start(struct net_device *dev) state(hdlc)->n391cnt = 0; state(hdlc)->txseq = state(hdlc)->rxseq = 0; - setup_timer(&state(hdlc)->timer, fr_timer, - (unsigned long)dev); + state(hdlc)->dev = dev; + timer_setup(&state(hdlc)->timer, fr_timer, 0); /* First poll after 1 s */ state(hdlc)->timer.expires = jiffies + HZ; add_timer(&state(hdlc)->timer); -- GitLab From 9ba650a4ebdde5f5f59a62ed51563d7c4586e492 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:23 -0700 Subject: [PATCH 1471/1507] appletalk: Remove unneeded synchronization The use of del_timer_sync() will make sure a timer is not rescheduled. As such, there is no need to add external signals to kill timers. In preparation for switching the timer callback argument to the timer pointer, this drops the .data argument since it doesn't serve a meaningful purpose here. Cc: David Howells Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/appletalk/ltpc.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index e4aa374caa4d5..cc3dc9337eaea 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -880,14 +880,10 @@ static void ltpc_poll(unsigned long l) } ltpc_poll_counter--; } - - if (!dev) - return; /* we've been downed */ /* poll 20 times per second */ idle(dev); ltpc_timer.expires = jiffies + HZ/20; - add_timer(<pc_timer); } @@ -1252,8 +1248,6 @@ static void __exit ltpc_cleanup(void) if(debug & DEBUG_VERBOSE) printk("unregister_netdev\n"); unregister_netdev(dev_ltpc); - ltpc_timer.data = 0; /* signal the poll routine that we're done */ - del_timer_sync(<pc_timer); if(debug & DEBUG_VERBOSE) printk("freeing irq\n"); -- GitLab From 5f2585d4e570f2dffd148f6e57308fb431079175 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:24 -0700 Subject: [PATCH 1472/1507] drivers/net/appletalk: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Adds a static variable to hold the polled net_device. Cc: David Howells Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/appletalk/ltpc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index cc3dc9337eaea..75a5a9b87c5a4 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -694,6 +694,7 @@ static int do_read(struct net_device *dev, void *cbuf, int cbuflen, /* end of idle handlers -- what should be seen is do_read, do_write */ static struct timer_list ltpc_timer; +static struct net_device *ltpc_timer_dev; static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev); @@ -867,10 +868,8 @@ static void set_multicast_list(struct net_device *dev) static int ltpc_poll_counter; -static void ltpc_poll(unsigned long l) +static void ltpc_poll(struct timer_list *unused) { - struct net_device *dev = (struct net_device *) l; - del_timer(<pc_timer); if(debug & DEBUG_VERBOSE) { @@ -882,7 +881,7 @@ static void ltpc_poll(unsigned long l) } /* poll 20 times per second */ - idle(dev); + idle(ltpc_timer_dev); ltpc_timer.expires = jiffies + HZ/20; add_timer(<pc_timer); } @@ -1161,7 +1160,8 @@ struct net_device * __init ltpc_probe(void) dev->irq = 0; /* polled mode -- 20 times per second */ /* this is really, really slow... should it poll more often? */ - setup_timer(<pc_timer, ltpc_poll, (unsigned long)dev); + ltpc_timer_dev = dev; + timer_setup(<pc_timer, ltpc_poll, 0); ltpc_timer.expires = jiffies + HZ/20; add_timer(<pc_timer); -- GitLab From 11286125326bb9d5e295c7c85fb1dc91ca2af46b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:26 -0700 Subject: [PATCH 1473/1507] isdnloop: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Added missing initialization for rb_timer. Cc: Karsten Keil Cc: "David S. Miller" Cc: Al Viro Cc: Stephen Hemminger Cc: Arnd Bergmann Cc: Johannes Berg Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/isdnloop/isdnloop.c | 33 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 19 deletions(-) diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c index e97232646ba15..a4597e96c9160 100644 --- a/drivers/isdn/isdnloop/isdnloop.c +++ b/drivers/isdn/isdnloop/isdnloop.c @@ -90,9 +90,9 @@ isdnloop_bchan_send(isdnloop_card *card, int ch) * data = pointer to card struct, set by kernel timer.data */ static void -isdnloop_pollbchan(unsigned long data) +isdnloop_pollbchan(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, rb_timer); unsigned long flags; if (card->flags & ISDNLOOP_FLAGS_B1ACTIVE) @@ -305,9 +305,9 @@ isdnloop_putmsg(isdnloop_card *card, unsigned char c) * data = pointer to card struct */ static void -isdnloop_polldchan(unsigned long data) +isdnloop_polldchan(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, st_timer); struct sk_buff *skb; int avail; int left; @@ -373,8 +373,6 @@ isdnloop_polldchan(unsigned long data) card->flags |= ISDNLOOP_FLAGS_RBTIMER; spin_lock_irqsave(&card->isdnloop_lock, flags); del_timer(&card->rb_timer); - card->rb_timer.function = isdnloop_pollbchan; - card->rb_timer.data = (unsigned long) card; card->rb_timer.expires = jiffies + ISDNLOOP_TIMER_BCREAD; add_timer(&card->rb_timer); spin_unlock_irqrestore(&card->isdnloop_lock, flags); @@ -588,9 +586,10 @@ isdnloop_atimeout(isdnloop_card *card, int ch) * Wrapper for isdnloop_atimeout(). */ static void -isdnloop_atimeout0(unsigned long data) +isdnloop_atimeout0(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, c_timer[0]); + isdnloop_atimeout(card, 0); } @@ -598,9 +597,10 @@ isdnloop_atimeout0(unsigned long data) * Wrapper for isdnloop_atimeout(). */ static void -isdnloop_atimeout1(unsigned long data) +isdnloop_atimeout1(struct timer_list *t) { - isdnloop_card *card = (isdnloop_card *) data; + isdnloop_card *card = from_timer(card, t, c_timer[1]); + isdnloop_atimeout(card, 1); } @@ -617,13 +617,9 @@ isdnloop_start_ctimer(isdnloop_card *card, int ch) unsigned long flags; spin_lock_irqsave(&card->isdnloop_lock, flags); - init_timer(&card->c_timer[ch]); + timer_setup(&card->c_timer[ch], ch ? isdnloop_atimeout1 + : isdnloop_atimeout0, 0); card->c_timer[ch].expires = jiffies + ISDNLOOP_TIMER_ALERTWAIT; - if (ch) - card->c_timer[ch].function = isdnloop_atimeout1; - else - card->c_timer[ch].function = isdnloop_atimeout0; - card->c_timer[ch].data = (unsigned long) card; add_timer(&card->c_timer[ch]); spin_unlock_irqrestore(&card->isdnloop_lock, flags); } @@ -1113,10 +1109,9 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp) sdef.ptype); return -EINVAL; } - init_timer(&card->st_timer); + timer_setup(&card->rb_timer, isdnloop_pollbchan, 0); + timer_setup(&card->st_timer, isdnloop_polldchan, 0); card->st_timer.expires = jiffies + ISDNLOOP_TIMER_DCREAD; - card->st_timer.function = isdnloop_polldchan; - card->st_timer.data = (unsigned long) card; add_timer(&card->st_timer); card->flags |= ISDNLOOP_FLAGS_RUNNING; spin_unlock_irqrestore(&card->isdnloop_lock, flags); -- GitLab From de892f8f2cc8176368a490e0778fd2de15e9bfda Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:27 -0700 Subject: [PATCH 1474/1507] net: ethernet: apple: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Johannes Berg Cc: Jarod Wilson Cc: Rob Herring Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/apple/bmac.c | 12 +++++------- drivers/net/ethernet/apple/mace.c | 12 +++++------- 2 files changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index eac740c476ceb..5a655d289dd58 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -157,7 +157,7 @@ static irqreturn_t bmac_misc_intr(int irq, void *dev_id); static irqreturn_t bmac_txdma_intr(int irq, void *dev_id); static irqreturn_t bmac_rxdma_intr(int irq, void *dev_id); static void bmac_set_timeout(struct net_device *dev); -static void bmac_tx_timeout(unsigned long data); +static void bmac_tx_timeout(struct timer_list *t); static int bmac_output(struct sk_buff *skb, struct net_device *dev); static void bmac_start(struct net_device *dev); @@ -555,8 +555,6 @@ static inline void bmac_set_timeout(struct net_device *dev) if (bp->timeout_active) del_timer(&bp->tx_timeout); bp->tx_timeout.expires = jiffies + TX_TIMEOUT; - bp->tx_timeout.function = bmac_tx_timeout; - bp->tx_timeout.data = (unsigned long) dev; add_timer(&bp->tx_timeout); bp->timeout_active = 1; spin_unlock_irqrestore(&bp->lock, flags); @@ -1321,7 +1319,7 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match) bp->queue = (struct sk_buff_head *)(bp->rx_cmds + N_RX_RING + 1); skb_queue_head_init(bp->queue); - init_timer(&bp->tx_timeout); + timer_setup(&bp->tx_timeout, bmac_tx_timeout, 0); ret = request_irq(dev->irq, bmac_misc_intr, 0, "BMAC-misc", dev); if (ret) { @@ -1471,10 +1469,10 @@ bmac_output(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void bmac_tx_timeout(unsigned long data) +static void bmac_tx_timeout(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct bmac_data *bp = netdev_priv(dev); + struct bmac_data *bp = from_timer(bp, t, tx_timeout); + struct net_device *dev = macio_get_drvdata(bp->mdev); volatile struct dbdma_regs __iomem *td = bp->tx_dma; volatile struct dbdma_regs __iomem *rd = bp->rx_dma; volatile struct dbdma_cmd *cp; diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index e58b157b7d7c4..0b5429d76bcf2 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -86,7 +86,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id); static irqreturn_t mace_txdma_intr(int irq, void *dev_id); static irqreturn_t mace_rxdma_intr(int irq, void *dev_id); static void mace_set_timeout(struct net_device *dev); -static void mace_tx_timeout(unsigned long data); +static void mace_tx_timeout(struct timer_list *t); static inline void dbdma_reset(volatile struct dbdma_regs __iomem *dma); static inline void mace_clean_rings(struct mace_data *mp); static void __mace_set_address(struct net_device *dev, void *addr); @@ -196,7 +196,7 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match) memset((char *) mp->tx_cmds, 0, (NCMDS_TX*N_TX_RING + N_RX_RING + 2) * sizeof(struct dbdma_cmd)); - init_timer(&mp->tx_timeout); + timer_setup(&mp->tx_timeout, mace_tx_timeout, 0); spin_lock_init(&mp->lock); mp->timeout_active = 0; @@ -521,8 +521,6 @@ static inline void mace_set_timeout(struct net_device *dev) if (mp->timeout_active) del_timer(&mp->tx_timeout); mp->tx_timeout.expires = jiffies + TX_TIMEOUT; - mp->tx_timeout.function = mace_tx_timeout; - mp->tx_timeout.data = (unsigned long) dev; add_timer(&mp->tx_timeout); mp->timeout_active = 1; } @@ -801,10 +799,10 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void mace_tx_timeout(unsigned long data) +static void mace_tx_timeout(struct timer_list *t) { - struct net_device *dev = (struct net_device *) data; - struct mace_data *mp = netdev_priv(dev); + struct mace_data *mp = from_timer(mp, t, tx_timeout); + struct net_device *dev = macio_get_drvdata(mp->mdev); volatile struct mace __iomem *mb = mp->mace; volatile struct dbdma_regs __iomem *td = mp->tx_dma; volatile struct dbdma_regs __iomem *rd = mp->rx_dma; -- GitLab From 0822c5d94e10d9790e82bdfea20a10f0884bca54 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:28 -0700 Subject: [PATCH 1475/1507] net: ethernet: sun: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Philippe Reynes Cc: Jarod Wilson Cc: Shannon Nelson Cc: Rob Herring Cc: chris hyser Cc: Tushar Dave Cc: Tobias Klauser Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/cassini.c | 7 ++++--- drivers/net/ethernet/sun/ldmvsw.c | 3 +-- drivers/net/ethernet/sun/niu.c | 10 ++++------ drivers/net/ethernet/sun/sunbmac.c | 10 ++++------ drivers/net/ethernet/sun/sungem.c | 6 +++--- drivers/net/ethernet/sun/sunhme.c | 10 ++++------ drivers/net/ethernet/sun/sunvnet.c | 3 +-- drivers/net/ethernet/sun/sunvnet_common.c | 4 ++-- drivers/net/ethernet/sun/sunvnet_common.h | 2 +- 9 files changed, 24 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index a74d78f64af90..113bd57e2ea04 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -4079,9 +4079,9 @@ static void cas_reset_task(struct work_struct *work) #endif } -static void cas_link_timer(unsigned long data) +static void cas_link_timer(struct timer_list *t) { - struct cas *cp = (struct cas *) data; + struct cas *cp = from_timer(cp, t, link_timer); int mask, pending = 0, reset = 0; unsigned long flags; @@ -5039,7 +5039,8 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&cp->stat_lock[N_TX_RINGS]); mutex_init(&cp->pm_mutex); - setup_timer(&cp->link_timer, cas_link_timer, (unsigned long)cp); + timer_setup(&cp->link_timer, cas_link_timer, 0); + #if 1 /* Just in case the implementation of atomic operations * change so that an explicit initialization is necessary. diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5feeaa9f0a9e0..5ea037672e6f2 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -363,8 +363,7 @@ static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) list_add_rcu(&port->list, &vp->port_list); spin_unlock_irqrestore(&vp->lock, flags); - setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common, - (unsigned long)port); + timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0); err = register_netdev(dev); if (err) { diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index bde19b307d0da..ab502ee35fb29 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -2221,9 +2221,9 @@ static int niu_link_status(struct niu *np, int *link_up_p) return err; } -static void niu_timer(unsigned long __opaque) +static void niu_timer(struct timer_list *t) { - struct niu *np = (struct niu *) __opaque; + struct niu *np = from_timer(np, t, timer); unsigned long off; int err, link_up; @@ -6123,7 +6123,7 @@ static int niu_open(struct net_device *dev) err = niu_init_hw(np); if (!err) { - setup_timer(&np->timer, niu_timer, (unsigned long)np); + timer_setup(&np->timer, niu_timer, 0); np->timer.expires = jiffies + HZ; err = niu_enable_interrupts(np, 1); @@ -6773,10 +6773,8 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu) err = niu_init_hw(np); if (!err) { - init_timer(&np->timer); + timer_setup(&np->timer, niu_timer, 0); np->timer.expires = jiffies + HZ; - np->timer.data = (unsigned long) np; - np->timer.function = niu_timer; err = niu_enable_interrupts(np, 1); if (err) diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 3189722110c26..0b1f41f6bceba 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -523,9 +523,9 @@ static int try_next_permutation(struct bigmac *bp, void __iomem *tregs) return -1; } -static void bigmac_timer(unsigned long data) +static void bigmac_timer(struct timer_list *t) { - struct bigmac *bp = (struct bigmac *) data; + struct bigmac *bp = from_timer(bp, t, bigmac_timer); void __iomem *tregs = bp->tregs; int restart_timer = 0; @@ -613,8 +613,6 @@ static void bigmac_begin_auto_negotiation(struct bigmac *bp) bp->timer_state = ltrywait; bp->timer_ticks = 0; bp->bigmac_timer.expires = jiffies + (12 * HZ) / 10; - bp->bigmac_timer.data = (unsigned long) bp; - bp->bigmac_timer.function = bigmac_timer; add_timer(&bp->bigmac_timer); } @@ -921,7 +919,7 @@ static int bigmac_open(struct net_device *dev) printk(KERN_ERR "BIGMAC: Can't order irq %d to go.\n", dev->irq); return ret; } - init_timer(&bp->bigmac_timer); + timer_setup(&bp->bigmac_timer, bigmac_timer, 0); ret = bigmac_init_hw(bp, 0); if (ret) free_irq(dev->irq, bp); @@ -1172,7 +1170,7 @@ static int bigmac_ether_init(struct platform_device *op, "board-version", 1); /* Init auto-negotiation timer state. */ - init_timer(&bp->bigmac_timer); + timer_setup(&bp->bigmac_timer, bigmac_timer, 0); bp->timer_state = asleep; bp->timer_ticks = 0; diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index b75ab8f44968a..a7afcee3c5ae6 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1496,9 +1496,9 @@ static int gem_mdio_link_not_up(struct gem *gp) } } -static void gem_link_timer(unsigned long data) +static void gem_link_timer(struct timer_list *t) { - struct gem *gp = (struct gem *) data; + struct gem *gp = from_timer(gp, t, link_timer); struct net_device *dev = gp->dev; int restart_aneg = 0; @@ -2910,7 +2910,7 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) gp->msg_enable = DEFAULT_MSG; - setup_timer(&gp->link_timer, gem_link_timer, (unsigned long)gp); + timer_setup(&gp->link_timer, gem_link_timer, 0); INIT_WORK(&gp->reset_task, gem_reset_task); diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 9e983e1d82498..0431f1e5f5112 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -685,9 +685,9 @@ static int is_lucent_phy(struct happy_meal *hp) return ret; } -static void happy_meal_timer(unsigned long data) +static void happy_meal_timer(struct timer_list *t) { - struct happy_meal *hp = (struct happy_meal *) data; + struct happy_meal *hp = from_timer(hp, t, happy_timer); void __iomem *tregs = hp->tcvregs; int restart_timer = 0; @@ -1413,8 +1413,6 @@ happy_meal_begin_auto_negotiation(struct happy_meal *hp, hp->timer_ticks = 0; hp->happy_timer.expires = jiffies + (12 * HZ)/10; /* 1.2 sec. */ - hp->happy_timer.data = (unsigned long) hp; - hp->happy_timer.function = happy_meal_timer; add_timer(&hp->happy_timer); } @@ -2819,7 +2817,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) hp->timer_state = asleep; hp->timer_ticks = 0; - init_timer(&hp->happy_timer); + timer_setup(&hp->happy_timer, happy_meal_timer, 0); hp->dev = dev; dev->netdev_ops = &hme_netdev_ops; @@ -3133,7 +3131,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, hp->timer_state = asleep; hp->timer_ticks = 0; - init_timer(&hp->happy_timer); + timer_setup(&hp->happy_timer, happy_meal_timer, 0); hp->irq = pdev->irq; hp->dev = dev; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 0b95105f70600..27fb226388852 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -492,8 +492,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) pr_info("%s: PORT ( remote-mac %pM%s )\n", vp->dev->name, port->raddr, switch_port ? " switch-port" : ""); - setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common, - (unsigned long)port); + timer_setup(&port->clean_timer, sunvnet_clean_timer_expire_common, 0); napi_enable(&port->napi); vio_port_up(&port->vio); diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index ecf456c7b6d14..8aa3ce46bb81e 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1040,9 +1040,9 @@ static inline void vnet_free_skbs(struct sk_buff *skb) } } -void sunvnet_clean_timer_expire_common(unsigned long port0) +void sunvnet_clean_timer_expire_common(struct timer_list *t) { - struct vnet_port *port = (struct vnet_port *)port0; + struct vnet_port *port = from_timer(port, t, clean_timer); struct sk_buff *freeskbs; unsigned pending; diff --git a/drivers/net/ethernet/sun/sunvnet_common.h b/drivers/net/ethernet/sun/sunvnet_common.h index b20d6fa7ef25b..656673c310666 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.h +++ b/drivers/net/ethernet/sun/sunvnet_common.h @@ -129,7 +129,7 @@ struct vnet { ((__port)->vsw ? (__port)->dev : (__port)->vp->dev) /* Common funcs */ -void sunvnet_clean_timer_expire_common(unsigned long port0); +void sunvnet_clean_timer_expire_common(struct timer_list *t); int sunvnet_open_common(struct net_device *dev); int sunvnet_close_common(struct net_device *dev); void sunvnet_set_rx_mode_common(struct net_device *dev, struct vnet *vp); -- GitLab From 6fd9c53f71862a4797b7ed8a5de80e2c64829f56 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:29 -0700 Subject: [PATCH 1476/1507] net: seeq: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Russell King Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/seeq/ether3.c | 11 ++++++----- drivers/net/ethernet/seeq/ether3.h | 1 + 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index 244c1e1710173..da4807723a067 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -170,9 +170,11 @@ ether3_setbuffer(struct net_device *dev, buffer_rw_t read, int start) /* * Switch LED off... */ -static void ether3_ledoff(unsigned long data) +static void ether3_ledoff(struct timer_list *t) { - struct net_device *dev = (struct net_device *)data; + struct dev_priv *private = from_timer(priv, t, timer); + struct net_device *dev = private->dev; + ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2); } @@ -183,8 +185,6 @@ static inline void ether3_ledon(struct net_device *dev) { del_timer(&priv(dev)->timer); priv(dev)->timer.expires = jiffies + HZ / 50; /* leave on for 1/50th second */ - priv(dev)->timer.data = (unsigned long)dev; - priv(dev)->timer.function = ether3_ledoff; add_timer(&priv(dev)->timer); if (priv(dev)->regs.config2 & CFG2_CTRLO) ether3_outw(priv(dev)->regs.config2 &= ~CFG2_CTRLO, REG_CONFIG2); @@ -783,7 +783,8 @@ ether3_probe(struct expansion_card *ec, const struct ecard_id *id) ether3_addr(dev->dev_addr, ec); - init_timer(&priv(dev)->timer); + priv(dev)->dev = dev; + timer_setup(&priv(dev)->timer, ether3_ledoff, 0); /* Reset card... */ diff --git a/drivers/net/ethernet/seeq/ether3.h b/drivers/net/ethernet/seeq/ether3.h index 2db63b08bdf37..ea2ba286e6655 100644 --- a/drivers/net/ethernet/seeq/ether3.h +++ b/drivers/net/ethernet/seeq/ether3.h @@ -165,6 +165,7 @@ struct dev_priv { unsigned char tx_tail; /* buffer nr of transmitting packet */ unsigned int rx_head; /* address to fetch next packet from */ struct timer_list timer; + net_device *dev; int broken; /* 0 = ok, 1 = something went wrong */ }; -- GitLab From 41e9475c325a3643572639283318b0a07bbb8e0b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:30 -0700 Subject: [PATCH 1477/1507] hamradio/scc: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Joerg Reuter Cc: linux-hams@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/hamradio/scc.c | 69 +++++++++++++++++++------------------- 1 file changed, 35 insertions(+), 34 deletions(-) diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 295f267b73ea2..c9f7215c5dc23 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -185,14 +185,15 @@ static const char banner[] __initconst = KERN_INFO \ "AX.25: Z8530 SCC driver version "VERSION".dl1bke\n"; -static void t_dwait(unsigned long); -static void t_txdelay(unsigned long); -static void t_tail(unsigned long); -static void t_busy(unsigned long); -static void t_maxkeyup(unsigned long); -static void t_idle(unsigned long); +static void t_dwait(struct timer_list *t); +static void t_txdelay(struct timer_list *t); +static void t_tail(struct timer_list *t); +static void t_busy(struct timer_list *); +static void t_maxkeyup(struct timer_list *); +static void t_idle(struct timer_list *t); static void scc_tx_done(struct scc_channel *); -static void scc_start_tx_timer(struct scc_channel *, void (*)(unsigned long), unsigned long); +static void scc_start_tx_timer(struct scc_channel *, + void (*)(struct timer_list *), unsigned long); static void scc_start_maxkeyup(struct scc_channel *); static void scc_start_defer(struct scc_channel *); @@ -992,24 +993,27 @@ static void scc_key_trx(struct scc_channel *scc, char tx) /* ----> SCC timer interrupt handler and friends. <---- */ -static void __scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when) +static void __scc_start_tx_timer(struct scc_channel *scc, + void (*handler)(struct timer_list *t), + unsigned long when) { del_timer(&scc->tx_t); if (when == 0) { - handler((unsigned long) scc); + handler(&scc->tx_t); } else if (when != TIMER_OFF) { - scc->tx_t.data = (unsigned long) scc; - scc->tx_t.function = handler; + scc->tx_t.function = (TIMER_FUNC_TYPE)handler; scc->tx_t.expires = jiffies + (when*HZ)/100; add_timer(&scc->tx_t); } } -static void scc_start_tx_timer(struct scc_channel *scc, void (*handler)(unsigned long), unsigned long when) +static void scc_start_tx_timer(struct scc_channel *scc, + void (*handler)(struct timer_list *t), + unsigned long when) { unsigned long flags; @@ -1027,8 +1031,7 @@ static void scc_start_defer(struct scc_channel *scc) if (scc->kiss.maxdefer != 0 && scc->kiss.maxdefer != TIMER_OFF) { - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = t_busy; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_busy; scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxdefer; add_timer(&scc->tx_wdog); } @@ -1044,8 +1047,7 @@ static void scc_start_maxkeyup(struct scc_channel *scc) if (scc->kiss.maxkeyup != 0 && scc->kiss.maxkeyup != TIMER_OFF) { - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = t_maxkeyup; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)t_maxkeyup; scc->tx_wdog.expires = jiffies + HZ*scc->kiss.maxkeyup; add_timer(&scc->tx_wdog); } @@ -1121,9 +1123,9 @@ static inline int is_grouped(struct scc_channel *scc) * fulldup == 2: mintime expired, reset status or key trx and start txdelay */ -static void t_dwait(unsigned long channel) +static void t_dwait(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); if (scc->stat.tx_state == TXS_WAIT) /* maxkeyup or idle timeout */ { @@ -1163,9 +1165,9 @@ static void t_dwait(unsigned long channel) * kick transmission by a fake scc_txint(scc), start 'maxkeyup' watchdog. */ -static void t_txdelay(unsigned long channel) +static void t_txdelay(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); scc_start_maxkeyup(scc); @@ -1184,9 +1186,9 @@ static void t_txdelay(unsigned long channel) * transmission after 'mintime' seconds */ -static void t_tail(unsigned long channel) +static void t_tail(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1211,9 +1213,9 @@ static void t_tail(unsigned long channel) * throw away send buffers if DCD remains active too long. */ -static void t_busy(unsigned long channel) +static void t_busy(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); del_timer(&scc->tx_t); netif_stop_queue(scc->dev); /* don't pile on the wabbit! */ @@ -1230,9 +1232,9 @@ static void t_busy(unsigned long channel) * this is our watchdog. */ -static void t_maxkeyup(unsigned long channel) +static void t_maxkeyup(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1264,9 +1266,9 @@ static void t_maxkeyup(unsigned long channel) * expires. */ -static void t_idle(unsigned long channel) +static void t_idle(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_t); del_timer(&scc->tx_wdog); @@ -1397,9 +1399,9 @@ static unsigned long scc_get_param(struct scc_channel *scc, unsigned int cmd) /* * Send calibration pattern * */ /* ******************************************************************* */ -static void scc_stop_calibrate(unsigned long channel) +static void scc_stop_calibrate(struct timer_list *t) { - struct scc_channel *scc = (struct scc_channel *) channel; + struct scc_channel *scc = from_timer(scc, t, tx_wdog); unsigned long flags; spin_lock_irqsave(&scc->lock, flags); @@ -1426,8 +1428,7 @@ scc_start_calibrate(struct scc_channel *scc, int duration, unsigned char pattern del_timer(&scc->tx_wdog); - scc->tx_wdog.data = (unsigned long) scc; - scc->tx_wdog.function = scc_stop_calibrate; + scc->tx_wdog.function = (TIMER_FUNC_TYPE)scc_stop_calibrate; scc->tx_wdog.expires = jiffies + HZ*duration; add_timer(&scc->tx_wdog); @@ -1522,8 +1523,8 @@ static int scc_net_alloc(const char *name, struct scc_channel *scc) dev->ml_priv = scc; scc->dev = dev; spin_lock_init(&scc->lock); - init_timer(&scc->tx_t); - init_timer(&scc->tx_wdog); + timer_setup(&scc->tx_t, NULL, 0); + timer_setup(&scc->tx_wdog, NULL, 0); err = register_netdevice(dev); if (err) { -- GitLab From dfc57004945b34cf83f600c697a54afca1fd15c5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:31 -0700 Subject: [PATCH 1478/1507] net/ethernet/sgi: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Ralf Baechle Cc: linux-mips@linux-mips.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/sgi/ioc3-eth.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 9c0488e0f08ec..18d533fdf14c4 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -764,9 +764,9 @@ static inline void ioc3_setup_duplex(struct ioc3_private *ip) ioc3_w_emcr(ip->emcr); } -static void ioc3_timer(unsigned long data) +static void ioc3_timer(struct timer_list *t) { - struct ioc3_private *ip = (struct ioc3_private *) data; + struct ioc3_private *ip = from_timer(ip, t, ioc3_timer); /* Print the link status if it has changed */ mii_check_media(&ip->mii, 1, 0); @@ -818,8 +818,6 @@ static int ioc3_mii_init(struct ioc3_private *ip) static void ioc3_mii_start(struct ioc3_private *ip) { ip->ioc3_timer.expires = jiffies + (12 * HZ)/10; /* 1.2 sec. */ - ip->ioc3_timer.data = (unsigned long) ip; - ip->ioc3_timer.function = ioc3_timer; add_timer(&ip->ioc3_timer); } @@ -1291,7 +1289,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif spin_lock_init(&ip->ioc3_lock); - init_timer(&ip->ioc3_timer); + timer_setup(&ip->ioc3_timer, ioc3_timer, 0); ioc3_stop(ip); ioc3_init(dev); -- GitLab From d28bb967aa928d5cfd50a9a182f3b4218088c79d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:32 -0700 Subject: [PATCH 1479/1507] net: usb: Convert timers to use timer_setup() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Woojung Huh Cc: Microchip Linux Driver Support Cc: "David S. Miller" Cc: Ben Hutchings Cc: Philippe Reynes Cc: Jarod Wilson Cc: Arvind Yadav Cc: "Bjørn Mork" Cc: "Stefan Brüns" Cc: Alexey Dobriyan Cc: Greg Ungerer Cc: linux-usb@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/usb/catc.c | 6 +++--- drivers/net/usb/lan78xx.c | 10 +++------- drivers/net/usb/sierra_net.c | 12 ++++-------- 3 files changed, 10 insertions(+), 18 deletions(-) diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index aeb62e17d19d6..18d36dff97ea6 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -611,9 +611,9 @@ static void catc_stats_done(struct catc *catc, struct ctrl_queue *q) catc->stats_vals[index >> 1] = data; } -static void catc_stats_timer(unsigned long data) +static void catc_stats_timer(struct timer_list *t) { - struct catc *catc = (void *) data; + struct catc *catc = from_timer(catc, t, timer); int i; for (i = 0; i < 8; i++) @@ -805,7 +805,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id spin_lock_init(&catc->tx_lock); spin_lock_init(&catc->ctrl_lock); - setup_timer(&catc->timer, catc_stats_timer, (long)catc); + timer_setup(&catc->timer, catc_stats_timer, 0); catc->ctrl_urb = usb_alloc_urb(0, GFP_KERNEL); catc->tx_urb = usb_alloc_urb(0, GFP_KERNEL); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 0161f77641fac..94c7804903c48 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3516,11 +3516,9 @@ static const struct net_device_ops lan78xx_netdev_ops = { .ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid, }; -static void lan78xx_stat_monitor(unsigned long param) +static void lan78xx_stat_monitor(struct timer_list *t) { - struct lan78xx_net *dev; - - dev = (struct lan78xx_net *)param; + struct lan78xx_net *dev = from_timer(dev, t, stat_monitor); lan78xx_defer_kevent(dev, EVENT_STAT_UPDATE); } @@ -3571,10 +3569,8 @@ static int lan78xx_probe(struct usb_interface *intf, netdev->watchdog_timeo = TX_TIMEOUT_JIFFIES; netdev->ethtool_ops = &lan78xx_ethtool_ops; - dev->stat_monitor.function = lan78xx_stat_monitor; - dev->stat_monitor.data = (unsigned long)dev; dev->delta = 1; - init_timer(&dev->stat_monitor); + timer_setup(&dev->stat_monitor, lan78xx_stat_monitor, 0); mutex_init(&dev->stats.access_lock); diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 2110ab3513f04..c43087e066963 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -189,9 +189,6 @@ struct lsi_umts_dual { #define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \ (SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN) -/* Forward definitions */ -static void sierra_sync_timer(unsigned long syncdata); - /* Our own net device operations structure */ static const struct net_device_ops sierra_net_device_ops = { .ndo_open = usbnet_open, @@ -475,8 +472,6 @@ static void sierra_net_dosync(struct usbnet *dev) "Send SYNC failed, status %d\n", status); /* Now, start a timer and make sure we get the Restart Indication */ - priv->sync_timer.function = sierra_sync_timer; - priv->sync_timer.data = (unsigned long) dev; priv->sync_timer.expires = jiffies + SIERRA_NET_SYNCDELAY; add_timer(&priv->sync_timer); } @@ -593,9 +588,10 @@ static void sierra_net_defer_kevent(struct usbnet *dev, int work) /* * Sync Retransmit Timer Handler. On expiry, kick the work queue */ -static void sierra_sync_timer(unsigned long syncdata) +static void sierra_sync_timer(struct timer_list *t) { - struct usbnet *dev = (struct usbnet *)syncdata; + struct sierra_net_data *priv = from_timer(priv, t, sync_timer); + struct usbnet *dev = priv->usbnet; dev_dbg(&dev->udev->dev, "%s", __func__); /* Kick the tasklet */ @@ -752,7 +748,7 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf) INIT_WORK(&priv->sierra_net_kevent, sierra_net_kevent); /* Only need to do this once */ - init_timer(&priv->sync_timer); + timer_setup(&priv->sync_timer, sierra_sync_timer, 0); /* verify fw attributes */ status = sierra_net_get_fw_attr(dev, &fwattr); -- GitLab From e84a2ac9ffa9b1ba211c8982f07cd92f60239c3e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:33 -0700 Subject: [PATCH 1480/1507] net: neterion: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Jon Mason Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/neterion/s2io.c | 13 ++++--------- drivers/net/ethernet/neterion/s2io.h | 2 +- 2 files changed, 5 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 462eda926b1c4..b8983e73265a0 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -337,12 +337,6 @@ static const char ethtool_driver_stats_keys[][ETH_GSTRING_LEN] = { #define S2IO_TEST_LEN ARRAY_SIZE(s2io_gstrings) #define S2IO_STRINGS_LEN (S2IO_TEST_LEN * ETH_GSTRING_LEN) -#define S2IO_TIMER_CONF(timer, handle, arg, exp) \ - init_timer(&timer); \ - timer.function = handle; \ - timer.data = (unsigned long)arg; \ - mod_timer(&timer, (jiffies + exp)) \ - /* copy mac addr to def_mac_addr array */ static void do_s2io_copy_mac_addr(struct s2io_nic *sp, int offset, u64 mac_addr) { @@ -4193,9 +4187,9 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) } static void -s2io_alarm_handle(unsigned long data) +s2io_alarm_handle(struct timer_list *t) { - struct s2io_nic *sp = (struct s2io_nic *)data; + struct s2io_nic *sp = from_timer(sp, t, alarm_timer); struct net_device *dev = sp->dev; s2io_handle_errors(dev); @@ -7186,7 +7180,8 @@ static int s2io_card_up(struct s2io_nic *sp) return -ENODEV; } - S2IO_TIMER_CONF(sp->alarm_timer, s2io_alarm_handle, sp, (HZ/2)); + timer_setup(&sp->alarm_timer, s2io_alarm_handle, 0); + mod_timer(&sp->alarm_timer, jiffies + HZ / 2); set_bit(__S2IO_STATE_CARD_UP, &sp->state); diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 6c5997dc8afc0..1a24a72187948 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1094,7 +1094,7 @@ static int s2io_poll_msix(struct napi_struct *napi, int budget); static int s2io_poll_inta(struct napi_struct *napi, int budget); static void s2io_init_pci(struct s2io_nic * sp); static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr); -static void s2io_alarm_handle(unsigned long data); +static void s2io_alarm_handle(struct timer_list *t); static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id); static irqreturn_t -- GitLab From d039ef68e94eae81c13b0b39a18f0c3455491e4c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:34 -0700 Subject: [PATCH 1481/1507] net: hns: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Switches test of .data field to .function, since .data will be going away. Cc: Yisen Zhuang Cc: Salil Mehta Cc: "David S. Miller" Cc: lipeng Cc: Lin Yun Sheng Cc: Kejian Yan Cc: Arnd Bergmann Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 7 +++---- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 13 ++++++------- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 36520634c96ae..91565c8fee080 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2159,9 +2159,9 @@ static void hns_nic_task_schedule(struct hns_nic_priv *priv) (void)schedule_work(&priv->service_task); } -static void hns_nic_service_timer(unsigned long data) +static void hns_nic_service_timer(struct timer_list *t) { - struct hns_nic_priv *priv = (struct hns_nic_priv *)data; + struct hns_nic_priv *priv = from_timer(priv, t, service_timer); (void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ); @@ -2451,8 +2451,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(ndev); - setup_timer(&priv->service_timer, hns_nic_service_timer, - (unsigned long)priv); + timer_setup(&priv->service_timer, hns_nic_service_timer, 0); INIT_WORK(&priv->service_task, hns_nic_service_task); set_bit(NIC_STATE_SERVICE_INITED, &priv->state); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c322b45341482..6e93943c489a1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2350,11 +2350,11 @@ static int hclge_get_status(struct hnae3_handle *handle) return hdev->hw.mac.link; } -static void hclge_service_timer(unsigned long data) +static void hclge_service_timer(struct timer_list *t) { - struct hclge_dev *hdev = (struct hclge_dev *)data; - (void)mod_timer(&hdev->service_timer, jiffies + HZ); + struct hclge_dev *hdev = from_timer(hdev, t, service_timer); + mod_timer(&hdev->service_timer, jiffies + HZ); hclge_task_schedule(hdev); } @@ -3204,7 +3204,7 @@ static int hclge_ae_start(struct hnae3_handle *handle) /* mac enable */ hclge_cfg_mac_mode(hdev, true); clear_bit(HCLGE_STATE_DOWN, &hdev->state); - (void)mod_timer(&hdev->service_timer, jiffies + HZ); + mod_timer(&hdev->service_timer, jiffies + HZ); ret = hclge_mac_start_phy(hdev); if (ret) @@ -4436,8 +4436,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_dcb_ops_set(hdev); - setup_timer(&hdev->service_timer, hclge_service_timer, - (unsigned long)hdev); + timer_setup(&hdev->service_timer, hclge_service_timer, 0); INIT_WORK(&hdev->service_task, hclge_service_task); set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state); @@ -4464,7 +4463,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) if (IS_ENABLED(CONFIG_PCI_IOV)) hclge_disable_sriov(hdev); - if (hdev->service_timer.data) + if (hdev->service_timer.function) del_timer_sync(&hdev->service_timer); if (hdev->service_task.func) cancel_work_sync(&hdev->service_task); -- GitLab From 26566eae80512d8a6b52e9d6f880f960893c96b4 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:35 -0700 Subject: [PATCH 1482/1507] ethernet/intel: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Switches test of .data field to .function, since .data will be going away. Cc: Jeff Kirsher Cc: intel-wired-lan@lists.osuosl.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/e100.c | 6 +++--- drivers/net/ethernet/intel/e1000e/netdev.c | 14 ++++++-------- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 8 ++++---- drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++---- .../net/ethernet/intel/i40evf/i40evf_main.c | 8 ++++---- drivers/net/ethernet/intel/igb/igb_main.c | 18 ++++++++---------- drivers/net/ethernet/intel/igbvf/netdev.c | 7 +++---- drivers/net/ethernet/intel/ixgb/ixgb_main.c | 9 ++++----- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 7 +++---- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 8 ++++---- 10 files changed, 43 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 184f11242f56d..44b3937f7e81a 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1710,9 +1710,9 @@ static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex) } } -static void e100_watchdog(unsigned long data) +static void e100_watchdog(struct timer_list *t) { - struct nic *nic = (struct nic *)data; + struct nic *nic = from_timer(nic, t, watchdog); struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; u32 speed; @@ -2920,7 +2920,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic); + timer_setup(&nic->watchdog, e100_watchdog, 0); INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index bf8f38f769534..f2f49239b0150 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4823,9 +4823,9 @@ static void e1000e_update_phy_task(struct work_struct *work) * Need to wait a few seconds after link up to get diagnostic information from * the phy **/ -static void e1000_update_phy_info(unsigned long data) +static void e1000_update_phy_info(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, phy_info_timer); if (test_bit(__E1000_DOWN, &adapter->state)) return; @@ -5159,9 +5159,9 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter) * e1000_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void e1000_watchdog(unsigned long data) +static void e1000_watchdog(struct timer_list *t) { - struct e1000_adapter *adapter = (struct e1000_adapter *)data; + struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -7267,10 +7267,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - setup_timer(&adapter->watchdog_timer, e1000_watchdog, - (unsigned long)adapter); - setup_timer(&adapter->phy_info_timer, e1000_update_phy_info, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0); + timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0); INIT_WORK(&adapter->reset_task, e1000_reset_task); INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 1e9ae3197b172..7f605221a6867 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -213,9 +213,10 @@ static void fm10k_start_service_event(struct fm10k_intfc *interface) * fm10k_service_timer - Timer Call-back * @data: pointer to interface cast into an unsigned long **/ -static void fm10k_service_timer(unsigned long data) +static void fm10k_service_timer(struct timer_list *t) { - struct fm10k_intfc *interface = (struct fm10k_intfc *)data; + struct fm10k_intfc *interface = from_timer(interface, t, + service_timer); /* Reset the timer */ mod_timer(&interface->service_timer, (HZ * 2) + jiffies); @@ -2315,8 +2316,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Initialize service timer and service task late in order to avoid * cleanup issues. */ - setup_timer(&interface->service_timer, &fm10k_service_timer, - (unsigned long)interface); + timer_setup(&interface->service_timer, fm10k_service_timer, 0); INIT_WORK(&interface->service_task, fm10k_service_task); /* Setup the MAC/VLAN queue */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bb31d53c49234..39989147b30ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8800,9 +8800,9 @@ static void i40e_service_task(struct work_struct *work) * i40e_service_timer - timer callback * @data: pointer to PF struct **/ -static void i40e_service_timer(unsigned long data) +static void i40e_service_timer(struct timer_list *t) { - struct i40e_pf *pf = (struct i40e_pf *)data; + struct i40e_pf *pf = from_timer(pf, t, service_timer); mod_timer(&pf->service_timer, round_jiffies(jiffies + pf->service_timer_period)); @@ -12648,7 +12648,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #endif /* CONFIG_I40E_DCB */ /* set up periodic task facility */ - setup_timer(&pf->service_timer, i40e_service_timer, (unsigned long)pf); + timer_setup(&pf->service_timer, i40e_service_timer, 0); pf->service_timer_period = HZ; INIT_WORK(&pf->service_task, i40e_service_task); @@ -12972,7 +12972,7 @@ static void i40e_remove(struct pci_dev *pdev) /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); - if (pf->service_timer.data) + if (pf->service_timer.function) del_timer_sync(&pf->service_timer); if (pf->service_task.func) cancel_work_sync(&pf->service_task); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 5bcbd46e2f6c4..ca2ebdbd24d7c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1594,9 +1594,10 @@ static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) * i40evf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long **/ -static void i40evf_watchdog_timer(unsigned long data) +static void i40evf_watchdog_timer(struct timer_list *t) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)data; + struct i40evf_adapter *adapter = from_timer(adapter, t, + watchdog_timer); schedule_work(&adapter->watchdog_task); /* timer will be rescheduled in watchdog task */ @@ -2748,8 +2749,7 @@ static void i40evf_init_task(struct work_struct *work) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - setup_timer(&adapter->watchdog_timer, &i40evf_watchdog_timer, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0); mod_timer(&adapter->watchdog_timer, jiffies + 1); adapter->tx_desc_count = I40EVF_DEFAULT_TXD; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 837d9b46a3905..58d01a2113678 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -133,8 +133,8 @@ static void igb_clean_all_rx_rings(struct igb_adapter *); static void igb_clean_tx_ring(struct igb_ring *); static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); -static void igb_update_phy_info(unsigned long); -static void igb_watchdog(unsigned long); +static void igb_update_phy_info(struct timer_list *); +static void igb_watchdog(struct timer_list *); static void igb_watchdog_task(struct work_struct *); static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *); static void igb_get_stats64(struct net_device *dev, @@ -2538,10 +2538,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); } - setup_timer(&adapter->watchdog_timer, igb_watchdog, - (unsigned long) adapter); - setup_timer(&adapter->phy_info_timer, igb_update_phy_info, - (unsigned long) adapter); + timer_setup(&adapter->watchdog_timer, igb_watchdog, 0); + timer_setup(&adapter->phy_info_timer, igb_update_phy_info, 0); INIT_WORK(&adapter->reset_task, igb_reset_task); INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); @@ -4425,9 +4423,9 @@ static void igb_spoof_check(struct igb_adapter *adapter) /* Need to wait a few seconds after link up to get diagnostic information from * the phy */ -static void igb_update_phy_info(unsigned long data) +static void igb_update_phy_info(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *) data; + struct igb_adapter *adapter = from_timer(adapter, t, phy_info_timer); igb_get_phy_info(&adapter->hw); } @@ -4514,9 +4512,9 @@ static void igb_check_lvmmc(struct igb_adapter *adapter) * igb_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igb_watchdog(unsigned long data) +static void igb_watchdog(struct timer_list *t) { - struct igb_adapter *adapter = (struct igb_adapter *)data; + struct igb_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 1ed556911b147..713e8df23744a 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1915,9 +1915,9 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter) * igbvf_watchdog - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void igbvf_watchdog(unsigned long data) +static void igbvf_watchdog(struct timer_list *t) { - struct igbvf_adapter *adapter = (struct igbvf_adapter *)data; + struct igbvf_adapter *adapter = from_timer(adapter, t, watchdog_timer); /* Do the rest outside of interrupt context */ schedule_work(&adapter->watchdog_task); @@ -2878,8 +2878,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->addr_len); } - setup_timer(&adapter->watchdog_timer, &igbvf_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, igbvf_watchdog, 0); INIT_WORK(&adapter->reset_task, igbvf_reset_task); INIT_WORK(&adapter->watchdog_task, igbvf_watchdog_task); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 1e6ec2277d547..2353c383f0a7d 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -83,7 +83,7 @@ static void ixgb_setup_rctl(struct ixgb_adapter *adapter); static void ixgb_clean_tx_ring(struct ixgb_adapter *adapter); static void ixgb_clean_rx_ring(struct ixgb_adapter *adapter); static void ixgb_set_multi(struct net_device *netdev); -static void ixgb_watchdog(unsigned long data); +static void ixgb_watchdog(struct timer_list *t); static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev); static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); @@ -508,8 +508,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw); - setup_timer(&adapter->watchdog_timer, ixgb_watchdog, - (unsigned long)adapter); + timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0); INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); @@ -1151,9 +1150,9 @@ ixgb_set_multi(struct net_device *netdev) **/ static void -ixgb_watchdog(unsigned long data) +ixgb_watchdog(struct timer_list *t) { - struct ixgb_adapter *adapter = (struct ixgb_adapter *)data; + struct ixgb_adapter *adapter = from_timer(adapter, t, watchdog_timer); struct net_device *netdev = adapter->netdev; struct ixgb_desc_ring *txdr = &adapter->tx_ring; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 7683c14024aa1..3e83edd10e23a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7690,9 +7690,9 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) * ixgbe_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbe_service_timer(unsigned long data) +static void ixgbe_service_timer(struct timer_list *t) { - struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)data; + struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer); unsigned long next_event_offset; /* poll faster when waiting for link */ @@ -10508,8 +10508,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); - setup_timer(&adapter->service_timer, &ixgbe_service_timer, - (unsigned long) adapter); + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { err = -EIO; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 032f8ac06357a..12d3601b1d57f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2747,9 +2747,10 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) * ixgbevf_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbevf_service_timer(unsigned long data) +static void ixgbevf_service_timer(struct timer_list *t) { - struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; + struct ixgbevf_adapter *adapter = from_timer(adapter, t, + service_timer); /* Reset the timer */ mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); @@ -4120,8 +4121,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_sw_init; } - setup_timer(&adapter->service_timer, &ixgbevf_service_timer, - (unsigned long)adapter); + timer_setup(&adapter->service_timer, ixgbevf_service_timer, 0); INIT_WORK(&adapter->service_task, ixgbevf_service_task); set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); -- GitLab From 99767f278ccf74a1857069bb3eec991e572f94cd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:36 -0700 Subject: [PATCH 1483/1507] net/core: Convert sk_timer users to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly for all users of sk_timer. Cc: "David S. Miller" Cc: Ralf Baechle Cc: Andrew Hendry Cc: Eric Dumazet Cc: Paolo Abeni Cc: David Howells Cc: Julia Lawall Cc: linzhang Cc: Ingo Molnar Cc: netdev@vger.kernel.org Cc: linux-hams@vger.kernel.org Cc: linux-x25@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/core/sock.c | 2 +- net/netrom/af_netrom.c | 6 +++--- net/netrom/nr_timer.c | 47 +++++++++++++++++++++--------------------- net/rose/rose_timer.c | 8 +++---- net/x25/af_x25.c | 8 ++++--- net/x25/x25_timer.c | 17 ++++++++------- 6 files changed, 46 insertions(+), 42 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index f577df17bcf24..35656a9e4e445 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2683,7 +2683,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk_init_common(sk); sk->sk_send_head = NULL; - setup_timer(&sk->sk_timer, NULL, (unsigned long)sk); + timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index ebf16f7f90892..2dec3583c97d0 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -241,9 +241,9 @@ void nr_destroy_socket(struct sock *); /* * Handler for deferred kills. */ -static void nr_destroy_timer(unsigned long data) +static void nr_destroy_timer(struct timer_list *t) { - struct sock *sk=(struct sock *)data; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); sock_hold(sk); nr_destroy_socket(sk); @@ -284,7 +284,7 @@ void nr_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ - sk->sk_timer.function = nr_destroy_timer; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_destroy_timer; sk->sk_timer.expires = jiffies + 2 * HZ; add_timer(&sk->sk_timer); } else diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index f84ce71f1f5f6..43569aea0f5e2 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -29,23 +29,23 @@ #include #include -static void nr_heartbeat_expiry(unsigned long); -static void nr_t1timer_expiry(unsigned long); -static void nr_t2timer_expiry(unsigned long); -static void nr_t4timer_expiry(unsigned long); -static void nr_idletimer_expiry(unsigned long); +static void nr_heartbeat_expiry(struct timer_list *); +static void nr_t1timer_expiry(struct timer_list *); +static void nr_t2timer_expiry(struct timer_list *); +static void nr_t4timer_expiry(struct timer_list *); +static void nr_idletimer_expiry(struct timer_list *); void nr_init_timers(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - setup_timer(&nr->t1timer, nr_t1timer_expiry, (unsigned long)sk); - setup_timer(&nr->t2timer, nr_t2timer_expiry, (unsigned long)sk); - setup_timer(&nr->t4timer, nr_t4timer_expiry, (unsigned long)sk); - setup_timer(&nr->idletimer, nr_idletimer_expiry, (unsigned long)sk); + timer_setup(&nr->t1timer, nr_t1timer_expiry, 0); + timer_setup(&nr->t2timer, nr_t2timer_expiry, 0); + timer_setup(&nr->t4timer, nr_t4timer_expiry, 0); + timer_setup(&nr->idletimer, nr_idletimer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.function = &nr_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)nr_heartbeat_expiry; } void nr_start_t1timer(struct sock *sk) @@ -112,9 +112,9 @@ int nr_t1timer_running(struct sock *sk) return timer_pending(&nr_sk(sk)->t1timer); } -static void nr_heartbeat_expiry(unsigned long param) +static void nr_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct nr_sock *nr = nr_sk(sk); bh_lock_sock(sk); @@ -151,10 +151,10 @@ static void nr_heartbeat_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t2timer_expiry(unsigned long param) +static void nr_t2timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t2timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); if (nr->condition & NR_COND_ACK_PENDING) { @@ -164,19 +164,20 @@ static void nr_t2timer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t4timer_expiry(unsigned long param) +static void nr_t4timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct nr_sock *nr = from_timer(nr, t, t4timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); } -static void nr_idletimer_expiry(unsigned long param) +static void nr_idletimer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, idletimer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); @@ -201,10 +202,10 @@ static void nr_idletimer_expiry(unsigned long param) bh_unlock_sock(sk); } -static void nr_t1timer_expiry(unsigned long param) +static void nr_t1timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; - struct nr_sock *nr = nr_sk(sk); + struct nr_sock *nr = from_timer(nr, t, t1timer); + struct sock *sk = &nr->sock; bh_lock_sock(sk); switch (nr->state) { diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index e082011852145..ea613b2a97358 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -28,7 +28,7 @@ #include #include -static void rose_heartbeat_expiry(unsigned long); +static void rose_heartbeat_expiry(struct timer_list *t); static void rose_timer_expiry(struct timer_list *); static void rose_idletimer_expiry(struct timer_list *); @@ -36,7 +36,7 @@ void rose_start_heartbeat(struct sock *sk) { del_timer(&sk->sk_timer); - sk->sk_timer.function = &rose_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; add_timer(&sk->sk_timer); @@ -119,9 +119,9 @@ void rose_stop_idletimer(struct sock *sk) del_timer(&rose_sk(sk)->idletimer); } -static void rose_heartbeat_expiry(unsigned long param) +static void rose_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); struct rose_sock *rose = rose_sk(sk); bh_lock_sock(sk); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index c590c0bd13933..ea87143314f30 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -374,9 +374,11 @@ static void __x25_destroy_socket(struct sock *); /* * handler for deferred kills. */ -static void x25_destroy_timer(unsigned long data) +static void x25_destroy_timer(struct timer_list *t) { - x25_destroy_socket_from_timer((struct sock *)data); + struct sock *sk = from_timer(sk, t, sk_timer); + + x25_destroy_socket_from_timer(sk); } /* @@ -413,7 +415,7 @@ static void __x25_destroy_socket(struct sock *sk) if (sk_has_allocations(sk)) { /* Defer: outstanding buffers */ sk->sk_timer.expires = jiffies + 10 * HZ; - sk->sk_timer.function = x25_destroy_timer; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_destroy_timer; add_timer(&sk->sk_timer); } else { /* drop last reference so sock_put will free */ diff --git a/net/x25/x25_timer.c b/net/x25/x25_timer.c index de5cec41d1008..1dfba3c23459e 100644 --- a/net/x25/x25_timer.c +++ b/net/x25/x25_timer.c @@ -26,17 +26,17 @@ #include #include -static void x25_heartbeat_expiry(unsigned long); -static void x25_timer_expiry(unsigned long); +static void x25_heartbeat_expiry(struct timer_list *t); +static void x25_timer_expiry(struct timer_list *t); void x25_init_timers(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); - setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk); + timer_setup(&x25->timer, x25_timer_expiry, 0); /* initialized by sock_init_data */ - sk->sk_timer.function = &x25_heartbeat_expiry; + sk->sk_timer.function = (TIMER_FUNC_TYPE)x25_heartbeat_expiry; } void x25_start_heartbeat(struct sock *sk) @@ -92,9 +92,9 @@ unsigned long x25_display_timer(struct sock *sk) return x25->timer.expires - jiffies; } -static void x25_heartbeat_expiry(unsigned long param) +static void x25_heartbeat_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct sock *sk = from_timer(sk, t, sk_timer); bh_lock_sock(sk); if (sock_owned_by_user(sk)) /* can currently only occur in state 3 */ @@ -159,9 +159,10 @@ static inline void x25_do_timer_expiry(struct sock * sk) } } -static void x25_timer_expiry(unsigned long param) +static void x25_timer_expiry(struct timer_list *t) { - struct sock *sk = (struct sock *)param; + struct x25_sock *x25 = from_timer(x25, t, timer); + struct sock *sk = &x25->sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* can currently only occur in state 3 */ -- GitLab From ba421793505f91026cccbf9398ff866dd308036d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:37 -0700 Subject: [PATCH 1484/1507] net: atm: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Also drops a redundant initialization that is already set up by DEFINE_TIMER. Cc: "David S. Miller" Cc: Hans Liljestrand Cc: "Reshetova, Elena" Cc: Bhumika Goyal Cc: Johannes Berg Cc: Roopa Prabhu Cc: Augusto Mecking Caringi Cc: Jarod Wilson Cc: Kalle Valo Cc: Thomas Gleixner Cc: Alexey Dobriyan Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/atm/clip.c | 4 ++-- net/atm/lec.c | 19 +++++++++---------- net/atm/mpc.c | 1 - 3 files changed, 11 insertions(+), 13 deletions(-) diff --git a/net/atm/clip.c b/net/atm/clip.c index 65f706e4344c3..d4f6029d5109a 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -153,7 +153,7 @@ static int neigh_check_cb(struct neighbour *n) return 1; } -static void idle_timer_check(unsigned long dummy) +static void idle_timer_check(struct timer_list *unused) { write_lock(&arp_tbl.lock); __neigh_for_each_release(&arp_tbl, neigh_check_cb); @@ -887,7 +887,7 @@ static int __init atm_clip_init(void) register_netdevice_notifier(&clip_dev_notifier); register_inetaddr_notifier(&clip_inet_notifier); - setup_timer(&idle_timer, idle_timer_check, 0); + timer_setup(&idle_timer, idle_timer_check, 0); #ifdef CONFIG_PROC_FS { diff --git a/net/atm/lec.c b/net/atm/lec.c index a3d93a1bb133e..c976196da3ea1 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1232,7 +1232,7 @@ static void lane2_associate_ind(struct net_device *dev, const u8 *mac_addr, #define LEC_ARP_REFRESH_INTERVAL (3*HZ) static void lec_arp_check_expire(struct work_struct *work); -static void lec_arp_expire_arp(unsigned long data); +static void lec_arp_expire_arp(struct timer_list *t); /* * Arp table funcs @@ -1559,8 +1559,7 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } ether_addr_copy(to_return->mac_addr, mac_addr); INIT_HLIST_NODE(&to_return->next); - setup_timer(&to_return->timer, lec_arp_expire_arp, - (unsigned long)to_return); + timer_setup(&to_return->timer, lec_arp_expire_arp, 0); to_return->last_used = jiffies; to_return->priv = priv; skb_queue_head_init(&to_return->tx_wait); @@ -1569,11 +1568,11 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, } /* Arp sent timer expired */ -static void lec_arp_expire_arp(unsigned long data) +static void lec_arp_expire_arp(struct timer_list *t) { struct lec_arp_table *entry; - entry = (struct lec_arp_table *)data; + entry = from_timer(entry, t, timer); pr_debug("\n"); if (entry->status == ESI_ARP_PENDING) { @@ -1591,10 +1590,10 @@ static void lec_arp_expire_arp(unsigned long data) } /* Unknown/unused vcc expire, remove associated entry */ -static void lec_arp_expire_vcc(unsigned long data) +static void lec_arp_expire_vcc(struct timer_list *t) { unsigned long flags; - struct lec_arp_table *to_remove = (struct lec_arp_table *)data; + struct lec_arp_table *to_remove = from_timer(to_remove, t, timer); struct lec_priv *priv = to_remove->priv; del_timer(&to_remove->timer); @@ -1799,7 +1798,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv, else send_to_lecd(priv, l_arp_xmt, mac_to_find, NULL, NULL); entry->timer.expires = jiffies + (1 * HZ); - entry->timer.function = lec_arp_expire_arp; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_arp; add_timer(&entry->timer); found = priv->mcast_vcc; } @@ -1999,7 +1998,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->old_recv_push = old_push; entry->status = ESI_UNKNOWN; entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; hlist_add_head(&entry->next, &priv->lec_no_forward); add_timer(&entry->timer); dump_arp_table(priv); @@ -2083,7 +2082,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, entry->status = ESI_UNKNOWN; hlist_add_head(&entry->next, &priv->lec_arp_empty_ones); entry->timer.expires = jiffies + priv->vcc_timeout_period; - entry->timer.function = lec_arp_expire_vcc; + entry->timer.function = (TIMER_FUNC_TYPE)lec_arp_expire_vcc; add_timer(&entry->timer); pr_debug("After vcc was added\n"); dump_arp_table(priv); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 5677147209e81..b43d99430eb64 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -799,7 +799,6 @@ static int atm_mpoa_mpoad_attach(struct atm_vcc *vcc, int arg) int err; if (mpcs == NULL) { - init_timer(&mpc_timer); mpc_timer_refresh(); /* This lets us now how our LECs are doing */ -- GitLab From cac6a8f9017b532b39ecb9a9b040eadf26895035 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:38 -0700 Subject: [PATCH 1485/1507] net/xen-netback: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Wei Liu Cc: Paul Durrant Cc: xen-devel@lists.xenproject.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/xen-netback/common.h | 2 +- drivers/net/xen-netback/interface.c | 2 +- drivers/net/xen-netback/netback.c | 6 ++---- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 5b1d2e8402d9d..a46a1e94505d0 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -307,7 +307,7 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif) return to_xenbus_device(vif->dev->dev.parent); } -void xenvif_tx_credit_callback(unsigned long data); +void xenvif_tx_credit_callback(struct timer_list *t); struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index dcfcb153918c5..5cbe0ae55a070 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -520,7 +520,7 @@ int xenvif_init_queue(struct xenvif_queue *queue) queue->credit_bytes = queue->remaining_credit = ~0UL; queue->credit_usec = 0UL; - setup_timer(&queue->credit_timeout, xenvif_tx_credit_callback, 0UL); + timer_setup(&queue->credit_timeout, xenvif_tx_credit_callback, 0); queue->credit_window_start = get_jiffies_64(); queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 5042ff8d449af..a27daa23c9dc9 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -183,9 +183,9 @@ static void tx_add_credit(struct xenvif_queue *queue) queue->rate_limited = false; } -void xenvif_tx_credit_callback(unsigned long data) +void xenvif_tx_credit_callback(struct timer_list *t) { - struct xenvif_queue *queue = (struct xenvif_queue *)data; + struct xenvif_queue *queue = from_timer(queue, t, credit_timeout); tx_add_credit(queue); xenvif_napi_schedule_or_enable_events(queue); } @@ -700,8 +700,6 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size) /* Still too big to send right now? Set a callback. */ if (size > queue->remaining_credit) { - queue->credit_timeout.data = - (unsigned long)queue; mod_timer(&queue->credit_timeout, next_credit); queue->credit_window_start = next_credit; -- GitLab From 7d85b2c8d1ca09040e16a3cd7f019d6a9ddd22d7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:39 -0700 Subject: [PATCH 1486/1507] net: fs_enet: Remove unused timer Removes unused timer and its old initialization call. Cc: Pantelis Antoniou Cc: Vitaly Bordug Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 2 -- drivers/net/ethernet/freescale/fs_enet/fs_enet.h | 1 - 2 files changed, 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 753259091b227..7892f2f0c6b56 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -1023,8 +1023,6 @@ static int fs_enet_probe(struct platform_device *ofdev) ndev->ethtool_ops = &fs_ethtool_ops; - init_timer(&fep->phy_timer_list); - netif_carrier_off(ndev); ndev->features |= NETIF_F_SG; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h index 5ce516c8a62a1..dd306deb7cf10 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h @@ -137,7 +137,6 @@ struct fs_enet_private { cbd_t __iomem *cur_rx; cbd_t __iomem *cur_tx; int tx_free; - struct timer_list phy_timer_list; const struct phy_info *phy; u32 msg_enable; struct mii_if_info mii_if; -- GitLab From 02ab4fcaf0b50434529cb263082ff95b5158c8ca Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:40 -0700 Subject: [PATCH 1487/1507] um: net: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. (Note that this timer is actually disabled.) Cc: Jeff Dike Cc: Richard Weinberger Cc: "David S. Miller" Cc: Jarod Wilson Cc: user-mode-linux-devel@lists.sourceforge.net Cc: user-mode-linux-user@lists.sourceforge.net Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- arch/um/drivers/net_kern.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 1669240c7a25f..b305f82479095 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -168,7 +168,6 @@ static int uml_net_open(struct net_device *dev) goto out_close; } - lp->tl.data = (unsigned long) &lp->user; netif_start_queue(dev); /* clear buffer - it can happen that the host side of the interface @@ -278,10 +277,11 @@ static const struct ethtool_ops uml_net_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, }; -static void uml_net_user_timer_expire(unsigned long _conn) +static void uml_net_user_timer_expire(struct timer_list *t) { #ifdef undef - struct connection *conn = (struct connection *)_conn; + struct uml_net_private *lp = from_timer(lp, t, tl); + struct connection *conn = &lp->user; dprintk(KERN_INFO "uml_net_user_timer_expire [%p]\n", conn); do_connect(conn); @@ -458,9 +458,8 @@ static void eth_configure(int n, void *init, char *mac, .add_address = transport->user->add_address, .delete_address = transport->user->delete_address }); - init_timer(&lp->tl); + timer_setup(&lp->tl, uml_net_user_timer_expire, 0); spin_lock_init(&lp->lock); - lp->tl.function = uml_net_user_timer_expire; memcpy(lp->mac, dev->dev_addr, sizeof(lp->mac)); if ((transport->user->init != NULL) && -- GitLab From 1ab791dc27faef5aee80fe76d73980d2de0bebc8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:41 -0700 Subject: [PATCH 1488/1507] ipv4: timewait: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/ipv4/inet_timewait_sock.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 5b039159e67a6..a4bab81f1462c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -142,9 +142,9 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); -static void tw_timer_handler(unsigned long data) +static void tw_timer_handler(struct timer_list *t) { - struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data; + struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); if (tw->tw_kill) __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); @@ -188,8 +188,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); - setup_pinned_timer(&tw->tw_timer, tw_timer_handler, - (unsigned long)tw); + timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this -- GitLab From ff861c4d64f2df1c7eaabaf2ba8f2f8ebc4b28e3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 16 Oct 2017 17:29:42 -0700 Subject: [PATCH 1489/1507] sunrpc: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: "David S. Miller" Cc: linux-nfs@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/sunrpc/sched.c | 8 ++++---- net/sunrpc/svc.c | 2 +- net/sunrpc/svc_xprt.c | 9 ++++----- net/sunrpc/xprt.c | 9 ++++----- 4 files changed, 13 insertions(+), 15 deletions(-) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 0cc83839c13c3..5dea47eb31bba 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -44,7 +44,7 @@ static mempool_t *rpc_buffer_mempool __read_mostly; static void rpc_async_schedule(struct work_struct *); static void rpc_release_task(struct rpc_task *task); -static void __rpc_queue_timer_fn(unsigned long ptr); +static void __rpc_queue_timer_fn(struct timer_list *t); /* * RPC tasks sit here while waiting for conditions to improve. @@ -228,7 +228,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c queue->maxpriority = nr_queues - 1; rpc_reset_waitqueue_priority(queue); queue->qlen = 0; - setup_timer(&queue->timer_list.timer, __rpc_queue_timer_fn, (unsigned long)queue); + timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0); INIT_LIST_HEAD(&queue->timer_list.list); rpc_assign_waitqueue_name(queue, qname); } @@ -635,9 +635,9 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status) } EXPORT_SYMBOL_GPL(rpc_wake_up_status); -static void __rpc_queue_timer_fn(unsigned long ptr) +static void __rpc_queue_timer_fn(struct timer_list *t) { - struct rpc_wait_queue *queue = (struct rpc_wait_queue *)ptr; + struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer); struct rpc_task *task, *n; unsigned long expires, now, timeo; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index aa04666f929db..33f4ae68426d6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -455,7 +455,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); - init_timer(&serv->sv_temptimer); + timer_setup(&serv->sv_temptimer, NULL, 0); spin_lock_init(&serv->sv_lock); __svc_init_bc(serv); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index d16a8b423c20b..71de77bd44236 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -28,7 +28,7 @@ module_param(svc_rpc_per_connection_limit, uint, 0644); static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); -static void svc_age_temp_xprts(unsigned long closure); +static void svc_age_temp_xprts(struct timer_list *t); static void svc_delete_xprt(struct svc_xprt *xprt); /* apparently the "standard" is that clients close @@ -785,8 +785,7 @@ static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt serv->sv_tmpcnt++; if (serv->sv_temptimer.function == NULL) { /* setup timer to age temp transports */ - setup_timer(&serv->sv_temptimer, svc_age_temp_xprts, - (unsigned long)serv); + serv->sv_temptimer.function = (TIMER_FUNC_TYPE)svc_age_temp_xprts; mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } @@ -960,9 +959,9 @@ int svc_send(struct svc_rqst *rqstp) * Timer function to close old temporary transports, using * a mark-and-sweep algorithm. */ -static void svc_age_temp_xprts(unsigned long closure) +static void svc_age_temp_xprts(struct timer_list *t) { - struct svc_serv *serv = (struct svc_serv *)closure; + struct svc_serv *serv = from_timer(serv, t, sv_temptimer); struct svc_xprt *xprt; struct list_head *le, *next; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e741ec2b4d8e6..4b00302e18674 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -696,9 +696,9 @@ xprt_schedule_autodisconnect(struct rpc_xprt *xprt) } static void -xprt_init_autodisconnect(unsigned long data) +xprt_init_autodisconnect(struct timer_list *t) { - struct rpc_xprt *xprt = (struct rpc_xprt *)data; + struct rpc_xprt *xprt = from_timer(xprt, t, timer); spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) @@ -1422,10 +1422,9 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args) xprt->idle_timeout = 0; INIT_WORK(&xprt->task_cleanup, xprt_autoclose); if (xprt_has_timer(xprt)) - setup_timer(&xprt->timer, xprt_init_autodisconnect, - (unsigned long)xprt); + timer_setup(&xprt->timer, xprt_init_autodisconnect, 0); else - init_timer(&xprt->timer); + timer_setup(&xprt->timer, NULL, 0); if (strlen(args->servername) > RPC_MAXNETNAMELEN) { xprt_destroy(xprt); -- GitLab From 2dc7c1fef9565c73c5054fd3c134afada09476c1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 10:12:54 -0700 Subject: [PATCH 1490/1507] tools: bpftool: use more common tag format Program tag is usually displayed as string of bytes without any separators (e.g. as "aa5520b1090cfeb6" vs MAC addr-like format bpftool uses currently: "aa:55:20:b1:09:0c:fe:b6"). Make bptfool use the more common format both for displaying the tag and selecting the program by tag. This was pointed out in review but I misunderstood the comment. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- tools/bpf/bpftool/Documentation/bpftool-prog.rst | 2 +- tools/bpf/bpftool/main.h | 3 +-- tools/bpf/bpftool/prog.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 04d12f768f06a..3968f0bd37dbe 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -55,7 +55,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 00:5a:3d:21:23:62:0c:8b + 10: xdp name some_prog tag 005a3d2123620c8b loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 8e809b2bb3111..844e4ef6db56f 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -53,8 +53,7 @@ #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) #define BAD_ARG() ({ err("what is '%s'?\n", *argv); -1; }) -#define BPF_TAG_FMT "%02hhx:%02hhx:%02hhx:%02hhx:" \ - "%02hhx:%02hhx:%02hhx:%02hhx" +#define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 9e2681c837179..d60f5307b6e21 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -224,7 +224,7 @@ static int show_prog(int fd) printf("name %s ", info.name); printf("tag "); - print_hex(info.tag, BPF_TAG_SIZE, ":"); + print_hex(info.tag, BPF_TAG_SIZE, ""); printf("\n"); if (info.load_time) { -- GitLab From 48167c9ce0b91c068430345bf039c7be23fa2f3f Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:05 +0300 Subject: [PATCH 1491/1507] fsl/fman: remove of_node The FMan MAC driver allocates a platform device for the Ethernet driver to probe on. Setting pdev->dev.of_node with the MAC node triggers the MAC driver probing of the new platform device. While this fails quickly and does not affect the functionality of the drivers, it is incorrect and must be removed. This was added to address a report that DSA code using of_find_net_device_by_node() is unable to use the DPAA interfaces. Error message seen before this fix: fsl_mac dpaa-ethernet.0: __devm_request_mem_region(mac) failed fsl_mac: probe of dpaa-ethernet.0 failed with error -16 Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/mac.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 387eb4a88b723..9a265f8620653 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -623,7 +623,6 @@ static struct platform_device *dpaa_eth_add_device(int fman_id, goto no_mem; } - pdev->dev.of_node = node; pdev->dev.parent = priv->dev; set_dma_ops(&pdev->dev, get_dma_ops(priv->dev)); -- GitLab From 3c38ec67867c0a3fe9eeda68a3d2a945d5d09a24 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:06 +0300 Subject: [PATCH 1492/1507] dpaa_eth: move of_phy_connect() to the eth driver Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 48 ++++++++- drivers/net/ethernet/freescale/fman/mac.c | 97 ++++--------------- drivers/net/ethernet/freescale/fman/mac.h | 5 +- 3 files changed, 66 insertions(+), 84 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 42258060f1422..7cf61d62ad5ee 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2435,6 +2435,48 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) } } +static void dpaa_adjust_link(struct net_device *net_dev) +{ + struct mac_device *mac_dev; + struct dpaa_priv *priv; + + priv = netdev_priv(net_dev); + mac_dev = priv->mac_dev; + mac_dev->adjust_link(mac_dev); +} + +static int dpaa_phy_init(struct net_device *net_dev) +{ + struct mac_device *mac_dev; + struct phy_device *phy_dev; + struct dpaa_priv *priv; + + priv = netdev_priv(net_dev); + mac_dev = priv->mac_dev; + + phy_dev = of_phy_connect(net_dev, mac_dev->phy_node, + &dpaa_adjust_link, 0, + mac_dev->phy_if); + if (!phy_dev) { + netif_err(priv, ifup, net_dev, "init_phy() failed\n"); + return -ENODEV; + } + + /* Remove any features not supported by the controller */ + phy_dev->supported &= mac_dev->if_support; + + /* Enable the symmetric and asymmetric PAUSE frame advertisements, + * as most of the PHY drivers do not enable them by default. + */ + phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + phy_dev->advertising = phy_dev->supported; + + mac_dev->phy_dev = phy_dev; + net_dev->phydev = phy_dev; + + return 0; +} + static int dpaa_open(struct net_device *net_dev) { struct mac_device *mac_dev; @@ -2445,12 +2487,8 @@ static int dpaa_open(struct net_device *net_dev) mac_dev = priv->mac_dev; dpaa_eth_napi_enable(priv); - net_dev->phydev = mac_dev->init_phy(net_dev, priv->mac_dev); - if (!net_dev->phydev) { - netif_err(priv, ifup, net_dev, "init_phy() failed\n"); - err = -ENODEV; + if (dpaa_phy_init(net_dev)) goto phy_init_failed; - } for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { err = fman_port_enable(mac_dev->port[i]); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 9a265f8620653..a0a3107c1f45e 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -57,9 +57,7 @@ struct mac_priv_s { struct device *dev; void __iomem *vaddr; u8 cell_index; - phy_interface_t phy_if; struct fman *fman; - struct device_node *phy_node; struct device_node *internal_phy_node; /* List of multicast addresses */ struct list_head mc_addr_list; @@ -106,7 +104,7 @@ static void set_fman_mac_params(struct mac_device *mac_dev, resource_size(mac_dev->res)); memcpy(¶ms->addr, mac_dev->addr, sizeof(mac_dev->addr)); params->max_speed = priv->max_speed; - params->phy_if = priv->phy_if; + params->phy_if = mac_dev->phy_if; params->basex_if = false; params->mac_id = priv->cell_index; params->fm = (void *)priv->fman; @@ -419,15 +417,12 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, } EXPORT_SYMBOL(fman_get_pause_cfg); -static void adjust_link_void(struct net_device *net_dev) +static void adjust_link_void(struct mac_device *mac_dev) { } -static void adjust_link_dtsec(struct net_device *net_dev) +static void adjust_link_dtsec(struct mac_device *mac_dev) { - struct device *dev = net_dev->dev.parent; - struct dpaa_eth_data *eth_data = dev->platform_data; - struct mac_device *mac_dev = eth_data->mac_dev; struct phy_device *phy_dev = mac_dev->phy_dev; struct fman_mac *fman_mac; bool rx_pause, tx_pause; @@ -444,14 +439,12 @@ static void adjust_link_dtsec(struct net_device *net_dev) fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); if (err < 0) - netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); + dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n", + err); } -static void adjust_link_memac(struct net_device *net_dev) +static void adjust_link_memac(struct mac_device *mac_dev) { - struct device *dev = net_dev->dev.parent; - struct dpaa_eth_data *eth_data = dev->platform_data; - struct mac_device *mac_dev = eth_data->mac_dev; struct phy_device *phy_dev = mac_dev->phy_dev; struct fman_mac *fman_mac; bool rx_pause, tx_pause; @@ -463,60 +456,12 @@ static void adjust_link_memac(struct net_device *net_dev) fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); if (err < 0) - netdev_err(net_dev, "fman_set_mac_active_pause() = %d\n", err); -} - -/* Initializes driver's PHY state, and attaches to the PHY. - * Returns 0 on success. - */ -static struct phy_device *init_phy(struct net_device *net_dev, - struct mac_device *mac_dev, - void (*adj_lnk)(struct net_device *)) -{ - struct phy_device *phy_dev; - struct mac_priv_s *priv = mac_dev->priv; - - phy_dev = of_phy_connect(net_dev, priv->phy_node, adj_lnk, 0, - priv->phy_if); - if (!phy_dev) { - netdev_err(net_dev, "Could not connect to PHY\n"); - return NULL; - } - - /* Remove any features not supported by the controller */ - phy_dev->supported &= mac_dev->if_support; - /* Enable the symmetric and asymmetric PAUSE frame advertisements, - * as most of the PHY drivers do not enable them by default. - */ - phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phy_dev->advertising = phy_dev->supported; - - mac_dev->phy_dev = phy_dev; - - return phy_dev; -} - -static struct phy_device *dtsec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, &adjust_link_dtsec); -} - -static struct phy_device *tgec_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, adjust_link_void); -} - -static struct phy_device *memac_init_phy(struct net_device *net_dev, - struct mac_device *mac_dev) -{ - return init_phy(net_dev, mac_dev, &adjust_link_memac); + dev_err(mac_dev->priv->dev, "fman_set_mac_active_pause() = %d\n", + err); } static void setup_dtsec(struct mac_device *mac_dev) { - mac_dev->init_phy = dtsec_init_phy; mac_dev->init = dtsec_initialization; mac_dev->set_promisc = dtsec_set_promiscuous; mac_dev->change_addr = dtsec_modify_mac_address; @@ -528,14 +473,13 @@ static void setup_dtsec(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_dtsec; mac_dev->priv->enable = dtsec_enable; mac_dev->priv->disable = dtsec_disable; } static void setup_tgec(struct mac_device *mac_dev) { - mac_dev->init_phy = tgec_init_phy; mac_dev->init = tgec_initialization; mac_dev->set_promisc = tgec_set_promiscuous; mac_dev->change_addr = tgec_modify_mac_address; @@ -547,14 +491,13 @@ static void setup_tgec(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_void; mac_dev->priv->enable = tgec_enable; mac_dev->priv->disable = tgec_disable; } static void setup_memac(struct mac_device *mac_dev) { - mac_dev->init_phy = memac_init_phy; mac_dev->init = memac_initialization; mac_dev->set_promisc = memac_set_promiscuous; mac_dev->change_addr = memac_modify_mac_address; @@ -566,7 +509,7 @@ static void setup_memac(struct mac_device *mac_dev) mac_dev->set_multi = set_multi; mac_dev->start = start; mac_dev->stop = stop; - + mac_dev->adjust_link = adjust_link_memac; mac_dev->priv->enable = memac_enable; mac_dev->priv->disable = memac_disable; } @@ -850,13 +793,13 @@ static int mac_probe(struct platform_device *_of_dev) mac_node); phy_if = PHY_INTERFACE_MODE_SGMII; } - priv->phy_if = phy_if; + mac_dev->phy_if = phy_if; - priv->speed = phy2speed[priv->phy_if]; + priv->speed = phy2speed[mac_dev->phy_if]; priv->max_speed = priv->speed; mac_dev->if_support = DTSEC_SUPPORTED; /* We don't support half-duplex in SGMII mode */ - if (priv->phy_if == PHY_INTERFACE_MODE_SGMII) + if (mac_dev->phy_if == PHY_INTERFACE_MODE_SGMII) mac_dev->if_support &= ~(SUPPORTED_10baseT_Half | SUPPORTED_100baseT_Half); @@ -865,12 +808,12 @@ static int mac_probe(struct platform_device *_of_dev) mac_dev->if_support |= SUPPORTED_1000baseT_Full; /* The 10G interface only supports one mode */ - if (priv->phy_if == PHY_INTERFACE_MODE_XGMII) + if (mac_dev->phy_if == PHY_INTERFACE_MODE_XGMII) mac_dev->if_support = SUPPORTED_10000baseT_Full; /* Get the rest of the PHY information */ - priv->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); - if (!priv->phy_node && of_phy_is_fixed_link(mac_node)) { + mac_dev->phy_node = of_parse_phandle(mac_node, "phy-handle", 0); + if (!mac_dev->phy_node && of_phy_is_fixed_link(mac_node)) { struct phy_device *phy; err = of_phy_register_fixed_link(mac_node); @@ -884,8 +827,8 @@ static int mac_probe(struct platform_device *_of_dev) goto _return_dev_set_drvdata; } - priv->phy_node = of_node_get(mac_node); - phy = of_phy_find_device(priv->phy_node); + mac_dev->phy_node = of_node_get(mac_node); + phy = of_phy_find_device(mac_dev->phy_node); if (!phy) { err = -EINVAL; goto _return_dev_set_drvdata; @@ -903,7 +846,7 @@ static int mac_probe(struct platform_device *_of_dev) err = mac_dev->init(mac_dev); if (err < 0) { dev_err(dev, "mac_dev->init() = %d\n", err); - of_node_put(priv->phy_node); + of_node_put(mac_dev->phy_node); goto _return_dev_set_drvdata; } diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index d7313f0c5135f..1ca85a18ab38e 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -50,6 +50,8 @@ struct mac_device { struct fman_port *port[2]; u32 if_support; struct phy_device *phy_dev; + phy_interface_t phy_if; + struct device_node *phy_node; bool autoneg_pause; bool rx_pause_req; @@ -58,11 +60,10 @@ struct mac_device { bool tx_pause_active; bool promisc; - struct phy_device *(*init_phy)(struct net_device *net_dev, - struct mac_device *mac_dev); int (*init)(struct mac_device *mac_dev); int (*start)(struct mac_device *mac_dev); int (*stop)(struct mac_device *mac_dev); + void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); int (*set_multi)(struct net_device *net_dev, -- GitLab From c6e26ea8c893687a83c9feda7ab4f89205e19726 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:07 +0300 Subject: [PATCH 1493/1507] dpaa_eth: change device used Change device used for DMA mapping to the MAC device that is an of_device, with proper DMA ops. Using this device for the netdevice should also address the issue with DSA scenarios that need the netdevice to be backed by an of_device. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 42 ++++++------------- drivers/net/ethernet/freescale/fman/mac.c | 37 +++++++--------- drivers/net/ethernet/freescale/fman/mac.h | 1 - 3 files changed, 27 insertions(+), 53 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 7cf61d62ad5ee..823aa6597e56a 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -385,34 +385,19 @@ static int dpaa_setup_tc(struct net_device *net_dev, enum tc_setup_type type, static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev) { - struct platform_device *of_dev; struct dpaa_eth_data *eth_data; - struct device *dpaa_dev, *dev; - struct device_node *mac_node; + struct device *dpaa_dev; struct mac_device *mac_dev; dpaa_dev = &pdev->dev; eth_data = dpaa_dev->platform_data; - if (!eth_data) + if (!eth_data) { + dev_err(dpaa_dev, "eth_data missing\n"); return ERR_PTR(-ENODEV); - - mac_node = eth_data->mac_node; - - of_dev = of_find_device_by_node(mac_node); - if (!of_dev) { - dev_err(dpaa_dev, "of_find_device_by_node(%pOF) failed\n", - mac_node); - of_node_put(mac_node); - return ERR_PTR(-EINVAL); } - of_node_put(mac_node); - - dev = &of_dev->dev; - - mac_dev = dev_get_drvdata(dev); + mac_dev = eth_data->mac_dev; if (!mac_dev) { - dev_err(dpaa_dev, "dev_get_drvdata(%s) failed\n", - dev_name(dev)); + dev_err(dpaa_dev, "mac_dev missing\n"); return ERR_PTR(-EINVAL); } @@ -2696,7 +2681,13 @@ static int dpaa_eth_probe(struct platform_device *pdev) int err = 0, i, channel; struct device *dev; - dev = &pdev->dev; + /* device used for DMA mapping */ + dev = pdev->dev.parent; + err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40)); + if (err) { + dev_err(dev, "dma_coerce_mask_and_coherent() failed\n"); + return err; + } /* Allocate this early, so we can store relevant information in * the private area @@ -2738,14 +2729,6 @@ static int dpaa_eth_probe(struct platform_device *pdev) priv->buf_layout[RX].priv_data_size = DPAA_RX_PRIV_DATA_SIZE; /* Rx */ priv->buf_layout[TX].priv_data_size = DPAA_TX_PRIV_DATA_SIZE; /* Tx */ - /* device used for DMA mapping */ - set_dma_ops(dev, get_dma_ops(&pdev->dev)); - err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(40)); - if (err) { - dev_err(dev, "dma_coerce_mask_and_coherent() failed\n"); - goto dev_mask_failed; - } - /* bp init */ for (i = 0; i < DPAA_BPS_NUM; i++) { int err; @@ -2879,7 +2862,6 @@ static int dpaa_eth_probe(struct platform_device *pdev) dpaa_bps_free(priv); bp_create_failed: fq_probe_failed: -dev_mask_failed: mac_probe_failed: dev_set_drvdata(dev, NULL); free_netdev(net_dev); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index a0a3107c1f45e..1d6da1ea7bfb2 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -542,8 +542,7 @@ static const u16 phy2speed[] = { }; static struct platform_device *dpaa_eth_add_device(int fman_id, - struct mac_device *mac_dev, - struct device_node *node) + struct mac_device *mac_dev) { struct platform_device *pdev; struct dpaa_eth_data data; @@ -556,10 +555,8 @@ static struct platform_device *dpaa_eth_add_device(int fman_id, data.mac_dev = mac_dev; data.mac_hw_id = priv->cell_index; data.fman_hw_id = fman_id; - data.mac_node = node; mutex_lock(ð_lock); - pdev = platform_device_alloc("dpaa-ethernet", dpaa_eth_dev_cnt); if (!pdev) { ret = -ENOMEM; @@ -648,9 +645,6 @@ static int mac_probe(struct platform_device *_of_dev) goto _return; } - /* Register mac_dev */ - dev_set_drvdata(dev, mac_dev); - INIT_LIST_HEAD(&priv->mc_addr_list); /* Get the FM node */ @@ -659,7 +653,7 @@ static int mac_probe(struct platform_device *_of_dev) dev_err(dev, "of_get_parent(%pOF) failed\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } of_dev = of_find_device_by_node(dev_node); @@ -693,7 +687,7 @@ static int mac_probe(struct platform_device *_of_dev) if (err < 0) { dev_err(dev, "of_address_to_resource(%pOF) = %d\n", mac_node, err); - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } mac_dev->res = __devm_request_region(dev, @@ -703,7 +697,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!mac_dev->res) { dev_err(dev, "__devm_request_mem_region(mac) failed\n"); err = -EBUSY; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->vaddr = devm_ioremap(dev, mac_dev->res->start, @@ -711,7 +705,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!priv->vaddr) { dev_err(dev, "devm_ioremap() failed\n"); err = -EIO; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } if (!of_device_is_available(mac_node)) { @@ -728,7 +722,7 @@ static int mac_probe(struct platform_device *_of_dev) if (err) { dev_err(dev, "failed to read cell-index for %pOF\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->cell_index = (u8)val; @@ -737,7 +731,7 @@ static int mac_probe(struct platform_device *_of_dev) if (!mac_addr) { dev_err(dev, "of_get_mac_address(%pOF) failed\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } memcpy(mac_dev->addr, mac_addr, sizeof(mac_dev->addr)); @@ -747,14 +741,14 @@ static int mac_probe(struct platform_device *_of_dev) dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n", mac_node); err = nph; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } if (nph != ARRAY_SIZE(mac_dev->port)) { dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n", mac_node); err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } for (i = 0; i < ARRAY_SIZE(mac_dev->port); i++) { @@ -818,20 +812,20 @@ static int mac_probe(struct platform_device *_of_dev) err = of_phy_register_fixed_link(mac_node); if (err) - goto _return_dev_set_drvdata; + goto _return_of_get_parent; priv->fixed_link = kzalloc(sizeof(*priv->fixed_link), GFP_KERNEL); if (!priv->fixed_link) { err = -ENOMEM; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } mac_dev->phy_node = of_node_get(mac_node); phy = of_phy_find_device(mac_dev->phy_node); if (!phy) { err = -EINVAL; - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } priv->fixed_link->link = phy->link; @@ -847,7 +841,7 @@ static int mac_probe(struct platform_device *_of_dev) if (err < 0) { dev_err(dev, "mac_dev->init() = %d\n", err); of_node_put(mac_dev->phy_node); - goto _return_dev_set_drvdata; + goto _return_of_get_parent; } /* pause frame autonegotiation enabled */ @@ -868,7 +862,7 @@ static int mac_probe(struct platform_device *_of_dev) mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2], mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]); - priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev, mac_node); + priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev); if (IS_ERR(priv->eth_dev)) { dev_err(dev, "failed to add Ethernet platform device for MAC %d\n", priv->cell_index); @@ -879,9 +873,8 @@ static int mac_probe(struct platform_device *_of_dev) _return_of_node_put: of_node_put(dev_node); -_return_dev_set_drvdata: +_return_of_get_parent: kfree(priv->fixed_link); - dev_set_drvdata(dev, NULL); _return: return err; } diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 1ca85a18ab38e..eefb3357e304a 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -83,7 +83,6 @@ struct mac_device { }; struct dpaa_eth_data { - struct device_node *mac_node; struct mac_device *mac_dev; int mac_hw_id; int fman_hw_id; -- GitLab From 8b9b5a2c27e1a7292f1e97e0eb19b0ae603dfa68 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:08 +0300 Subject: [PATCH 1494/1507] dpaa_eth: cleanup dpaa_eth_probe() error paths Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 53 +++++++------------ 1 file changed, 20 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 823aa6597e56a..c6b97a1b6e43c 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2695,7 +2695,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA_ETH_TXQ_NUM); if (!net_dev) { dev_err(dev, "alloc_etherdev_mq() failed\n"); - goto alloc_etherdev_mq_failed; + return -ENOMEM; } /* Do this here, so we can be verbose early */ @@ -2711,7 +2711,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (IS_ERR(mac_dev)) { dev_err(dev, "dpaa_mac_dev_get() failed\n"); err = PTR_ERR(mac_dev); - goto mac_probe_failed; + goto free_netdev; } /* If fsl_fm_max_frm is set to a higher value than the all-common 1500, @@ -2735,7 +2735,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) dpaa_bps[i] = dpaa_bp_alloc(dev); if (IS_ERR(dpaa_bps[i])) - return PTR_ERR(dpaa_bps[i]); + goto free_dpaa_bps; /* the raw size of the buffers used for reception */ dpaa_bps[i]->raw_size = bpool_buffer_raw_size(i, DPAA_BPS_NUM); /* avoid runtime computations by keeping the usable size here */ @@ -2743,11 +2743,8 @@ static int dpaa_eth_probe(struct platform_device *pdev) dpaa_bps[i]->dev = dev; err = dpaa_bp_alloc_pool(dpaa_bps[i]); - if (err < 0) { - dpaa_bps_free(priv); - priv->dpaa_bps[i] = NULL; - goto bp_create_failed; - } + if (err < 0) + goto free_dpaa_bps; priv->dpaa_bps[i] = dpaa_bps[i]; } @@ -2758,7 +2755,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_alloc_all_fqs(dev, &priv->dpaa_fq_list, &port_fqs); if (err < 0) { dev_err(dev, "dpaa_alloc_all_fqs() failed\n"); - goto fq_probe_failed; + goto free_dpaa_bps; } priv->mac_dev = mac_dev; @@ -2767,7 +2764,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (channel < 0) { dev_err(dev, "dpaa_get_channel() failed\n"); err = channel; - goto get_channel_failed; + goto free_dpaa_bps; } priv->channel = (u16)channel; @@ -2787,20 +2784,20 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_eth_cgr_init(priv); if (err < 0) { dev_err(dev, "Error initializing CGR\n"); - goto tx_cgr_init_failed; + goto free_dpaa_bps; } err = dpaa_ingress_cgr_init(priv); if (err < 0) { dev_err(dev, "Error initializing ingress CGR\n"); - goto rx_cgr_init_failed; + goto delete_egress_cgr; } /* Add the FQs to the interface, and make them active */ list_for_each_entry_safe(dpaa_fq, tmp, &priv->dpaa_fq_list, list) { err = dpaa_fq_init(dpaa_fq, false); if (err < 0) - goto fq_alloc_failed; + goto free_dpaa_fqs; } priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]); @@ -2810,7 +2807,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) err = dpaa_eth_init_ports(mac_dev, dpaa_bps, DPAA_BPS_NUM, &port_fqs, &priv->buf_layout[0], dev); if (err) - goto init_ports_failed; + goto free_dpaa_fqs; /* Rx traffic distribution based on keygen hashing defaults to on */ priv->keygen_in_use = true; @@ -2819,7 +2816,7 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (!priv->percpu_priv) { dev_err(dev, "devm_alloc_percpu() failed\n"); err = -ENOMEM; - goto alloc_percpu_failed; + goto free_dpaa_fqs; } for_each_possible_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); @@ -2832,11 +2829,11 @@ static int dpaa_eth_probe(struct platform_device *pdev) /* Initialize NAPI */ err = dpaa_napi_add(net_dev); if (err < 0) - goto napi_add_failed; + goto delete_dpaa_napi; err = dpaa_netdev_init(net_dev, &dpaa_ops, tx_timeout); if (err < 0) - goto netdev_init_failed; + goto delete_dpaa_napi; dpaa_eth_sysfs_init(&net_dev->dev); @@ -2845,31 +2842,21 @@ static int dpaa_eth_probe(struct platform_device *pdev) return 0; -netdev_init_failed: -napi_add_failed: +delete_dpaa_napi: dpaa_napi_del(net_dev); -alloc_percpu_failed: -init_ports_failed: +free_dpaa_fqs: dpaa_fq_free(dev, &priv->dpaa_fq_list); -fq_alloc_failed: qman_delete_cgr_safe(&priv->ingress_cgr); qman_release_cgrid(priv->ingress_cgr.cgrid); -rx_cgr_init_failed: +delete_egress_cgr: qman_delete_cgr_safe(&priv->cgr_data.cgr); qman_release_cgrid(priv->cgr_data.cgr.cgrid); -tx_cgr_init_failed: -get_channel_failed: +free_dpaa_bps: dpaa_bps_free(priv); -bp_create_failed: -fq_probe_failed: -mac_probe_failed: +free_netdev: dev_set_drvdata(dev, NULL); free_netdev(net_dev); -alloc_etherdev_mq_failed: - for (i = 0; i < DPAA_BPS_NUM && dpaa_bps[i]; i++) { - if (atomic_read(&dpaa_bps[i]->refs) == 0) - devm_kfree(dev, dpaa_bps[i]); - } + return err; } -- GitLab From c69fde72bf03d7aa2c8d8ab158cc55835a2c0026 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:09 +0300 Subject: [PATCH 1495/1507] fsl/fman: add dpaa in module names This change just renames the FMan driver modules, using a common prefix for the DPAA FMan and DPAA Ethernet drivers. Besides making the names more aligned, this allows writing udev rules that match on either driver name, if needed, using the fsl_dpaa_* prefix. The change of netdev dev required for the DSA probing makes the previous rules written using this prefix fail, this change makes them work again, ensuring backwards compatibility for their users. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/Makefile | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile index 2c38119b172c2..4ae524a352a29 100644 --- a/drivers/net/ethernet/freescale/fman/Makefile +++ b/drivers/net/ethernet/freescale/fman/Makefile @@ -1,9 +1,9 @@ subdir-ccflags-y += -I$(srctree)/drivers/net/ethernet/freescale/fman -obj-$(CONFIG_FSL_FMAN) += fsl_fman.o -obj-$(CONFIG_FSL_FMAN) += fsl_fman_port.o -obj-$(CONFIG_FSL_FMAN) += fsl_mac.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_fman_port.o +obj-$(CONFIG_FSL_FMAN) += fsl_dpaa_mac.o -fsl_fman-objs := fman_muram.o fman.o fman_sp.o fman_keygen.o -fsl_fman_port-objs := fman_port.o -fsl_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o +fsl_dpaa_fman-objs := fman_muram.o fman.o fman_sp.o fman_keygen.o +fsl_dpaa_fman_port-objs := fman_port.o +fsl_dpaa_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o -- GitLab From f1851a69b1f4008a7d29c6e446b3da13ed13b7da Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Mon, 16 Oct 2017 21:36:10 +0300 Subject: [PATCH 1496/1507] dpaa_eth: remove obsolete comment Comment is no longer valid for a long time now. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index c6b97a1b6e43c..a8d0be8241496 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2449,10 +2449,6 @@ static int dpaa_phy_init(struct net_device *net_dev) /* Remove any features not supported by the controller */ phy_dev->supported &= mac_dev->if_support; - - /* Enable the symmetric and asymmetric PAUSE frame advertisements, - * as most of the PHY drivers do not enable them by default. - */ phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); phy_dev->advertising = phy_dev->supported; -- GitLab From 86e58cce939cefd806105922e4a0840e9a04a88f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 16 Oct 2017 15:11:22 -0500 Subject: [PATCH 1497/1507] decnet: af_decnet: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/decnet/af_decnet.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index d4c9a8bbad3e3..518cea17b8113 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -630,10 +630,12 @@ static void dn_destroy_sock(struct sock *sk) goto disc_reject; case DN_RUN: scp->state = DN_DI; + /* fall through */ case DN_DI: case DN_DR: disc_reject: dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); + /* fall through */ case DN_NC: case DN_NR: case DN_RJ: @@ -647,6 +649,7 @@ static void dn_destroy_sock(struct sock *sk) break; default: printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); + /* fall through */ case DN_O: dn_stop_slow_timer(sk); -- GitLab From fcfd6dfab97006d44c7db5d6c908eac383af6649 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 16 Oct 2017 15:48:55 -0500 Subject: [PATCH 1498/1507] ipv4: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Notice that in some cases I placed the "fall through" comment on its own line, which is what GCC is expecting to find. Addresses-Coverity-ID: 115108 Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 3 ++- net/ipv4/arp.c | 1 + net/ipv4/devinet.c | 1 + net/ipv4/ipmr.c | 1 + net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 3 ++- net/ipv4/tcp_input.c | 2 ++ net/ipv4/tcp_ipv4.c | 3 ++- 7 files changed, 11 insertions(+), 3 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 43a1bbed7a427..ce4aa827be059 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -827,6 +827,7 @@ int inet_shutdown(struct socket *sock, int how) err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for POLLHUP, even on eg. unconnected UDP sockets -- RR */ + /* fall through */ default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) @@ -840,7 +841,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* Fall through */ + /* fall through */ case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 7c45b88967098..a8d7c5a9fb052 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1180,6 +1180,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; + /* fall through */ case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6d9b072d903b0..e1e2ec0525e6b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1522,6 +1522,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ + /* fall through */ case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b3ee01b0551bd..40a43ad294cb3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1528,6 +1528,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; + /* fall through */ case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index a0f37b2082682..0443ca4120b09 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -276,7 +276,8 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d0682ce2a5d67..b2390bfdc68fa 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2885,6 +2885,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, (*ack_flag & FLAG_LOST_RETRANS))) return; /* Change state if cwnd is undone or retransmits are lost */ + /* fall through */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -6044,6 +6045,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LAST_ACK: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; + /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5418ecf03b787..ecee4ddb24c5b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1779,8 +1779,9 @@ int tcp_v4_rcv(struct sk_buff *skb) refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; -- GitLab From fb6ff75e18937a20dbec1eb47b5f893f38eabae4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 16 Oct 2017 14:24:02 -0700 Subject: [PATCH 1499/1507] tcp: Use pI6c in tcp tracepoint The compact form for IPv6 addresses is more user friendly than the full version. For example: compact: 2001:db8:1::1 full: 2001:0db8:0001:0000:0000:0000:0000:0004i Update the tcp tracepoint to show the compact form. Signed-off-by: David Ahern Acked-by: Cong Wang Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/trace/events/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 3d1cbd072b7e5..1ffab6d96e943 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -57,7 +57,7 @@ TRACE_EVENT(tcp_retransmit_skb, } ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6 daddrv6=%pI6", + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6) ); -- GitLab From 275757e6bae15a8621130907a78096afd1e15d2c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 16 Oct 2017 16:36:52 -0500 Subject: [PATCH 1500/1507] ipv6: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Notice that in some cases I placed the "fall through" comment on its own line, which is what GCC is expecting to find. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/ipv6/ah6.c | 1 + net/ipv6/exthdrs.c | 1 + net/ipv6/icmp.c | 6 ++---- net/ipv6/ip6_fib.c | 4 ++++ net/ipv6/ip6_tunnel.c | 1 + net/ipv6/ip6mr.c | 1 + net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 3 ++- net/ipv6/raw.c | 4 ++++ net/ipv6/tcp_ipv6.c | 3 ++- net/ipv6/xfrm6_policy.c | 1 + 10 files changed, 19 insertions(+), 6 deletions(-) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 7802b72196f32..37bb33fbc7425 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -271,6 +271,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) case NEXTHDR_DEST: if (dir == XFRM_POLICY_OUT) ipv6_rearrange_destopt(iph, exthdr.opth); + /* fall through */ case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { net_dbg_ratelimited("overrun %sopts\n", diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 95516138e861c..7835dea930b45 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -89,6 +89,7 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff) */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; + /* fall through */ case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); return false; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4e52d52a6752f..6ae5dd3f4d0de 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -864,10 +864,8 @@ static int icmpv6_rcv(struct sk_buff *skb) goto discard_it; hdr = icmp6_hdr(skb); - /* - * Drop through to notify - */ - + /* to notify */ + /* fall through */ case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 548af48212fcb..1ada9672d1986 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1780,6 +1780,7 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_L; #endif + /* fall through */ case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { @@ -1788,6 +1789,7 @@ static int fib6_walk_continue(struct fib6_walker *w) continue; } w->state = FWS_R; + /* fall through */ case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { @@ -1797,6 +1799,7 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); + /* fall through */ case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -1815,6 +1818,7 @@ static int fib6_walk_continue(struct fib6_walker *w) } skip: w->state = FWS_U; + /* fall through */ case FWS_U: if (fn == w->root) return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 825548680b1e2..4212879ff35e5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -593,6 +593,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, case NDISC_REDIRECT: rel_type = ICMP_REDIRECT; rel_code = ICMP_REDIR_HOST; + /* fall through */ default: return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index f5500f5444e98..59fad81e5f7ad 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1722,6 +1722,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; + /* fall through */ case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 46d6dba506989..1d2fb9267d6fa 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -290,7 +290,8 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + /* Only ICMPs can be IP_CT_IS_REPLY: */ + /* fall through */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e4462b0ff801b..761a473a07c52 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1055,6 +1055,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } @@ -1077,6 +1078,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1138,6 +1140,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } @@ -1160,6 +1163,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; + /* fall through */ default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 64d94afa427f8..ae83615b7f6d5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1577,8 +1577,9 @@ static int tcp_v6_rcv(struct sk_buff *skb) refcounted = false; goto process; } - /* Fall through to ACK */ } + /* to ACK */ + /* fall through */ case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 11d1314ab6c5c..4ed9f8cc3b6af 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -152,6 +152,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; + /* fall through */ case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: -- GitLab From d4f4da3e13ae7a405fa1da11ff4070588e700445 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 16 Oct 2017 16:53:16 -0500 Subject: [PATCH 1501/1507] net: ipx: mark expected switch fall-through In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- net/ipx/af_ipx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index ac598ec905894..d21a9d128d3e4 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1867,6 +1867,7 @@ static int ipx_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = -EPERM; if (!capable(CAP_NET_ADMIN)) break; + /* fall through */ case SIOCGIFADDR: rc = ipxitf_ioctl(cmd, argp); break; -- GitLab From 386fd5da401dc6c4b0ab6a54d333609876b699fe Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 16 Oct 2017 15:32:07 -0700 Subject: [PATCH 1502/1507] tcp: Check daddr_cache before use in tracepoint Running perf in one window to capture tcp_retransmit_skb tracepoint: $ perf record -e tcp:tcp_retransmit_skb -a And causing a retransmission on an active TCP session (e.g., dropping packets in the receiver, changing MTU on the interface to 500 and back to 1500) triggers a panic: [ 58.543144] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 58.545300] IP: perf_trace_tcp_retransmit_skb+0xd0/0x145 [ 58.546770] PGD 0 P4D 0 [ 58.547472] Oops: 0000 [#1] SMP [ 58.548328] Modules linked in: vrf [ 58.549262] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.14.0-rc4+ #26 [ 58.551004] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [ 58.554560] task: ffffffff81a0e540 task.stack: ffffffff81a00000 [ 58.555817] RIP: 0010:perf_trace_tcp_retransmit_skb+0xd0/0x145 [ 58.557137] RSP: 0018:ffff88003fc03d68 EFLAGS: 00010282 [ 58.558292] RAX: 0000000000000000 RBX: ffffe8ffffc0ec80 RCX: ffff880038543098 [ 58.559850] RDX: 0400000000000000 RSI: ffff88003fc03d70 RDI: ffff88003fc14b68 [ 58.561099] RBP: ffff88003fc03da8 R08: 0000000000000000 R09: ffffea0000d3224a [ 58.562005] R10: ffff88003fc03db8 R11: 0000000000000010 R12: ffff8800385428c0 [ 58.562930] R13: ffffe8ffffc0e478 R14: ffffffff81a93a40 R15: ffff88003d4f0c00 [ 58.563845] FS: 0000000000000000(0000) GS:ffff88003fc00000(0000) knlGS:0000000000000000 [ 58.564873] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 58.565613] CR2: 0000000000000008 CR3: 000000003d68f004 CR4: 00000000000606f0 [ 58.566538] Call Trace: [ 58.566865] [ 58.567140] __tcp_retransmit_skb+0x4ab/0x4c6 [ 58.567704] ? tcp_set_ca_state+0x22/0x3f [ 58.568231] tcp_retransmit_skb+0x14/0xa3 [ 58.568754] tcp_retransmit_timer+0x472/0x5e3 [ 58.569324] ? tcp_write_timer_handler+0x1e9/0x1e9 [ 58.569946] tcp_write_timer_handler+0x95/0x1e9 [ 58.570548] tcp_write_timer+0x2a/0x58 Check that daddr_cache is non-NULL before de-referencing. Fixes: e086101b150a ("tcp: add a tracepoint for tcp retransmission") Signed-off-by: David Ahern Acked-by: Cong Wang Signed-off-by: David S. Miller --- include/trace/events/tcp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 1ffab6d96e943..f51c130f1e0fc 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -27,7 +27,6 @@ TRACE_EVENT(tcp_retransmit_skb, ), TP_fast_assign( - struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct in6_addr *pin6; __be32 *p32; @@ -44,11 +43,12 @@ TRACE_EVENT(tcp_retransmit_skb, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; - if (np) { + /* IPv6 socket ? */ + if (inet6_sk(sk)) { pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = np->saddr; + *pin6 = sk->sk_v6_rcv_saddr; pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = *(np->daddr_cache); + *pin6 = sk->sk_v6_daddr; } else { pin6 = (struct in6_addr *)__entry->saddr_v6; ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); -- GitLab From 7de16e3a35578f4f5accc6f5f23970310483d0a2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:53 -0700 Subject: [PATCH 1503/1507] bpf: split verifier and program ops struct bpf_verifier_ops contains both verifier ops and operations used later during program's lifetime (test_run). Split the runtime ops into a different structure. BPF_PROG_TYPE() will now append ## _prog_ops or ## _verifier_ops to the names. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 15 ++++++++----- include/linux/bpf_types.h | 28 ++++++++++++------------ kernel/bpf/syscall.c | 16 +++++++++++--- kernel/bpf/verifier.c | 12 +++++------ kernel/trace/bpf_trace.c | 15 ++++++++++--- net/core/filter.c | 45 +++++++++++++++++++++++++++++++-------- 6 files changed, 91 insertions(+), 40 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6d4dd844828a1..e1fba5504ca59 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -157,6 +157,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +struct bpf_prog_ops { + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +}; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -172,8 +177,6 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); - int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); }; struct bpf_prog_aux { @@ -184,7 +187,8 @@ struct bpf_prog_aux { u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; - const struct bpf_verifier_ops *ops; + const struct bpf_prog_ops *ops; + const struct bpf_verifier_ops *vops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; @@ -279,8 +283,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -#define BPF_PROG_TYPE(_id, _ops) \ - extern const struct bpf_verifier_ops _ops; +#define BPF_PROG_TYPE(_id, _name) \ + extern const struct bpf_prog_ops _name ## _prog_ops; \ + extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #include diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 814c1081a4a98..36418ad432457 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -1,22 +1,22 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 54fba06942f5e..444902b5a30da 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -739,9 +739,18 @@ static int map_get_next_key(union bpf_attr *attr) return err; } -static const struct bpf_verifier_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _ops) \ - [_id] = &_ops, +static const struct bpf_prog_ops * const bpf_prog_types[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _prog_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #include #undef BPF_PROG_TYPE @@ -754,6 +763,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) return -EINVAL; prog->aux->ops = bpf_prog_types[type]; + prog->aux->vops = bpf_verifier_ops[type]; prog->type = type; return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e4d5136725a2f..38e24d69fc955 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -856,8 +856,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, *reg_type = info.reg_type; return 0; } - } else if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + } else if (env->prog->aux->vops->is_valid_access && + env->prog->aux->vops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -1565,8 +1565,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return -EINVAL; } - if (env->prog->aux->ops->get_func_proto) - fn = env->prog->aux->ops->get_func_proto(func_id); + if (env->prog->aux->vops->get_func_proto) + fn = env->prog->aux->vops->get_func_proto(func_id); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), @@ -4035,7 +4035,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->ops; + const struct bpf_verifier_ops *ops = env->prog->aux->vops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4236,7 +4236,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->ops->get_func_proto(insn->imm); + fn = prog->aux->vops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 04ea5314f2bc9..3126da2f468a5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -561,11 +561,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type return true; } -const struct bpf_verifier_ops kprobe_prog_ops = { +const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; +const struct bpf_prog_ops kprobe_prog_ops = { +}; + BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { @@ -667,11 +670,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type return true; } -const struct bpf_verifier_ops tracepoint_prog_ops = { +const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -727,8 +733,11 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops perf_event_prog_ops = { +const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; + +const struct bpf_prog_ops perf_event_prog_ops = { +}; diff --git a/net/core/filter.c b/net/core/filter.c index 4d88e0665c413..1dd3034f846f2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4395,68 +4395,95 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops sk_filter_prog_ops = { +const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -const struct bpf_verifier_ops tc_cls_act_prog_ops = { +const struct bpf_prog_ops sk_filter_prog_ops = { +}; + +const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops xdp_prog_ops = { +const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, +}; + +const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; -const struct bpf_verifier_ops cg_skb_prog_ops = { +const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_inout_prog_ops = { +const struct bpf_verifier_ops lwt_inout_verifier_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_inout_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_xmit_prog_ops = { +const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops cg_sock_prog_ops = { +const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = sock_filter_convert_ctx_access, }; -const struct bpf_verifier_ops sock_ops_prog_ops = { +const struct bpf_prog_ops cg_sock_prog_ops = { +}; + +const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; -const struct bpf_verifier_ops sk_skb_prog_ops = { +const struct bpf_prog_ops sock_ops_prog_ops = { +}; + +const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; +const struct bpf_prog_ops sk_skb_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; -- GitLab From 00176a34d9e27ab1e77db75fe13abc005cffe0ca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:54 -0700 Subject: [PATCH 1504/1507] bpf: remove the verifier ops from program structure Since the verifier ops don't have to be associated with the program for its entire lifetime we can move it to verifier's struct bpf_verifier_env. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 - include/linux/bpf_verifier.h | 1 + kernel/bpf/syscall.c | 10 ---------- kernel/bpf/verifier.c | 23 +++++++++++++++++------ 4 files changed, 18 insertions(+), 17 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1fba5504ca59..cf91977e87196 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -188,7 +188,6 @@ struct bpf_prog_aux { struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; - const struct bpf_verifier_ops *vops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f00ef751c1c52..feeaea93d959f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -141,6 +141,7 @@ struct bpf_ext_analyzer_ops { */ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ + const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 444902b5a30da..0e893cac6795c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -748,22 +748,12 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = { #undef BPF_MAP_TYPE }; -static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { -#define BPF_PROG_TYPE(_id, _name) \ - [_id] = & _name ## _verifier_ops, -#define BPF_MAP_TYPE(_id, _ops) -#include -#undef BPF_PROG_TYPE -#undef BPF_MAP_TYPE -}; - static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) return -EINVAL; prog->aux->ops = bpf_prog_types[type]; - prog->aux->vops = bpf_verifier_ops[type]; prog->type = type; return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 38e24d69fc955..3b6e2c550e96d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23,6 +23,15 @@ #include "disasm.h" +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -856,8 +865,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, *reg_type = info.reg_type; return 0; } - } else if (env->prog->aux->vops->is_valid_access && - env->prog->aux->vops->is_valid_access(off, size, t, &info)) { + } else if (env->ops->is_valid_access && + env->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -1565,8 +1574,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return -EINVAL; } - if (env->prog->aux->vops->get_func_proto) - fn = env->prog->aux->vops->get_func_proto(func_id); + if (env->ops->get_func_proto) + fn = env->ops->get_func_proto(func_id); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), @@ -4035,7 +4044,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->vops; + const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4236,7 +4245,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->vops->get_func_proto(insn->imm); + fn = env->ops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ @@ -4294,6 +4303,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->insn_aux_data) goto err_free_env; env->prog = *prog; + env->ops = bpf_verifier_ops[env->prog->type]; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -4406,6 +4416,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, if (!env->insn_aux_data) goto err_free_env; env->prog = prog; + env->ops = bpf_verifier_ops[env->prog->type]; env->analyzer_ops = ops; env->analyzer_priv = priv; -- GitLab From 4f9218aaf8a463f76cac40aa08d859d065f8cc9e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:55 -0700 Subject: [PATCH 1505/1507] bpf: move knowledge about post-translation offsets out of verifier Use the fact that verifier ops are now separate from program ops to define a separate set of callbacks for verification of already translated programs. Since we expect the analyzer ops to be defined only for a small subset of all program types initialize their array by hand (don't use linux/bpf_types.h). Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ kernel/bpf/verifier.c | 55 +++++++++++++------------------------------ net/core/filter.c | 40 +++++++++++++++++++++++++++++++ 3 files changed, 59 insertions(+), 39 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cf91977e87196..d67ccdc0099f1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -291,6 +291,9 @@ DECLARE_PER_CPU(int, bpf_prog_active); #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; +extern const struct bpf_verifier_ops xdp_analyzer_ops; + struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3b6e2c550e96d..545b8c45a578c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -822,36 +822,6 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, return err; } -static bool analyzer_is_valid_access(struct bpf_verifier_env *env, int off, - struct bpf_insn_access_aux *info) -{ - switch (env->prog->type) { - case BPF_PROG_TYPE_XDP: - switch (off) { - case offsetof(struct xdp_buff, data): - info->reg_type = PTR_TO_PACKET; - return true; - case offsetof(struct xdp_buff, data_end): - info->reg_type = PTR_TO_PACKET_END; - return true; - } - return false; - case BPF_PROG_TYPE_SCHED_CLS: - switch (off) { - case offsetof(struct sk_buff, data): - info->reg_type = PTR_TO_PACKET; - return true; - case offsetof(struct sk_buff, cb) + - offsetof(struct bpf_skb_data_end, data_end): - info->reg_type = PTR_TO_PACKET_END; - return true; - } - return false; - default: - return false; - } -} - /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type) @@ -860,13 +830,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, .reg_type = *reg_type, }; - if (env->analyzer_ops) { - if (analyzer_is_valid_access(env, off, &info)) { - *reg_type = info.reg_type; - return 0; - } - } else if (env->ops->is_valid_access && - env->ops->is_valid_access(off, size, t, &info)) { + if (env->ops->is_valid_access && + env->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -874,9 +839,12 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * will only allow for whole field access and rejects any other * type of narrower access. */ - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; *reg_type = info.reg_type; + if (env->analyzer_ops) + return 0; + + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -4400,12 +4368,21 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) return ret; } +static const struct bpf_verifier_ops * const bpf_analyzer_ops[] = { + [BPF_PROG_TYPE_XDP] = &xdp_analyzer_ops, + [BPF_PROG_TYPE_SCHED_CLS] = &tc_cls_act_analyzer_ops, +}; + int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, void *priv) { struct bpf_verifier_env *env; int ret; + if (prog->type >= ARRAY_SIZE(bpf_analyzer_ops) || + !bpf_analyzer_ops[prog->type]) + return -EOPNOTSUPP; + env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; @@ -4416,7 +4393,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, if (!env->insn_aux_data) goto err_free_env; env->prog = prog; - env->ops = bpf_verifier_ops[env->prog->type]; + env->ops = bpf_analyzer_ops[env->prog->type]; env->analyzer_ops = ops; env->analyzer_priv = priv; diff --git a/net/core/filter.c b/net/core/filter.c index 1dd3034f846f2..7373a08fbef73 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3732,6 +3732,23 @@ static bool tc_cls_act_is_valid_access(int off, int size, return bpf_skb_is_valid_access(off, size, type, info); } +static bool +tc_cls_act_is_valid_access_analyzer(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case offsetof(struct sk_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct sk_buff, cb) + + offsetof(struct bpf_skb_data_end, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; +} + static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) @@ -3766,6 +3783,21 @@ static bool xdp_is_valid_access(int off, int size, return __is_valid_xdp_access(off, size); } +static bool xdp_is_valid_access_analyzer(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case offsetof(struct xdp_buff, data): + info->reg_type = PTR_TO_PACKET; + return true; + case offsetof(struct xdp_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + return true; + } + return false; +} + void bpf_warn_invalid_xdp_action(u32 act) { const u32 act_max = XDP_REDIRECT; @@ -4411,6 +4443,10 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .gen_prologue = tc_cls_act_prologue, }; +const struct bpf_verifier_ops tc_cls_act_analyzer_ops = { + .is_valid_access = tc_cls_act_is_valid_access_analyzer, +}; + const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; @@ -4421,6 +4457,10 @@ const struct bpf_verifier_ops xdp_verifier_ops = { .convert_ctx_access = xdp_convert_ctx_access, }; +const struct bpf_verifier_ops xdp_analyzer_ops = { + .is_valid_access = xdp_is_valid_access_analyzer, +}; + const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; -- GitLab From 29d1b33a2e0a3288374102b004a15cb278a2303e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:56 -0700 Subject: [PATCH 1506/1507] bpf: allow access to skb->len from offloads Since we are now doing strict checking of what offloads may access, make sure skb->len is on that list. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 7373a08fbef73..09e011f20291e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3738,6 +3738,8 @@ tc_cls_act_is_valid_access_analyzer(int off, int size, struct bpf_insn_access_aux *info) { switch (off) { + case offsetof(struct sk_buff, len): + return true; case offsetof(struct sk_buff, data): info->reg_type = PTR_TO_PACKET; return true; -- GitLab From b9f1f1ce866c28e3d9b86202441b220244754a69 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Oct 2017 19:38:35 -0700 Subject: [PATCH 1507/1507] tcp: fix tcp_xmit_retransmit_queue() after rbtree introduction I tried to hard avoiding a call to rb_first() (via tcp_rtx_queue_head) in tcp_xmit_retransmit_queue(). But this was probably too bold. Quoting Yuchung : We might miss re-arming the RTO if tp->retransmit_skb_hint is not NULL. This can happen when RACK marks the first packet lost again and resets tp->retransmit_skb_hint for example (tcp_rack_mark_skb_lost()) Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue") Signed-off-by: Eric Dumazet Reported-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6c74f2a397787..53dc1267c85e6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2921,7 +2921,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb, *rtx_head = NULL, *hole = NULL; + struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); u32 max_segs; int mib_idx; @@ -2929,11 +2929,8 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (!tp->packets_out) return; - skb = tp->retransmit_skb_hint; - if (!skb) { - rtx_head = tcp_rtx_queue_head(sk); - skb = rtx_head; - } + rtx_head = tcp_rtx_queue_head(sk); + skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); skb_rbtree_walk_from(skb) { __u8 sacked; -- GitLab